Instructions to use Qwen/Qwen2.5-72B-Instruct-GPTQ-Int8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Qwen/Qwen2.5-72B-Instruct-GPTQ-Int8 with Transformers:

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

pipe = pipeline("text-generation", model="Qwen/Qwen2.5-72B-Instruct-GPTQ-Int8")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-72B-Instruct-GPTQ-Int8")
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-72B-Instruct-GPTQ-Int8")
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 Settings

vLLM

How to use Qwen/Qwen2.5-72B-Instruct-GPTQ-Int8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Qwen/Qwen2.5-72B-Instruct-GPTQ-Int8"
# 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/Qwen2.5-72B-Instruct-GPTQ-Int8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Qwen/Qwen2.5-72B-Instruct-GPTQ-Int8

SGLang

How to use Qwen/Qwen2.5-72B-Instruct-GPTQ-Int8 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/Qwen2.5-72B-Instruct-GPTQ-Int8" \
    --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/Qwen2.5-72B-Instruct-GPTQ-Int8",
		"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/Qwen2.5-72B-Instruct-GPTQ-Int8" \
        --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/Qwen2.5-72B-Instruct-GPTQ-Int8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Qwen/Qwen2.5-72B-Instruct-GPTQ-Int8 with Docker Model Runner:
```
docker model run hf.co/Qwen/Qwen2.5-72B-Instruct-GPTQ-Int8
```

jklj077 commited on Sep 18, 2024

Commit

3810f87

verified ·

1 Parent(s): 4a5fa12

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -20,7 +20,7 @@ Qwen2.5 is the latest series of Qwen large language models. For Qwen2.5, we rele
 - **Long-context Support** up to 128K tokens and can generate up to 8K tokens.
 - **Multilingual support** for over 29 languages, including Chinese, English, French, Spanish, Portuguese, German, Italian, Russian, Japanese, Korean, Vietnamese, Thai, Arabic, and more.
-**This repo contains the GPTQ-quantized 4-bit instruction-tuned 72B Qwen2.5 model**, which has the following features:
 - Type: Causal Language Models
 - Training Stage: Pretraining & Post-training
 - Architecture: transformers with RoPE, SwiGLU, RMSNorm, and Attention QKV bias

 - **Long-context Support** up to 128K tokens and can generate up to 8K tokens.
 - **Multilingual support** for over 29 languages, including Chinese, English, French, Spanish, Portuguese, German, Italian, Russian, Japanese, Korean, Vietnamese, Thai, Arabic, and more.
+**This repo contains the GPTQ-quantized 8-bit instruction-tuned 72B Qwen2.5 model**, which has the following features:
 - Type: Causal Language Models
 - Training Stage: Pretraining & Post-training
 - Architecture: transformers with RoPE, SwiGLU, RMSNorm, and Attention QKV bias