Patricide 12B Unslop Mell V2

🚀 patricide-12B-Unslop-Mell-v2

This is a merged pre - trained language model aiming to provide stable and viable answers, with a focus on balancing parameters and testing NuSLERP.

🚀 Quick Start

This is a merge of pre - trained language models created using mergekit. It's the author's seventh model. The author chose TheDrummer/UnslopNemo-12B-v4 over TheDrummer/UnslopNemo-12B-v4.1 due to its supposed higher anti - GPTism influence at the cost of intelligence, and plans to use it in future merges. The author also tweaked the parameters for a more balanced state and is testing NuSLERP.

✨ Features

Testing stage

• Early testing: The model is in the early testing stage. The author doesn't know how it performs over long - term context, but early tests showed stability and viable answers.

Parameters

Quantization

Static GGUF Quants are available at:

• MaziyarPanahi/patricide-12B-Unslop-Mell-v2-GGUF
• mradermacher/patricide-12B-Unslop-Mell-v2-GGUF

Merge Details

Merge Method

This model was merged using the NuSLERP merge method.

Models Merged

The following models were included in the merge:

• inflatebot/MN-12B-Mag-Mell-R1
• TheDrummer/UnslopNemo-12B-v4

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: TheDrummer/UnslopNemo-12B-v4
    parameters:
      weight: [0.6, 0.5, 0.3, 0.5, 0.6]
  - model: inflatebot/MN-12B-Mag-Mell-R1
    parameters:
      weight: [0.4, 0.5, 0.7, 0.5, 0.4]
merge_method: nuslerp
dtype: bfloat16
chat_template: "chatml"
tokenizer:
  source: union
parameters:
  normalize: true
  int8_mask: true

📄 License

This project is licensed under the apache - 2.0 license.