SeaWolf-AI/Darwin-gemma-4-E4B-it-x-Gemma-4-E4B-Claude-4-08292

Darwin V6 Evolved Model

Created by Darwin V6 diagnostic-guided evolutionary merge engine.

Parent Models

• Father: google/gemma-4-E4B-it
• Mother: arsovskidev/Gemma-4-E4B-Claude-4.6-Opus-Reasoning-Distilled

Evolution Result

• Benchmark score: 0.8292
• Merge method: slerp
• Merge hash: d33cb3bd

Merge Statistics

• Total tensors merged: 0
• Transplant A (Father preserved): 0
• Transplant B (Mother preserved): 0
• Blended: 0

Optimal Genome

  global_ratio: 0.4989
  attn_ratio: 0.1766
  ffn_ratio: 0.9021
  embed_ratio: 0.6122
  density_a: 0.9951
  density_b: 0.9617
  block_0_ratio: 0.5740
  block_1_ratio: 0.5811
  block_2_ratio: 0.5736
  block_3_ratio: 0.4697
  block_4_ratio: 0.4930
  block_5_ratio: 0.8418
  block_6_ratio: 0.4907
  block_7_ratio: 0.3623
  mri_trust: 0.8521
  merge_method_weight: 0.9519

MRI Prescription Summary

• Average ratio_b: nan
• Attention ratio: nan
• FFN ratio: nan
• Embed ratio: 0.500
• Transplant A: 0
• Transplant B: 0
• Blended: 1160

Health Check

failed: Repo id must be in the form 'repo_name' or 'namespace/repo_name': '/data/ray_temp/ginipick/darwin_merge_cache/merged_233e0e73'. Use repo_type argument if needed.

Method

Darwin V6 implements DARE-TIES merge directly via PyTorch tensor operations. Per-tensor ratios are determined by MRI diagnostic (static tensor analysis + probe-based functional importance) combined with evolutionary genome search.

Formula: final_ratio = mri_ratio * mri_trust + genome_ratio * (1 - mri_trust)

DARE-TIES algorithm: Yadav et al., 2023 (re-implemented, not library-dependent)

Built by VIDRAFT. Apache 2.0.