ClaudioItaly/Pulzar-DPO-7

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:

• ClaudioItaly/Evolutionstory-7B-v2.2
• flammenai/flammen15-gutenberg-DPO-v1-7B

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: flammenai/flammen15-gutenberg-DPO-v1-7B
  - model: ClaudioItaly/Evolutionstory-7B-v2.2
merge_method: slerp
tokenizer_merge_method: slerp
tokenizer_parameters:
  t: 0.3  # Dà più peso al tokenizer di Evolutionstory-7B-v2.2
base_model: ClaudioItaly/Evolutionstory-7B-v2.2
dtype: bfloat16
parameters:
  t: [0, 0.2, 0.4, 0.5, 0.4, 0.2, 0]  # Curva che favorisce leggermente Evolutionstory-7B-v2.2
  temp: 1.3 # Temperatura per smoothare il merge
density:  # Density merging per bilanciare le caratteristiche dei due modelli
  - threshold: 0.1
    t: 0.7
  - threshold: 0.5
    t: 0.5
  - threshold: 0.9
    t: 0.3