27182812 / ChatGLM-LLaMA-chinese-insturct
探索中文instruct数据在ChatGLM, LLaMA上的微调表现
☆390Updated last year
Alternatives and similar repositories for ChatGLM-LLaMA-chinese-insturct:
Users that are interested in ChatGLM-LLaMA-chinese-insturct are comparing it to the libraries listed below
- ChatGLM-6B 指令学习|指令数据|Instruct☆655Updated last year
- alpaca中文指令微调数据集☆392Updated last year
- CamelBell（驼铃) is be a Chinese Language Tuning project based on LoRA. CamelBell is belongs to Project Luotuo(骆驼), an open sourced Chinese-…☆172Updated last year
- ChatGLM-6B fine-tuning.☆135Updated last year
- chatglm多gpu用deepspeed和☆408Updated 8 months ago
- pCLUE: 1000000+多任务提示学习数据集☆485Updated 2 years ago
- 基于sentence transformers和chatglm实现的文档搜索工具☆154Updated last year
- 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.☆264Updated last year
- Implementation of Chinese ChatGPT☆287Updated last year
- Humanable Chat Generative-model Fine-tuning | LLM微调☆207Updated last year
- 语言模型中文认知能力分析☆235Updated last year
- 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）。☆358Updated last year
- chatglm-6b微调/LORA/PPO/推理, 样本为自动生成的整数/小数加减乘除运算, 可gpu/cpu☆164Updated 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☆408Updated last year
- ChatGLM2-6B 全参数微调，支持多轮对话的高效微调。☆398Updated last year
- BiLLa: A Bilingual LLaMA with Enhanced Reasoning Ability☆420Updated last year
- ☆306Updated last year
- 人工精调的中文对话数据集和一段chatglm的微调代码☆1,174Updated 10 months ago
- 微调ChatGLM☆125Updated 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☆150Updated 2 weeks ago
- llama inference for tencentpretrain☆98Updated last year
- PromptCLUE, 全中文任务支持零样本学习模型☆662Updated last year
- unified embedding model☆851Updated last year
- A Chinese Open-Domain Dialogue System☆319Updated last year
- Code for fintune ChatGLM-6b using low-rank adaptation (LoRA)☆722Updated last year
- Baichuan-13B 指令微调☆89Updated last year
- 骆驼:A Chinese finetuned instruction LLaMA. Developed by 陈启源 @ 华中师范大学 & 李鲁鲁 @ 商汤科技 & 冷子昂 @ 商汤科技☆716Updated last year
- 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.☆249Updated last year
- ☆279Updated 10 months ago