Mistral-qwq-12b-merge

---

Strange model

---

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 BeaverAI/MN-2407-DSK-QwQify-v0.1-12B as a base.

Models Merged

The following models were included in the merge:

• Delta-Vector/Francois-PE-V2-Huali-12B
• Nitral-AI/Mag-Mell-Reasoner-12B
• Dans-DiscountModels/12b-mn-dans-reasoning-test-5
• CreitinGameplays/Mistral-Nemo-12B-R1-v0.2

Configuration

The following YAML configuration was used to produce this model:

merge_method: dare_ties
base_model: BeaverAI/MN-2407-DSK-QwQify-v0.1-12B
models:
  - model: BeaverAI/MN-2407-DSK-QwQify-v0.1-12B
    parameters:
      weight: 0.225
  - model: CreitinGameplays/Mistral-Nemo-12B-R1-v0.2
    parameters:
      weight: 0.225
  - model: Nitral-AI/Mag-Mell-Reasoner-12B
    parameters:
      weight: 0.225
  - model: Dans-DiscountModels/12b-mn-dans-reasoning-test-5
    parameters:
      weight: 0.225
  - model: Delta-Vector/Francois-PE-V2-Huali-12B
    parameters:
      weight: 0.1
parameters:
  density: 0.35