You can deploy this model and start earning money today!

merge

Name: Persona-V1-70B
Availability: InStock

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 Sao10K/70B-L3.3-mhnnn-x1 as a base.

Models Merged

The following models were included in the merge:

flammenai/Mahou-1.5-llama3.1-70B
SentientAGI/Dobby-Unhinged-Llama-3.3-70B
flammenai/Llama3.1-Flammades-70B

Configuration

The following YAML configuration was used to produce this model:

yaml

models:
  - model: flammenai/Mahou-1.5-llama3.1-70B
    parameters:
      weight: 0.25
      density: 0.5
  - model: flammenai/Llama3.1-Flammades-70B
    parameters:
      weight: 0.25
      density: 0.5
  - model: SentientAGI/Dobby-Unhinged-Llama-3.3-70B
    parameters:
      weight: 0.25
      density: 0.5
  - model: Sao10K/70B-L3.3-mhnnn-x1
    parameters:
      weight: 0.25
      density: 0.5
merge_method: dare_ties
base_model: Sao10K/70B-L3.3-mhnnn-x1
parameters:
  normalize: false
  int8_mask: true
dtype: bfloat16
chat_template: llama3
tokenizer:
 source: base
 pad_to_multiple_of: 8

TareksLab/Persona-V1-70B

merge

Merge Details

Merge Method

Models Merged

Configuration

TareksLab/
Persona-V1-70B