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: 0.4
  - model: Sorawiz/MistralSmall-Creative-24B
    parameters:
      weight: 0.3
  - model: ReadyArt/Forgotten-Safeword-24B-v4.0
    parameters:
      weight: 0.3
parameters:
  density: 1.00
tokenizer:
  source: mrfakename/mistral-small-3.1-24b-instruct-2503-hf
chat_template: auto
Downloads last month
18
Safetensors
Model size
23.6B params
Tensor type
BF16
·
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.

Model tree for Sorawiz/MistralCreative-24B-Chat

Collection including Sorawiz/MistralCreative-24B-Chat