DenebUniverse

ReST-MCTS

ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search

SpatialLM-StepGame

Codes and data for AAAI-24 paper "Advancing Spatial Reasoning in Large Language Models: An In-depth Evaluation and Enhancement Using the StepGame Benchmark"

tree-of-thought-llm

[NeurIPS 2023] Tree of Thoughts: Deliberate Problem Solving with Large Language Models

LiveBench

LiveBench: A Challenging, Contamination-Free LLM Benchmark

Puzzle-Generator-and-Solver

Puzzle Generator; Einstein's Riddle, Zebra Puzzle and Blood Donation Puzzle Solver. For non-commercial use only!

leetcode

🔥LeetCode solutions in any programming language | 多种编程语言实现 LeetCode、《剑指 Offer（第 2 版）》、《程序员面试金典（第 6 版）》题解

Q-BERT

Agents that build knowledge graphs and explore textual worlds by asking questions

MACM

MACM: Utilizing a Multi-Agent System for Condition Mining in Solving Complex Mathematical Problems

BECEL

Awesome-LLM-Self-Consistency

Awesome LLM Self-Consistency: a curated list of Self-consistency in Large Language Models

flameshot

Powerful yet simple to use screenshot software :desktop_computer: :camera_flash:

nuggets

arena-hard-auto

Arena-Hard-Auto: An automatic LLM benchmark.

llm-course

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

ChatLM-mini-Chinese

中文对话0.2B小模型（ChatLM-Chinese-0.2B），开源所有数据集来源、数据清洗、tokenizer训练、模型预训练、SFT指令微调、RLHF优化等流程的全部代码。支持下游任务sft微调，给出三元组信息抽取微调示例。

kenlm

KenLM: Faster and Smaller Language Model Queries

OpenWebMath

self-correction-llm-papers

This is a collection of research papers for Self-Correcting Large Language Models with Automated Feedback.

Step-DPO

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

self-instruct

Aligning pretrained language models with instruction data generated by themselves.

Firefly

Firefly: 大模型训练工具，支持训练Qwen2、Yi1.5、Phi-3、Llama3、Gemma、MiniCPM、Yi、Deepseek、Orion、Xverse、Mixtral-8x7B、Zephyr、Mistral、Baichuan2、Llma2、Llama、Qwen、Baichuan、ChatGLM2、InternLM、Ziya2、Vicuna、Bloom等大模型

clean-dialog

A framework for cleaning Chinese dialog data

dial-clean

中文对话数据清洗

dsir

DSIR large-scale data selection framework for language model training

OVM

LLMs-as-Instructors

AutoDetect

Official github repo for AutoDetect, an automated weakness detection framework for LLMs.

LLM-SFT

中文大模型微调(LLM-SFT), 数学指令数据集MWP-Instruct, 支持模型(ChatGLM-6B, LLaMA, Bloom-7B, baichuan-7B), 支持(LoRA, QLoRA, DeepSpeed, UI, TensorboardX), 支持(微调, 推理, 测评, 接口)等.

PandaLM

deduplicate-text-datasets