kacolab/Qwen-2.5

EXP-aicomps-mm20 — SFT vs SDFT under 20% mismatched demonstrations

Research checkpoints: Qwen/Qwen2.5-7B-Instruct fully fine-tuned on the ToolUse task with SFT or SDFT, on clean demonstrations or with 20% of demonstrations deliberately mismatched to other questions (mm20). Only the seed-42 final checkpoint of each of the 4 configurations is published; each lives in its own subfolder with a model card, sha256 list and eval results.

Subfolder	Method	Training data
tooluse-sft-clean-seed42	SFT	clean
tooluse-sft-mismatch-seed42	SFT	20% mismatched
tooluse-sdft-clean-seed42	SDFT	clean
tooluse-sdft-mismatch-seed42	SDFT	20% mismatched

mismatch models were trained on intentionally corrupted data and are for research only.

PROTOCOL.md is the locked experiment protocol. manifests/ holds the train/val split (record ids) and the corruption mapping (record indices + hashes; no dataset text).