vxfla / kanchil
Kanchil(鼷鹿)是世界上最小的偶蹄目动物,这个开源项目意在探索小模型(6B以下)是否也能具备和人类偏好对齐的能力。
☆113Updated 2 years ago
Alternatives and similar repositories for kanchil:
Users that are interested in kanchil are comparing it to the libraries listed below
- deep learning☆149Updated this week
- 骆驼QA,中文大语言阅读理解模型。☆74Updated last year
- 探索中文instruct数据在ChatGLM, LLaMA上的微调表现☆390Updated 2 years ago
- 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-…☆174Updated 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
- GTS Engine: A powerful NLU Training System。GTS引擎(GTS-Engine)是一款开箱即用且性能强大的自然语言理解引擎,聚焦于小样本任务,能够仅用小样本就能自动化生产NLP模型。☆91Updated 2 years ago
- ChatGLM-6B fine-tuning.☆135Updated 2 years ago
- llama inference for tencentpretrain☆98Updated last year
- A unified tokenization tool for Images, Chinese and English.☆152Updated 2 years ago
- moss chat finetuning☆50Updated last year
- 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…☆115Updated last year
- ☆172Updated 2 years ago
- Simple implementation of using lora form the peft library to fine-tune the chatglm-6b☆84Updated 2 years ago
- A more efficient GLM implementation!☆55Updated 2 years ago
- ☆308Updated 2 years ago
- ChatGLM2-6B微调, SFT/LoRA, instruction finetune☆107Updated last year
- 基于sentence transformers和chatglm实现的文档搜索工具☆154Updated 2 years ago
- Implementation of Chinese ChatGPT☆287Updated last year
- chatglm_rlhf_finetuning☆28Updated last year
- alpaca中文指令微调数据集☆393Updated 2 years ago
- Silk Road will be the dataset zoo for Luotuo(骆驼). Luotuo is an open sourced Chinese-LLM project founded by 陈启源 @ 华 中师范大学 & 李鲁鲁 @ 商汤科技 & 冷子…☆39Updated last year
- 中文图书语料MD5链接☆217Updated last year
- 使用qlora对中文大语言模型进行微调,包含ChatGLM、Chinese-LLaMA-Alpaca、BELLE☆86Updated 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
- Chinese large language model base generated through incremental pre-training on Chinese datasets☆236Updated last year
- 百川Dynamic NTK-ALiBi的代码实现:无需微调即可推理更长文本☆47Updated last year
- zero零训练llm调参☆31Updated last year
- 基于baichuan-7b的开源多模态大语言模型☆73Updated 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.☆266Updated last year
- 文本去重☆71Updated 11 months ago