MistralRP-Noromaid-NSFW-Mistral-7B-GGUF/README.md

base_model, library_name, tags

base_model	library_name	tags
	transformers	mergekit merge

Model

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

Model Details

Prompt template: Alpaca

Below is an instruction that describes a task. Write a response that appropriately completes the request.

### Instruction:
{prompt}

### Response:

Merge Details

Merge Method

This model was merged using the SLERP merge method.

Models Merged

The following models were included in the merge:

• Undi95/Mistral-RP-0.1-7B
• MaziyarPanahi/NSFW_DPO_Noromaid-7b-Mistral-7B-Instruct-v0.1

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
      - model: Undi95/Mistral-RP-0.1-7B
        layer_range: [0, 32]
      - model: MaziyarPanahi/NSFW_DPO_Noromaid-7b-Mistral-7B-Instruct-v0.1
        layer_range: [0, 32]
merge_method: slerp
base_model: Undi95/Mistral-RP-0.1-7B
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5 # fallback for rest of tensors
dtype: bfloat16