Mortdecai 48df42b042 docs: Mortdecai 0.6.0 model analysis — fine-tunes broken, base model rankings ...

Full analysis of mortdecai:0.6.0-9b and mortdecai:latest (27B) fine-tunes
vs 6 base model candidates. Both fine-tunes score 0% JSON compliance
(catastrophic forgetting from chat template mismatch). Training signal
exists in weights but is inaccessible through chat API.

Base model rankings: phi4:14b (100%, 7.4s) > gemma3:12b (100%, 12.9s) >
gemma3:27b (100%, 25.3s). Qwen3.5 not recommended for conductor role.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

2026-03-26 02:39:52 -04:00

..

base_model_interview.py

docs: Mortdecai 0.6.0 model analysis — fine-tunes broken, base model rankings

2026-03-26 02:39:52 -04:00

deep_probe.py

docs: Mortdecai 0.6.0 model analysis — fine-tunes broken, base model rankings

2026-03-26 02:39:52 -04:00

model_interview.py

docs: Mortdecai 0.6.0 model analysis — fine-tunes broken, base model rankings

2026-03-26 02:39:52 -04:00