chaoliangUNSW/Jev-Style-0.8B-Decision-v3
Copyright 2026 chaoliangUNSW. Licensed under the Apache License, Version 2.0 (see LICENSE).

This model is a fine-tuned derivative of Qwen3.5-0.8B (https://huggingface.co/Qwen/Qwen3.5-0.8B,
revision 2fc06364715b967f1860aea9cf38778875588b17), Copyright 2026 Alibaba Cloud, licensed under the Apache
License, Version 2.0. The LICENSE file in this repository is the license file distributed with Qwen3.5-0.8B.

Modifications relative to Qwen3.5-0.8B:
- all text-model weights were fine-tuned (full fine-tuning, bf16 training) to score typed decision questions
  (choice / score / true-false) with a verdict readout: logit(" yes") - logit(" no") at one " ->" slot per
  option; calibration temperatures were fitted afterwards (readout_config.json);
- the vision tower (model.visual.*) and the multi-token-prediction head (mtp.*) were removed; the checkpoint
  is a text-only Qwen3_5ForCausalLM with tied input/output embeddings;
- added the runtime script, readout/release configuration files, the integrity manifest and this NOTICE.

The question types (choice / score / noul) follow the typed-decision convention of Laya
(https://github.com/NandhaKishorM/laya, Apache-2.0) so both models can be evaluated on the same
inputs. No Laya code or weights are included.

Third generation (v3) of the Jev-Style decision series. Earlier generations: v1 =
chaoliangUNSW/Jev-Style-Qwen3.5-2B-Decision (public GGUF release: chaoliangUNSW/Jev-Style-Qwen3.5-2B-Decision-GGUF) and
v2 = chaoliangUNSW/Jev-Style-Qwen3.5-2B-Decision-v2, both 2B models built on Qwen3.5-2B-Base. v3 is fine-tuned from
Qwen3.5-0.8B; no weights of v1 or v2 were reused.

Not affiliated with, endorsed by or connected to TypeSafe or Jev. "Jev-Style" only describes the kind
of model (a small typed-decision model in a similar style); no Jev weights, code or outputs are included.
Not affiliated with or endorsed by Alibaba Cloud / the Qwen team or the Laya authors.