Matthias Reso 7702d702cc Add missing file extension 2 rokov pred
..
chat_completion 3ddf755539 Move examples into subfolders 2 rokov pred
code_llama ccda6fb8ca Move inference scripts into example folder 2 rokov pred
hf_text_generation_inference ccda6fb8ca Move inference scripts into example folder 2 rokov pred
vllm 3ddf755539 Move examples into subfolders 2 rokov pred
README.md 42d09ac202 Document installation of optional dependencies 2 rokov pred
finetuning.py 7702d702cc Add missing file extension 2 rokov pred
inference.py ccda6fb8ca Move inference scripts into example folder 2 rokov pred
multi_node.slurm 682943551f Move quickstart nb, finetuning script and slurm config to examples 2 rokov pred
quickstart.ipynb 682943551f Move quickstart nb, finetuning script and slurm config to examples 2 rokov pred
samsum_prompt.txt ccda6fb8ca Move inference scripts into example folder 2 rokov pred

README.md

Inference

This folder contains inference examples for Llama 2. So far, we have provided support for three methods of inference:

  1. inference script script provides support for Hugging Face accelerate, PEFT and FSDP fine tuned models.

  2. vllm/inference.py script takes advantage of vLLM's paged attention concept for low latency.

  3. The hf_text_generation_inference folder contains information on Hugging Face Text Generation Inference (TGI).

For more in depth information on inference including inference safety checks and examples, see the inference documentation here.

Note The vLLM example requires additional dependencies. Please refer to installation section of the main README.md for details