Giruvegan

Giruvegan's Stars

• KLUE-benchmark/KLUE

  📖 Korean NLU Benchmark

  55856

• AnyLoc/AnyLoc

  AnyLoc: Universal Visual Place Recognition (RA-L 2023)

  Language:Python44039

• cvg/LightGlue

  LightGlue: Local Feature Matching at Light Speed (ICCV 2023)

  Language:Python3.3k319

• RuojinCai/doppelgangers

  Doppelgangers: Learning to Disambiguate Images of Similar Structures

  Language:Jupyter Notebook17323

• chicleee/Image-Matching-Paper-List

  A personal list of papers and resources of image matching and pose estimation, including perspective images and panoramas.

  24530

• google-research/omniglue

  Code release for CVPR'24 submission 'OmniGlue'

  Language:Python52743

• verlab/accelerated_features

  Implementation of XFeat (CVPR 2024). Do you need robust and fast local feature extraction? You are in the right place!

  Language:Jupyter Notebook89992

• McGill-NLP/llm2vec

  Code for 'LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders'

  Language:Python1.1k86

• OpenGVLab/InternVL

  [CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的开源多模态对话模型

  Language:Python5.5k434

• BM-K/Sentence-Embedding-Is-All-You-Need

  Korean Sentence Embedding Repository

  Language:Python19916

• sail-sg/metaformer

  MetaFormer Baselines for Vision (TPAMI 2024)

  Language:Python40023

• Parskatt/RoMa

  [CVPR 2024] RoMa: Robust Dense Feature Matching; RoMa is the robust dense feature matcher capable of estimating pixel-dense warps and reliable certainties for almost any image pair.

  Language:Python54743

• embeddings-benchmark/mteb

  MTEB: Massive Text Embedding Benchmark

  Language:Jupyter Notebook1.8k240

• open-webui/open-webui

  User-friendly WebUI for LLMs (Formerly Ollama WebUI)

  Language:Svelte39.8k4.7k

• NVIDIA/NeMo-Guardrails

  NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.

  Language:Python4k365

• kyegomez/RT-2

  Democratization of RT-2 "RT-2: New model translates vision and language into action"

  Language:Python35347

• mit-han-lab/efficientvit

  EfficientViT is a new family of vision models for efficient high-resolution vision.

  Language:Python1.8k163

• SKTBrain/KVQA

  Korean Visual Question Answering

  575

• bytedance/MTVQA

  MTVQA: Benchmarking Multilingual Text-Centric Visual Question Answering. A comprehensive evaluation of multimodal large model multilingual text perception and comprehension capabilities across nine widely-used yet low-resource languages.

  Language:Python331

• THUDM/GLM-4

  GLM-4 series: Open Multilingual Multimodal Chat LMs | 开源多语言多模态对话模型

  Language:Python4.7k376

• QwenLM/Qwen-VL

  The official repo of Qwen-VL (通义千问-VL) chat & pretrained large vision language model proposed by Alibaba Cloud.

  Language:Python4.8k366

• OpenBMB/MiniCPM-V

  MiniCPM-V 2.6: A GPT-4V Level MLLM for Single Image, Multi Image and Video on Your Phone

  Language:Python12k842

• mapluisch/LLaVA-CLI-with-multiple-images

  LLaVA inference with multiple images at once for cross-image analysis.

  Language:Python424

• khanrc/honeybee

  Official implementation of project Honeybee (CVPR 2024)

  Language:Python41518

• naklecha/llama3-from-scratch

  llama3 implementation one matrix multiplication at a time

  Language:Jupyter Notebook13.1k1k

• naver/deep-image-retrieval

  End-to-end learning of deep visual representations for image retrieval

  Language:Python639101

• LLaVA-VL/LLaVA-NeXT

  Language:Python2.5k178

• huggingface/pytorch-image-models

  The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more

  Language:Python31.6k4.7k

• philschmid/optimum-transformers-optimizations

  Language:Jupyter Notebook296

• NomaDamas/awesome-korean-llm

  Awesome list of Korean Large Language Models.

  43427