RewardAnything: Generalizable Principle-Following Reward Models

A sleek dataset viewer built entirely by AI Agent. Supports streaming large files from WebDAV, S3, SSH, Local or Hugging Face.

50+ solvers for logical puzzles, with 8k+ datasets, including Sudoku-like puzzles, Slitherlink, Pentomino, Hitori, Shikaku, Heyawake, Mosaic, Tent, Creek, Atari, Suguru, Kakuro, etc. Solved via SCI…

EMNLP 2022: Generating Natural Language Proofs with Verifier-Guided Search https://arxiv.org/abs/2205.12443

paper list on reasoning in NLP

The related works and background techniques about Openai o1

Reasoning in LLMs: Papers and Resources, including Chain-of-Thought, OpenAI o1, and DeepSeek-R1 🍓

Awesome Reasoning LLM Tutorial/Survey/Guide

Harnessing the Reasoning Economy: A Survey of Efficient Reasoning for Large Language Models

A curated list of Awesome-LLM-Ensemble papers for the survey "Harnessing Multiple Large Language Models: A Survey on LLM Ensemble"

Papers & Works for large languange models (OpenAI GPT-4, Meta Llama, etc.).

LogicBench is a natural language question-answering dataset consisting of 25 different reasoning patterns spanning over propositional, first-order, and non-monotonic logics.

content-neutral dataset of logical reasoning

[TMLR] A curated list of language modeling researches for code (and other software engineering activities), plus related datasets.

🐳 Efficient Triton implementations for "Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention"

AIInfra（AI 基础设施）指AI系统从底层芯片等硬件，到上层软件栈支持AI大模型训练和推理。

Integrate the DeepSeek API into popular softwares

基于标贝数据继续训练，同时对原本的FastSpeech2模型做了改进，引入了韵律表征以及韵律预测模块，使中文发音更生动且富有节奏

Awesome speech/audio LLMs, representation learning, and codec models

LLaMA-Omni is a low-latency and high-quality end-to-end speech interaction model built upon Llama-3.1-8B-Instruct, aiming to achieve speech capabilities at the GPT-4o level.

为GPT/GLM等LLM大语言模型提供实用化交互接口，特别优化论文阅读/润色/写作体验，模块化设计，支持自定义快捷按钮&函数插件，支持Python和C++等项目剖析&自译解功能，PDF/LaTex论文翻译&总结功能，支持并行问询多种LLM模型，支持chatglm3等本地模型。接入通义千问, deepseekcoder, 讯飞星火, 文心一言, llama2, rwkv, claude2, m…

Ring attention implementation with flash attention

flash attention tutorial written in python, triton, cuda, cutlass

[ACL 2024 (Oral)] A Prospector of Long-Dependency Data for Large 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.

📰 Must-read papers and blogs on LLM based Long Context Modeling 🔥