Luke-Bergen
/

Mineral-7B

Image-Text-to-Text

Model card Files Files and versions

A newer version of this model is available: zai-org/GLM-4.6

Mineral-7B

Parameters: 7B

Author: Luke-Bergen

Base Model: tencent/HunyuanImage-3.0

License: Apache 2.0

Model Description

Mineral-7B is a 7-billion parameter multimodal language model with vision and memory capabilities.

Architecture

Parameters: 7B
Layers: 32
Hidden Size: 4096
Vision Encoder: 224x224
Memory: 8192 tokens

Downloads last month: -

Inference Providers NEW

Image-Text-to-Text

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

Model tree for Luke-Bergen/Mineral-7B

Base model

tencent/HunyuanImage-3.0

Adapter

(7)

this model

Dataset used to train Luke-Bergen/Mineral-7B