Codebase for reproducing the experiments of the semantic uncertainty paper (short-phrase and sentence-length experiments).

Dermatology ddx dataset, Jax implementations of Monte Carlo conformal prediction, plausibility regions and statistical annotation aggregation from our recent work on uncertain ground truth (TMLR'23…

Code for STaR: Bootstrapping Reasoning With Reasoning (NeurIPS 2022)

Official implementation of Phi-Mamba. A MOHAWK-distilled model (Transformers to SSMs: Distilling Quadratic Knowledge to Subquadratic Models)

This repository contains the paper list for the paper: Igniting Language Intelligence: The Hitchhiker's Guide From Chain-of-Thought Reasoning to Language Agents

CodeGeeX: An Open Multilingual Code Generation Model (KDD 2023)

GLM-4 series: Open Multilingual Multimodal Chat LMs | 开源多语言多模态对话模型

SWE-bench: Can Language Models Resolve Real-world Github Issues?

中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs)

Llama3、Llama3.1 中文后训练版仓库 - 微调、魔改版本有趣权重 & 训练、推理、评测、部署教程视频 & 文档。

[ICLR 2025] Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing. Your efficient and high-quality synthetic data generation pipeline!

Finetune Llama-3-8b on the MathInstruct dataset

A family of compressed models obtained via pruning and knowledge distillation

[ACL 2024] The project of Symbol-LLM

PaL: Program-Aided Language Models (ICML 2023)

Mix of Minimal Optimal Sets (MMOS) of dataset has two advantages for two aspects, higher performance and lower construction costs on math reasoning.

ToRA is a series of Tool-integrated Reasoning LLM Agents designed to solve challenging mathematical reasoning problems by interacting with tools [ICLR'24].

Train transformer language models with reinforcement learning.

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

代码大模型 预训练&微调&DPO 数据处理 业界处理pipeline sota

Lightweight and portable LLM sandbox runtime (code interpreter) Python library.

Parse LaTeX math expressions

[NeurIPS 2023 Spotlight] LightZero: A Unified Benchmark for Monte Carlo Tree Search in General Sequential Decision Scenarios (awesome MCTS)

(ICML 2024) Alphazero-like Tree-Search can guide large language model decoding and training

Hackable and optimized Transformers building blocks, supporting a composable construction.

Implementation for "Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs"

Claude Engineer is an interactive command-line interface (CLI) that leverages the power of Anthropic's Claude-3.5-Sonnet model to assist with software development tasks.This framework enables Claud…