An open API service indexing awesome lists of open source software.

https://github.com/atasoglu/awesome-turkish-vlm

A curated list of models, datasets and other useful resources for Turkish Vision-Language Models (VLM).
https://github.com/atasoglu/awesome-turkish-vlm

List: awesome-turkish-vlm

awesome awesome-list computer-vision datasets deep-learning fine-tuning multimodal nlp pretrained-models turkish vision-language-model vlm

Last synced: about 1 year ago
JSON representation

A curated list of models, datasets and other useful resources for Turkish Vision-Language Models (VLM).

Awesome Lists containing this project

README

          

# awesome-turkish-vlm
A curated list of models, datasets and other useful resources for Turkish Vision-Language Models (VLM).

## 🚀 Introduction

This repository is an awesome list of curated resources dedicated to Turkish Vision-Language Models (VLM). It includes pretrained/fine-tuned models, datasets, and related works you need to get started or deepen your research in Turkish multimodal AI.

Contributions and suggestions are warmly welcomed! 🌟

## 🤖 Models

|Name|Size|License|
|:---|:---|:------|
|[ytu-ce-cosmos/Turkish-LLaVA-v0.1](https://huggingface.co/ytu-ce-cosmos/Turkish-LLaVA-v0.1)|8B|MIT|
|TraVisionLM [Base](https://huggingface.co/ucsahin/TraVisionLM-base) - [DPO](https://huggingface.co/ucsahin/TraVisionLM-DPO) - [Object-Detection-ft](https://huggingface.co/ucsahin/TraVisionLM-Object-Detection-ft) |875M|Apache 2.0|

## 📚 Datasets

|Name|Description|Size|License|
|:---|:----------|:---|:------|
|[ytu-ce-cosmos/turkce-kitap](https://huggingface.co/datasets/ytu-ce-cosmos/turkce-kitap)|Book cover collection designed to improve the Turkish OCR ability.|108k||
|[ytu-ce-cosmos/Turkish-LLaVA-Pretrain](https://huggingface.co/datasets/ytu-ce-cosmos/Turkish-LLaVA-Pretrain)|Pretraining dataset for Turkish base VLM.|595k||MIT|
|[ytu-ce-cosmos/Turkish-LLaVA-Finetune](https://huggingface.co/datasets/ytu-ce-cosmos/Turkish-LLaVA-Finetune)|Fine-tuning dataset for Turkish VLM.|||
|[ucsahin/COCO-OD-TR-Single-Objects-v2](https://huggingface.co/datasets/ucsahin/COCO-OD-TR-Single-Objects-v2)|Combined dataset for object detection task.|153k||
|[ucsahin/Turkish-VLM-Mix-Benchmark](https://huggingface.co/datasets/ucsahin/Turkish-VLM-Mix-Benchmark)|Combined dataset for benchmark.|35k||
|[ucsahin/TR-VLM-DPO-Dataset](https://huggingface.co/datasets/ucsahin/TR-VLM-DPO-Dataset)|DPO formatted instruction-following dataset.|10k||
|[atasoglu/flickr30k-turkish](https://huggingface.co/datasets/atasoglu/flickr30k-turkish)|Turkish translation of the Flickr30k dataset.|30k||
|[atasoglu/flickr8k-turkish-mt](https://huggingface.co/datasets/atasoglu/flickr8k-turkish-mt)|Turkish translation of the Flickr8k dataset.|8k||
|[atasoglu/flickr8k-turkish](https://huggingface.co/datasets/atasoglu/flickr8k-turkish)|Native Turkish version of the Flickr8k dataset.|8k|CC0 1.0|
|[atasoglu/flickr8k-turkish-detailed-captions](https://huggingface.co/datasets/atasoglu/flickr8k-turkish-detailed-captions)|Flickr8k dataset with long captions.|8k|CC0 1.0|
|[99eren99/LLaVA1.5-Data-Turkish](https://huggingface.co/datasets/99eren99/LLaVA1.5-Data-Turkish)|Combined dataset for instruction-following.||CC BY 4.0|
|[mcemilg/laion2B-multi-turkish-subset](https://huggingface.co/datasets/mcemilg/laion2B-multi-turkish-subset)|Turkish subset of the Laion2b-multi.|34M|CC BY 4.0|
|[NexusAI-tddi/VisIT-Bench-tr](https://huggingface.co/datasets/NexusAI-tddi/VisIT-Bench-tr)|Bench dataset for instruction-following.|574||
|[umarigan/turkish_clip_dataset_with_text_embeddings](https://huggingface.co/datasets/umarigan/turkish_clip_dataset_with_text_embeddings)|Turkish-English caption pairs with embeddings.|410k|CreativeML Open RAIL-M|
|[YxBxRyXJx/cut_TRV_ver2_1019](https://huggingface.co/datasets/YxBxRyXJx/cut_TRV_ver2_1019)|Turkish object detection dataset.|2k||
|[selimc/tr-textbook-ColPali](https://huggingface.co/datasets/selimc/tr-textbook-ColPali)|Dataset for document retrieving from Turkish textbook.|3k||
|[muhammetfatihaktug/bilim_teknik_mini_colpali](https://huggingface.co/datasets/muhammetfatihaktug/bilim_teknik_mini_colpali)|Dataset for document retrieving from Turkish science magazine.|4k|MIT|
|[umarigan/PD12M-Turkish](https://huggingface.co/datasets/umarigan/PD12M-Turkish)|A large Turkish captioning dataset.|12M|CDLA-Permissive-2.0|