5 days ago
-
State training dataset in card body
-
Link training dataset (YAML datasets field for HF filter)
6 days ago
-
Fix tags list indentation (decision-model tag was parsed as one string)
-
Add decision-model tag (HF Hub decision-model filter, Oct 2026)
24 days ago
-
README: remove stale dataset-version references
-
LoRA adapter: Student B (Qwen2.5-0.5B memory-relevance judge)
-
Model card: 10k benchmark, distillation fidelity, pipeline, roadmap
-
initial commit
