StarRing2022 / MiniRWKV-4
实现Blip2RWKV+QFormer的多模态图文对话大模型,使用Two-Step Cognitive Psychology Prompt方法,仅3B参数的模型便能够出现类人因果思维链。对标MiniGPT-4,ImageBind等图文对话大语言模型,力求以更小的算力和资源实现更好的智能效果。
☆38Updated last year
Alternatives and similar repositories for MiniRWKV-4:
Users that are interested in MiniRWKV-4 are comparing it to the libraries listed below
- rwkv finetuning☆36Updated 11 months ago
- ✅4g GPU可用 | 简易实现ChatGLM单机调用多个计算设备(GPU、CPU)进行推理☆34Updated 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…☆116Updated 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
- 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
- deep learning☆150Updated 3 weeks 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
- Just for debug☆56Updated last year
- This project is established for real-time training of the RWKV model.☆49Updated 10 months ago
- 首个llama2 13b 中文版模型 (Base + 中文对话SFT,实现流畅多轮人机自然语言交互)☆90Updated last year
- ☆43Updated last year
- Finetune Llama 3, Mistral & Gemma LLMs 2-5x faster with 80% less memory☆28Updated 10 months ago
- 全球首个StableVicuna中文优化版。☆64Updated last year
- ☆82Updated 10 months ago
- 骆驼QA,中文大语言阅读理解模型。☆75Updated last year
- Its an open source LLM based on MOE Structure.☆58Updated 9 months ago
- 演示 vllm 对中文大语言模型的神奇效果☆31Updated last year
- 使用甄嬛语料微调的chatglm☆84Updated last year
- 多显卡部署版 | ChatGLM-6B:开源双语对话语言模型 | An Open Bilingual Dialogue Language Model☆62Updated 2 years ago
- 基于RWKV模型的角色扮演,实际上是个改的妈都不认识的 RWKV_Role_Playing☆16Updated last year
- 一个简单的,由ChatGPT主导编写的api,使用简单的请求访问ChatRWKV☆15Updated last year
- Qwen-Efficient-Tuning☆43Updated last year
- ☆115Updated 2 weeks ago
- 想要从零开始训练一个中文的mini大语言模型,可以进行基本的对话,模型大小根据手头的机器决定☆59Updated 7 months ago
- llama inference for tencentpretrain☆98Updated last year
- qwen models finetuning☆94Updated 3 weeks ago
- self-host ChatGLM-6B API made with fastapi☆78Updated 2 years ago
- SUS-Chat: Instruction tuning done right☆48Updated last year
- Imitate OpenAI with Local Models☆88Updated 7 months ago
- 打造人人都会的NLP,开源不易,记得star哦☆101Updated last year