TareksLab/Carnelian-V2-LLaMa-70B

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 TareksLab/Carnelian-V2a-LLaMa-70B + reissbaker/llama-3.1-70b-abliterated-lora as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

slices:
- sources:
  - layer_range: [0, 80]
    model: TareksLab/Carnelian-V2a-LLaMa-70B+reissbaker/llama-3.1-70b-abliterated-lora
    parameters:
      weight: 1.0
base_model: TareksLab/Carnelian-V2a-LLaMa-70B+reissbaker/llama-3.1-70b-abliterated-lora
dtype: float32
out_dtype: bfloat16
merge_method: task_arithmetic
parameters:
  normalize: false
chat_template: llama3
tokenizer:
 source: TareksLab/Carnelian-V2a-LLaMa-70B
 pad_to_multiple_of: 8