TareksGraveyard/Soothsayer-V1-LLaMa-70B

MERGE1

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

Merge Details

Merge Method

This model was merged using the Linear DELLA merge method using TareksLab/Scrivener-Base-V2-LLaMA-70B as a base.

Models Merged

The following models were included in the merge:

• Sao10K/70B-L3.3-mhnnn-x1
• SicariusSicariiStuff/Negative_LLAMA_70B
• Sao10K/L3.1-70B-Hanami-x1
• EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.1
• mlabonne/Hermes-3-Llama-3.1-70B-lorablated
• TheDrummer/Fallen-Llama-3.3-R1-70B-v1

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: TheDrummer/Fallen-Llama-3.3-R1-70B-v1
    parameters:
      weight: 0.14
  - model: mlabonne/Hermes-3-Llama-3.1-70B-lorablated
    parameters:
      weight: 0.14
  - model: EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.1
    parameters:
      weight: 0.14
  - model: Sao10K/L3.1-70B-Hanami-x1
    parameters:
      weight: 0.14
  - model: SicariusSicariiStuff/Negative_LLAMA_70B
    parameters:
      weight: 0.14
  - model: Sao10K/70B-L3.3-mhnnn-x1
    parameters:
      weight: 0.14
  - model: TareksLab/Scrivener-Base-V2-LLaMA-70B
    parameters:
      weight: 0.16
merge_method: della_linear
base_model: TareksLab/Scrivener-Base-V2-LLaMA-70B
parameters:
  density: 0.7
  epsilon: 0.2
  lambda: 1.1
  normalize: false
dtype: float32
out_dtype: bfloat16
chat_template: llama3
tokenizer:
 source: base