minghaochen / chatglm3-base-tuningLinks
chatglm3base模型的有监督微调SFT
☆76Updated last year
Alternatives and similar repositories for chatglm3-base-tuning
Users that are interested in chatglm3-base-tuning are comparing it to the libraries listed below
Sorting:
- 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)。☆360Updated last year
- chatglm多gpu用deepspeed和☆408Updated last year
- Firefly中文LLaMA-2大模型,支持增量预训练Baichuan2、Llama2、Llama、Falcon、Qwen、Baichuan、InternLM、Bloom等大模型☆411Updated last year
- Q&A based on elasticsearch+langchain+chatglm2 | 基于elasticsearch,langchain,chatglm2的自有知识库问答☆243Updated last year
- unified embedding model☆864Updated last year
- 基于sentence transformers和chatglm实现的文档搜索工具☆156Updated 2 years ago
- 中文大模型微调(LLM-SFT), 数学指令数据集MWP-Instruct, 支持模型(ChatGLM-6B, LLaMA, Bloom-7B, baichuan-7B), 支持(LoRA, QLoRA, DeepSpeed, UI, TensorboardX), 支持(微…☆206Updated last year
- chatglm-6B for tools application using langchain☆75Updated 2 years ago
- kbqa,langchain,large langauge model, chatgpt☆81Updated 9 months ago
- ChatGLM2-6B 全参数微调,支持多轮对话的高效微调。☆399Updated last year
- ChatGLM-6B 指令学习|指令数据|Instruct☆653Updated 2 years ago
- Easy and Efficient Finetuning LLMs. (Supported LLama, LLama2, LLama3, Qwen, Baichuan, GLM , Falcon) 大模型高效量化训练+部署.☆610Updated 6 months ago
- 本地知识库 + chatGLM6B + CustomAgent☆270Updated 2 years ago
- Alpaca Chinese Dataset -- 中文指令微调数据集☆210Updated 10 months ago
- ☆520Updated last year
- 雅意信息抽取大模型:在百万级人工构造的高质量信息抽取数据上进行指令微调,由中科闻歌算法团队研发。 (Repo for YAYI Unified Information Extraction Model)☆307Updated last year
- 开源SFT数据集整理,随时补充☆530Updated 2 years ago
- Integrating ONgDB database into langchain ecosystem☆77Updated 2 years ago
- langchain学习笔记,包含langchain源码解读、langchain中使用中文模型、langchain实例等。☆216Updated 2 years ago
- 《ChatGPT原理与实战:大型语言模型的算法、技术和私有化》☆363Updated last year
- 微调ChatGLM☆126Updated 2 years ago
- 阿里通义千问(Qwen-7B-Chat/Qwen-7B), 微调/LORA/推理☆113Updated last year
- ChatGLM2-6B微调, SFT/LoRA, instruction finetune☆108Updated 2 years ago
- SMP 2023 ChatGLM金融大模型挑战赛 60 分baseline思路介绍☆185Updated last year
- 实现了Baichuan-Chat微调,Lora、QLora等各种微调方式,一键运行。☆71Updated last year
- 探索中文instruct数据在ChatGLM, LLaMA上的微调表现☆390Updated 2 years ago
- Tuning LLMs with no tears💦; Sample Design Engineering (SDE) for more efficient downstream-tuning.☆1,009Updated last year
- Humanable Chat Generative-model Fine-tuning | LLM微调☆206Updated last year
- QA based on local knowledge and LLM.☆231Updated 6 months ago
- 本项目是针对RAG中的Retrieve阶段的召回技术及算法效果所做评估实验。使用主体框架为LlamaIndex.☆272Updated 2 weeks ago