percent4 / llm_math_solverLinks
本项目用于大模型数学解题能力方面的数据集合成,模型训练及评测,相关文章记录。
☆95Updated last year
Alternatives and similar repositories for llm_math_solver
Users that are interested in llm_math_solver are comparing it to the libraries listed below
Sorting:
- 怎么训练一个LLM分词器☆153Updated 2 years ago
- ☆115Updated 10 months ago
- 1st Solution For Conversational Multi-Doc QA Workshop & International Challenge @ WSDM'24 - Xiaohongshu.Inc☆161Updated 2 months ago
- 使用单个24G显卡,从0开始训练LLM☆55Updated 2 months ago
- Official Repository for SIGIR2024 Demo Paper "An Integrated Data Processing Framework for Pretraining Foundation Models"☆82Updated last year
- 大语言模型应用:RAG、NL2SQL、聊天机器人、预训练、MOE混合专家模型、微调训练、强化学习、天池数据竞赛☆69Updated 7 months ago
- ☆147Updated last year
- ☆232Updated last year
- CLongEval: A Chinese Benchmark for Evaluating Long-Context Large Language Models☆42Updated last year
- a-m-team's exploration in large language modeling☆188Updated 4 months ago
- ☆54Updated last year
- 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。☆123Updated 6 months ago
- ☆125Updated last year
- ☆118Updated last year
- Code for a New Loss for Mitigating the Bias of Learning Difficulties in Generative Language Models☆65Updated 7 months ago
- ☆231Updated last year
- ☆145Updated last year
- 在verl上做reward的定制开发☆117Updated 4 months ago
- ☆176Updated last year
- 大语言模型指令调优工具(支持 FlashAttention)☆178Updated last year
- 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。☆220Updated last year
- A Toolkit for Table-based Question Answering☆113Updated last year
- 中文原生检索增强生成测评基准☆122Updated last year
- 数据合成工具,简单高效的合成不同业务场景的大模型训练数据☆29Updated 9 months ago
- [NAACL'24] Self-data filtering of LLM instruction-tuning data using a novel perplexity-based difficulty score, without using any other mo…☆395Updated 3 months ago
- 欢迎来到 "LLM-travel" 仓库!探索大语言模型(LLM)的奥秘 🚀。致力于深入理解、探讨以及实现与大模型相关的各种技术、原理和应用。☆343Updated last year
- 一些 LLM 方面的从零复现笔记☆221Updated 5 months ago
- ☆73Updated 8 months ago
- 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。☆228Updated 3 months ago
- 基于DPO算法微调语言大模型,简单好上手。☆45Updated last year