radu/LLamaRecipes @ 711c467848dc7e3fdd6bf1b61ab6bf6a3dd39304

Connor Treacy 711c467848 Update build_with_llama_api.ipynb		7 mēneši atpakaļ
..
RAG	aa60f75d44 Fixed all "Open in Colab" absolute paths	9 mēneši atpakaļ
finetuning	691bcce716 use absolute links	9 mēneši atpakaļ
inference	73e8da5176 deprecate octoai	9 mēneši atpakaļ
responsible_ai	5907e0c23e Removed installation and training outputs from the notebook based on review	7 mēneši atpakaļ
README.md	216447a490 Llama 4 4.3 release (#24)	7 mēneši atpakaļ
build_with_llama_4.ipynb	d5b3422d7c Fix Maverick typo (#912)	7 mēneši atpakaļ
build_with_llama_4_api.ipynb	5499f352e7 Adding build with Llama in the API notebook	7 mēneši atpakaļ
build_with_llama_api.ipynb	711c467848 Update build_with_llama_api.ipynb	7 mēneši atpakaļ

Llama-cookbook Getting Started

If you are new to developing with Meta Llama models, this is where you should start. This folder contains introductory-level notebooks across different techniques relating to Meta Llama.

The Build_with_Llama 4 notebook showcases a comprehensive walkthrough of the new capabilities of Llama 4 Scout models, including long context, multi-images and function calling.
The inference folder contains scripts to deploy Llama for inference on server and mobile. See also 3p_integrations/vllm and 3p_integrations/tgi for hosting Llama on open-source model servers.
The RAG folder contains a simple Retrieval-Augmented Generation application using Llama.
The finetuning folder contains resources to help you finetune Llama on your custom datasets, for both single- and multi-GPU setups. The scripts use the native llama-cookbook finetuning code found in finetuning.py which supports these features:

README.md

Llama-cookbook Getting Started