Concept Bottleneck Large Language Models
Paper • 2412.07992 • Published • 1
How to use from
SGLangUse 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 "cesun/cbllm-generation" \
--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": "cesun/cbllm-generation",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'Quick Links
Concept Bottleneck Large Language Models
This repository contains the Concept Bottleneck Large Language Model (CB-LLM) presented in Concept Bottleneck Large Language Models.
Code: https://github.com/Trustworthy-ML-Lab/CB-LLMs
This model offers inherent interpretability and controllability in text generation. See the linked paper and GitHub repository for details on training and usage.
Install from pip and serve model
# Install SGLang from pip: pip install sglang# Start the SGLang server: python3 -m sglang.launch_server \ --model-path "cesun/cbllm-generation" \ --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": "cesun/cbllm-generation", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'