Popular repositories Loading

1. galactic galactic Public

   data cleaning and curation for unstructured text

   Python 322 14

2. mlx_embedding_models mlx_embedding_models Public

   run embeddings in MLX

   Python 62 6

3. onnx_embedding_models onnx_embedding_models Public

   utilities for loading and running text embeddings with onnx

   Python 39 4

4. BERTgery BERTgery Public

   utilities for doing model surgery (remove layers, extend position embeddings, add flash attention, etc.)

   Python 2

5. taylor-pipelines taylor-pipelines Public

   pipelines for pulling and processing data

   Python 1 1

6. nanoT5 nanoT5 Public

   Forked from PiotrNawrot/nanoT5

   Fast & Simple repository for pre-training and fine-tuning T5-style models

   Python