dive-into-papers Goto Github PK

agent_debugger

Causal Analysis of Agent Behavior for AI Safety

aqlm

Official Pytorch repository for Extreme Compression of Large Language Models via Additive Quantization https://arxiv.org/pdf/2401.06118.pdf

autodistill-siglip

SigLIP base model for use with Autodistill.

awesome-information-retrieval

A curated list of awesome information retrieval resources

awesome-mamba

Awesome list of papers that extend Mamba to various applications.

awesome-multimodal-large-language-models

:sparkles::sparkles:Latest Papers and Datasets on Multimodal Large Language Models, and Their Evaluation.

awesome-remote-sensing-foundation-models

awesome-tool-llm

awesome-vlm-architectures

Famous Vision Language Models and Their Architectures

beir

A Heterogeneous Benchmark for Information Retrieval. Easy to use, evaluate your models across 15+ diverse IR datasets.

big_vision

Official codebase used to develop Vision Transformer, SigLIP, MLP-Mixer, LiT and more.

cog-siglip

cog wrapper for SigLip

comfyui_vlm_nodes

Custom ComfyUI nodes for Vision Language Models, Large Language Models, Image2Music, Consistent and Random Creative Prompt Generation

compressed_vision

deepmind-research

This repository contains implementations and illustrative code to accompany DeepMind publications

differential-diffusion

fm-cheatsheet

Website for hosting the Open Foundation Models Cheat Sheet.

funsearch

gemma.cpp

lightweight, standalone C++ inference engine for Google's Gemma models.

imp

a family of multimodal small language models

keras_big_vision

Keras implementation of SigLIP

language_modeling_is_compression

language_to_reward_2023

llm-continual-learning-survey

llm_papers

Notes on LLM papers

math-evaluation-harness

A simple toolkit for benchmarking LLMs on mathematical reasoning tasks. 🧮✨

mdfe

Framework for learning multi-domain image embeddings suitable for multi-domain image retrieval at instance-level

multimodal_transformers

n-levels-of-rag

objectclassification-with-fastsam-and-embeddings

Este proyecto presenta una solución de Computer Vision para la detección y clasificación de objetos en imágenes, las cuales son extraídas como frames de vídeos. Utiliza el modelo FastSAM para la detección de objetos, y para la clasificación, emplea embeddings que pueden ser generados mediante dos modelos distintos: CLIP o SigLIP.