FlagOpen / FlagData

Related projects ⓘ

Alternatives and complementary repositories for FlagData

• THUDM / AlignBench
  大模型多维度中文对齐评测基准 (ACL 2024)
  ☆330Updated 2 months ago
• chaoswork / sft_datasets
  开源SFT数据集整理,随时补充
  ☆440Updated last year
• twang2218 / vocab-coverage
  语言模型中文认知能力分析
  ☆235Updated last year
• ArtificialZeng / Baichuan2-Explained
  Baichuan2代码的逐行解析版本，适合小白
  ☆209Updated last year
• modelscope / evalscope
  A streamlined and customizable framework for efficient large model evaluation and performance benchmarking
  ☆231Updated this week
• SupritYoung / RLHF-Label-Tool
  用于大模型 RLHF 进行人工数据标注排序的工具。A tool for manual response data annotation sorting in RLHF stage.
  ☆241Updated last year
• CASIA-LM / ChineseWebText
  ☆158Updated 11 months ago
• SpursGoZmy / Tabular-LLM
  本项目旨在收集开源的表格智能任务数据集（比如表格问答、表格-文本生成等），将原始数据整理为指令微调格式的数据并微调LLM，进而增强LLM对于表格数据的理解，最终构建出专门面向表格智能任务的大型语言模型。
  ☆463Updated 6 months ago
• wenge-research / YAYI-UIE
  雅意信息抽取大模型：在百万级人工构造的高质量信息抽取数据上进行指令微调，由中科闻歌算法团队研发。 (Repo for YAYI Unified Information Extraction Model)
  ☆269Updated 3 months ago
• NLPJCL / RAG-Retrieval
  Unify Efficient Fine-tuning of RAG Retrieval, including Embedding, ColBERT,Cross Encoder
  ☆497Updated last week
• yangjianxin1 / Firefly-LLaMA2-Chinese
  Firefly中文LLaMA-2大模型，支持增量预训练Baichuan2、Llama2、Llama、Falcon、Qwen、Baichuan、InternLM、Bloom等大模型
  ☆396Updated last year
• percent4 / embedding_rerank_retrieval
  本项目是针对RAG中的Retrieve阶段的召回技术及算法效果所做评估实验。使用主体框架为LlamaIndex.
  ☆171Updated 2 months ago
• IAAR-Shanghai / CRUD_RAG
  CRUD-RAG: A Comprehensive Chinese Benchmark for Retrieval-Augmented Generation of Large Language Models
  ☆236Updated last week
• zejunwang1 / LLMTuner
  大语言模型指令调优工具（支持 FlashAttention）
  ☆166Updated 10 months ago
• zhanshijinwat / Steel-LLM
  Train a Chinese LLM From 0 by Personal
  ☆197Updated last week
• QwenLM / vllm-gptq
  A high-throughput and memory-efficient inference and serving engine for LLMs
  ☆121Updated 10 months ago
• 360AILAB-NLP / 360LayoutAnalysis
  360LayoutAnaylsis, a series Document Analysis Models and Datasets deleveped by 360 AI Research Institute
  ☆234Updated last month
• yongzhuo / 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…
  ☆166Updated 5 months ago
• SUFE-AIFLM-Lab / FinEval
  FinEval是一个中文金融领域高质量多项选择与文本问答题的集合。
  ☆160Updated 2 weeks ago
• CLUEbenchmark / SuperCLUE-RAG
  中文原生检索增强生成测评基准
  ☆98Updated 6 months ago
• xubuvd / LLMs
  专注于中文领域大语言模型，落地到某个行业某个领域，成为一个行业大模型、公司级别或行业级别领域大模型。
  ☆111Updated last month
• jiahe7ay / MINI_LLM
  This is a repository used by individuals to experiment and reproduce the pre-training process of LLM.
  ☆353Updated 6 months ago
• sufengniu / RefGPT
  ☆157Updated last year
• alipay / financial_evaluation_dataset
  ☆168Updated 10 months ago
• stanleylsx / llms_tool
  一个基于HuggingFace开发的大语言模型训练、测试工具。支持各模型的webui、终端预测，低参数量及全参数模型训练(预训练、SFT、RM、PPO、DPO)和融合、量化。
  ☆202Updated 11 months ago
• zjunlp / IEPile
  [ACL 2024] IEPile: A Large-Scale Information Extraction Corpus
  ☆168Updated this week
• yangjianxin1 / LLMPruner
  ☆297Updated last year
• liucongg / ChatGPTBook
  《ChatGPT原理与实战：大型语言模型的算法、技术和私有化》
  ☆338Updated 11 months ago
• Chinese-Tiny-LLM / Chinese-Tiny-LLM
  ☆213Updated 5 months ago
• flageval-baai / FlagEval
  FlagEval is an evaluation toolkit for AI large foundation models.
  ☆299Updated 3 months ago