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 2 years ago
Alternatives and similar repositories for MiniRWKV-4
Users that are interested in MiniRWKV-4 are comparing it to the libraries listed below
Sorting:
- ✅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
- 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 2 years ago
- 全球首个StableVicuna中文优化版。☆63Updated 2 years ago
- rwkv finetuning☆37Updated last year
- A QQ Chatbot based on RWKV (W.I.P.)☆80Updated last year
- 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。☆127Updated 2 years 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)☆91Updated 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
- 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
- 使用甄嬛语料微调的chatglm☆86Updated 2 years ago
- This project is established for real-time training of the RWKV model.☆50Updated last year
- Its an open source LLM based on MOE Structure.☆58Updated 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☆149Updated 3 months ago
- 打造人人都会的NLP，开源不易，记得star哦☆102Updated 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☆115Updated 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
- Humanable Chat Generative-model Fine-tuning | LLM微调☆207Updated last year
- 利用LLM+敏感词库，来自动判别是否涉及敏感词。☆127Updated 2 years ago
- ☆42Updated last year
- zero零训练llm调参☆32Updated 2 years ago
- Just for debug☆56Updated last year
- Tracking the hot Github repos and update daily 每天自动追踪Github热门项目☆49Updated this week
- 演示 vllm 对中文大语言模型的神奇效果☆31Updated 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。☆261Updated last year
- Finetune Llama 3, Mistral & Gemma LLMs 2-5x faster with 80% less memory☆28Updated last year
- Customize APIs from GLM, ChatGLM☆69Updated 6 months 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-…☆173Updated last year
- XVERSE-65B: A multilingual large language model developed by XVERSE Technology Inc.☆141Updated last year
- llama inference for tencentpretrain☆99Updated 2 years ago