Instructions to use professorsynapse/eh-qwen3-4b-clean-sft-grpo-v2-seed2-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use professorsynapse/eh-qwen3-4b-clean-sft-grpo-v2-seed2-lora with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("/workspace/repo/scratch/schema_response_confidence/runs/sft_schema_clean_seed2_full/20260731_232307/Qwen3-4B-bnb-4bit/merged-16bit") model = PeftModel.from_pretrained(base_model, "professorsynapse/eh-qwen3-4b-clean-sft-grpo-v2-seed2-lora") - Notebooks
- Google Colab
- Kaggle
eh-qwen3-4b-clean-sft-grpo-v2-seed2-lora
Status: exploratory response-confidence-track result, replicated across
three seeds. Not the PROTOCOL v0.3 plain-answer headline; never pooled with
it. From experiments/grpo-three-seed-confirmatory (SIGNED 2026-07-31,
resolved 2026-08-07, verdict: Replicated).
What this is
Seed 2 of the plain SFT->GRPO-v2 arm (clean_sft_grpo_v2) in the GRPO
three-seed confirmatory block, which rebuilds the entire GRPO lineage at two
fresh seeds (2, 3) alongside the existing seed 1
(eh-qwen3-4b-clean-sft-grpo-v2-seed1-lora) so the GRPO layer carries a
three-seed interval like its DPO/KTO siblings.
Loads on the seed-2-specific merged clean-schema-SFT base, NOT the seed-1
merge, released alongside this adapter as
professorsynapse/eh-qwen3-4b-clean-sft-seed2-merged-16bit.
Every seed in this block rebuilds its own complete lineage from the
foundation model — a registered rule (Amendment G §3, carried forward), not
an implementation detail.
Result (G1/G2 replicated at this seed, per the registered gates)
Against its own same-seed base (clean_schema_sft_merged_seed2): refusal
recall 89.92% -> 94.28% (+4.36pp), answer-on-unknown 10.08% -> 5.72%
(-4.36pp) — both clear the registered >=3.0pp floor (G1 PASS). Full 3,369-row
SelfAware eval: over_refusal_pct 66.75, correct_on_known_pct 54.05,
truthful_pct 41.35, mean_stated_confidence 0.819,
brier_vs_response_appropriateness 0.406.
Standing limitations (reported per the amendment's own rules)
- Stated confidence is collapsed and behavior-insensitive across every GRPO-touching arm in this block (pre-registered, non-gating observation, not a defect specific to this checkpoint).
- 117 SelfAware known questions (128-union across seeds) appear verbatim in
the training files; a clean-subset sensitivity check
(
analysis/clean_subset_sensitivity.py, n=3,241) leaves every gated delta unchanged. - Report this arm's numbers labeled "GRPO three-seed confirmatory / response-confidence track, exploratory" — never as a tier-1 confirmed result, and never pooled with the PROTOCOL v0.3 headline matrix.
Full record: experiments/grpo-three-seed-confirmatory/AMENDMENT.md
(Outcome section) and NOTEBOOK.md.
- Downloads last month
- 5