TDSMike
/

ALF-qwen3B-privilege

Text Generation

privileged-information

knowledge-distillation

Model card Files Files and versions

ALF-qwen3B-privilege / code

74.4 kB

Ctrl+K

Ctrl+K

1 contributor

History: 1 commit

TDSMike's picture

Publish privileged ALFWorld Qwen2.5-3B teacher, structured hints, reproduction code, and evaluation audit

8f4f748 verified 2 months ago

accept_exclusions_and_rewrite_hints.py

8.58 kB
Publish privileged ALFWorld Qwen2.5-3B teacher, structured hints, reproduction code, and evaluation audit 2 months ago
audit_teacher_gate.py

5.01 kB
Publish privileged ALFWorld Qwen2.5-3B teacher, structured hints, reproduction code, and evaluation audit 2 months ago
checkpointing.py

2.04 kB
Publish privileged ALFWorld Qwen2.5-3B teacher, structured hints, reproduction code, and evaluation audit 2 months ago
eval_student.py

14 kB
Publish privileged ALFWorld Qwen2.5-3B teacher, structured hints, reproduction code, and evaluation audit 2 months ago
prepare_structured_hints.py

22.2 kB
Publish privileged ALFWorld Qwen2.5-3B teacher, structured hints, reproduction code, and evaluation audit 2 months ago
prompts.py

2.42 kB
Publish privileged ALFWorld Qwen2.5-3B teacher, structured hints, reproduction code, and evaluation audit 2 months ago
sft_teacher.py

20.2 kB
Publish privileged ALFWorld Qwen2.5-3B teacher, structured hints, reproduction code, and evaluation audit 2 months ago