marcuscedricridia/cursa-o1-7b-v1.1

merge

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

Merge Details

Merge Method

This model was merged using the SLERP merge method.

Models Merged

The following models were included in the merge:

• marcuscedricridia/pre-cursa-o1-v1.2
• marcuscedricridia/post-cursa-o1

Configuration

The following YAML configuration was used to produce this model:

model_name: "post-cursa-o1"
base_model: marcuscedricridia/post-cursa-o1
merge_method: slerp
dtype: bfloat16
tokenizer_source: "union"  # or "base" or a model path
chat_template: "auto"  # or a template name or Jinja2 template
slices:
  - sources:
      - model: marcuscedricridia/pre-cursa-o1-v1.2
        layer_range: [0, 28]
      - model: marcuscedricridia/post-cursa-o1
        layer_range: [0, 28]
parameters:
  t:
    - filter: self_attn
      value: [0.0, 0.3, 0.5, 0.7, 1.0]
    - filter: mlp
      value: [1.0, 0.7, 0.5, 0.3, 0.0]
    - filter: input_layernorm|post_attention_layernorm
      value: 0.5
    - value: 0.5