OctopusMind / DPOLinks
dpo算法实现
☆50Updated last year
Alternatives and similar repositories for DPO
Users that are interested in DPO are comparing it to the libraries listed below
Sorting:
- 基于DPO算法微调语言大模型,简单好上手。☆50Updated last year
- 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。☆368Updated last year
- 怎么训练一个LLM分词器☆154Updated 2 years ago
- Code for a New Loss for Mitigating the Bias of Learning Difficulties in Generative Language Models☆67Updated 11 months ago
- ☆115Updated last year
- an implementation of transformer, bert, gpt, and diffusion models for learning purposes☆160Updated last year
- The complete training code of the open-source high-performance Llama model, including the full process from pre-training to RLHF.☆67Updated 2 years ago
- ☆77Updated 2 years ago
- ☆120Updated last year
- 使用单个24G显卡,从0开始训练LLM☆56Updated 6 months ago
- 基于Gated Attention Unit的Transformer模型(尝鲜版)☆98Updated 2 years ago
- a-m-team's exploration in large language modeling☆195Updated 8 months ago
- 中文 Instruction tuning datasets☆141Updated last year
- ☆48Updated 11 months ago
- 使用sentencepiece中BPE训练中文词表,并在transformers中进行使用。☆120Updated 2 years ago
- 更纯粹、更高压缩率的Tokenizer☆488Updated last year
- NTK scaled version of ALiBi position encoding in Transformer.☆69Updated 2 years ago
- [ICLR 2024]EMO: Earth Mover Distance Optimization for Auto-Regressive Language Modeling(https://arxiv.org/abs/2310.04691)☆128Updated last year
- ☆84Updated 2 years ago
- make LLM easier to use☆59Updated 2 years ago
- 使用 Qwen2ForSequenceClassification 简单实现文本分类任务。☆88Updated 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。☆99Updated last year
- Qwen1.5-SFT(阿里, Ali), Qwen_Qwen1.5-2B-Chat/Qwen_Qwen1.5-7B-Chat微调(transformers)/LORA(peft)/推理☆69Updated last year
- Fantastic Data Engineering for Large Language Models☆93Updated last year
- SuperCLUE-Math6:新一代中文原生多轮多步数学推理数据集的探索之旅☆59Updated 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。☆126Updated 10 months ago
- 大语言模型指令调优工具(支持 FlashAttention)☆178Updated 2 years ago
- ☆184Updated 2 years ago
- This is a personal reimplementation of Google's Infini-transformer, utilizing a small 2b model. The project includes both model and train…☆58Updated last year
- Official github repo for E-Eval, a Chinese K12 education evaluation benchmark for LLMs.☆29Updated last year