Pinned Loading

1. All_things_attention All_things_attention Public

   Comparison of different kinds of attentions

   Jupyter Notebook 1

2. deepseek-moe deepseek-moe Public

   Python

3. huggingface/trl huggingface/trl Public

   Train transformer language models with reinforcement learning.

   Python 19.1k 2.9k

4. deepseek-mla deepseek-mla Public

   Implementation of DeepSeek's Multihead Latent Attention architecture

   Python

5. OLMo-core OLMo-core Public

   Forked from allenai/OLMo-core

   PyTorch building blocks for the OLMo ecosystem

   Python 6 1