Python 排行榜

GPU 性能与 AI Infra 学习项目：CUDA/Triton 算子、NCU/NSYS、vLLM/SGLang/TRT-LLM/ms-swift、PyTorch/DeepSpeed/ms-swift 训练、并行架构

[TACL, EMNLP 2025 Oral] Code, datasets, and checkpoints for the paper "CRAFT Your Dataset: Task-Specific Synthetic Dataset Generation Through Corpus Retrieval and Augmentation"

疫情期间网民情绪识别比赛baseline，使用BERT进行端到端的fine-tuning，datafountain平台，平台评测F1值0.716。

Training pipeline for fine tuning Phi-3-mini-instruct to follow the Socratic method

This project leverages Claude Code’s powerful agent capabilities to build a multi-agent system that simulates the real-world collaboration process of a data science team. Through the division of labor among AI agents with different areas of expertise, the system delivers a complete end-to-end data science solution—from raw data to the final analysi

Turn any YouTube videos into well-written Medium blog posts with this automation script (made with lots of love). Writes a delightful and professional article from a given full YouTube channel.

A deterministic, zero-dependency prompt-pruning layer for long-running LLM conversations — expires stale tool state, collapses duplicate context, and proves it never drops a fact a later turn still depends on.

A Word Level Transformer layer based on PyTorch and 🤗 Transformers.

Enterprise-grade Knowledge Distillation framework for Persian Mental Health analysis. Distills reasoning capabilities from Llama-3-70b into a local Gemma-3-1b model using QLoRA and synthetic Chain-of-Thought datasets.

[ICDE 2024] VDTuner - Automated Performance Tuning for Vector Data Management Systems (Vector Databases)

A Python-Script Based Generative AI platform

ComfyUI custom nodes to compute and visualize optical flow and to apply it to another image

ImageReward nodes for ComfyUI.

AUTOMATIC1111 UI extension to find the best settings for running img2img.

A tool to streamline AI image captioning

Train LoRA using Microsoft's official implementation with Stable Diffusion models.

A highly memory-efficient fine-tuning toolkit for SDXL and ANIMA, combining modern VRAM-saving techniques with custom optimizers to enable full-quality model training on GPUs with as little as 12 GB of VRAM.

Use text-to-image models Stable Diffusion, DALL-E2, DALL-E3, SDXL, SSD-1B, Kandinsky-2.2, and LCM from UI. Add images directly to your dataset!

🎨 Lightweight async Python API for NovelAI image generation

Multimodal datasets.