Qwen2-Instruct-7B-COIG-P

73

7.0B

license:apache-2.0

by

m-a-p

Language Model

OTHER

7B params

New

73 downloads

Early-stage

Try on Hugging Face Add to Compare

Edge AI:

Mobile

Laptop

Server

16GB+ RAM

Mobile

Laptop

Server

Quick Summary

This model, Qwen2-Instruct-7B-COIG-P, is a 7B parameter large language model fine-tuned for instruction following, particularly within the Chinese language domain.

Device Compatibility

Mobile

4-6GB RAM

Laptop

16GB RAM

Server

GPU

Minimum Recommended

7GB+ RAM

Code Examples

Recommendationspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

device = "cuda" if torch.cuda.is_available() else "cpu"
model = AutoModelForCausalLM.from_pretrained("m-a-p/Qwen2-Instruct-7B-COIG-P", trust_remote_code=True, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained("m-a-p/Qwen2-Instruct-7B-COIG-P")

prompt = "Give me a short introduction to large language models."
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(device)

generated_ids = model.generate(model_inputs.input_ids, max_new_tokens=512)
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)

Recommendationspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

device = "cuda" if torch.cuda.is_available() else "cpu"
model = AutoModelForCausalLM.from_pretrained("m-a-p/Qwen2-Instruct-7B-COIG-P", trust_remote_code=True, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained("m-a-p/Qwen2-Instruct-7B-COIG-P")

prompt = "Give me a short introduction to large language models."
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(device)

generated_ids = model.generate(model_inputs.input_ids, max_new_tokens=512)
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)

Recommendationspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

device = "cuda" if torch.cuda.is_available() else "cpu"
model = AutoModelForCausalLM.from_pretrained("m-a-p/Qwen2-Instruct-7B-COIG-P", trust_remote_code=True, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained("m-a-p/Qwen2-Instruct-7B-COIG-P")

prompt = "Give me a short introduction to large language models."
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(device)

generated_ids = model.generate(model_inputs.input_ids, max_new_tokens=512)
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)

Recommendationspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

device = "cuda" if torch.cuda.is_available() else "cpu"
model = AutoModelForCausalLM.from_pretrained("m-a-p/Qwen2-Instruct-7B-COIG-P", trust_remote_code=True, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained("m-a-p/Qwen2-Instruct-7B-COIG-P")

prompt = "Give me a short introduction to large language models."
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(device)

generated_ids = model.generate(model_inputs.input_ids, max_new_tokens=512)
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)

Recommendationspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

device = "cuda" if torch.cuda.is_available() else "cpu"
model = AutoModelForCausalLM.from_pretrained("m-a-p/Qwen2-Instruct-7B-COIG-P", trust_remote_code=True, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained("m-a-p/Qwen2-Instruct-7B-COIG-P")

prompt = "Give me a short introduction to large language models."
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(device)

generated_ids = model.generate(model_inputs.input_ids, max_new_tokens=512)
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)

Recommendationspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

device = "cuda" if torch.cuda.is_available() else "cpu"
model = AutoModelForCausalLM.from_pretrained("m-a-p/Qwen2-Instruct-7B-COIG-P", trust_remote_code=True, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained("m-a-p/Qwen2-Instruct-7B-COIG-P")

prompt = "Give me a short introduction to large language models."
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(device)

generated_ids = model.generate(model_inputs.input_ids, max_new_tokens=512)
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)

Recommendationspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

device = "cuda" if torch.cuda.is_available() else "cpu"
model = AutoModelForCausalLM.from_pretrained("m-a-p/Qwen2-Instruct-7B-COIG-P", trust_remote_code=True, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained("m-a-p/Qwen2-Instruct-7B-COIG-P")

prompt = "Give me a short introduction to large language models."
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(device)

generated_ids = model.generate(model_inputs.input_ids, max_new_tokens=512)
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)

Recommendationspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

device = "cuda" if torch.cuda.is_available() else "cpu"
model = AutoModelForCausalLM.from_pretrained("m-a-p/Qwen2-Instruct-7B-COIG-P", trust_remote_code=True, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained("m-a-p/Qwen2-Instruct-7B-COIG-P")

prompt = "Give me a short introduction to large language models."
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(device)

generated_ids = model.generate(model_inputs.input_ids, max_new_tokens=512)
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)

Recommendationspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

device = "cuda" if torch.cuda.is_available() else "cpu"
model = AutoModelForCausalLM.from_pretrained("m-a-p/Qwen2-Instruct-7B-COIG-P", trust_remote_code=True, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained("m-a-p/Qwen2-Instruct-7B-COIG-P")

prompt = "Give me a short introduction to large language models."
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(device)

generated_ids = model.generate(model_inputs.input_ids, max_new_tokens=512)
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)

Recommendationspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

device = "cuda" if torch.cuda.is_available() else "cpu"
model = AutoModelForCausalLM.from_pretrained("m-a-p/Qwen2-Instruct-7B-COIG-P", trust_remote_code=True, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained("m-a-p/Qwen2-Instruct-7B-COIG-P")

prompt = "Give me a short introduction to large language models."
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(device)

generated_ids = model.generate(model_inputs.input_ids, max_new_tokens=512)
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)

Recommendationspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

device = "cuda" if torch.cuda.is_available() else "cpu"
model = AutoModelForCausalLM.from_pretrained("m-a-p/Qwen2-Instruct-7B-COIG-P", trust_remote_code=True, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained("m-a-p/Qwen2-Instruct-7B-COIG-P")

prompt = "Give me a short introduction to large language models."
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(device)

generated_ids = model.generate(model_inputs.input_ids, max_new_tokens=512)
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)

Recommendationspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

device = "cuda" if torch.cuda.is_available() else "cpu"
model = AutoModelForCausalLM.from_pretrained("m-a-p/Qwen2-Instruct-7B-COIG-P", trust_remote_code=True, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained("m-a-p/Qwen2-Instruct-7B-COIG-P")

prompt = "Give me a short introduction to large language models."
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(device)

generated_ids = model.generate(model_inputs.input_ids, max_new_tokens=512)
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)

Recommendationspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

device = "cuda" if torch.cuda.is_available() else "cpu"
model = AutoModelForCausalLM.from_pretrained("m-a-p/Qwen2-Instruct-7B-COIG-P", trust_remote_code=True, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained("m-a-p/Qwen2-Instruct-7B-COIG-P")

prompt = "Give me a short introduction to large language models."
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(device)

generated_ids = model.generate(model_inputs.input_ids, max_new_tokens=512)
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)

Recommendationspythontransformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

device = "cuda" if torch.cuda.is_available() else "cpu"
model = AutoModelForCausalLM.from_pretrained("m-a-p/Qwen2-Instruct-7B-COIG-P", trust_remote_code=True, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained("m-a-p/Qwen2-Instruct-7B-COIG-P")

prompt = "Give me a short introduction to large language models."
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(device)

generated_ids = model.generate(model_inputs.input_ids, max_new_tokens=512)
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)

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.