Python 排行榜

FlashHead: Efficient Drop-In Replacement for the Classification Head in Language Model Inference

GLM-5.2 on 4x DGX Spark with adaptive MTP K2/K4/K5, FULL CUDA graphs, DCP2, 520K context, and a downloadable ARM64 runtime image.

Benchmark OpenAI-compatible AI endpoints and AI Accelerators in a reproducible structured way

DeepSeek-V4-Flash-0731 tuned on 4x DGX Spark (GB10) at TP=4 — 123.13 tok/s decode. Every variable measured one at a time, with the values that lost.

This project fine-tunes the Qwen2-1.5B model for Arabic language tasks using Quantized LoRA (QLoRA).

Landcover classification on sentinel-2 data with Prithvi, EfficientNet-Unet and OSM / CNES Landcover labels.

🎙️ CosyVoice LoRA 微调框架：LLM+Flow 联合训练，实现无 Prompt 语音合成

A fine tuned yolov111 model to detect fire

AgriMind: The smart LLM application that every farmer truly needs

Code the ICML 2024 paper: "Variance-reduced Zeroth-Order Methods for Fine-Tuning Language Models"

[ICML 2025] Vulnerability-Aware Alignment: Mitigating Uneven Forgetting in Harmful Fine-Tuning

🧪 SynthForge — toolkit for generating high-quality synthetic datasets for LLM fine-tuning. Multi-backend, filterable, GPU-accelerated. Early-stage experimental project.

Adversarial LLM arena using GRPO + SFT to train a model that generates questions hard LLMs can't solve

Fine-tune a local LLM on your own chat history to mimic how you write — an AI doppelganger / digital-twin toolkit built on LLaMA-Factory (LoRA SFT).

Distributed model and API infrastructure for PyTorch and Hugging Face.

Blenderbot

Generate accompaniment part with chords using Evolutionary algorithm.

Billus 大模型技能库：面向 LLM、VL、多模态与图像生成模型的训练、调参、剪枝、量化与工程化技能库

An AI powered photobooth for your next profile picture

Caption images across your datasets with state of the art models from Hugging Face and Replicate!