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
- ✅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
- rwkv finetuning☆36Updated 10 months ago
- 全球首个StableVicuna中文优化版。☆64Updated 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
- ☆81Updated 9 months ago
- deep learning☆150Updated 8 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☆164Updated last year
- Just for debug☆56Updated 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)☆89Updated last year
- This project is established for real-time training of the RWKV model.☆49Updated 9 months ago
- XVERSE-65B: A multilingual large language model developed by XVERSE Technology Inc.☆138Updated 10 months ago
- ☆104Updated this week
- 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 last year
- 使用甄嬛语料微调的chatglm☆84Updated last year
- Finetune Llama 3, Mistral & Gemma LLMs 2-5x faster with 80% less memory☆28Updated 9 months ago
- 演示 vllm 对中文大语言模型的神奇效果☆31Updated last year
- A QQ Chatbot based on RWKV (W.I.P.)☆80Updated last year
- chatglm2 6b finetuning and alpaca finetuning☆145Updated 10 months ago
- ChatGLM-6B fine-tuning.☆135Updated last year
- SUS-Chat: Instruction tuning done right☆48Updated last year
- self-host ChatGLM-6B API made with fastapi☆78Updated 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 last year
- ☆43Updated 11 months ago
- 用户友好、开箱即用的 RWKV Prompts 示例,适用于所有用户。Awesome RWKV Prompts for general users, more user-friendly, ready-to-use prompt examples.☆33Updated last month
- Its an open source LLM based on MOE Structure.☆58Updated 8 months ago
- 基于ChatGLM-6B,低成本实现类Instruction效果的角色扮演☆42Updated last year
- 骆驼QA,中文大语言阅读理解模型。☆74Updated last year
- zero零训练llm调参☆31Updated last year
- 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☆111Updated last year
- share data, prompt data , pretraining data☆35Updated last year