Instructions to use lmsys/longchat-13b-16k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use lmsys/longchat-13b-16k with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="lmsys/longchat-13b-16k")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("lmsys/longchat-13b-16k") model = AutoModelForCausalLM.from_pretrained("lmsys/longchat-13b-16k", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use lmsys/longchat-13b-16k with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "lmsys/longchat-13b-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-13b-16k", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/lmsys/longchat-13b-16k
- SGLang
How to use lmsys/longchat-13b-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-13b-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-13b-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-13b-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-13b-16k", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use lmsys/longchat-13b-16k with Docker Model Runner:
docker model run hf.co/lmsys/longchat-13b-16k
Please add the monkey patch so it can be load using transformers with `trust_remote_code=True`
#1
by fahadh4ilyas - opened
I know that this model has it's own monkey patches for forward function and additional rotary positional embedding layer. But, because it's not added here, loading model blindly using transformers might not work as expected. At least put the monkey patches in the repo so user can load the model easily using transformers. Or you could add instruction to load the model in the model card.