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 last year
Alternatives and similar repositories for kanchil:
Users that are interested in kanchil are comparing it to the libraries listed below
- 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 last year
- llama inference for tencentpretrain☆97Updated 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
- A more efficient GLM implementation!☆55Updated 2 years ago
- deep learning☆150Updated 7 months ago
- ChatGLM-6B fine-tuning.☆135Updated last year
- Simple implementation of using lora form the peft library to fine-tune the chatglm-6b☆85Updated 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 last year
- alpaca中文指令微调数据集☆392Updated 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…☆117Updated last year
- 探索中文instruct数据在ChatGLM, LLaMA上的微调表现☆390Updated last year
- ☆304Updated last year
- A unified tokenization tool for Images, Chinese and English.☆151Updated last year
- ☆173Updated 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.☆263Updated last year
- 文本去重☆68Updated 8 months ago
- ChatGLM2-6B微调, SFT/LoRA, instruction finetune☆105Updated last year
- 基于baichuan-7b的开源多模态大语言模型☆73Updated last year
- Implementation of Chinese ChatGPT☆287Updated 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
- 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…☆38Updated last year
- chatglm2 6b finetuning and alpaca finetuning☆145Updated 10 months ago
- 骆驼QA，中文大语言阅读理解模型。☆74Updated last year
- A framework for cleaning Chinese dialog data☆265Updated 3 years ago
- ChatGLM-6B-Slim：裁减掉20K图片Token的ChatGLM-6B，完全一样的性能，占用更小的显存。☆126Updated last year
- 中文图书语料MD5链接☆213Updated last year
- Chinese large language model base generated through incremental pre-training on Chinese datasets☆235Updated last year
- ☆90Updated last year
- code for Scaling Laws of RoPE-based Extrapolation☆70Updated last year
- 中文 Instruction tuning datasets☆126Updated 10 months ago