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 mrfakename/mistral-small-3.1-24b-instruct-2503-hf as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

merge_method: dare_ties
base_model: mrfakename/mistral-small-3.1-24b-instruct-2503-hf
models:
  - model: mrfakename/mistral-small-3.1-24b-instruct-2503-hf
    parameters:
      weight: 0.2
  - model: aixonlab/Eurydice-24b-v2
    parameters:
      weight: 0.3
  - model: TroyDoesAI/BlackSheep-24B
    parameters:
      weight: 0.3
  - model: Sorawiz/MistralCreative-24B
    parameters:
      weight: 0.2
parameters:
  density: 1
tokenizer:
  source: union
chat_template: auto
Downloads last month
111
Safetensors
Model size
23.6B params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Sorawiz/MistralCreative-24B-Chat

Collection including Sorawiz/MistralCreative-24B-Chat