HighCWu / rwkv-paddle
☆11Updated last year
Alternatives and similar repositories for rwkv-paddle:
Users that are interested in rwkv-paddle are comparing it to the libraries listed below
- 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
- 全球首个StableVicuna中文优化版。☆64Updated last year
- The paddle implementation of meta's LLaMA.☆45Updated last year
- share data， prompt data , pretraining data☆35Updated last year
- AGI模块库架构图☆75Updated last year
- Its an open source LLM based on MOE Structure.☆58Updated 7 months ago
- 我们是第一个完全可商用的角色大模型。☆39Updated 6 months ago
- 使用甄嬛语料微调的chatglm☆84Updated 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
- Another ChatGLM2 implementation for GPTQ quantization☆54Updated last year
- 纯c++的全平台llm加速库，支持python调用，支持baichuan, glm, llama, moss基座，手机端流畅运行chatglm-6B级模型单卡可达10000+token / s，☆45Updated last year
- zero零训练llm调参☆31Updated last year
- 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…☆37Updated last year
- Gradio UI for RWKV LLM☆28Updated 2 years ago
- qwen2 and llama3 cpp implementation☆40Updated 8 months ago
- rwkv finetuning☆36Updated 10 months ago
- Python3 package for Chinese/English OCR, with paddleocr-v4 onnx model(~14MB). 基于ppocr-v4-onnx模型推理，可实现 CPU 上毫秒级的 OCR 精准预测，通用场景中英文OCR达到开源SO…☆59Updated last month
- 用于SenseVoice的api项目，输出带时间戳字幕☆25Updated 3 months ago
- ☆81Updated 9 months ago
- llama inference for tencentpretrain☆97Updated last year
- TianMu: A modern AI tool with multi-platform support, markdown support, multimodal, continuous conversation, and customizable commands. 一…☆83Updated last year
- kimi-chat 测试数据☆7Updated last year
- 演示 vllm 对中文大语言模型的神奇效果☆31Updated last year
- This project is established for real-time training of the RWKV model.☆49Updated 9 months ago
- A more efficient GLM implementation!☆55Updated 2 years ago
- self-host ChatGLM-6B API made with fastapi☆77Updated 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
- ⚡ boost inference speed of GPT models in transformers by onnxruntime☆53Updated 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
- CodeLLaMA 中文版 - 代码生成助手，huggingface累积下载2w+次☆45Updated last year