The best-DPO refinement of the v4 SFT base and the live-served coach on the demo (Modal endpoint chess-coach-v6dpo2-4bit-maia, tuned:true). It is a stronger, tier-targeted successor to chess-coach-32b-v6-dpo, built on the chess-coach-32b-v4-qlora SFT base, which remains the full-reproducible-eval reference and the fallback endpoint.

Model family and roles

chess-coach-32b-v4-qlora: the SFT base, the full-reproducible-eval reference, and the fallback endpoint.
chess-coach-32b-v6-dpo2: the live-served coach on the demo (Modal chess-coach-v6dpo2-4bit-maia, tuned:true), the best-DPO refinement of the v4 SFT base.
chess-coach-32b-v6-dpo: the earlier DPO adapter, superseded by v6-dpo2.
chess-coach-32b-v6-distill: the behavior-in-weights research adapter, evaluated with no grounding (0.325 tier-policy match).

What it is

Base: unsloth/Qwen3-32B-unsloth-bnb-4bit (the same 4-bit base as v4).
Init: a two-adapter TRL DPO setup initialized from the v4 SFT LoRA for BOTH the policy and the frozen reference, so it is a clean superset of v6-dpo with no DPO-on-DPO drift.
Training: harder, tier-targeted, style-matched preference pairs. Beginner learns to prefer the human-findable move over the sharp engine move; advanced learns to prefer the sharpest engine-best move over the softer sound move; intermediate keeps the original v6 pairs to preserve its gain. Selected checkpoint step 200. Preference data from chess-coach-v6.

Honest result (corrected v6 benchmark, 120 held-out TEST, grounded)

Re-scored in one controlled session against the deep-verified v6 labels, same strict extractor as the v4 reference eval (RESULTS_STAGE4_CORRECTED.md):

Model (grounded)	tier-policy match	beginner	intermediate	advanced	move-sound	distinct
v4 (SFT-base baseline)	0.861	0.858	0.750	0.975	0.983	0.987
v6-dpo	0.881	0.858	0.808	0.975	0.983	0.987
v6-dpo2 (this, best DPO)	0.892	0.858	0.842	0.975	0.983	0.987

Overall tier-policy match 0.892 is the best DPO result: +0.031 vs v4 and +0.011 vs v6-dpo. Honestly, the entire gain is the intermediate tier (0.842 vs v4 0.750, vs v6-dpo 0.808). Beginner (0.858) and advanced (0.975) are byte-identical to v4 and v6-dpo because both already sit at their ceiling under grounding, so this is a stronger v6-dpo, not a beginner or advanced breakthrough. Soundness (0.983) and distinct-moves (0.987) are unchanged and names-a-move is nominally higher (0.986). Format (0.925) is marginally under v4 (0.939), a 256-token-cap prose-length artifact, not a move or soundness regression.

Honest limits

The gain is confined to the intermediate tier; beginner and advanced are ceilinged.
Tier-policy match is agreement with the project's select_tier_move rule, a learnability metric, not certified best teaching.
Grounding is required at inference. Without the per-tier Maia signal the three tiers collapse to a single move; the behavior does not live in the weights.

Use

Load the base 4-bit model and apply this adapter with PEFT (the tokenizer is the base Qwen3 tokenizer). Run it with engine grounding in the prompt, the same move-review format v4 was trained on.

Links

Resource	Link
Shipped model (v4)	chess-coach-32b-v4-qlora
Earlier DPO adapter	chess-coach-32b-v6-dpo
Preference dataset	chess-coach-v6
Demo	chess-coach-studio
Code / GitHub repo	Alpha-AI-Engineering-Khoi/chess-instructor-llm

License Apache-2.0, inherited from Qwen3-32B. The preference data is CC-BY-NC-4.0.

khoilamalphaai/chess-coach-32b-v6-dpo2

Chess Coach 32B v6-dpo2 (best DPO adapter, live-served coach)

Model family and roles

What it is

Honest result (corrected v6 benchmark, 120 held-out TEST, grounded)

Honest limits

Use

Links

khoilamalphaai/
chess-coach-32b-v6-dpo2