Instructions to use Qwen/Qwen-14B-Chat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Qwen/Qwen-14B-Chat with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Qwen/Qwen-14B-Chat", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen-14B-Chat", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use Qwen/Qwen-14B-Chat with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Qwen/Qwen-14B-Chat" # 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-14B-Chat", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Qwen/Qwen-14B-Chat
- SGLang
How to use Qwen/Qwen-14B-Chat 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-14B-Chat" \ --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-14B-Chat", "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-14B-Chat" \ --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-14B-Chat", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Qwen/Qwen-14B-Chat with Docker Model Runner:
docker model run hf.co/Qwen/Qwen-14B-Chat
Request: DOI
#19 opened 5 months ago
by
Coranoire
chat_stream 的使用
#16 opened over 2 years ago
by
jayceeNice
Can you please submit this to leaderboard?
6
#15 opened over 2 years ago
by
gblazex
Max sequence length config
1
#14 opened over 2 years ago
by
ihungalexhsu
如何让模型输出的结果,严格按照定义的json结构进行输出?
👍 2
1
#12 opened over 2 years ago
by
tang0430
Copyright Concerns on Commercial Use of Distilled GPT-3.5 Data - GPT-3.5 蒸馏数据用于商业用途的版权疑虑
#4 opened over 2 years ago
by
JosephusCheung
支持ollama运行吗?
#3 opened over 2 years ago
by
esqer