zypan0
Follow
Stars
🧑🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), ga…
Finetune Llama 3.3, DeepSeek-R1 & Reasoning LLMs 2x faster with 70% less memory! 🦥
Implementation of Nougat Neural Optical Understanding for Academic Documents
A framework for few-shot evaluation of language models.
KAG is a logical form-guided reasoning and retrieval framework based on OpenSPG engine and LLMs. It is used to build logical reasoning and factual Q&A solutions for professional domain knowledge ba…
This is a replicate of DeepSeek-R1-Zero and DeepSeek-R1 training on small models with limited data
A system for agentic LLM-powered data processing and ETL
Empowering RAG with a memory-based data interface for all-purpose applications!
A lightweight, low-dependency, unified API to use all common reranking and cross-encoder models.
Recipes to train reward model for RLHF.
The official implementation of RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval
RAGEN is the first open-source reproduction of DeepSeek-R1 on AGENT training.
Detect the programming language of a source code
ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search (NeurIPS 2024)
GPT4 based personalized ArXiv paper assistant bot
[EMNLP 2024] LongAlign: A Recipe for Long Context Alignment of LLMs
An automated pipeline for evaluating LLMs for role-playing.
PantheonRL is a package for training and testing multi-agent reinforcement learning environments. PantheonRL supports cross-play, fine-tuning, ad-hoc coordination, and more.
Simple extension on vLLM to help you speed up reasoning model without training.