Instructions to use Qwen/Qwen-72B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Qwen/Qwen-72B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Qwen/Qwen-72B", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen-72B", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use Qwen/Qwen-72B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Qwen/Qwen-72B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Qwen/Qwen-72B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Qwen/Qwen-72B
- SGLang
How to use Qwen/Qwen-72B 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/Qwen-72B" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Qwen/Qwen-72B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'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/Qwen-72B" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Qwen/Qwen-72B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Qwen/Qwen-72B with Docker Model Runner:
docker model run hf.co/Qwen/Qwen-72B
为什么计算softmax之前要将logits转为float?
#10 opened almost 2 years ago
by
yuanshuai
how did you guys pretrain the tokenizer using tiktoken ?
#9 opened almost 2 years ago
by
StephennFernandes
是否可以运行在两张不同型号的GPU上
#8 opened about 2 years ago
by
XCZDH
Adding Evaluation Results
#7 opened about 2 years ago
by
leaderboard-pr-bot
On how much English token was the model trained onn
3
#5 opened over 2 years ago
by
aslawliet
_set_gradient_checkpointing() got an unexpected keyword argument 'enable'
👍 2
2
#3 opened over 2 years ago
by
ehartford