SOG_10k_70B

Merge_SAOPLUS

My on the shoulders of giants (SOG) love letter to Sao10K. Extremely solid base RP model to be used for future SOG merges.

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 SicariusSicariiStuff/Negative_LLAMA_70B as a base.

Models Merged

The following models were included in the merge:

• Sao10K/70B-L3.3-Cirrus-x1
• TheDrummer/Anubis-70B-v1
• Sao10K/Llama-3.3-70B-Vulpecula-r1
• Writer/Palmyra-Med-70B-32K
• Sao10K/L3.1-70B-Hanami-x1
• Sao10K/L3.3-70B-Euryale-v2.3
• Sao10K/70B-L3.3-mhnnn-x1

Configuration

The following YAML configuration was used to produce this model:

models:
  
  - model: Sao10K/Llama-3.3-70B-Vulpecula-r1
    parameters:
      weight: 0.1
      density: 0.1

  - model: Sao10K/70B-L3.3-Cirrus-x1
    parameters:
      weight: 0.1
      density: 0.1

  - model: Sao10K/70B-L3.3-mhnnn-x1
    parameters:
      weight: 0.1
      density: 0.1

  - model: Sao10K/L3.3-70B-Euryale-v2.3
    parameters:
      weight: 0.1
      density: 0.1

  - model: Sao10K/L3.1-70B-Hanami-x1
    parameters:
      weight: 0.1
      density: 0.1

  - model: TheDrummer/Anubis-70B-v1
    parameters:
      weight: 0.1
      density: 0.1

  - model: SicariusSicariiStuff/Negative_LLAMA_70B
    parameters:
      weight: 0.1
      density: 0.1

  - model: Writer/Palmyra-Med-70B-32K
    parameters:
      weight: 0.1
      density: 0.1


merge_method: dare_ties
base_model: SicariusSicariiStuff/Negative_LLAMA_70B
parameters:    
    normalize: false
dtype: float32
out_dtype: bfloat16
chat_template: llama3
tokenizer:
    source: SicariusSicariiStuff/Negative_LLAMA_70B