Lunzima/NQLSG-Qwen2-VL-2B-v2

Untitled Model (1)

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the Model Stock merge method using Lunzima/NQLSG-Qwen2-VL-2B-v2-pass6 as a base.

Models Merged

The following models were included in the merge:

• Lunzima/NQLSG-Qwen2-VL-2B-v2-pass2
• Lunzima/NQLSG-Qwen2-VL-2B-v2-pass3
• Lunzima/NQLSG-Qwen2-VL-2B-v2-pass5
• Lunzima/NQLSG-Qwen2-VL-2B-v2-pass4

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: Lunzima/NQLSG-Qwen2-VL-2B-v2-pass6
  - model: Lunzima/NQLSG-Qwen2-VL-2B-v2-pass5
  - model: Lunzima/NQLSG-Qwen2-VL-2B-v2-pass4
  - model: Lunzima/NQLSG-Qwen2-VL-2B-v2-pass3
  - model: Lunzima/NQLSG-Qwen2-VL-2B-v2-pass2
merge_method: model_stock
base_model: Lunzima/NQLSG-Qwen2-VL-2B-v2-pass6
parameters:
  int8_mask: true
dtype: bfloat16