Mehti Musa(y)ev's starred repositories
label-studio
Label Studio is a multi-type data labeling and annotation tool with standardized output format
onnxruntime
ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
scientific-visualization-book
An open access book on scientific visualization using python and matplotlib
text-generation-inference
Large Language Model Text Generation Inference
ru-test-assignments
Тестовые задания для самостоятельного выполнения от разных it компаний
StoryDiffusion
Create Magic Story!
mistral.rs
Blazingly fast LLM inference.
auto-code-rover
A project structure aware autonomous software engineer aiming for autonomous program improvement. Resolved 30.67% tasks (pass@1) in SWE-bench lite with each task costs less than $0.7.
text-embeddings-inference
A blazing fast inference solution for text embeddings models
executorch
On-device AI across mobile, embedded and edge for PyTorch
torchtitan
A native PyTorch Library for large model training
mPLUG-DocOwl
mPLUG-DocOwl: Modularized Multimodal Large Language Model for Document Understanding
llm-datasets
High-quality datasets, tools, and concepts for LLM fine-tuning.
ConsistentID
Customized ID Consistent for human
wunjo.wladradchenko.ru
Wunjo CE: Face Swap, Lip Sync, Control Remove Objects & Text & Background, Restyling, Audio Separator, Clone Voice, Video Generation. Open Source, Local & Free.
prometheus-eval
Evaluate your LLM's response with Prometheus and GPT4 💯
HairFastGAN
Official Implementation for "HairFastGAN: Realistic and Robust Hair Transfer with a Fast Encoder-Based Approach"
lmstudio.js
LM Studio TypeScript SDK (pre-release public alpha)
video2game
Code release of Video2Game
Airbnb-Build
Full Stack Airbnb Clone with Next.js 13 Tailwind-css, Prisma, MongoDB, NextAuth, Framer-motionSocial, Login (Google and Facebook), Image upload, Cloudinary CDN, Location selection, Map component, Country autocomplete, Fetching listings with server components
starcoder2-self-align
StarCoder2-Instruct: Fully Transparent and Permissive Self-Alignment for Code Generation