llama-recipes

llama-recipes copied to clipboard

Project summary should say what it does

2

### System Info All ### Information - [X] The official example scripts - [ ] My own modified scripts ### 🐛 Describe the bug The first sentence of the project...

yavin5

llama3.2 fine tuning generates repeated pattern towards the end of one epoch

6

### System Info PyTorch version: 2.4.1+cu121 Is debug build: False CUDA used to build PyTorch: 12.1 GPU Type and number: A100 80GB x 1 ### Information - [x] The official...

ruian1

# What does this PR do? This PR added llama3 support for alpaca dataset so that people can do alpaca finetune, model conversion and inference. Fixes # ([634](https://github.com/meta-llama/llama-recipes/issues/634)) ## Feature/Issue...

wukaixingxp

### 🚀 The feature, motivation and pitch I saw the fine-tuning recipe of Llama 3.2 Vision but how to do inferencing after fine-tuning. Add a complete guide on that. ###...

himanshushukla12

### 🚀 The feature, motivation and pitch The current llama-recipes codebase only supports eval for llama 3.1 models. It would be very helpful to add eval for llama 3.2 1B-Base/Instruct...

LeoXinhaoLee

Series of Notebooks going from Zero-to-hero for Llama model family - [ ] Module 1: Understanding Llama - [ ] Module 2: Prompt Engineering? - [ ] Module 3: Agents...

init27

Quickstart docs: Fix path to location of dict for custom datasets

2

The file [recipes/quickstart/finetuning/datasets/README.md](https://github.com/meta-llama/llama-recipes/tree/main/recipes/quickstart/finetuning/datasets#adding-new-dataset) explains how to add a new dataset. It notes to edit a dict, but that dict seems to have moved to a different file by now. This...

j-klesen

All functionality has been consolidated into a single file for CLI/UI/Checkpointing and Added fix for issue 702 and added code for that as well, added instructions in local_inference /README.md as well

5

# What does this PR do? This PR adds detailed instructions for using the `code-merge-inference.py` script to generate text from images after fine-tuning the Llama 3.2 vision model. The script...

himanshushukla12

Update Step-1 PDF-Pre-Processing-Logic.ipynb

1

Replace "text" with "extracted_text" # What does this PR do? Fix the error, Fixes # (issue) ## Feature/Issue validation/testing Please describe the tests that you ran to verify your changes...

sharmax-vikas

# What does this PR do? Fix NotebookLlama demo - remove pkg `warnings` from requirements, since we can directly `import warnings` in python 3 - add imports for `wavfile`, `AudioSegment`...

ZacWang