NanoLM-0.3B-Instruct-v2

Name: NanoLM-0.3B-Instruct-v2
Rating: 7.6 (10 reviews)
Author: Mxode

300M

1 language

license:gpl-3.0

Mxode

Language Model

OTHER

0.3B params

New

4 downloads

Early-stage

Try on Hugging Face Add to Compare

Edge AI:

Mobile

Laptop

Server

1GB+ RAM

Mobile

Laptop

Server

Quick Summary

License GPL-3.0. Language English.

Device Compatibility

Mobile

4-6GB RAM

Laptop

16GB RAM

Server

GPU

Minimum Recommended

1GB+ RAM

Code Examples

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

How to usepythontransformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-0.3B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt1 = "Calculate (4 - 1) * 7"
print(get_response(prompt1, do_sample=False))

"""
To calculate the expression (4 - 1) * 7, we need to follow the order of operations (PEMDAS):

1. Evaluate the expression inside the parentheses: 4 - 1 = 3
2. Multiply 3 by 7: 3 * 7 = 21

So, (4 - 1) * 7 = 21.
"""

Deploy This Model

Production-ready deployment in minutes

Together.ai

Instant API access to this model

Fastest API

Production-ready inference API. Start free, scale to millions.

Try Free API

Replicate

One-click model deployment

Easiest Setup

Run models in the cloud with simple API. No DevOps required.

Deploy Now

Disclosure: We may earn a commission from these partners. This helps keep LLMYourWay free.