Python 排行榜

MODA: open fashion retrieval benchmark and models by Hopit AI. MODA (203M, open source), MODA Pro Lite (213M, open weights), MODA Pro (hosted). Full-corpus benchmarks vs FashionSigLIP, SigLIP-SO400M and ZooClaw — one harness, losses shown. #1 open model on LookBench.

An end-to-end image captioning project using a CNN encoder (ResNet-50) and LSTM decoder in PyTorch. Includes vocabulary building, preprocessing, training with BLEU evaluation, and inference. Generates natural language captions for images with saved metrics, model checkpoints, and visualization outputs.

ONNX-compatible Fast SeamlessM4T—Massively Multilingual & Multimodal Machine Translation

Codes and datasets for our ICASSP2023 paper, Evaluating parameter-efficient transfer learning approaches on SURE benchmark for speech understanding

AI commit messages from your local LLM - Ollama / llama-cpp backed, offline, Conventional Commits, with review + changelog modes.

A CLI-first AI code review tool for git diffs and CI workflows. Analyze changes with relevant codebase context using local Ollama models or cloud LLMs.

AI assistant built with Streamlit, NVIDIA NIM (LLaMa 3.3:70B) / Ollama, and Model Control Protocol (MCP).

AI Data Engineering Healthcare Platform: PySpark Medallion Lakehouse, Airflow DAGs, 5 ML Models, Local LLM RAG, and FastAPI Clinical Architecture.

Repository of Ollama Models!

A Continual Learning Framework for Production LLM Agents

LLM-powered assistant for first-time dads, fine-tuned on real parenting discussions using Mistral 7B

A standardized framework for enhancing how LLMs process and respond to prompts through composable decorators, featuring an official open standard specification and Python reference implementation. Claude Code plugin and MCP server integration.

Serving Qwen3.8-27B-FP8 on a single DGX Spark (GB10): 7.88 to 58.5 tok/s single-stream from decode strategy alone, weights untouched. Speculative decoding and prefix caching benchmarked, plus DFlash 2 — the only Qwen3.8-27B build that can serve it under vLLM.

This pattern describes how to use AWS Control Tower Controls, AWS Cloud Development Kit (CDK) and infrastructure as code to implement and administer preventive, detective and proactive security on AWS.

Structured pruning, knowledge distillation, and fairness analysis for Large Language Models.

RATransformers 🐭- Make your transformer (like BERT, RoBERTa, GPT-2 and T5) Relation Aware!

Airflow Pipeline for Machine Learning

A repo that attempts to train stable diffusion 3 from scratch

End-to-end pipeline for seeing how LLMs actually process your prompts. Capture attention across every layer, render heatmaps and cooking curves, compare variants with evidence — not vibes.

Official implementation of the paper: Unsupervised MRI Reconstruction via Zero-Shot Learned Adversarial Transformers