hscspring / hcgf
Humanable Chat Generative-model Fine-tuning | LLM微调
☆204Updated last year
Related projects ⓘ
Alternatives and complementary repositories for hcgf
- 探索中文instruct数据在ChatGLM, LLaMA上的微调表现☆388Updated last year
- alpaca中文指令微调数据集☆391Updated last year
- 基于sentence transformers和chatglm实现的文档搜索工具☆154Updated last year
- ChatGLM-6B 指令学习|指令数据|Instruct☆653Updated last year
- chatglm2 6b finetuning and alpaca finetuning☆144Updated 7 months ago
- 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☆163Updated 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-…☆171Updated 11 months ago
- ChatGLM-6B fine-tuning.☆135Updated last year
- chatglm多gpu用deepspeed和☆403Updated 4 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.☆259Updated last year
- 微调ChatGLM☆123Updated last year
- ChatGLM2-6B 全参数微调,支持多轮对话的高效微调。☆395Updated last year
- deep learning☆149Updated 4 months ago
- 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☆397Updated 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)。☆356Updated last year
- 骆驼QA,中文大语言阅读理解模型。☆72Updated last year
- pCLUE: 1000000+多任务提示学习数据集☆469Updated 2 years ago
- 实现一种多Lora权值集成切换+Zero-Finetune零微调增强的跨模型技术方案,LLM-Base+LLM-X+Alpaca,初期,LLM-Base为Chatglm6B底座模型,LLM-X是LLAMA增强模型。该方案简易高效,目标是使此类语言模型能够低能耗广泛部署,并最…☆117Updated last year
- 人工精调的中文对话数据集和一段chatglm的微调代码☆1,158Updated 6 months ago
- 为ChatGLM设计的微调数据集生成工具,速来制作自己的猫娘。☆595Updated 8 months ago
- 语言模型中文认知能力分析☆235Updated last year
- Implement OpenAI APIs and plugin-enabled ChatGPT with open source LLM and other models.☆122Updated 5 months ago
- ChatGLM2-6B微调, SFT/LoRA, instruction finetune☆106Updated 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.☆242Updated last year
- llama inference for tencentpretrain☆96Updated last year
- BiLLa: A Bilingual LLaMA with Enhanced Reasoning Ability☆421Updated 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☆711Updated 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☆189Updated last year