Сводка 07.07.2024 — 14.07.2024
А теперь о том, что происходило в последнее время на других ресурсах.
Обсуждения
Блог PSF
StackOverflow на русском
Популярное на GitHub
microsoft/graphrag — A modular graph-based Retrieval-Augmented Generation (RAG) system |
stanford-oval/storm — An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations. |
Azure-Samples/graphrag-accelerator — One-click deploy of a Knowledge Graph powered RAG (GraphRAG) in Azure |
Lightning-AI/litgpt — 20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale. |
d2l-ai/d2l-zh — 《动手学深度学习》:面向中文读者、能运行、可讨论。中英文版被70多个国家的500多所大学用于教学。 |
huggingface/transformers — 🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX. |
vllm-project/vllm — A high-throughput and memory-efficient inference and serving engine for LLMs |
infiniflow/ragflow — RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding. |
pytube/pytube — A lightweight, dependency-free Python library (and command-line utility) for downloading YouTube Videos. |
NVlabs/VILA — VILA - a multi-image visual language model with training, inference and evaluation recipe, deployable from cloud to edge (Jetson Orin and laptops) |
InternLM/InternLM-XComposer — InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output |
donnemartin/system-design-primer — Learn how to design large-scale systems. Prep for the system design interview. Includes Anki flashcards. |
paul-gauthier/aider — aider is AI pair programming in your terminal |
Dao-AILab/flash-attention — Fast and memory-efficient exact attention |
На заметку
Зарегистрированные пользователи могут публиковать свои Статьи.