Instructions to use lmsys/longchat-7b-16k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use lmsys/longchat-7b-16k with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="lmsys/longchat-7b-16k")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("lmsys/longchat-7b-16k") model = AutoModelForCausalLM.from_pretrained("lmsys/longchat-7b-16k") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use lmsys/longchat-7b-16k with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "lmsys/longchat-7b-16k" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "lmsys/longchat-7b-16k", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/lmsys/longchat-7b-16k
- SGLang
How to use lmsys/longchat-7b-16k 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 "lmsys/longchat-7b-16k" \ --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": "lmsys/longchat-7b-16k", "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 "lmsys/longchat-7b-16k" \ --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": "lmsys/longchat-7b-16k", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use lmsys/longchat-7b-16k with Docker Model Runner:
docker model run hf.co/lmsys/longchat-7b-16k
is chinese supported in this model?
#1
by aslan9 - opened
whether language usage is limited in English
The model isn't limited in English, but it doesn't support Chinese well. LongChat series is extended from the LLama models. According to this discussion, Meta trained its model using 20 languages that use Latin or Cyrillic scripts but there are only 700 Chinese characters in the vocabulary. So very bad performance in Chinese is expected.
rulins changed discussion status to closed