TareksLab/Carnelian-DL-V2-LLaMa-70B

MERGEDL

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/L33R1-T-BASE-70B as a base.

Models Merged

The following models were included in the merge:

• flammenai/Mahou-1.5-llama3.1-70B
• nbeerbower/llama3.1-kartoffeldes-70B
• SentientAGI/Dobby-Unhinged-Llama-3.3-70B
• flammenai/Llama3.1-Flammades-70B
• tenyx/Llama3-TenyxChat-70B

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: nbeerbower/llama3.1-kartoffeldes-70B
    parameters:
      weight: 0.18
      density: 0.7
      epsilon: 0.2
      lambda: 1.1
  - model: flammenai/Mahou-1.5-llama3.1-70B
    parameters:
      weight: 0.16
      density: 0.7
      epsilon: 0.2
      lambda: 1.1
  - model: flammenai/Llama3.1-Flammades-70B
    parameters:
      weight: 0.16
      density: 0.7
      epsilon: 0.2
      lambda: 1.1
  - model: SentientAGI/Dobby-Unhinged-Llama-3.3-70B
    parameters:
      weight: 0.16
      density: 0.7
      epsilon: 0.2
      lambda: 1.1
  - model: tenyx/Llama3-TenyxChat-70B
    parameters:
      weight: 0.16
      density: 0.7
      epsilon: 0.2
      lambda: 1.1
  - model: TareksLab/L33R1-T-BASE-70B
    parameters:
      weight: 0.18
      density: 0.7
      epsilon: 0.1
      lambda: 1.0
merge_method: della_linear
base_model: TareksLab/L33R1-T-BASE-70B
parameters:
  normalize: false
  int8_mask: true
dtype: float32
out_dtype: bfloat16
chat_template: llama3
tokenizer:
 source: union
 pad_to_multiple_of: 8