suu990901 / LLaMA-MiLe-Loss
Code for a New Loss for Mitigating the Bias of Learning Difficulties in Generative Language Models
☆62Updated 2 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
- 怎么训练一个LLM分词器☆144Updated last year
- ☆140Updated last year
- 使用单个24G显卡，从0开始训练LLM☆53Updated 6 months ago
- ☆109Updated 5 months ago
- Clustering and Ranking: Diversity-preserved Instruction Selection through Expert-aligned Quality Estimation☆78Updated 5 months ago
- Trinity-RFT is a general-purpose, flexible and scalable framework designed for reinforcement fine-tuning (RFT) of large language models (…☆71Updated this week
- llama，chatglm 等模型的微调☆88Updated 9 months ago
- 大语言模型指令调优工具（支持 FlashAttention）☆172Updated last year
- ☆169Updated last year
- Finetuning LLaMA with RLHF (Reinforcement Learning with Human Feedback) based on DeepSpeed Chat☆115Updated 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 …☆32Updated 4 months ago
- ☆81Updated 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。☆317Updated 9 months ago
- ☆109Updated 10 months ago
- ☆41Updated 2 months ago
- Dataset and evaluation script for "Evaluating Hallucinations in Chinese Large Language Models"☆125Updated 11 months ago
- 基于DPO算法微调语言大模型，简单好上手。☆37Updated 10 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☆83Updated last year
- an implementation of transformer, bert, gpt, and diffusion models for learning purposes☆155Updated 6 months ago
- InsTag: A Tool for Data Analysis in LLM Supervised Fine-tuning☆256Updated 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☆54Updated last year
- CLongEval: A Chinese Benchmark for Evaluating Long-Context Large Language Models☆40Updated last year
- deepspeed+trainer简单高效实现多卡微调大模型☆125Updated last year
- Fantastic Data Engineering for Large Language Models☆87Updated 4 months ago
- ☆143Updated 10 months ago
- 1st Solution For Conversational Multi-Doc QA Workshop & International Challenge @ WSDM'24 - Xiaohongshu.Inc☆161Updated last year
- ☆97Updated last year
- NTK scaled version of ALiBi position encoding in Transformer.☆67Updated last year
- pytorch分布式训练☆65Updated last year
- ☆160Updated 2 years ago