Popular repositories Loading

1. MoE MoE Public

   some mixture of experts architecture implementations

   Python 7 1

2. nanotron nanotron Public

   Forked from huggingface/nanotron

   Minimalistic large language model 3D-parallelism training

   Python 7 5

3. lighteval-multilingual lighteval-multilingual Public

   Forked from huggingface/lighteval

   LightEval is a lightweight LLM evaluation suite that Hugging Face has been using internally with the recently released LLM data processing library datatrove and LLM training library nanotron.

   Python 2

4. video2dataset video2dataset Public

   Forked from iejMac/video2dataset

   Easily create large video dataset from video urls

   Python 1

5. Megatron-LLM Megatron-LLM Public

   Forked from epfLLM/Megatron-LLM

   distributed trainer for LLMs

   Python

6. data-PDF-pipeline data-PDF-pipeline Public

   PDF pipeline for creating training corpora (mainly for llm, multimodal and alignment horizontals)

   Python