AgentNativeResearchLab
/

Qwen3.5-9B-PULP-DAPT

domain-adaptive-pretraining

knowledge-injection

Model card Files Files and versions

AmberLJC commited on Aug 30

Commit

11447fa

·

verified ·

1 Parent(s): 9cf71e3

Upload README.md with huggingface_hub

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -35,7 +35,7 @@ memorization questions** (loss 0.80→0.35, offsets 1/42 → 1/42). All gains co
 knowledge-rewriting augmentation stage: every fact restated through 24 LLM-generated
 templates (⅓ reversed forms), full-coverage over all facts (not just evaluated ones), plus
 whole-table narrative documents to fight similar-fact interference. Full recipe, data
-pipeline, benchmark, and findings: **https://github.com/ARA-Labs/chip-knowledge-dapt**
 ## Training

 knowledge-rewriting augmentation stage: every fact restated through 24 LLM-generated
 templates (⅓ reversed forms), full-coverage over all facts (not just evaluated ones), plus
 whole-table narrative documents to fight similar-fact interference. Full recipe, data
+pipeline, benchmark, and findings: **https://github.com/ARA-Labs/PULP-LLM**
 ## Training