Python 排行榜

GDB: GraphicDesignBench - A real-world benchmark for evaluating AI on graphic design tasks

Chain of Images for Intuitively Reasoning

A semantic file retrieval application based on LLM（一个轻量级基于大模型解析的多模态文件语义检索工具，不同于传统基于文件名或metadata检索的方式，该工具可实现基于文件内容的语义检索，支持各类主流格式文档、图片、音频、视频。)

I forgot to fork the repo of LineVD project at first so I create this repository to store the current work, I will add the original work link at the readme file

Чат-бот с LLL + RAG

A new optimizer, Gradient Ascent: Gradient Ascent adjusts the parameters in the direction of the gradient to maximize some objective function.

Official PyTorch implementation for "Where You Edit is What You Get: Text-Guided Image Editing with Region-Based Attention" (Pattern Recognition)

Codebase for the paper titled 'A Shared Encoder Approach to Multimodal Representation Learning'

Official codebase for RetFiner: A Vision-Language Refinement Scheme for Retinal Foundation Models

A local personal memory lab with programmable fractal search and evidence governance.

A voice assistant with local LLM as a backend

Lna-Lab production pipeline: GGUF -> modelopt-format NVFP4 + working MTP head for vLLM on RTX PRO 6000 Blackwell (SM120). Stages 2 (NVFP4) and 3 (MTP graft) are Lna-Lab originals; stage 1 (GGUF->bf16) reuses li-yifei/gguf-to-nvfp4.

SkyPortal SDK & CLI - Open Source

Reproducible kit to deploy DeepSeek-V4-Flash-DSpark on a 2× NVIDIA DGX Spark (GB10) cluster: vLLM TP=2 over QSFP 200GbE, NVFP4 KV, DSpark speculative decoding, 1M context, systemd self-heal. Apache-2.0.

面向 A 股投研，针对分析时效差、逻辑不全及数据难量化痛点，自主构建以 Qwen2.5-72B-AWQ 为核心的全链路自动化投研系统。利用 LangGraph 编排多智能体协作流，融合 LoRA 垂直微调、MCP 工具链与 CoT+ReAct 架构，实现从行情舆情实时采集、产业链知识图谱多维推演到 Reflexion 反思审核的投研全闭环，每日 9:00 定时产出机构级专业研报推送飞书，显著提升投研决策自动化水平。

Phlox is a self-hostable chat platform with an agentic harness, document RAG, code execution, MCP integration and LLM gateway — running over any model provider: AWS Bedrock or any OpenAI-compatible endpoint (OpenAI, Ollama, OpenRouter, vLLM, LiteLLM, LM Studio, local models).

📞 Локальный AI-секретарь, тех. поддержка и менеджер по продажам с клонированием голоса XTTS v2, real-time распознаванием речи (Vosk/Whisper) и offline LLM (vLLM + Qwen/Llama и тп). Полноценная админ-панель (Vue 3), Telegram-бот, виджет для сайта, fine-tuning pipeline. Self-hosted, приватность данных, СМС и телефонные звонки .

Advanced LLM fine-tuning techniques: SFT (LoRA, QLoRA, DoRA, P-/Prefix-Tuning), GRPO, DPO, ORPO, KTO & PPO; composable correctness/format rewards + LLM-as-a-Judge evals (DeepEval, Evidently AI) across math, multi-hop, medical & general QA on Llama 3, Mistral, Phi-4, Gemma & Qwen3. Built on TRL, PEFT & Unsloth.

An intelligent web crawling and content extraction tool that transforms web content into structured JSON data suitable for fine-tuning Large Language Models (LLMs).

A style-aware deep learning model for adaptive cell instance segmentation by contrastive fine-tuning.