Modelpublic

Lunzima/NQLSG-Qwen2.5-14B-MegaFusion-v9.2

sourceHugging Faceapache-2.0updated 2y agoView on Hugging Face

1likes26downloads

Model Card

merge

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-Qwen2.5-14B-MegaFusion-v9.1 + Lunzima/NQLSG-Qwen2.5-14B-MegaFusion-v9.1-alpaca-lora as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

yaml

merge_method:     model_stock
base_model:       Lunzima/NQLSG-Qwen2.5-14B-MegaFusion-v9.1+Lunzima/NQLSG-Qwen2.5-14B-MegaFusion-v9.1-alpaca-lora
tokenizer_source: base
dtype:            bfloat16
parameters:
  int8_mask:      true
models:
  - model:        Lunzima/NQLSG-Qwen2.5-14B-MegaFusion-v9.1
  - model:        Lunzima/NQLSG-Qwen2.5-14B-MegaFusion-v9.1+Lunzima/NQLSG-Qwen2.5-14B-MegaFusion-v9.1-alpaca-lora
  - model:        Cran-May/tempmotacilla-cinerea-0308
  - model:        suayptalha/Lamarckvergence-14B
  - model:        suayptalha/Lix-14B-v0.1