Python 排行榜

Running Large Language Model easily.

Benchmarks and notes for running modern LLMs with vLLM on 8x Tesla V100-32GB in 2026.

Reproducible recipe: serve abliterated Gemma-4-12B (gemma4_unified) at 50-118 tok/s on no-NVLink Blackwell (SM120) via vLLM nightly + ModelOpt FP8/NVFP4 + MTP spec-decode.

FlashAttention-style custom attention backend for vLLM on AMD MI50/MI60/Radeon VII (gfx906). Downstream fork of mixa3607/ML-gfx906 with replacement HIP kernels and a vllm.general_plugins entry point.

This Russia Doesn't Exist

HypeLoRA: Hypernetwork-Generated LoRA Adapters for Calibrated Language Model Fine-Tuning

CosyVoice3 LoRA fine-tuning companion repo — PEFT integration, 9 known pitfalls from IMDA NSC production runs, corrected from failed full-SFT attempt

Kairos: An autonomous development supervisor powered by Context Engineering. It provides a living memory and a contextual constitution for your projects to prevent AI context loss.

Tool for auto-generating README documentation for code repositories

LoRA supervised fine-tuning, RLHF (PPO) and RAG with llama-3-8B on the TLDR summarization dataset

Mantissa Log is an open-source and cost-transparent engine that uses a natural language interface to "Ask Questions. Detect Threats. Trace Performance. Automate Responses."

Infrastructure configuration and serverless backend of WasedaTime

An application that summarizes and classifies long text using zero-shot transfer-learning hosted on Huggingface spaces.

预训练模型知识量度量竞赛 Baseline F1 0.35 BERTForMaskedLM

Finetune Web UI is a user-interface for training and deploying pre-trained models.

High Quality Image Generation Model - Powered with NVIDIA A100

An implementation of LazyLLM token pruning for LLaMa 2 model family.

LegalEase AI is a document simplification tool built using Gemini API, Streamlit, and Hugging Face models. It allows users to upload legal PDFs and automatically receive simplified summaries, clause-level insights, and structured information designed for clarity and accessibility.

An MCP server for dataset generation, fine-tuning, RL, and evaluation of LLMs — directly from your coding agent.

【Join our constellation of stargazers!⭐️】An interactive AI-powered story generator that creates dynamic narratives through collaborative storytelling between users and Meta's Llama model. Built with Gradio for an intuitive UI and leveraging the Hugging Face Inference API.