OpenCoder-8B-Instruct

1.5K

199

8.0B

llama

by

infly

Language Model

OTHER

8B params

New

1K downloads

Early-stage

Try on Hugging Face Add to Compare

Edge AI:

Mobile

Laptop

Server

18GB+ RAM

Mobile

Laptop

Server

Quick Summary

AI model with specialized capabilities.

Device Compatibility

Mobile

4-6GB RAM

Laptop

16GB RAM

Server

GPU

Minimum Recommended

8GB+ RAM

Code Examples

5. Inferencepythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

model_name = "infly/OpenCoder-8B-Instruct"
model = AutoModelForCausalLM.from_pretrained(model_name,
                                             torch_dtype=torch.bfloat16,
                                             device_map="auto",
                                             trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)

messages=[
    { 'role': 'user', 'content': "write a quick sort algorithm in python."}
]

inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt")

outputs = model.generate(inputs, max_new_tokens=512, do_sample=False)

result = tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True)
print(result)

5. Inferencepythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

model_name = "infly/OpenCoder-8B-Instruct"
model = AutoModelForCausalLM.from_pretrained(model_name,
                                             torch_dtype=torch.bfloat16,
                                             device_map="auto",
                                             trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)

messages=[
    { 'role': 'user', 'content': "write a quick sort algorithm in python."}
]

inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt")

outputs = model.generate(inputs, max_new_tokens=512, do_sample=False)

result = tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True)
print(result)

5. Inferencepythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

model_name = "infly/OpenCoder-8B-Instruct"
model = AutoModelForCausalLM.from_pretrained(model_name,
                                             torch_dtype=torch.bfloat16,
                                             device_map="auto",
                                             trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)

messages=[
    { 'role': 'user', 'content': "write a quick sort algorithm in python."}
]

inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt")

outputs = model.generate(inputs, max_new_tokens=512, do_sample=False)

result = tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True)
print(result)

5. Inferencepythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

model_name = "infly/OpenCoder-8B-Instruct"
model = AutoModelForCausalLM.from_pretrained(model_name,
                                             torch_dtype=torch.bfloat16,
                                             device_map="auto",
                                             trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)

messages=[
    { 'role': 'user', 'content': "write a quick sort algorithm in python."}
]

inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt")

outputs = model.generate(inputs, max_new_tokens=512, do_sample=False)

result = tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True)
print(result)

5. Inferencepythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

model_name = "infly/OpenCoder-8B-Instruct"
model = AutoModelForCausalLM.from_pretrained(model_name,
                                             torch_dtype=torch.bfloat16,
                                             device_map="auto",
                                             trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)

messages=[
    { 'role': 'user', 'content': "write a quick sort algorithm in python."}
]

inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt")

outputs = model.generate(inputs, max_new_tokens=512, do_sample=False)

result = tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True)
print(result)

5. Inferencepythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

model_name = "infly/OpenCoder-8B-Instruct"
model = AutoModelForCausalLM.from_pretrained(model_name,
                                             torch_dtype=torch.bfloat16,
                                             device_map="auto",
                                             trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)

messages=[
    { 'role': 'user', 'content': "write a quick sort algorithm in python."}
]

inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt")

outputs = model.generate(inputs, max_new_tokens=512, do_sample=False)

result = tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True)
print(result)

5. Inferencepythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

model_name = "infly/OpenCoder-8B-Instruct"
model = AutoModelForCausalLM.from_pretrained(model_name,
                                             torch_dtype=torch.bfloat16,
                                             device_map="auto",
                                             trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)

messages=[
    { 'role': 'user', 'content': "write a quick sort algorithm in python."}
]

inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt")

outputs = model.generate(inputs, max_new_tokens=512, do_sample=False)

result = tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True)
print(result)

5. Inferencepythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

model_name = "infly/OpenCoder-8B-Instruct"
model = AutoModelForCausalLM.from_pretrained(model_name,
                                             torch_dtype=torch.bfloat16,
                                             device_map="auto",
                                             trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)

messages=[
    { 'role': 'user', 'content': "write a quick sort algorithm in python."}
]

inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt")

outputs = model.generate(inputs, max_new_tokens=512, do_sample=False)

result = tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True)
print(result)

5. Inferencepythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

model_name = "infly/OpenCoder-8B-Instruct"
model = AutoModelForCausalLM.from_pretrained(model_name,
                                             torch_dtype=torch.bfloat16,
                                             device_map="auto",
                                             trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)

messages=[
    { 'role': 'user', 'content': "write a quick sort algorithm in python."}
]

inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt")

outputs = model.generate(inputs, max_new_tokens=512, do_sample=False)

result = tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True)
print(result)

5. Inferencepythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

model_name = "infly/OpenCoder-8B-Instruct"
model = AutoModelForCausalLM.from_pretrained(model_name,
                                             torch_dtype=torch.bfloat16,
                                             device_map="auto",
                                             trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)

messages=[
    { 'role': 'user', 'content': "write a quick sort algorithm in python."}
]

inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt")

outputs = model.generate(inputs, max_new_tokens=512, do_sample=False)

result = tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True)
print(result)

5. Inferencepythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

model_name = "infly/OpenCoder-8B-Instruct"
model = AutoModelForCausalLM.from_pretrained(model_name,
                                             torch_dtype=torch.bfloat16,
                                             device_map="auto",
                                             trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)

messages=[
    { 'role': 'user', 'content': "write a quick sort algorithm in python."}
]

inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt")

outputs = model.generate(inputs, max_new_tokens=512, do_sample=False)

result = tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True)
print(result)

5. Inferencepythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

model_name = "infly/OpenCoder-8B-Instruct"
model = AutoModelForCausalLM.from_pretrained(model_name,
                                             torch_dtype=torch.bfloat16,
                                             device_map="auto",
                                             trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)

messages=[
    { 'role': 'user', 'content': "write a quick sort algorithm in python."}
]

inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt")

outputs = model.generate(inputs, max_new_tokens=512, do_sample=False)

result = tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True)
print(result)

5. Inferencepythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

model_name = "infly/OpenCoder-8B-Instruct"
model = AutoModelForCausalLM.from_pretrained(model_name,
                                             torch_dtype=torch.bfloat16,
                                             device_map="auto",
                                             trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)

messages=[
    { 'role': 'user', 'content': "write a quick sort algorithm in python."}
]

inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt")

outputs = model.generate(inputs, max_new_tokens=512, do_sample=False)

result = tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True)
print(result)

5. Inferencepythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

model_name = "infly/OpenCoder-8B-Instruct"
model = AutoModelForCausalLM.from_pretrained(model_name,
                                             torch_dtype=torch.bfloat16,
                                             device_map="auto",
                                             trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)

messages=[
    { 'role': 'user', 'content': "write a quick sort algorithm in python."}
]

inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt")

outputs = model.generate(inputs, max_new_tokens=512, do_sample=False)

result = tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True)
print(result)

5. Inferencepythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

model_name = "infly/OpenCoder-8B-Instruct"
model = AutoModelForCausalLM.from_pretrained(model_name,
                                             torch_dtype=torch.bfloat16,
                                             device_map="auto",
                                             trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)

messages=[
    { 'role': 'user', 'content': "write a quick sort algorithm in python."}
]

inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt")

outputs = model.generate(inputs, max_new_tokens=512, do_sample=False)

result = tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True)
print(result)

5. Inferencepythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

model_name = "infly/OpenCoder-8B-Instruct"
model = AutoModelForCausalLM.from_pretrained(model_name,
                                             torch_dtype=torch.bfloat16,
                                             device_map="auto",
                                             trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)

messages=[
    { 'role': 'user', 'content': "write a quick sort algorithm in python."}
]

inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt")

outputs = model.generate(inputs, max_new_tokens=512, do_sample=False)

result = tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True)
print(result)

5. Inferencepythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

model_name = "infly/OpenCoder-8B-Instruct"
model = AutoModelForCausalLM.from_pretrained(model_name,
                                             torch_dtype=torch.bfloat16,
                                             device_map="auto",
                                             trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)

messages=[
    { 'role': 'user', 'content': "write a quick sort algorithm in python."}
]

inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt")

outputs = model.generate(inputs, max_new_tokens=512, do_sample=False)

result = tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True)
print(result)

5. Inferencepythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

model_name = "infly/OpenCoder-8B-Instruct"
model = AutoModelForCausalLM.from_pretrained(model_name,
                                             torch_dtype=torch.bfloat16,
                                             device_map="auto",
                                             trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)

messages=[
    { 'role': 'user', 'content': "write a quick sort algorithm in python."}
]

inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt")

outputs = model.generate(inputs, max_new_tokens=512, do_sample=False)

result = tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True)
print(result)

5. Inferencepythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

model_name = "infly/OpenCoder-8B-Instruct"
model = AutoModelForCausalLM.from_pretrained(model_name,
                                             torch_dtype=torch.bfloat16,
                                             device_map="auto",
                                             trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)

messages=[
    { 'role': 'user', 'content': "write a quick sort algorithm in python."}
]

inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt")

outputs = model.generate(inputs, max_new_tokens=512, do_sample=False)

result = tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True)
print(result)

5. Inferencepythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

model_name = "infly/OpenCoder-8B-Instruct"
model = AutoModelForCausalLM.from_pretrained(model_name,
                                             torch_dtype=torch.bfloat16,
                                             device_map="auto",
                                             trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)

messages=[
    { 'role': 'user', 'content': "write a quick sort algorithm in python."}
]

inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt")

outputs = model.generate(inputs, max_new_tokens=512, do_sample=False)

result = tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True)
print(result)

5. Inferencepythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

model_name = "infly/OpenCoder-8B-Instruct"
model = AutoModelForCausalLM.from_pretrained(model_name,
                                             torch_dtype=torch.bfloat16,
                                             device_map="auto",
                                             trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)

messages=[
    { 'role': 'user', 'content': "write a quick sort algorithm in python."}
]

inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt")

outputs = model.generate(inputs, max_new_tokens=512, do_sample=False)

result = tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True)
print(result)

5. Inferencepythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

model_name = "infly/OpenCoder-8B-Instruct"
model = AutoModelForCausalLM.from_pretrained(model_name,
                                             torch_dtype=torch.bfloat16,
                                             device_map="auto",
                                             trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)

messages=[
    { 'role': 'user', 'content': "write a quick sort algorithm in python."}
]

inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt")

outputs = model.generate(inputs, max_new_tokens=512, do_sample=False)

result = tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True)
print(result)

5. Inferencepythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

model_name = "infly/OpenCoder-8B-Instruct"
model = AutoModelForCausalLM.from_pretrained(model_name,
                                             torch_dtype=torch.bfloat16,
                                             device_map="auto",
                                             trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)

messages=[
    { 'role': 'user', 'content': "write a quick sort algorithm in python."}
]

inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt")

outputs = model.generate(inputs, max_new_tokens=512, do_sample=False)

result = tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True)
print(result)

5. Inferencepythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

model_name = "infly/OpenCoder-8B-Instruct"
model = AutoModelForCausalLM.from_pretrained(model_name,
                                             torch_dtype=torch.bfloat16,
                                             device_map="auto",
                                             trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)

messages=[
    { 'role': 'user', 'content': "write a quick sort algorithm in python."}
]

inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt")

outputs = model.generate(inputs, max_new_tokens=512, do_sample=False)

result = tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True)
print(result)

5. Inferencepythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

model_name = "infly/OpenCoder-8B-Instruct"
model = AutoModelForCausalLM.from_pretrained(model_name,
                                             torch_dtype=torch.bfloat16,
                                             device_map="auto",
                                             trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)

messages=[
    { 'role': 'user', 'content': "write a quick sort algorithm in python."}
]

inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt")

outputs = model.generate(inputs, max_new_tokens=512, do_sample=False)

result = tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True)
print(result)

5. Inferencepythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

model_name = "infly/OpenCoder-8B-Instruct"
model = AutoModelForCausalLM.from_pretrained(model_name,
                                             torch_dtype=torch.bfloat16,
                                             device_map="auto",
                                             trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)

messages=[
    { 'role': 'user', 'content': "write a quick sort algorithm in python."}
]

inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt")

outputs = model.generate(inputs, max_new_tokens=512, do_sample=False)

result = tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True)
print(result)

5. Inferencepythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

model_name = "infly/OpenCoder-8B-Instruct"
model = AutoModelForCausalLM.from_pretrained(model_name,
                                             torch_dtype=torch.bfloat16,
                                             device_map="auto",
                                             trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)

messages=[
    { 'role': 'user', 'content': "write a quick sort algorithm in python."}
]

inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt")

outputs = model.generate(inputs, max_new_tokens=512, do_sample=False)

result = tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True)
print(result)

5. Inferencepythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

model_name = "infly/OpenCoder-8B-Instruct"
model = AutoModelForCausalLM.from_pretrained(model_name,
                                             torch_dtype=torch.bfloat16,
                                             device_map="auto",
                                             trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)

messages=[
    { 'role': 'user', 'content': "write a quick sort algorithm in python."}
]

inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt")

outputs = model.generate(inputs, max_new_tokens=512, do_sample=False)

result = tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True)
print(result)

5. Inferencepythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

model_name = "infly/OpenCoder-8B-Instruct"
model = AutoModelForCausalLM.from_pretrained(model_name,
                                             torch_dtype=torch.bfloat16,
                                             device_map="auto",
                                             trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)

messages=[
    { 'role': 'user', 'content': "write a quick sort algorithm in python."}
]

inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt")

outputs = model.generate(inputs, max_new_tokens=512, do_sample=False)

result = tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True)
print(result)

5. Inferencepythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

model_name = "infly/OpenCoder-8B-Instruct"
model = AutoModelForCausalLM.from_pretrained(model_name,
                                             torch_dtype=torch.bfloat16,
                                             device_map="auto",
                                             trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)

messages=[
    { 'role': 'user', 'content': "write a quick sort algorithm in python."}
]

inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt")

outputs = model.generate(inputs, max_new_tokens=512, do_sample=False)

result = tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True)
print(result)

5. Inferencepythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

model_name = "infly/OpenCoder-8B-Instruct"
model = AutoModelForCausalLM.from_pretrained(model_name,
                                             torch_dtype=torch.bfloat16,
                                             device_map="auto",
                                             trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)

messages=[
    { 'role': 'user', 'content': "write a quick sort algorithm in python."}
]

inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt")

outputs = model.generate(inputs, max_new_tokens=512, do_sample=False)

result = tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True)
print(result)

5. Inferencepythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

model_name = "infly/OpenCoder-8B-Instruct"
model = AutoModelForCausalLM.from_pretrained(model_name,
                                             torch_dtype=torch.bfloat16,
                                             device_map="auto",
                                             trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)

messages=[
    { 'role': 'user', 'content': "write a quick sort algorithm in python."}
]

inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt")

outputs = model.generate(inputs, max_new_tokens=512, do_sample=False)

result = tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True)
print(result)

5. Inferencepythontransformers

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

model_name = "infly/OpenCoder-8B-Instruct"
model = AutoModelForCausalLM.from_pretrained(model_name,
                                             torch_dtype=torch.bfloat16,
                                             device_map="auto",
                                             trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)

messages=[
    { 'role': 'user', 'content': "write a quick sort algorithm in python."}
]

inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt")

outputs = model.generate(inputs, max_new_tokens=512, do_sample=False)

result = tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True)
print(result)

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.

Replicate

One-click model deployment

Easiest Setup

Run models in the cloud with simple API. No DevOps required.

Disclosure: We may earn a commission from these partners. This helps keep LLMYourWay free.