Non-autoregressive System 1 decision engine. Typed choice, score and yes/no decisions over any text in a single forward pass, in 100+ languages, with a router that picks the right checkpoint per request.
pix2tex: Using a ViT to convert images of equations into LaTeX code.
A very simple framework for state-of-the-art Natural Language Processing (NLP)
- pytorch
- nlp
- named-entity-recognition
- sequence-labeling
A unified, comprehensive and efficient recommendation library
- recommender-systems
- collaborative-filtering
- knowledge-graph
- ctr-prediction
📐 Compute distance between sequences. 30+ algorithms, pure python implementation, common interface, optional external libs usage.
My tensorflow implementation of "A neural conversational model", a Deep learning based chatbot
Multilingual Automatic Speech Recognition with word-level timestamps and confidence
Serve large Qwen models fast on the GPUs you actually own. Qwen3.8-27B on a single 24 GB card with vLLM: 127 tok/s single-user (381 when the answer quotes the prompt), ~1,035 tok/s at 64 concurrent, 150k-262k context. vLLM patches, requant pipeline, benchmarks.
✨ Open-source DORA metrics platform for engineering teams ✨
- dora
- dora-metrics
- devops
- dev-tool
Implementation of DiffDock: Diffusion Steps, Twists, and Turns for Molecular Docking
Brian is a free, open source simulator for spiking neural networks.
Simple shell script to use OpenAI's ChatGPT and DALL-E from the terminal. No Python or JS required.
RNNLIB is a recurrent neural network library for sequence learning problems. Forked from Alex Graves work http://sourceforge.net/projects/rnnl/
DNABERT: pre-trained Bidirectional Encoder Representations from Transformers model for DNA-language in genome
- kmer
- dnabert-model
- kmer-format
- gpu
Bias Auditing & Fair ML Toolkit
- fairness
- bias
- machine-bias
- fairness-testing
Tasks Assessing Protein Embeddings (TAPE), a set of five biologically relevant semi-supervised learning tasks spread across different domains of protein biology.
- deep-learning
- protein-sequences
- protein-structure
- semi-supervised-learning
Sequence learning toolkit for Python
Generation of protein sequences and evolutionary alignments via discrete diffusion models
- discrete-diffusion
- generative-model
- multiple-sequence-alignment
- protein-sequences
A Euclidean diffusion model for structure-based drug design.
- ddpm
- drug-design
- equivariance
- generative-model
An Analysis Toolkit for Natural Language Generation (Translation, Captioning, Summarization, etc.)
💃 Free CC0 mannequin pose reference library for AI image tools (Nano Banana, ChatGPT, ComfyUI, Midjourney) — 250+ poses × 5 angles in line art, names in ja/zh/en/ko
- ai-art
- line-art
- mannequin
- pose-reference
The official implementation of 3D Equivariant Diffusion for Target-Aware Molecule Generation and Affinity Prediction (ICLR 2023)
RNA-seq prediction with deep convolutional neural networks.
Bi-Directional Equivariant Long-Range DNA Sequence Modeling