pix2tex: Using a ViT to convert images of equations into LaTeX code.
Repository Index
47,133 repositories indexed
25–48 of 70 · Most stars
Nano vLLM
A theoretical reconstruction of the Claude Mythos architecture, built from first principles using the available research literature.
RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RNN and transformer - great performance, linear time, constant space (no kv-cache), fast training, infinite ctx_len, and free sentence embedding.
- attention-mechanism
- deep-learning
- gpt
- gpt-2
[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer
A framework for few-shot evaluation of language models.
- evaluation-framework
- language-model
- transformer
💡 All-in-one AI framework for semantic search, LLM orchestration and language model workflows
- python
- search
- nlp
- semantic-search
Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.
- deep-learning
- pytorch
- grad-cam
- visualizations
Easy-to-use and powerful LLM and SLM library with awesome model zoo.
- nlp
- embedding
- bert
- ernie
HunyuanVideo: A Systematic Framework For Large Video Generation Model
- video-generation
- diffusion-models
- diffusion-transformer
Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Streaming TTS with text frontend, Speaker Verification System, End-to-End Speech Translation and Keyword Spotting. Won NAACL2022 Best Demo Award.
- transformer
- conformer
- speech-translation
- streaming-asr
A PyTorch-based Speech Toolkit
- speech-recognition
- speech-toolkit
- speaker-recognition
- speech-to-text
Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.
- segmentation
- image-processing
- pspnet
- unet
[ECCV 2024] Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"
- object-detection
- open-world
- open-world-detection
- vision-language
🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading
- bloom
- deep-learning
- distributed-systems
- language-models
Hackable and optimized Transformers building blocks, supporting a composable construction.
TranslatedTranslate manga/image: one-click translation of text in all kinds of images https://cotrans.touhou.ai/ (no longer working)
- manga
- anime
- ocr
- deep-learning
Open-source offline translation library written in Python
- python
- machine-translation
- transformers
- translation
Superduper: End-to-end framework for building custom AI applications and agents.
- ai
- mlops
- torch
- transformers
Scalable and user friendly neural :brain: forecasting algorithms.
- deep-learning
- forecasting
- esrnn
- nbeats
Seamlessly integrate LLMs into scikit-learn.
Multilingual Automatic Speech Recognition with word-level timestamps and confidence
Turn any LLM into a Jev-style decision model: typed decisions, real probabilities, no training. (continue updating, welcome any issue and PR request)
- calibration
- decision-model
- jev
- jev-model
Transpile trained scikit-learn estimators and transformers to C, C#, Go, Java, JavaScript, PHP and Ruby.