-
MIPT
- @ihumaunkabir
Highlights
- Pro
Lists (1)
Sort Name ascending (A-Z)
Stars
Finetune Llama 3.3, Mistral, Phi, Qwen 2.5 & Gemma LLMs 2-5x faster with 70% less memory
Simple, unified interface to multiple Generative AI providers
Materials for the Hugging Face Diffusion Models Course
🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch and FLAX.
Generating figures from research papers, using textual captions from the paper.
An open-source time-series SQL database optimized for fast ingest and complex queries. Packaged as a PostgreSQL extension.
OCR-VQGAN, a discrete image encoder (tokenizer and detokenizer) for figure images in Paper2Fig100k dataset. Implementation of OCR Perceptual loss for clear text-within-image generation. Fork from V…
Synthesizing Graphics Programs for Scientific Figures and Sketches with TikZ
An implementation of model parallel GPT-2 and GPT-3-style models using the mesh-tensorflow library.
Outline Client and Manager, developed by Jigsaw. Outline Manager makes it easy to create your own VPN server. Outline Client lets you share access to your VPN with anyone in your network, giving th…
Secret CLI is a command-line tool designed for securely managing secrets and sensitive information. It provides a simple and efficient interface for creating, storing, and retrieving secrets in a s…
mPLUG-Owl: The Powerful Multi-modal Large Language Model Family
A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API
Interact with your documents using the power of GPT, 100% privately, no data leaks
meta's LLMA-2 based chat framework, optimized for news contents.
Neural Networks: Zero to Hero
The simplest, fastest repository for training/finetuning medium-sized GPTs.
tiktoken is a fast BPE tokeniser for use with OpenAI's models.
OpenAI CLIP text encoders for multiple languages!
GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use.
State-of-the-Art Text Embeddings
Carrot2: Text Clustering Algorithms and Applications
Software in C and data files for the popular GloVe model for distributed word representations, a.k.a. word vectors or embeddings