Qwen-3.5_0.8B

This repo contains a fine tuned model mainly for ocr related task

The backbone already had great vision capabilities this is the reason why we went with lora with the lora rank of 16

Safetensors

Model size

0.9B params

Tensor type

F32

BF16

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Parveshiiii/Qwen-3.5-0.8B-OCR

Base model

Finetuned

Finetuned

(155)

this model

Quantizations