TareksLab/GRADIENT-TEST-1

merge

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

Merge Details

Merge Method

This model was merged using the Task Arithmetic merge method using huihui-ai/Llama-3.3-70B-Instruct-abliterated as a base.

Models Merged

The following models were included in the merge:

• Sao10K/Llama-3.3-70B-Vulpecula-r1
• SicariusSicariiStuff/Negative_LLAMA_70B
• Sao10K/L3.3-70B-Euryale-v2.3
• Doctor-Shotgun/L3.3-70B-Magnum-v4-SE

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: Doctor-Shotgun/L3.3-70B-Magnum-v4-SE
    parameters:
      weight: [0.11, 0.12, 0.17, 0.25, 0.35]
  - model: Sao10K/L3.3-70B-Euryale-v2.3
    parameters:
      weight: [0.13, 0.16, 0.2, 0.27, 0.24]
  - model: SicariusSicariiStuff/Negative_LLAMA_70B
    parameters:
      weight: [0.17, 0.2, 0.26, 0.20, 0.17]
  - model: Sao10K/Llama-3.3-70B-Vulpecula-r1
    parameters:
      weight: [0.24, 0.27, 0.2, 0.16, 0.13]
  - model: huihui-ai/Llama-3.3-70B-Instruct-abliterated
    parameters:
      weight: [0.35, 0.25, 0.17, 0.12, 0.11]
merge_method: task_arithmetic
base_model: huihui-ai/Llama-3.3-70B-Instruct-abliterated
parameters:
  normalize: false
  int8_mask: true
dtype: bfloat16
chat_template: llama3
tokenizer:
 source: union