Paul33333 / SFT-and-DPO
This is a detailed code demo on how to conduct Full-Param Supervised Fine-tuning (SFT) and DPO (Direct Preference Optimization)
☆12Updated 2 months ago
Alternatives and similar repositories for SFT-and-DPO:
Users that are interested in SFT-and-DPO are comparing it to the libraries listed below
- ☆106Updated 9 months ago
- 该仓库主要记录 大模型(LLMs) 算法工程师相关的面试题与我写的答案☆22Updated last year
- 使用单个24G显卡,从0开始训练LLM☆50Updated 5 months ago
- ☆66Updated last year
- 基于DPO算法微调语言大模型,简单好上手。☆33Updated 8 months 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☆58Updated last month
- LLM Tokenizer with BPE algorithm☆31Updated 10 months ago
- kaggle 2024 Eedi 第10名 金牌方案☆31Updated 3 months ago
- ☆68Updated last month
- pytorch分布式训练☆64Updated last year
- 大模型基础学习和面试八股文☆98Updated last year
- ☆40Updated 7 months ago
- 本项目用于Embedding模型的相关实验,包括Embedding模型评估、Embedding模型微调、Embedding模型量化等。☆44Updated 8 months ago
- GAIIC赛道一:影像学 NLP — 医学影像诊断报告生成 [A100换你大棚甜瓜 Rank-12 方案]☆62Updated last year
- RAG 论文学习☆91Updated last week
- 通义千问的DPO训练☆40Updated 6 months ago
- WWW2025 Multimodal Intent Recognition for Dialogue Systems Challenge☆118Updated 4 months ago
- 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☆27Updated 8 months ago
- 对llama3进行全参微调、lora微调以及qlora微调。☆187Updated 5 months ago
- Inference code for LLaMA models☆118Updated last year
- Code for a New Loss for Mitigating the Bias of Learning Difficulties in Generative Language Models☆62Updated last month
- Clustering and Ranking: Diversity-preserved Instruction Selection through Expert-aligned Quality Estimation☆76Updated 4 months ago
- 快速入门RAG与私有化部署☆163Updated 11 months ago
- 1st Solution For Conversational Multi-Doc QA Workshop & International Challenge @ WSDM'24 - Xiaohongshu.Inc☆162Updated last year
- 使用 Qwen2ForSequenceClassification 简单实现文本分类任务。☆59Updated 9 months ago
- 手搓Llama,个人学习用☆12Updated 10 months ago
- 一些 LLM 方面的从零复现笔记☆177Updated 6 months ago
- ☆50Updated 6 months ago
- 怎么训练一个LLM分词器☆142Updated 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☆82Updated last year