Downloads · 30 days
15
23% of all-time downloads
suchirsalhan/qwen3.5-0.8b-playpen-rest
qwen3.5-0.8b-playpen-rest is a machine learning model from suchirsalhan. 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.
Format-repair + self-ReST finetune of Qwen/Qwen3.5-0.8B for clembench/Playpen dialogue games. Teacher demonstrations (Qwen/Qwen2.5-3B-Instruct) on abort-starved games seed format compliance, then one self-ReST round.…
Downloads · 30 days
15
23% of all-time downloads
All-time downloads
65
Public
Parameters
752M
3 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors1.5 GB · 99%
From the Hugging Face model README
Format-repair + self-ReST finetune of Qwen/Qwen3.5-0.8B for clembench/Playpen dialogue games.
Teacher demonstrations (Qwen/Qwen2.5-3B-Instruct) on abort-starved games seed format compliance, then one
self-ReST round. best=qwen-fmt-rest; 5-game full-instance clemscore 6.667 -> 20.266 (Δ 13.60).