https://github.com/meta-llama/llama-recipes

Scripts for fine-tuning Meta Llama3 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting a number of candid inference solutions such as HF TGI, VLLM for local or cloud deployment. Demo apps to showcase Meta Llama3 for WhatsApp & Messenger.
https://github.com/meta-llama/llama-recipes

ai finetuning langchain llama llama2 llm machine-learning python pytorch vllm

Last synced: about 1 month ago
JSON representation

Scripts for fine-tuning Meta Llama3 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting a number of candid inference solutions such as HF TGI, VLLM for local or cloud deployment. Demo apps to showcase Meta Llama3 for WhatsApp & Messenger.

• Host: GitHub
• URL: https://github.com/meta-llama/llama-recipes
• Owner: meta-llama
• Created: 2023-07-17T07:33:48.000Z (about 1 year ago)
• Default Branch: main
• Last Pushed: 2024-05-22T19:29:19.000Z (4 months ago)
• Last Synced: 2024-05-23T01:54:02.561Z (4 months ago)
• Topics: ai, finetuning, langchain, llama, llama2, llm, machine-learning, python, pytorch, vllm
• Language: Jupyter Notebook
• Homepage:
• Size: 24.3 MB
• Stars: 9,797
• Watchers: 81
• Forks: 1,387
• Open Issues: 163
• Metadata Files:
  • Readme: README.md
  • Contributing: CONTRIBUTING.md
  • Code of conduct: CODE_OF_CONDUCT.md

Awesome Lists containing this project

• awesome-llama2-resources - Meta's llama-recipes
• awesome - meta-llama/llama-recipes - Scripts for fine-tuning Meta Llama3 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting a (Jupyter Notebook)
• jimsghstars - meta-llama/llama-recipes - Scripts for fine-tuning Meta Llama3 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting a (Jupyter Notebook)
• awesome-rainmana - meta-llama/llama-recipes - Scripts for fine-tuning Meta Llama3 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting a (Jupyter Notebook)
• AiTreasureBox - meta-llama/llama-recipes - 09-08_11522_2](https://img.shields.io/github/stars/meta-llama/llama-recipes.svg)|Scripts for fine-tuning Llama2 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization & question answering. Supporting a number of candid inference solutions such as HF TGI, VLLM for local or cloud deployment.Demo apps to showcase Llama2 for WhatsApp & Messenger| (Repos)