heyblackC / BetterMixture-Top1-SolutionLinks
天池算法比赛《BetterMixture - 大模型数据混合挑战赛》的第一名top1解决方案
☆31Updated 11 months ago
Alternatives and similar repositories for BetterMixture-Top1-Solution
Users that are interested in BetterMixture-Top1-Solution are comparing it to the libraries listed below
Sorting:
- kaggle 2024 Eedi 第10名 金牌方案☆35Updated 5 months ago
- 基于DPO算法微调语言大模型,简单好上手。☆39Updated 11 months ago
- 使用单个24G显卡,从0开始训练LLM☆55Updated last month
- Llama-3-SynE: A Significantly Enhanced Version of Llama-3 with Advanced Scientific Reasoning and Chinese Language Capabilities | 继续预训练提升 …☆33Updated 3 weeks ago
- 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☆62Updated 4 months ago
- 通义千问的DPO训练☆49Updated 9 months ago
- ☆12Updated 3 months ago
- ☆111Updated 11 months ago
- Clustering and Ranking: Diversity-preserved Instruction Selection through Expert-aligned Quality Estimation☆81Updated 7 months ago
- 在verl上做reward的定制开发☆54Updated last month
- 通用简单工具项目☆19Updated 8 months ago
- Code for a New Loss for Mitigating the Bias of Learning Difficulties in Generative Language Models☆63Updated 4 months ago
- pytorch分布式训练☆66Updated last year
- 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。☆88Updated 9 months ago
- Qwen1.5-SFT(阿里, Ali), Qwen_Qwen1.5-2B-Chat/Qwen_Qwen1.5-7B-Chat微调(transformers)/LORA(peft)/推理☆63Updated last year
- 使用 Qwen2ForSequenceClassification 简单实现文本分类任务。☆67Updated last year
- LLM+RAG for QA☆22Updated last year
- WWW2025 Multimodal Intent Recognition for Dialogue Systems Challenge☆120Updated 7 months ago
- ChatGLM2-6B-Explained☆35Updated last year
- 这是个人关于llm的学习归纳,把我学到的知识分享给大家,让大家也能系统和简单学习llm理论及应用实战☆8Updated last year
- Official Repository for SIGIR2024 Demo Paper "An Integrated Data Processing Framework for Pretraining Foundation Models"☆81Updated 10 months ago
- 2023全球智能汽车AI挑战赛——赛道一:AI大模型检索问答, 75+ baseline☆58Updated last year
- 怎么训练一个LLM分词器☆150Updated last year
- 训练一个对中文支持更好的LLaVA模型,并开源训练代码和数据。☆61Updated 9 months ago
- 大语言模型训练和服务调研☆37Updated last year
- 阿里天池: 2023全球智能汽车AI挑战赛——赛道一:AI大模型检索问答 baseline 80+☆105Updated last year
- ChatGLM-6B添加了RLHF的实现,以及部分核心代码的逐行讲解 ,实例部分是做了个新闻短标题的生成,以及指定context推荐的RLHF的实现☆86Updated last year
- ☆48Updated last year
- The complete training code of the open-source high-performance Llama model, including the full process from pre-training to RLHF.☆66Updated 2 years ago
- deepspeed+trainer简单高效实现多卡微调大模型☆126Updated 2 years ago