Stars
slime is an LLM post-training framework for RL Scaling.
AI turns documents or topics into real, native PowerPoint decks—with native shapes, transitions and animations, data-backed charts and tables on demand, audio narration from speaker notes, and supp…
A feature-rich command-line audio/video downloader
AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
QuantaAlpha transforms how you discover quantitative alpha factors by combining LLM intelligence with evolutionary strategies. Just describe your research direction, and watch as factors are automa…
Qlib is an AI-oriented Quant investment platform that aims to use AI tech to empower Quant Research, from exploring ideas to implementing productions. Qlib supports diverse ML modeling paradigms, i…
Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models
💖🧸 Self hosted, you-owned Grok Companion, a container of souls of waifu, cyber livings to bring them into our worlds, wishing to achieve Neuro-sama's altitude. Capable of realtime voice chat, Minec…
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Gemma4, Llava, …
Middo: Model-Informed Dynamic Data Optimization for Enhanced LLM Fine-Tuning via Closed-Loop Learning (EMNLP 2025 Main)
A simple PyTorch implementation of influence functions.
微舆：人人可用的多Agent舆情分析助手，打破信息茧房，还原舆情原貌，预测未来走向，辅助决策！从0实现，不依赖任何框架。
An implementation of online data mixing for the Pile dataset, based on the GPT-NeoX library.
`dattri` is a PyTorch library for developing, benchmarking, and deploying efficient data attribution algorithms.
[CVPR 2026] MMR1: Enhancing Multimodal Reasoning with Variance-Aware Sampling and Open Resources
Official PyTorch implementation for "Large Language Diffusion Models"
Towards a Unified View of Large Language Model Post-Training
The official repository of paper "Pass@k Training for Adaptively Balancing Exploration and Exploitation of Large Reasoning Models''
Code for the paper-"Mirostat: A Perplexity-Controlled Neural Text Decoding Algorithm" (https://arxiv.org/abs/2007.14966).
Kimi K2 is the large language model series developed by Moonshot AI team
Official Repository of Absolute Zero Reasoner
OLMoE: Open Mixture-of-Experts Language Models
OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.
A simple tool to update bib entries with their official information (e.g., DBLP or the ACL anthology).
[NeurIPS 2023 Spotlight] LightZero: A Unified Benchmark for Monte Carlo Tree Search in General Sequential Decision Scenarios (awesome MCTS)
Extrapolating RLVR to General Domains without Verifiers
Muon is an optimizer for hidden layers in neural networks