Modelpublic

Disya/Qwen2.5-1M-RP-Context-Merge

sourceHugging Faceupdated 1y agoView on Hugging Face

0likes12downloads

Model Card

Qwen2.5-1M-RP-Context-Merge

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

Merge Details

Merge Method

This model was merged using the DARE TIES merge method using Qwen2.5-14B-Instruct-1M-abliterated as a base.

Models Merged

The following models were included in the merge:

—Omega-Darker_The-Final-Directive-14B
—ImpishQWEN14B-1M

Configuration

The following YAML configuration was used to produce this model:

yaml

merge_method: dare_ties
base_model: Qwen2.5-14B-Instruct-1M-abliterated
models:
  - model: Qwen2.5-14B-Instruct-1M-abliterated
    parameters:
      weight: 0.3
  - model: Omega-Darker_The-Final-Directive-14B
    parameters:
      weight: 0.35
  - model: Impish_QWEN_14B-1M
    parameters:
      weight: 0.35
parameters:
  density: 0.35