chaoliangUNSW/Jev-Style-2B-Decision-v3-MLX
Copyright 2026 chaoliangUNSW. Licensed under the Apache License, Version 2.0 (see LICENSE).

This model is a fine-tuned derivative of Qwen3.5-2B (https://huggingface.co/Qwen/Qwen3.5-2B,
revision 15852e8c16360a2fea060d615a32b45270f8a8fc), Copyright 2026 Alibaba Cloud, licensed under the Apache
License, Version 2.0. The LICENSE file in this repository is the license file distributed with Qwen3.5-2B.

Modifications relative to Qwen3.5-2B:
- all text-model weights were fine-tuned (full fine-tuning) to score typed decision questions
  (choice / score / true-false) with a verdict readout: logit(" yes") - logit(" no") at one " ->" slot per
  option, under a block-causal attention protocol (2,048-token blocks); one global calibration temperature was
  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;
- converted to MLX format with mlx-lm 0.31.3 / mlx 0.32.2 (https://github.com/ml-explore/mlx-lm,
  MIT License, Copyright Apple Inc.): bf16/ = bfloat16, 8bit/ = affine 8-bit quantisation, group size 64;
  each folder also holds macjev_norms_fp32.safetensors (the exact FP32 (1 + w) RMSNorm weights);
- the runtime script contains a modified copy of mlx-lm 0.31.3's qwen3_5 GatedDeltaNet.__call__ (MIT License,
  Copyright Apple Inc.; the q/k normalisation epsilon changed and the sharding branches removed); the MIT
  copyright and permission notice is reproduced in THIRD_PARTY_NOTICES.md;
- 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.

Part of the third generation (v3) of the Jev-Style decision series (v3 also includes
chaoliangUNSW/Jev-Style-0.8B-Decision-v3). 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 built on Qwen3.5-2B-Base. Jev-Style-2B-Decision-v3 is
a full fine-tune of Qwen/Qwen3.5-2B.

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.