TareksLab/Citrine-DL-V2-LLaMA-70B

MERGE2

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/Thinker-R1-LLaMa-70B as a base.

Models Merged

The following models were included in the merge:

• Steelskull/L3.3-Cu-Mai-R1-70b
• Sao10K/Llama-3.3-70B-Vulpecula-r1

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: Sao10K/Llama-3.3-70B-Vulpecula-r1
    parameters:
      weight: 0.35
      density: 0.7
      epsilon: 0.2
      lambda: 1.1
  - model: Steelskull/L3.3-Cu-Mai-R1-70b
    parameters:
      weight: 0.30
      density: 0.7
      epsilon: 0.2
      lambda: 1.1
  - model: TareksLab/Thinker-R1-LLaMa-70B
    parameters:
      weight: 0.35
      density: 0.7
      epsilon: 0.1
      lambda: 1.0
merge_method: della_linear
base_model: TareksLab/Thinker-R1-LLaMa-70B
parameters:
  normalize: false
  int8_mask: true
dtype: float32
out_dtype: bfloat16
chat_template: llama3
tokenizer:
 source: Sao10K/Llama-3.3-70B-Vulpecula-r1
 pad_to_multiple_of: 8