StarRing2022 / MiniRWKV-4Links
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
Sorting:
- 全球首个StableVicuna中文优化版。☆64Updated 2 years ago
- rwkv finetuning☆36Updated 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
- ✅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 2 years ago
- XVERSE-65B: A multilingual large language model developed by XVERSE Technology Inc.☆139Updated last year
- 使用甄嬛语料微调的chatglm☆86Updated 2 years ago
- share data, prompt data , pretraining data☆36Updated last year
- 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
- GPT+神器,简单实用的一站式AGI架构,内置本地化,LLM模型,agent,矢量数据库,智能链chain☆48Updated 2 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 2 years ago
- The Silk Magic Book will record the Magic Prompts on some very Large LLMs. The Silk Magic Book belongs to the project Luotuo(骆驼), which c…☆56Updated 2 years ago
- 👋 欢迎来到 ChatGLM 创意世界!你可以使用修订和续写的功能来生成创意内容!☆246Updated last year
- OrionStar-Yi-34B-Chat 是一款开源中英文Chat模型,由猎户星空基于Yi-34B开源模型、使用15W+高质量语料微调而成。☆259Updated last year
- Tracking the hot Github repos and update daily 每天自动追踪Github热门项目☆50Updated this week
- AGI模块库架构图☆76Updated last year
- XVERSE-7B: A multilingual large language model developed by XVERSE Technology Inc.☆53Updated last year
- 骆驼QA,中文大语言阅读理解模型。☆74Updated 2 years ago
- deep learning☆148Updated 2 months ago
- 利用LLM+敏感词库,来自动判别是否涉及敏感词。☆126Updated 2 years 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☆164Updated last year
- 演示 vllm 对中文大语言模型的神奇效果☆31Updated last year
- Humanable Chat Generative-model Fine-tuning | LLM微调☆207Updated last year
- SuperCLUE琅琊榜:中文通用大模型匿名对战评价基准☆145Updated last year
- zero零训练llm调参☆31Updated last year
- Its an open source LLM based on MOE Structure.☆58Updated last year
- Finetune Llama 3, Mistral & Gemma LLMs 2-5x faster with 80% less memory☆28Updated last year
- self-host ChatGLM-6B API made with fastapi☆78Updated 2 years ago
- 打造人人都会的NLP,开源不易,记得star哦☆101Updated 2 years ago
- ChatGLM 6B 的模型与UI,通过 LangChain 与向量匹配实现本地知识库问答,支持流式输出☆113Updated 2 years ago
- 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