minlik
/

Qwen2.5-Vl-3B-Instruct-GRPO-deepmath-ocr-7k

Model card Files Files and versions

https://github.com/minlik/math-ocr-zero

Downloads last month: -

Safetensors

Model size

4B params

Tensor type

BF16

·

Inference Providers NEW

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

Model tree for minlik/Qwen2.5-Vl-3B-Instruct-GRPO-deepmath-ocr-7k

Base model

Qwen/Qwen2.5-VL-3B-Instruct

Finetuned

(700)

this model

Dataset used to train minlik/Qwen2.5-Vl-3B-Instruct-GRPO-deepmath-ocr-7k