Alic-Li's starred repositories
RWKV-LM-ROCm
RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.
ROCK-Kernel-Driver
AMDGPU Driver with KFD used by the ROCm project. Also contains the current Linux Kernel that matches this base driver
EasySpider
A visual no-code/code-free web crawler/spider易采集:一个可视化浏览器自动化测试/数据采集/爬虫软件,可以无代码图形化的设计和执行爬虫任务。别名:ServiceWrapper面向Web应用的智能化服务封装系统。
RWKV_Pytorch
This is an inference framework for the RWKV large language model implemented purely in native PyTorch. The official native implementation is overly complex and lacks extensibility. Let's join the flexible PyTorch ecosystem and open-source it together!
fish-speech
Brand new TTS solution
CMWTAT_Digital_Edition
CloudMoe Windows 10/11 Activation Toolkit get digital license, the best open source Win 10/11 activator in GitHub. GitHub 上最棒的开源 Win10/Win11 数字权利(数字许可证)激活工具!
stable-diffusion-webui-localization-zh_Hans
SD-WebUI 简体中文翻译扩展 Simplified Chinese Localization for AUTOMATIC1111 Stable Diffusion WebUI
SMS_Bomber
短信轰炸机,可以给定多个手机号,疯狂发送验证码。This is a short message bomber.
RWKV_Role_Playing
使用Gradio制作的基于RWKV的角色扮演的webui
RWKV-Runner
A RWKV management and startup tool, full automation, only 8MB. And provides an interface compatible with the OpenAI API. RWKV is a large language model that is fully open source and available for commercial use.
hand-write
模拟手写效果,节约时间。
GPT-SoVITS
1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
MifareClassicTool
An Android NFC app for reading, writing, analyzing, etc. MIFARE Classic RFID tags.
facefusion
Next generation face swapper and enhancer
SteamTools
🛠「Watt Toolkit」是一个开源跨平台的多功能 Steam 工具箱。
rwkv-cpp-accelerated
A torchless, c++ rwkv implementation using 8bit quantization, written in cuda/hip/vulkan for maximum compatibility and minimum dependencies
RWKV-LM
RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.