Capability of Qwen3.6-27B with 50% less thinking tokens on average, and over 90% less in best cases. Achieved via finetuning Qwen3.6-27B (Qwen Team, 2026) with state-of-the-art algorithms on a curated set of problems...
Source du modèle
Extrait de la source
Capability of Qwen3.6-27B with 50% less thinking tokens on average, and over 90% less in best cases. Achieved via finetuning Qwen3.6-27B (Qwen Team, 2026) with state-of-the-art algorithms on a curated set of problems...
Sources
1 sourceVérifié 18 sept.
Artefacts du modèle
1 artefactmodel-base-aux.safetensors
safetensors · 810 MB · SHA-256 ecba8ef1d0c3…e4b6 · Hugging Face
TéléchargerExtraits de sources
2 extraits--- base_model: "Qwen/Qwen3.6-27B" base_model_relation: finetune library_name: transformers tags: - qwen3_6 - token-efficient - efficient-thinking license: apache-2.0 --- <a href="https://www.bottlecapai.com/"><img src="cap_header.png" alt="ThinkingCap — BottleCap AI" width="100%"></a> # ThinkingCap: Qwen 3.6 27B Capability of Qwen3.6-27B with **50% less** thinking tokens on average, and over **90% less** in best cases. Achieved via finetuning [Qwen3.6-27B (Qwen Team, 2026)](https://huggingface.co/Qwen/Qwen3.6-27B) with state-of-the-art algorithms on a curated set of problems of various domains and difficulty. We designed the finetuning to be as minimally invasive as possible, preserving all of the original answer quality and style of Qwen, while being more token efficient. Check [the blogpost](https://www.bottlecapai.com/thinkingcap-qwen3-6-27b) for more details. We rigorously evaluate the resulting checkpoint across general reasoning, non-reasoning multiple-choice question answering, everyday multi-turn conversations, system prompt adherence, safety, math, code and agentic use cases. Due to the high variability of reasoning quality at Qwen-recommended sampling temperature 1.0, we run each benchmark with multiple seeds and do statistical significance testing on all the results. We evaluate both in domain (holdout parts of selected datasets included in training) and out of domain. <p align="center"><img src="thinkingcap_6x.gif" alt="ThinkingCap reasoning demo (6× speed)" width="480" style="display:block;margin:0 auto"></p> ## Out-of-domain token efficiency <table width="100%" style="border-collapse:collapse;width:100%;display:table;table-layout:auto;font-size:14px;line-height:1.4;"> <thead> <tr><th rowspan="2" style="text-align:left;padding:8px 12px;border-bottom:1px solid rgba(128,128,128,0.22);vertical-align:bottom;color:#6b748a;font-weight:600;">Benchmark</th><th colspan="2" style="text-align:center;padding:6px 12px 3px;border-bottom:1px solid rgba(128,128,128,0.22);border-left:1px solid rgba(128,128,128,0.22);color:#7a67e6;font-weight:700;font-size:11px;letter-spacing:0.06em;text-transform:uppercase;">Accuracy</th><th colspan="3" style="text-align:center;padding:6px 12px 3px;border-bottom:1px solid rgba(128,128,128,0.22);border-left:1px solid rgba(128,128,128,0.22);color:#7a67e6;font-weight:700;font-size:11px;letter-spacing:0.06em;text-trans...
Source context: 8 downloads · 0 likes · Pipeline image-text-to-text · Library transformers · Repo Onnyx-4513/ThinkingCap-Qwen3.6-27B