Pinned Repositories
44Key
A simple, cheap, and somewhat secure USB Key for SSH authentication, costs < $5
44Player
Transparent OLED music player
44vba
BootNTR
desmume-wasm
NTR
p7zip-wasm
ProjectSend
Send files/images/text messages between your devices in local network.
SourceHanSans-Pixel
基于思源黑体的开源像素字体
vba-next-wasm
Optimized port of VBA-M to <del>Libretro</del> WebAssembly.
44670's Repositories
44670/desmume-wasm
44670/44vba
44670/44Player
Transparent OLED music player
44670/writeups
44670/pspkvm
44670/AIScripts
Some simple scripts that I use day-to-day when working with LLMs and Huggingface Hub
44670/awesome-web-desktops
Websites, web apps, portfolios which look like desktop operating systems
44670/llama.cpp
Port of Facebook's LLaMA model in C/C++
44670/SimpleDNS
44670/44Reader
44670/alpaca_eval
A automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.
44670/Cemu
Cemu is a Wii U emulator
44670/code-eval
Run evaluation on LLMs using human-eval benchmark
44670/crosvm
The Chrome OS Virtual Machine Monitor - Mirror of https://chromium.googlesource.com/crosvm/crosvm/
44670/FastChat
The release repo for "Vicuna: An Open Chatbot Impressing GPT-4"
44670/Firefly
Firefly(流萤): 中文对话式大语言模型(全量微调+QLoRA),支持微调Llma2、Llama、Baichuan、InternLM、Ziya、Bloom等大模型
44670/gpsp-wasm
gpSP for libretro.
44670/grok-1
Grok open release
44670/llama
Inference code for LLaMA models
44670/LLaMA-Factory
Unify Efficient Fine-Tuning of 100+ LLMs
44670/mdict-query
A python module for looking up mdict dictionary file (.mdx and .mdd).
44670/MeloTTS
High-quality multi-lingual text-to-speech library by MyShell.ai. Support English, Spanish, French, Chinese, Japanese and Korean.
44670/mvisor
A mini x86 hypervisor
44670/nanoGPT
The simplest, fastest repository for training/finetuning medium-sized GPTs.
44670/oss-fuzz
OSS-Fuzz - continuous fuzzing for open source software.
44670/python-markdownify
Convert HTML to Markdown
44670/stable-diffusion
Optimized Stable Diffusion modified to run on lower GPU VRAM
44670/StableCascade
44670/theta-calc
44670/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs