Instructions to use AdaptLLM/law-LLM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use AdaptLLM/law-LLM with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="AdaptLLM/law-LLM")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("AdaptLLM/law-LLM") model = AutoModelForCausalLM.from_pretrained("AdaptLLM/law-LLM", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use AdaptLLM/law-LLM with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "AdaptLLM/law-LLM" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "AdaptLLM/law-LLM", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/AdaptLLM/law-LLM
- SGLang
How to use AdaptLLM/law-LLM 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 "AdaptLLM/law-LLM" \ --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": "AdaptLLM/law-LLM", "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 "AdaptLLM/law-LLM" \ --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": "AdaptLLM/law-LLM", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use AdaptLLM/law-LLM with Docker Model Runner:
docker model run hf.co/AdaptLLM/law-LLM
GeneralLLM | Is it Llama 1 or 2?
#1
by jordanparker6 - opened
Hey is the GeneralLLM in the paper Llama 1 or 2?
Hi, it is LLaMA 1.
Thanks. Is the training and benchmarking code public. I would love to re-run the training and evaluation with the new Mistral-7b and see how results compare.
Thanks for your interest in our work! We plan to release the benchmarking code in the near future. For now, you may use our data transferring code to pre-process your data, and follow the official guide on HuggingFace🤗 to continue to pre-train the Mistral-7b model.
AdaptLLM changed discussion status to closed