README.md

metadata

license: cc-by-nc-sa-4.0
language:
  - en
pipeline_tag: text-generation

Explanation

• Merged three models using mergekit (dare_ties)

Models

• Sakura-SOLAR-Instruct
• Sakura-SOLRCA-Math-Instruct-DPO-v2
• Sakura-SOLRCA-Instruct-DPO

Merge Script

models:
  - model: kyujinpy/Sakura-SOLAR-Instruct
    parameters:
      density: 1.0
      weight: 1.0
  - model: kyujinpy/Sakura-SOLRCA-Math-Instruct-DPO-v2
    parameters:
      density: 0.5
      weight: [0.33, 0.4, 0.33]
  - model: kyujinpy/Sakura-SOLRCA-Instruct-DPO
    parameters:
      density: [0.33, 0.45, 0.66]
      weight: 0.66
merge_method: dare_ties
base_model: kyujinpy/Sakura-SOLAR-Instruct
parameters:
  normalize: true
  int8_mask: true
dtype: bfloat16
tokenizer_source : union

Original Author's HuggingFace profile

• kyujinpy

License

• Following the license written at the author's space