bluuwhale_-_NemoMerge-V1.0-12B-4bits

Quantization made by Richard Erkhov.

Github

Discord

Request more models

NemoMerge-V1.0-12B - bnb 4bits

• Model creator: https://huggingface.co/bluuwhale/
• Original model: https://huggingface.co/bluuwhale/NemoMerge-V1.0-12B/

Original model description:

base_model:

• unsloth/Mistral-Nemo-Instruct-2407
• cognitivecomputations/dolphin-2.9.3-mistral-nemo-12b
• Kooten/Mistral-Nemo-Instruct-2407-norefuse-OAS
• intervitens/mini-magnum-12b-v1.1
• NeverSleep/Lumimaid-v0.2-12B library_name: transformers tags:
• mergekit
• merge

---

Experimental Merge. I have no idea what the hell I'm doing.

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 unsloth/Mistral-Nemo-Instruct-2407 as a base.

Models Merged

The following models were included in the merge:

• cognitivecomputations/dolphin-2.9.3-mistral-nemo-12b
• Kooten/Mistral-Nemo-Instruct-2407-norefuse-OAS
• intervitens/mini-magnum-12b-v1.1
• NeverSleep/Lumimaid-v0.2-12B

Configuration

The following YAML configuration was used to produce this model:

base_model: unsloth/Mistral-Nemo-Instruct-2407
models:
  - model: intervitens/mini-magnum-12b-v1.1
    parameters:
      density: 0.5
      weight: 0.2
  - model: NeverSleep/Lumimaid-v0.2-12B
    parameters:
      density: 0.5
      weight: 0.5
  - model: Kooten/Mistral-Nemo-Instruct-2407-norefuse-OAS
    parameters:
      density: 0.6
      weight: 1.0
  - model: cognitivecomputations/dolphin-2.9.3-mistral-nemo-12b
    parameters:
      density: 0.6
      weight: 0.5
merge_method: dare_ties
dtype: float16