Python 排行榜

Simple Python library, distributed via binary wheels with few direct dependencies, for easily using wav2vec 2.0 models for speech recognition

Graphical Password Authentication System. This is used to increase the protection/security of a website. Our system is divided into further 4 layers of protection. Each layer is totally different and diverse than the others. This not only increases protection, but also makes sure that no non-human can log in to your account using different activities such as Brute Force Algorithm and so on.

Run and manage both vLLM and llama.cpp model servers from one terminal UI + CLI — shared Docker Compose profiles, live tok/s, and cross-backend port/GPU conflict checks. NVIDIA + Linux.

NVFP4 inference on Blackwell GeForce (RTX 5090/5080/5070 Ti/RTX PRO 6000) — SM120 patches for vLLM + FlashInfer + CUTLASS. 175 tok/s on Qwen3.6-35B MoE.

Train an LLM to generate cracked Manim animations for mathematical concepts.

🥉 Codalab-Microsoft-COCO-Image-Captioning-Challenge 3rd place solution(06.30.21)

Code for TR2-D2: Tree Search Guided Trajectory-Aware Fine-Tuning for Discrete Diffusion

An app to organize your research: A Paper Based Approach

A simple RAG chatbot that can retrieve from a mediawiki data dump

Machine Learning Project to Predict House Prices in Bangalore.

Local CLI for Google's TranslateGemma translation models with multi-platform support (MLX for Apple Silicon, PyTorch for CUDA/CPU).

Text simplification for a better world: Deep-Martin Transformer 🤗

This node is based on MykolaL/StableDesign

Generate fake restaurant reviews with GPT-2 using Yelp Dataset

Open-source benchmark for evaluating LLMs on 220 real professional tasks across 9 sectors and 44 occupations. Reproducible experiments, artifact validation, grading, and a live evidence dashboard.

GraphRAG over any codebase — a Neo4j knowledge graph of code entities plus a 3072-dim vector index, bridged so one natural-language query walks structure and ranks by meaning. Python · Neo4j · OpenAI embeddings · Streamlit · Docker. Hybrid semantic + structural code search.

Optimizing bit-level Jaccard Index and Population Counts for large-scale quantized Vector Search via Harley-Seal CSA and Lookup Tables

An open source framework for Retrieval-Augmented System (RAG) uses semantic search helps to retrieve the expected results and generate human readable conversational response with the help of LLM (Large Language Model).

LLMs based multi-model framework for building AI apps.

XVO: Generalized Visual Odometry via Cross-Modal Self-Training [ICCV 2023]