Download the latest stable Synergy binaries.

计算机自学指南

The math library of Lean 4

Official codebase for the paper "Beyond A* Better Planning with Transformers via Search Dynamics Bootstrapping".

Conversion between Traditional and Simplified Chinese

The most comprehensive database of Chinese poetry 🧶最全中华古诗词数据库, 唐宋两朝近一万四千古诗人, 接近5.5万首唐诗加26万宋诗. 两宋时期1564位词人，21050首词。

MiniCheck: Efficient Fact-Checking of LLMs on Grounding Documents [EMNLP 2024]

A tool for extracting plain text from Wikipedia dumps

中文自然语言处理数据集，平时做做实验的材料。欢迎补充提交合并。

Meta-Transformer for Unified Multimodal Learning

Similarities: a toolkit for similarity calculation and semantic search. 相似度计算、匹配搜索工具包，支持亿级数据文搜文、文搜图、图搜图，python3开发，开箱即用。

A package to evaluate factuality of long-form generation. Original implementation of our EMNLP 2023 paper "FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation"

Scalable training for dense retrieval models.

Get up and running with Llama 3.1, Mistral, Gemma 2, and other large language models.

Official completion of “Training on the Benchmark Is Not All You Need”.

TextGen: Implementation of Text Generation models, include LLaMA, BLOOM, GPT2, BART, T5, SongNet and so on. 文本生成模型，实现了包括LLaMA，ChatGLM，BLOOM，GPT2，Seq2Seq，BART，T5，UDA等模型的训练和预测，开箱即用。

text2vec, text to vector. 文本向量表征工具，把文本转化为向量矩阵，实现了Word2Vec、RankBM25、Sentence-BERT、CoSENT等文本表征、文本相似度计算模型，开箱即用。

Fengshenbang-LM(封神榜大模型)是IDEA研究院认知计算与自然语言研究中心主导的大模型开源体系，成为中文AIGC和认知智能的基础设施。

[ACL 2024] User-friendly evaluation framework: Eval Suite & Benchmarks: UHGEval, HaluEval, HalluQA

Cool Papers - Immersive Paper Discovery

Dataset and evaluation script for "Evaluating Hallucinations in Chinese Large Language Models"

LLM hallucination paper list

Token-level Reference-free Hallucination Detection

Code of ICLR paper: https://openreview.net/forum?id=-cqvvvb-NkI

Teaching Models to Express Their Uncertainty in Words

Do Large Language Models Know What They Don’t Know?

EMNLP'2021: Simple Entity-centric Questions Challenge Dense Retrievers https://arxiv.org/abs/2109.08535

Leaderboard Comparing LLM Performance at Producing Hallucinations when Summarizing Short Documents