suu990901 / LLaMA-MiLe-LossLinks
Code for a New Loss for Mitigating the Bias of Learning Difficulties in Generative Language Models
☆62Updated 4 months ago
Alternatives and similar repositories for LLaMA-MiLe-Loss
Users that are interested in LLaMA-MiLe-Loss are comparing it to the libraries listed below
Sorting:
- 使用单个24G显卡,从0开始训练LLM☆55Updated last month
- ☆81Updated last year
- 基于DPO算法微调语言大模型,简单好上手。☆39Updated 11 months ago
- 在verl上做reward的定制开发☆54Updated last month
- Finetuning LLaMA with RLHF (Reinforcement Learning with Human Feedback) based on DeepSpeed Chat☆114Updated 2 years ago
- 怎么训练一个LLM分词器☆150Updated last year
- 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
- ☆141Updated last year
- ☆44Updated 4 months ago
- deepspeed+trainer简单高效实现多卡微调大模型☆126Updated 2 years ago
- ☆169Updated last year
- Clustering and Ranking: Diversity-preserved Instruction Selection through Expert-aligned Quality Estimation☆79Updated 7 months ago
- ☆111Updated 11 months ago
- 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
- an implementation of transformer, bert, gpt, and diffusion models for learning purposes☆154Updated 8 months ago
- 大语言模型指令调优工具(支持 FlashAttention)☆173Updated last year
- 中文 Instruction tuning datasets☆132Updated last year
- A Massive Multi-Level Multi-Subject Knowledge Evaluation benchmark☆102Updated last year
- pytorch分布式训练☆66Updated last year
- ☆109Updated 7 months ago
- Trinity-RFT is a general-purpose, flexible and scalable framework designed for reinforcement fine-tuning (RFT) of large language models (…☆127Updated this week
- CLongEval: A Chinese Benchmark for Evaluating Long-Context Large Language Models☆40Updated 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。☆328Updated 11 months ago
- a-m-team's exploration in large language modeling☆160Updated 3 weeks ago
- llama,chatglm 等模型的微调☆89Updated 11 months ago
- [ACL 2024] The official codebase for the paper "Self-Distillation Bridges Distribution Gap in Language Model Fine-tuning".☆122Updated 7 months ago
- 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
- ☆97Updated last year
- ☆97Updated last year
- ☆142Updated 11 months ago