fangyuan-ksgk / Mini-LLaVALinks
A minimal implementation of LLaVA-style VLM with interleaved image & text & video processing ability.
☆95Updated 8 months ago
Alternatives and similar repositories for Mini-LLaVA
Users that are interested in Mini-LLaVA are comparing it to the libraries listed below
Sorting:
- OLA-VLM: Elevating Visual Perception in Multimodal LLMs with Auxiliary Embedding Distillation, arXiv 2024☆60Updated 6 months ago
- a family of highly capabale yet efficient large multimodal models☆187Updated last year
- (WACV 2025 - Oral) Vision-language conversation in 10 languages including English, Chinese, French, Spanish, Russian, Japanese, Arabic, H…☆83Updated 3 weeks ago
- ☆69Updated last year
- Timm model explorer☆41Updated last year
- LongLLaVA: Scaling Multi-modal LLMs to 1000 Images Efficiently via Hybrid Architecture☆209Updated 7 months ago
- [CVPR'24 Highlight] PyTorch Implementation of Object Recognition as Next Token Prediction☆180Updated 3 months ago
- ☆93Updated 2 months ago
- ☆86Updated last year
- Python Library to evaluate VLM models' robustness across diverse benchmarks☆210Updated last week
- Parameter-efficient finetuning script for Phi-3-vision, the strong multimodal language model by Microsoft.☆58Updated last year
- ☆142Updated last year
- ☆27Updated last month
- Implementation of PALI3 from the paper PALI-3 VISION LANGUAGE MODELS: SMALLER, FASTER, STRONGER"☆145Updated last week
- Code for experiments for "ConvNet vs Transformer, Supervised vs CLIP: Beyond ImageNet Accuracy"☆101Updated 11 months ago
- ☆56Updated 9 months ago
- ☆182Updated 10 months ago
- This is the repo for the paper "PANGEA: A FULLY OPEN MULTILINGUAL MULTIMODAL LLM FOR 39 LANGUAGES"☆110Updated last month
- Reproduction of LLaVA-v1.5 based on Llama-3-8b LLM backbone.☆66Updated 10 months ago
- minimal GRPO implementation from scratch☆96Updated 5 months ago
- Implementation of the paper: "Mixture-of-Depths: Dynamically allocating compute in transformer-based language models"☆104Updated last week
- ☆59Updated last year
- OpenVLThinker: An Early Exploration to Vision-Language Reasoning via Iterative Self-Improvement☆107Updated last month
- Official Pytorch Implementation of Self-emerging Token Labeling☆35Updated last year
- ☆52Updated 7 months ago
- The official repo for the paper "VeCLIP: Improving CLIP Training via Visual-enriched Captions"☆246Updated 7 months ago
- ☆78Updated 10 months ago
- [Fully open] [Encoder-free MLLM] Vision as LoRA☆333Updated 2 months ago
- Repository for the paper: "TiC-CLIP: Continual Training of CLIP Models".☆103Updated last year
- [EMNLP 2024] Official PyTorch implementation code for realizing the technical part of Traversal of Layers (TroL) presenting new propagati…☆97Updated last year