shimmy
⚡ Pure-Rust WebGPU inference engine — OpenAI-API compatible, GGUF native, runs on any GPU. No Python. No llama.cpp. Single binary.
- 6k
- Rust
- Apache-2.0
- 10 d ago
⚡ Pure-Rust WebGPU inference engine — OpenAI-API compatible, GGUF native, runs on any GPU. No Python. No llama.cpp. Single binary.
Chronos: Pretrained Models for Time Series Forecasting
A Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines
Structured data extraction, instruction calling and agentic workflows with ML, LLM and Vision LLM
🧠💬 Articles I wrote about machine learning, archived from MachineCurve.com.
Social networking platform with automated content moderation and context-based authentication system
[CVPR 2025] Official PyTorch Implementation of MambaVision: A Hybrid Mamba-Transformer Vision Backbone
a fast and user-friendly runtime for transformer inference (Bert, Albert, GPT2, Decoders, etc) on CPU and GPU.
Trained models & code to predict toxic comments on all 3 Jigsaw Toxic Comment Challenges. Built using ⚡ Pytorch Lightning and 🤗 Transformers.
Distributed training & inference for multimodal perception: shared embeddings across text, images, video, audio, code & graphs from 64 to 1024 dimensions 🖼️
Transformer models from BERT to GPT-4, environments from Hugging Face to OpenAI. Fine-tuning, training, and prompt engineering examples. A bonus section with ChatGPT, GPT-3.5-turbo, GPT-4, and DALL-E including jump starting GPT-4, speech-to-text, text-to-speech, text to image generation with DALL-E, Google Cloud AI,HuggingGPT, and more
Learn Cloud Applied Generative AI Engineering (GenEng) using OpenAI, Gemini, Streamlit, Containers, Serverless, Postgres, LangChain, Pinecone, and Next.js
Browser-only Canva-style presentation studio, powered by local Web AI.
Multimodal model for text and tabular data with HuggingFace transformers as building block for text data
[EMNLP 2022] Unifying and multi-tasking structured knowledge grounding with language models
A tool for generating function arguments and choosing what function to call with local LLMs
Guide: Finetune GPT2-XL (1.5 Billion Parameters) and finetune GPT-NEO (2.7 B) on a single GPU with Huggingface Transformers using DeepSpeed
Easy-Translate is a script for translating large text files with a SINGLE COMMAND. Easy-Translate is designed to be as easy as possible for beginners and as seamlesscustomizable and as possible for advanced users.
Build and train state-of-the-art natural language processing models using BERT
DarkGPT Chat Explorer is an interactive web application that allows users to engage in conversations with various GPT (Generative Pre-trained Transformer) models in real-time. This repository contains the source code for the application.
Thonburian Whisper: Open models for fine-tuned Whisper in Thai. Try our demo on Huggingface space:
[ACL 2024] User-friendly evaluation framework: Eval Suite & Benchmarks: UHGEval, HaluEval, HalluQA, etc.
Demonstration for the Qwen-Image-Edit-2511 model with lazy-loaded LoRA adapters for advanced single- and multi-image editing. Supports 7+ specialized LoRAs including photo-to-anime, multi-angle camera control, pose transfer (Any-Pose), upscaling, style transfer, light migration, and manga tone. Features fast inference (4 steps default).
This repository guides you through the process of building a GPT-style Large Language Model (LLM) from scratch using PyTorch. The structure and approach are inspired by the book Build a Large Language Model (From Scratch) by Sebastian Raschka.
Learn GenAI and Agentic AI from Zero to Production
Codes and datasets of the paper Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment
Hands-on MLOps projects to explore and learn the practical aspects of machine learning engineering for production.
MLOps for Vision Models (TensorFlow) from 🤗 Transformers with TensorFlow Extended (TFX)
Multi-Class Text Classification for products based on their description with Machine Learning algorithms and Neural Networks (MLP, CNN, Distilbert).
FireRed-Image-Edit-1.0-Fast is a high-performance, AI-driven image editing application that utilizes advanced diffusers and the QIE+ Pipeline for precise, prompt-based image modifications.