exdysa/Orsta-32B-0326-Q4_K_M-GGUF

Original Model Link : https://huggingface.co/One-RL-to-See-Them-All/Orsta-32B-0326

name: Orsta-32B-0326-GGUF-Q4
base_model: Qwen/Qwen2.5-VL-32B-Instruct
license: mit
pipeline_tag: image-text-to-text
tasks :
 - text-generation
 - text2text-generation
 - text-to-text
 - visual-question-answering
 - image-to-text
 - image-text-to-text
 - OCR
 - object-detection
 - document-question-answering
language: en
datasets: One-RL-to-See-Them-All/Orsta-Data-47k

Orsta-32B-0326-GGUF-Q4

Orsta-32B-0326-GGUF-Q4 is a gguf quantization of the original model. The model uses Unified RL Framework (V-Triune) and Diverse Joint Task Optimization that provides excellent accuracy and robust features.