sugarandgugu / Simple-Trl-TrainingLinks
基于DPO算法微调语言大模型,简单好上手。
☆45Updated last year
Alternatives and similar repositories for Simple-Trl-Training
Users that are interested in Simple-Trl-Training are comparing it to the libraries listed below
Sorting:
- 怎么训练一个LLM分词器☆153Updated 2 years ago
- ☆119Updated last year
- Code for a New Loss for Mitigating the Bias of Learning Difficulties in Generative Language Models☆65Updated 8 months ago
- Clustering and Ranking: Diversity-preserved Instruction Selection through Expert-aligned Quality Estimation☆90Updated 11 months ago
- 使用单个24G显卡,从0开始训练LLM☆56Updated 3 months ago
- ☆145Updated 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。☆95Updated last year
- Official Repository for SIGIR2024 Demo Paper "An Integrated Data Processing Framework for Pretraining Foundation Models"☆84Updated last year
- ☆84Updated last year
- 在verl上做reward的定制开发☆120Updated 5 months ago
- 1st Solution For Conversational Multi-Doc QA Workshop & International Challenge @ WSDM'24 - Xiaohongshu.Inc☆161Updated 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。☆347Updated last year
- 使用 Qwen2ForSequenceClassification 简单实现文本分类任务。☆83Updated last year
- ☆70Updated 3 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☆32Updated last year
- ☆115Updated 11 months ago
- 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。☆125Updated 7 months ago
- Dataset and evaluation script for "Evaluating Hallucinations in Chinese Large Language Models"☆135Updated last year
- Reinforcement Learning in LLM and NLP.☆61Updated last month
- a-m-team's exploration in large language modeling☆189Updated 5 months ago
- 大语言模型指令调优工具(支持 FlashAttention)☆178Updated last year
- Fantastic Data Engineering for Large Language Models☆91Updated 10 months ago
- ☆47Updated 8 months ago
- ☆98Updated last year
- ☆74Updated last year
- ☆179Updated last year
- [NAACL'24] Self-data filtering of LLM instruction-tuning data using a novel perplexity-based difficulty score, without using any other mo…☆398Updated 4 months ago
- deepspeed+trainer简单高效实现多卡微调大模型☆129Updated 2 years ago
- 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 …☆34Updated 5 months ago
- llm & rl☆236Updated last week