mergekit-community/MN-Hekate-Kleidoukhos-12B

merge

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

Merge Details

Merge Method

This model was merged using the Model Stock merge method using mistralai/Mistral-Nemo-Instruct-2407 as a base.

Models Merged

The following models were included in the merge:

• mergekit-community/MN-Hecate-Chthonia-12B
• mergekit-community/MN-Chthonia-12B
• HumanLLMs/Human-Like-Mistral-Nemo-Instruct-2407 + XeroCodes/aurora-12b
• yamatazen/EtherealAurora-12B-v3
• mergekit-community/MN-Nyx-Chthonia-12B
• mergekit-community/MN-Ephemeros-12B
• mergekit-community/MN-Anathema-12B + jtatman/mistral_nemo_12b_reasoning_psychology_lora
• nbeerbower/Mistral-Nemo-Gutenberg-Doppel-12B-v2 + jtatman/mistral_nemo_12b_reasoning_psychology_lora

Configuration

The following YAML configuration was used to produce this model:

dtype: float32
out_dtype: bfloat16
merge_method: model_stock
base_model: mistralai/Mistral-Nemo-Instruct-2407
models:
  - model: mergekit-community/MN-Anathema-12B+jtatman/mistral_nemo_12b_reasoning_psychology_lora
  - model: mergekit-community/MN-Chthonia-12B
    parameters:
      weight: 1.2
  - model: mergekit-community/MN-Ephemeros-12B
    parameters:
      weight: 1.1
  - model: mergekit-community/MN-Hecate-Chthonia-12B
    parameters:
      weight: 0.6
  - model: mergekit-community/MN-Nyx-Chthonia-12B
    parameters:
      weight: 1.3
  - model: nbeerbower/Mistral-Nemo-Gutenberg-Doppel-12B-v2+jtatman/mistral_nemo_12b_reasoning_psychology_lora
  - model: HumanLLMs/Human-Like-Mistral-Nemo-Instruct-2407+XeroCodes/aurora-12b
  - model: yamatazen/EtherealAurora-12B-v3

chat_template: chatml
tokenizer:
  source: union
  tokens:
    "[INST]":
      source: mistralai/Mistral-Nemo-Instruct-2407
      force: true
    "[/INST]":
      source: mistralai/Mistral-Nemo-Instruct-2407
      force: true
    "<|im_start|>":
      source: yamatazen/EtherealAurora-12B-v3
      force: true
    "<|im_end|>":
      source: yamatazen/EtherealAurora-12B-v3
      force: true