Eissa Jamil f9ed020ed0 Quick update of attribution		před 11 měsíci
..
chat_completion	ed3e11e9a8 Add option to enable Llamaguard content safety check in chat_completion	před 1 rokem
code_llama	6853267317 update with the HF flash attention native	před 1 rokem
examples_with_aws	f9ed020ed0 Quick update of attribution	před 11 měsíci
hf_llama_conversion	4913d3ad24 Add missing copyright header	před 1 rokem
hf_text_generation_inference	2374b73aad Remove __init__.py files from examples	před 1 rokem
llama_guard	4913d3ad24 Add missing copyright header	před 1 rokem
vllm	33da341af5 upstream resolve conflict	před 1 rokem
Getting_to_know_Llama.ipynb	0190444849 minor updates	před 1 rokem
Prompt_Engineering_with_Llama_2.ipynb	1278e2dbcf Add Prompt Engineering with Llama 2	před 1 rokem
Purple_Llama_Anyscale.ipynb	f0fdd3c4fa Fix Anyscale API token URL in Purple_Llama_Anyscale.ipynb	před 1 rokem
README.md	273baf58f0 update READMEs	před 1 rokem
custom_dataset.py	8620ab8ac2 Fix invalid labels for context in custom dataset/oasst1	před 1 rokem
finetuning.py	7702d702cc Add missing file extension	před 1 rokem
inference.py	8776ceb833 update with the HF flash attention native	před 1 rokem
multi_node.slurm	360a658262 Adjusted docs to reflect move of qs nb + finetuning script into examples	před 1 rokem
plot_metrics.py	4913d3ad24 Add missing copyright header	před 1 rokem
quickstart.ipynb	a0cd3c7c77 Added dependency to qsnb	před 1 rokem
samsum_prompt.txt	ccda6fb8ca Move inference scripts into example folder	před 1 rokem

Examples

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

Finetuning

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.

Inference

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, code infilling and Llama2 70B code instruct.
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.

Train on custom dataset

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.