khoilamalphaai

chess-coach-32b-v6-dpo2

Deploy Dedicated

README

License: apache-2.0

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chess-coach-32b-v6-dpo: the earlier DPO adapter, superseded by v6-dpo2.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):

Table with columns: Model (grounded), tier-policy match, beginner, intermediate, advanced, move-sound, distinct
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

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

Table with columns: Resource, Link
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

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

Available on FriendliAI

Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Learn more

Container

Run this model inference with full control and performance in your environment.

Learn more

Model Details

Model Provider

khoilamalphaai

Model Tree

Base

unsloth/Qwen3-32B-unsloth-bnb-4bit

Adapter

this model

Input Modalities

Text

Output Modalities