Instructions to use AI4Chem/ChemLLM-7B-Chat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use AI4Chem/ChemLLM-7B-Chat with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="AI4Chem/ChemLLM-7B-Chat", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("AI4Chem/ChemLLM-7B-Chat", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use AI4Chem/ChemLLM-7B-Chat with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "AI4Chem/ChemLLM-7B-Chat" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "AI4Chem/ChemLLM-7B-Chat", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/AI4Chem/ChemLLM-7B-Chat
- SGLang
How to use AI4Chem/ChemLLM-7B-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 "AI4Chem/ChemLLM-7B-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": "AI4Chem/ChemLLM-7B-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 "AI4Chem/ChemLLM-7B-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": "AI4Chem/ChemLLM-7B-Chat", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use AI4Chem/ChemLLM-7B-Chat with Docker Model Runner:
docker model run hf.co/AI4Chem/ChemLLM-7B-Chat
Dataset
Is the dataset on chemical engineering publicly available? I saw online that it has been released, but I couldn't find the link. If it's available, could you provide the link? Thanks.
ChemLLM datasets is all open source now!
https://huggingface.co/papers/2402.06852
700K of SFT Dataset, ChemData700K For Chemistry of LLM!
https://huggingface.co/datasets/AI4Chem/ChemData700K
10K of DPO Dataset, ChemPref-10K, both English and Chinese!
https://huggingface.co/datasets/AI4Chem/ChemPref-DPO-for-Chemistry-data-en
https://huggingface.co/datasets/AI4Chem/ChemPref-DPO-for-Chemistry-data-cn
ChemBench-4K of 4100 high-quality single-choice benchmark for nine core Chemistry tasks!
https://huggingface.co/datasets/AI4Chem/ChemBench4K
C-MHChem, 600 real test questions written and checked manually, from 25 years of Chinese National Middle school chemistry Test!
https://huggingface.co/datasets/AI4Chem/C-MHChem-Benchmark-Chinese-Middle-high-school-Chemistry-Test
All hail to Open-source community!π€
thanks