Popular repositories Loading

1. mistralai-7B_training_using_DeepSpeed mistralai-7B_training_using_DeepSpeed Public

   using Deepspeed with multiple gpus to train mistralai instruction 7B with lora adapter + rlhf. Main dataset is nvidia/Nemotron-Post-Training-Dataset-v1. pyspark will be used to preprocess.Annotatio…

   Python 2

2. 3d-vlm-gaussian-splatting-pointclip-on-modelnet40-and-scanobjectnn 3d-vlm-gaussian-splatting-pointclip-on-modelnet40-and-scanobjectnn Public

   achieved over 96 % top1 accuracy on modelnet40 test dataset and 99.91% top1 accuracy on scanobjectnn test dataset with light weighted 3d custome models. projecting 3d pointcloud dataset(with gaussi…

   Python

3. ART ART Public

   Forked from OpenPipe/ART

   Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen2.5, Qwen3, Llama, Kimi, and more!

   Python

4. flash-attention flash-attention Public

   Forked from Dao-AILab/flash-attention

   Fast and memory-efficient exact attention

   Python