nepoticide-12B-Unslop-Unleashed-Mell-RPMax-v2

He stood in the way, for he didn't understand. Unfortunate - there was potential.

This is a merge of pre-trained language models created using mergekit.

This is my fifth model. The original model was created as a simple test of Model Stock, thus the name (nepoticide=nephew, not as important nor direct). A broken tokenizer caused me to remerge the model. I also chose to use TheDrummer/UnslopNemo-12B-v4, as TheDrummer stated that this model has more anti-gptism influence while taking a hit to intelligence, which should get balanced by the other models.

Testing stage: early testing

I do not know how this model holds up over long term context. Early testing showed stability and viable answers.

Parameters

Context size: Not more than 20k recommended - coherency may degrade.
Chat Template: ChatML; Metharme/Pygmalion (as per UnslopNemo) may work, but effects are untested
Samplers: A Temperature-Last of 1 and Min-P of 0.1 are viable, but haven't been finetuned. Activate DRY if repetition appears. XTC is untested.

Quantization

Static GGUF Quants available at:

iMatrix GGUF Quants available at: mradermacher/nepoticide-12B-Unslop-Unleashed-Mell-RPMax-v2-i1-GGUF ❤️

Merge Details

Merge Method

This model was merged using the Model Stock merge method using TheDrummer/UnslopNemo-12B-v4 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: MarinaraSpaghetti/NemoMix-Unleashed-12B
  - model: inflatebot/MN-12B-Mag-Mell-R1
  - model: ArliAI/Mistral-Nemo-12B-ArliAI-RPMax-v1.2
  - model: TheDrummer/UnslopNemo-12B-v4
base_model: TheDrummer/UnslopNemo-12B-v4
merge_method: model_stock
dtype: bfloat16
chat_template: "chatml"
tokenizer:
  source: union

redrix
/

nepoticide-12B-Unslop-Unleashed-Mell-RPMax-v2