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 Khetterman/AbominationScience-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:

dtype: float32
out_dtype: bfloat16
merge_method: model_stock
base_model: Khetterman/AbominationScience-12B-v4
models:
  - model: Khetterman/DarkAtom-12B-v3+jtatman/mistral_nemo_12b_reasoning_psychology_lora
  - model: mergekit-community/MN-Chthonia-12B
  - model: mergekit-community/MN-Hekate-Kleidoukhos-12B
    parameters:
      weight: 1.5
  - model: mergekit-community/MN-Nyx-Chthonia-12B
    parameters:
      weight: 1.5
  - model: mistralai/Mistral-Nemo-Instruct-2407+jtatman/mistral_nemo_12b_reasoning_psychology_lora
  - model: mistralai/Mistral-Nemo-Instruct-2407+XeroCodes/aurora-12b
  - model: nbeerbower/Mistral-Nemo-Gutenberg-Doppel-12B-v2
  - model: HumanLLMs/Human-Like-Mistral-Nemo-Instruct-2407+XeroCodes/aurora-12b
  - model: yamatazen/EtherealAurora-12B-v3
  - model: yamatazen/EtherealMoon-12B

chat_template: chatml
tokenizer:
  source: union
  tokens:
    "[INST]":
      source: Khetterman/AbominationScience-12B-v4
      force: true
    "[/INST]":
      source: Khetterman/AbominationScience-12B-v4
      force: true
    "<|im_start|>":
      source: yamatazen/EtherealAurora-12B-v3
      force: true
    "<|im_end|>":
      source: yamatazen/EtherealAurora-12B-v3
      force: true
Downloads last month
13
Safetensors
Model size
12.2B params
Tensor type
BF16
·
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.

Model tree for mergekit-community/MN-Hekate-Enodia-12B