MLX 8-bit conversion of opendatalab/MinerU2.5-Pro-2605-1.2B (Qwen2-VL 1.2B document-parsing model) for opengryd-ai Route-2 OCR. config.json carries the hoisted top-level tie_word_embeddings mlx-vlm needs.

Downloads last month: -

Safetensors

Model size

1B params

Tensor type

U32

BF16

Inference Providers NEW

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

Model tree for OpenGryd/MinerU2.5-Pro-2605-1.2B-MLX-8bit

Base model

opendatalab/MinerU2.5-Pro-2605-1.2B

Quantized

(6)

this model