Downloads · 30 days
0
chess-qwen35-0.8b-rl-20260710
Chess-Nut-Engine/chess-qwen35-0.8b-rl-20260710
chess-qwen35-0.8b-rl-20260710 is a machine learning model from Chess-Nut-Engine. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Four checkpoints from the RL phase (2026-07-09/10), all descending from the v3 SFT curriculum (...sft-v3-20260709). Gameplay scores are vs Stockfish limited to Elo 1320, 1,024 games, thinking mode unless noted.
Access
Public
Updated Jul 10, 2026
Repo size
10.6 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors10.5 GB · 99%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Jul 10, 2026
- Updated
- Jul 10, 2026
- SHA
- be3475ad
Base models
Model card
From the Hugging Face model README
chess-qwen35-0.8b-rl-20260710 — RL campaign checkpoints
Four checkpoints from the RL phase (2026-07-09/10), all descending from the
v3 SFT curriculum (...sft-v3-20260709). Gameplay scores are vs
Stockfish limited to Elo 1320, 1,024 games, thinking mode unless noted.
| subfolder | what it is | game score |
|---|---|---|
topup | v3-C + prompt-unified seed-pack top-up (the RL seed) | 0.1160 think / 0.1201 gut |
dpo_r2 | + iterative DPO on 30.8k stratified self-play pairs | 0.1337 think |
r5e_english | dpo_r2 + English-voice SFT top-up (verified 35B traces) — reasons in natural English (399/400 game traces), best diversity | 0.1260 think (statistical tie w/ dpo_r2) |
dopd_r1 | r5e + 200 steps DOPD token-routed distillation (arXiv 2606.30626 adaptation, same-weights privileged teacher) | pilot — see repo docs |
Key findings encoded in these checkpoints: thinking-mode play only pays when
trained-for (+0.018 for dpo_r2, nothing for the seed); preference training
nudges move choice but cannot shift trace style; one SFT top-up flipped the
model to natural-English reasoning at zero strength cost. Full records:
docs/experiments/2026-07-10_rl_campaign/ in the project repo.
Usage
from transformers import AutoModelForCausalLM, AutoTokenizer
m = AutoModelForCausalLM.from_pretrained(
"Chess-Nut-Engine/chess-qwen35-0.8b-rl-20260710",
subfolder="r5e_english", trust_remote_code=True)
t = AutoTokenizer.from_pretrained(
"Chess-Nut-Engine/chess-qwen35-0.8b-rl-20260710",
subfolder="r5e_english")
Planning protocol: <think>...</think><move>uci</move>; <move> tags are
tokenizer special tokens. Thinking mode requires the chat template's
enable_thinking=True.
- License
- apache-2.0
- Created
- Jul 10, 2026
- Updated
- Jul 10, 2026