Popular repositories Loading

1. llm_ppo_deepspeed llm_ppo_deepspeed Public

   Customized llm PPO (reinforcement learning) pipeline with deepSpeed. For Amex external usage. Training reward model, actor-critic models with referenced supervised fine-tuned model

   Python 1

2. jiayi jiayi Public

   Forked from cleanlab/cleanlab

   The standard data-centric AI package for data quality and machine learning with messy, real-world data and labels

   Python

3. llm_langchain_projects llm_langchain_projects Public

   Collection of llm_langchain_projects: Autolabelling, Search and Indexing

   Python

4. fairest_kg fairest_kg Public

   Implement of Knowledge graph to text model. Integrated with Fairseq (Meta Fair research library)

5. multimodal_scripts multimodal_scripts Public

   Customized training scripts of multimodal components: clip, ViT, detr

6. llm_peft llm_peft Public

   LLM PEFT finetuning scripts for llama2 and Chatglm