This folder contains finetuning and inference examples for Llama 2, Code Llama and (Purple Llama](https://ai.meta.com/llama/purple-llama/). For the full documentation on these examples please refer to docs/inference.md
Please refer to the main README.md for information on how to use the finetuning.py script. After installing the llama-recipes package through pip you can also invoke the finetuning in two ways:
python -m llama_recipes.finetuning <parameters>
python examples/finetuning.py <parameters>
Please see README.md for details.
So far, we have provide the following inference examples:
-
inference script script provides support for Hugging Face accelerate, PEFT and FSDP fine tuned models. It also demonstrates safety features to protect the user from toxic or harmful content.
-
vllm/inference.py script takes advantage of vLLM's paged attention concept for low latency.
-
The hf_text_generation_inference folder contains information on Hugging Face Text Generation Inference (TGI).
-
A chat completion example highlighting the handling of chat dialogs.
-
Code Llama folder which provides examples for code completion and code infilling.
-
The Purple Llama Using Anyscale is a notebook that shows how to use Anyscale hosted Llama Guard model to classify user inputs as safe or unsafe.
-
Llama Guard inference example and safety_checker for the main inference script. The standalone scripts allows to test Llama Guard on user input, or user input and agent response pairs. The safety_checker integration providers a way to integrate Llama Guard on all inference executions, both for the user input and model output.
For more in depth information on inference including inference safety checks and examples, see the inference documentation here.
Note The sensitive topics safety checker utilizes AuditNLG which is an optional dependency. Please refer to installation section of the main README.md for details.
Note The vLLM example requires additional dependencies. Please refer to installation section of the main README.md for details.
To show how to train a model on a custom dataset we provide an example to generate a custom dataset in custom_dataset.py. The usage of the custom dataset is further described in the datasets README.