Тег «исходный код» — 3 417

🎓 Path to a free self-taught education in Computer Science!

Claude Code за двое суток обновился три раза, 2.1.243, 2.1.245 и 2.1.246, и один пункт там важнее остальных. В 2.1.246 п

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. - Comfy-Org/ComfyUI

пошаговый учебник по созданию языковой модели уровня GPT

А вы ведь пользуетесь транскрибаторами? На самом деле это одна из самых простых и бустящих вашу продуктивность штук. Я

Наконец доехал техрепорт по DiffusionGemma. Мне нравится подход команды, они регулярно берут какую-то из базовых Gemma и

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024) - hiyouga/LlamaFactory

Machine Learning for Beginners

github.com

(⭐36k) <br>

каталог готовых MCP‑серверов для ИИ‑агентов

microsoft/AI-For-Beginners

github.com

12 Weeks, 24 Lessons, AI for All!

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

The simplest, fastest repository for training/finetuning medium-sized GPTs.

The best ChatGPT that $100 can buy.

Discord

создает RAG‑приложения и чат‑ботов по своим документам

Open-source desktop app for local LLMs. Text, vision, tool-calling, OpenAI/Anthropic-compatible API. 100% private. - oobabooga/textgen

Milvus is a high-performance, cloud-native vector database built for scalable vector ANN search

A library for efficient similarity search and clustering of dense vectors.

Anthropic's Interactive Prompt Engineering Tutorial

LLM101n: Let's build a Storyteller.

🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.

Qdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/

A distributed multi-model LLM serving system with web UI and OpenAI-compatible RESTful APIs.

ускоряет локальный запуск и дообучение ИИ‑моделей

Search infrastructure for AI.

A lightweight, powerful framework for multi-agent workflows

Generative Models by Stability AI.

35+ runnable Jupyter-notebook tutorials covering advanced RAG techniques: chunking, query transformation/HyDE, reranking, self-RAG, graph RAG, and evaluation.

The official Python SDK for Model Context Protocol servers and clients

A Python/C#/Java library from Microsoft that supports prompt templating, function chaining, vectorized memory, and intelligent planning.

Open-source vector similarity search for Postgres.

🐍 - A high-level framework for building MCP servers in Python

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

A framework for building industrial-strength applications with Transformer models and LLMs.

фреймворк Microsoft для систем из нескольких ИИ‑агентов

🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org