Alternatives and similar repositories for moss-finetune-and-moss-finetune-int8

Users that are interested in moss-finetune-and-moss-finetune-int8 are comparing it to the libraries listed below

• zejunwang1 / LLMTuner
  大语言模型指令调优工具（支持 FlashAttention）
  ☆178Updated last year
• sufengniu / RefGPT
  ☆163Updated 2 years ago
• mark1879 / Baichuan-13B-Finetuning
  Baichuan-13B 指令微调
  ☆90Updated 2 years ago
• Miraclemarvel55 / ChatGLM-RLHF
  对ChatGLM直接使用RLHF提升或降低目标输出概率|Modify ChatGLM output with only RLHF
  ☆195Updated 2 years ago
• Felixgithub2017 / MMCU
  MEASURING MASSIVE MULTITASK CHINESE UNDERSTANDING
  ☆88Updated last year
• CSHaitao / ChatGLM_mutli_gpu_tuning
  deepspeed+trainer简单高效实现多卡微调大模型
  ☆128Updated 2 years ago
• FreedomIntelligence / InstructionZoo
  ☆281Updated last year
• liangwq / Chatglm_lora_multi-gpu
  chatglm多gpu用deepspeed和
  ☆412Updated last year
• DA-southampton / RedGPT
  ☆67Updated 2 years ago
• git-cloner / llama2-lora-fine-tuning
  llama2 finetuning with deepspeed and lora
  ☆176Updated 2 years ago
• OpenBMB / ModelCenter
  Efficient, Low-Resource, Distributed transformer implementation based on BMTrain
  ☆262Updated last year
• xv44586 / Chinese-instruction-datasets
  中文 Instruction tuning datasets
  ☆135Updated last year
• CASIA-LM / MoDS
  ☆145Updated last year
• tjunlp-lab / M3KE
  A Massive Multi-Level Multi-Subject Knowledge Evaluation benchmark
  ☆101Updated 2 years ago
• X-PLUG / ChatPLUG
  A Chinese Open-Domain Dialogue System
  ☆324Updated 2 years ago
• yongzhuo / ChatGLM2-SFT
  ChatGLM2-6B微调, SFT/LoRA, instruction finetune
  ☆110Updated 2 years ago
• xubuvd / LLMs
  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。
  ☆122Updated 6 months ago
• CLUEbenchmark / pCLUE
  pCLUE: 1000000+多任务提示学习数据集
  ☆500Updated 2 years ago
• twang2218 / vocab-coverage
  语言模型中文认知能力分析
  ☆237Updated 2 years ago
• SupritYoung / RLHF-Label-Tool
  用于大模型 RLHF 进行人工数据标注排序的工具。A tool for manual response data annotation sorting in RLHF stage.
  ☆254Updated 2 years ago
• shuxueslpi / chatGLM-6B-QLoRA
  使用peft库，对chatGLM-6B/chatGLM2-6B实现4bit的QLoRA高效微调，并做lora model和base model的merge及4bit的量化（quantize）。
  ☆357Updated 2 years ago
• sunzeyeah / RLHF
  Implementation of Chinese ChatGPT
  ☆287Updated last year
• XueFuzhao / InstructionWild
  ☆460Updated last year
• bojone / NBCE
  Naive Bayes-based Context Extension
  ☆325Updated 9 months ago
• yangjianxin1 / LLMPruner
  ☆308Updated 2 years ago
• Alibaba-NLP / EcomGPT
  An Instruction-tuned Large Language Model for E-commerce
  ☆252Updated 2 years ago
• Pillars-Creation / ChatGLM-RLHF-LoRA-RM-PPO
  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
  ☆88Updated 2 years ago
• l294265421 / alpaca-rlhf
  Finetuning LLaMA with RLHF (Reinforcement Learning with Human Feedback) based on DeepSpeed Chat
  ☆114Updated 2 years ago
• MikeGu721 / XiezhiBenchmark
  ☆96Updated last year
• SmartLi8 / stella
  text embedding
  ☆147Updated 2 years ago