matsuo-llm-advanced-phase-f4a/README.md

base_model, library_name, tags

base_model	library_name	tags
Qwen/Qwen2.5-7B-Instruct	transformers	mergekit merge

phase_f4a

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

Merge Details

Merge Method

This model was merged using the DARE TIES merge method using Qwen/Qwen2.5-7B-Instruct as a base.

Models Merged

The following models were included in the merge:

• ./outputs/phase_e2b/merged_model
• ./outputs/phase_d/merged_model

Configuration

The following YAML configuration was used to produce this model:

# F4-a: DARE-TIES Merge (Phase D 0.6 + E2-b 0.4)
# Phase D: ALF 56%, DB 52.38% (balanced best)
# E2-b:   ALF 54%, DB 53.47% (DB highest ever, Invalid 12%)
# Goal: Combine Phase D's ALF strength with E2-b's DB strength

models:
  - model: ./outputs/phase_d/merged_model
    parameters:
      density: 0.5
      weight: 0.6
  - model: ./outputs/phase_e2b/merged_model
    parameters:
      density: 0.5
      weight: 0.4
merge_method: dare_ties
base_model: Qwen/Qwen2.5-7B-Instruct
parameters:
  normalize: true
  int8_mask: true
dtype: bfloat16