ssadqdsacf

cross-unlearning-case6-qwen35-4b-kl-min-epoch10

README

License: apache-2.0

Provenance

Protocol: qwen3.5-4b-profile-400-sft-v2-r32-cosine-15e-selected-epoch10
Protocol SHA256: d3cbada8c6bb2e5e1d676fdf2cf6297c5b93b9a68a4b7f543137dca22a97dabe
Model fingerprint: 96ed8e39896afc85c2f0898d76b90e77ca7436b4a857f4d2de40708350ab97f0
SFT selection: complete epoch 10 at optimizer step 2370 from a training run that later completed epoch 12; the cosine scheduler retained its original 15-epoch horizon.
Evaluation: fixed 4-shot greedy decoding. Classification uses native thinking; mask and generation disable thinking.

This is one of the six formal matrix models.

The repository includes the verified three-direction classification, mask, and generation summary.

See upload_manifest.json, selection/epoch10_selection_manifest.json, training/run_manifest.json, protocol/, and eval/ for machine-readable provenance.

Available on FriendliAI

Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Learn more

Model Details

Model Provider

ssadqdsacf

Model Tree

Base

ssadqdsacf/cross-unlearning-case6-qwen35-4b-sft-v2-epoch10-r32-cosine

Fine-tuned

this model

Input Modalities

TextImageVideo

Output Modalities

Text

Supported Functionality