Hugging Face's logo

NewEden-Forge
/
madness-12b-dare-ties

Text Generation
Transformers
Safetensors
mistral
mergekit
Merge
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
madness-12b-dare-ties / README.md
Delta-Vector's picture
Delta-Vector
Upload folder using huggingface_hub
8a457cd verified
preview code
|
raw
history blame contribute delete
1.42 kB
metadata
base_model:
  - nbeerbower/mistral-nemo-gutenberg-12B-v4
  - anthracite-org/magnum-v2.5-12b-kto
  - NewEden/nemo-erebus
  - TheDrummer/UnslopNemo-12B-v4.1
library_name: transformers
tags:
  - mergekit
  - merge

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 NewEden/nemo-erebus as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: anthracite-org/magnum-v2.5-12b-kto
    parameters:
      weight: 0.3
      density: 0.53
  - model: nbeerbower/mistral-nemo-gutenberg-12B-v4
    parameters:
      weight: 0.2
      density: 0.53
  - model: TheDrummer/UnslopNemo-12B-v4.1
    parameters:
      weight: 0.5
      density: 0.53
base_model: NewEden/nemo-erebus
merge_method: dare_ties
dtype: bfloat16