kyegomez / VisualNexus
An plug in and play pipeline that utilizes segment anything to segment datasets with rich detail for downstream fine-tuning on vision models like CLIP, ViT, Imagebind, and so on!
☆21Updated 8 months ago
Related projects ⓘ
Alternatives and complementary repositories for VisualNexus
- A public implementation of the ReLoRA pretraining method, built on Lightning-AI's Pytorch Lightning suite.☆33Updated 8 months ago
- ☆62Updated last month
- ☆29Updated 11 months ago
- MetaCLIP module for use with Autodistill.☆21Updated 11 months ago
- ☆30Updated 10 months ago
- QLoRA for Masked Language Modeling☆20Updated last year
- ☆13Updated last year
- My personal implementation of the model from "Qwen-VL: A Frontier Large Vision-Language Model with Versatile Abilities", they haven't rel…☆11Updated 9 months ago
- Unofficial implementation and experiments related to Set-of-Mark (SoM) 👁️☆76Updated last year
- ☆11Updated 3 weeks ago
- ☆57Updated last month
- An EXA-Scale repository of Multi-Modality AI resources from papers and models, to foundational libraries!☆41Updated 9 months ago
- The Benefits of a Concise Chain of Thought on Problem Solving in Large Language Models☆19Updated 9 months ago
- Using modal.com to process FineWeb-edu data☆19Updated 2 months ago
- ☆22Updated last year
- Official implementation of "Gemini in Reasoning: Unveiling Commonsense in Multimodal Large Language Models"☆35Updated 10 months ago
- BH hackathon☆14Updated 7 months ago
- Tools for content datamining and NLP at scale☆42Updated 4 months ago
- ☆14Updated last year
- [WIP] Transformer to embed Danbooru labelsets☆13Updated 7 months ago
- Finetune any model on HF in less than 30 seconds☆56Updated this week
- Modified Beam Search with periodical restart☆12Updated last month
- Visual RAG using less than 300 lines of code.☆23Updated 8 months ago
- ☆12Updated 7 months ago
- Official code repository for paper: "ExPLoRA: Parameter-Efficient Extended Pre-training to Adapt Vision Transformers under Domain Shifts"☆23Updated last month
- ☆26Updated 7 months ago
- Code for "Accelerating Training with Neuron Interaction and Nowcasting Networks"☆14Updated last week
- ☆18Updated last month
- Using multiple LLMs for ensemble Forecasting☆16Updated 9 months ago
- Use Grounding DINO, Segment Anything, and CLIP to label objects in images.☆23Updated 10 months ago