Source and artwork credits
- Decision 1.0 Sol-2B at
ce0c018a28de16d6639b1cd203b761bf643b89e6: direct weight origin; every weight was fine-tuned, and its own answer probabilities were the soft targets (Apache-2.0,LICENSE). Its own training data reach this model through its weights, among them Cosmos QA, SQuAD 2.0 answerability labels, SNLI, MultiNLI, CLINC150 and BANKING77; see its attributions. - Qwen3.5-2B at
15852e8c16360a2fea060d615a32b45270f8a8fc: upstream text backbone and tokenizer of Decision 1.0 Sol (Apache-2.0,LICENSES/Qwen3.5-2B-LICENSE.txt). - Training data of this fine-tune (not redistributed here; each keeps its own licence). Own Decision 1.0 corpora: CLINC150 (Larson et al., EMNLP-IJCNLP 2019; CC BY 3.0), BANKING77 (Casanueva et al., 2020; CC BY 4.0), MultiNLI non-fiction genres (Williams, Nangia and Bowman, NAACL 2018; OANC terms). Decision 2.0 data: GoEmotions (Demszky et al., ACL 2020; CC BY 4.0), SNLI (Bowman et al., EMNLP 2015; CC BY-SA 4.0), TyDi QA (Clark et al., TACL 2020; Apache-2.0, Wikipedia text CC BY-SA), WinoGrande (Sakaguchi et al., AAAI 2020; Apache-2.0), SQuAD 2.0 (Rajpurkar et al., ACL 2018; CC BY-SA 4.0), GSM8K (Cobbe et al., 2021; MIT), MLQE-PE (Fomicheva et al., LREC 2022; CC0 annotations, Wikipedia text CC BY-SA), 2WikiMultihopQA (Ho et al., COLING 2020; Apache-2.0, Wikipedia text CC BY-SA), HotpotQA (Yang et al., EMNLP 2018; CC BY-SA 4.0), KLUE MRC and STS (Park et al., 2021; CC BY-SA 4.0), IBM ArgQ-30k (Gretz et al., AAAI 2020; CC BY-SA 3.0), JGLUE JSQuAD and JSTS (Kurihara et al., LREC 2022; CC BY-SA 4.0), QuAC (Choi et al., EMNLP 2018; CC BY-SA 4.0, its dataset card says MIT), DRCD (Shao et al., 2018; CC BY-SA 3.0), SQAC (Gutiérrez-Fandiño et al., 2022; CC BY-SA 4.0), CMRC 2018 (Cui et al., EMNLP 2019; CC BY-SA 4.0), GermanQuAD (Möller et al., 2021; CC BY 4.0), CommonsenseQA (Talmor et al., NAACL 2019; MIT), MultiWOZ 2.2 (Zang et al., 2020; MIT), MTOP (Li et al., EACL 2021; CC BY-SA 4.0), PIAF (Keraron et al., LREC 2020; MIT), SciTail (Khot et al., AAAI 2018; Apache-2.0), MuSiQue (Trivedi et al., TACL 2022; CC BY 4.0, Wikipedia text CC BY-SA), DBpedia-14 (Zhang et al., NeurIPS 2015; CC BY-SA 3.0), Taskmaster-2 (Byrne et al., 2020; CC BY 4.0), ROPES (Lin et al., MRQA 2019; CC BY 4.0), SAF (Filighera et al., ACL 2022; CC BY 4.0), QuaRTz (Tafjord et al., EMNLP 2019; CC BY 4.0), OneStopEnglish (Vajjala and Lučić, BEA 2018; CC BY-SA 4.0), and project-generated decision tasks.
- Evaluation data shown on the card: JevArena v3 and JevBench public 231 (panels described in
evaluation/EVALUATION.md); mlx-diag Choice from the MASSIVE 1.1 test split (FitzGerald et al., 2022; CC BY 4.0) and Noul from the PAWS-X test split (Yang et al., EMNLP 2019). - Owl banner: Decision 1.0 Sol mosaic owl, unchanged pixels, in the DEV2.0 name layout; wordmark set in Poppins (SIL Open Font License) and DejaVu Sans Bold.