Instructions to use Qwen/Qwen2.5-Coder-3B-Instruct-AWQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Qwen/Qwen2.5-Coder-3B-Instruct-AWQ with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Qwen/Qwen2.5-Coder-3B-Instruct-AWQ")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-Coder-3B-Instruct-AWQ")
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-Coder-3B-Instruct-AWQ")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Qwen/Qwen2.5-Coder-3B-Instruct-AWQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Qwen/Qwen2.5-Coder-3B-Instruct-AWQ"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Qwen/Qwen2.5-Coder-3B-Instruct-AWQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Qwen/Qwen2.5-Coder-3B-Instruct-AWQ

SGLang

How to use Qwen/Qwen2.5-Coder-3B-Instruct-AWQ with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Qwen/Qwen2.5-Coder-3B-Instruct-AWQ" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Qwen/Qwen2.5-Coder-3B-Instruct-AWQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Qwen/Qwen2.5-Coder-3B-Instruct-AWQ" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Qwen/Qwen2.5-Coder-3B-Instruct-AWQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Qwen/Qwen2.5-Coder-3B-Instruct-AWQ with Docker Model Runner:
```
docker model run hf.co/Qwen/Qwen2.5-Coder-3B-Instruct-AWQ
```

Qwen2.5-Coder-3B-Instruct-AWQ

Commit History

update tokenizer_config.json,config.json,generation_config.json

5d26593

JustinLin610 commited on Nov 18, 2024

update README.md

5786c1c

feihu.hf commited on Nov 11, 2024

Merge branch 'main' of hf.co:Qwen/Qwen2.5-Coder-3B-Instruct-AWQ

44abe95

feihu.hf commited on Nov 11, 2024

update README.md

bb544f3

feihu.hf commited on Nov 11, 2024

Update README.md

5df7ee5
verified

cyente commited on Nov 11, 2024

update README.md

ac867ad

feihu.hf commited on Nov 11, 2024

update README.md

8d2adf1

feihu.hf commited on Nov 11, 2024

upload weights

b9dcdf9

feihu.hf commited on Nov 10, 2024

Commit History

update tokenizer_config.json,config.json,generation_config.json 5d26593

update README.md 5786c1c

Merge branch 'main' of hf.co:Qwen/Qwen2.5-Coder-3B-Instruct-AWQ 44abe95

update README.md bb544f3

Update README.md 5df7ee5 verified

update README.md ac867ad

update README.md 8d2adf1

upload weights b9dcdf9

update tokenizer_config.json,config.json,generation_config.json

5d26593

update README.md

5786c1c

Merge branch 'main' of hf.co:Qwen/Qwen2.5-Coder-3B-Instruct-AWQ

44abe95

update README.md

bb544f3

Update README.md

5df7ee5
verified

update README.md

ac867ad

update README.md

8d2adf1

upload weights

b9dcdf9