yangjianxin1 / Firefly-LLaMA2-Chinese
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
☆410Updated last year
Alternatives and similar repositories for Firefly-LLaMA2-Chinese
Users that are interested in Firefly-LLaMA2-Chinese are comparing it to the libraries listed below
Sorting:
- Baichuan2代码的逐行解析版本,适合小白☆214Updated last year
- chatglm多gpu用deepspeed和☆409Updated 10 months ago
- 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)。☆361Updated last year
- ChatGLM2-6B 全参数微调,支持多轮对话的高效微调。☆399Updated last year
- 语言模型中文认知能力分析☆237Updated last year
- ChatGLM-6B 指令学习|指令数据|Instruct☆654Updated 2 years ago
- 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.☆250Updated last year
- pCLUE: 1000000+多任务提示学习数据集☆493Updated 2 years ago
- OpenLLMWiki: Docs of OpenLLMAI. Survey, reproduction and domain/task adaptation of open source chatgpt alternatives/implementations. PiXi…☆259Updated 5 months ago
- alpaca中文指令微调数据集☆393Updated 2 years ago
- Implementation of Chinese ChatGPT☆287Updated last year
- ☆308Updated 2 years ago
- 活字通用大模型☆388Updated 8 months ago
- 开源SFT数据集整理,随时补充☆513Updated last year
- 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…☆199Updated 11 months ago
- Luotuo Embedding(骆驼嵌入) is a text embedding model, which developed by 李鲁鲁, 冷子昂, 陈启源, 蒟蒻等.☆267Updated last year
- 对ChatGLM直接使用RLHF提升或降低目标输出概率|Modify ChatGLM output with only RLHF☆192Updated last year
- deep learning☆149Updated last week
- 探索中文instruct数据在ChatGLM, LLaMA上的微调表现☆390Updated 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.☆602Updated 3 months ago
- 一个基于HuggingFace开发的大语言模型训练、测试工具。支持各模型的webui、终端预测,低参数量及全参数模型训练(预训练、SFT、RM、PPO、DPO)和融合、量化。☆217Updated last year
- 大模型多维度中文对齐评测基准 (ACL 2024)☆386Updated 9 months ago
- 《ChatGPT原理与实战:大型语言模型的算法、技术和私有化》☆355Updated last year
- ☆324Updated 11 months ago
- Tuning LLMs with no tears💦; Sample Design Engineering (SDE) for more efficient downstream-tuning.