#
Lists (4)
Starred repositories
Lightweight coding agent that runs in your terminal
Search-R1: An Efficient, Scalable RL Training Framework for Reasoning & Search Engine Calling interleaved LLM based on veRL
[ICML 2025 Spotlight] CodeI/O: Condensing Reasoning Patterns via Code Input-Output Prediction
Minimal reproduction of DeepSeek R1-Zero
Efficient Zero-Knowledge Proofs for LoRA Verification
A series of technical report on Slow Thinking with LLM
Sky-T1: Train your own O1 preview model within $450
Parlant is the open-source engine for controlled, compliant, and purposeful generative AI conversations. It gives you the power of LLMs without the unpredictability.
"GraphAgent: Agentic Graph Language Assistant"
LLM reads a paper and produce a working prototype
Mulberry, an o1-like Reasoning and Reflection MLLM Implemented via Collective MCTS
The implementation for the work "CoLLM: Integrating Collaborative Embeddings into Large Language Models for Recommendation".
Banishing LLM Hallucinations Requires Rethinking Generalization
Get your documents ready for gen AI
Python tool for converting files and office documents to Markdown.
CycleQD is a framework for parameter space model merging.
Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.
Production ready LLM model compression/quantization toolkit with hw accelerated inference support for both cpu/gpu via HF, vLLM, and SGLang.
FacTool: Factuality Detection in Generative AI
This repository contains the joint use of CPO and SimPO method for better reference-free preference learning methods.
Robust recipes to align language models with human and AI preferences
Out-of-the-box (OOTB) GUI Agent for Windows and macOS