Website: jevstyle.com — all JevStyle decision models, benchmarks and quickstart in one place. A Jev-style decision model: it does not write text. Give it a state, a question and a list of options, and one forward pass returns the decision with calibrated probabilities - in 77 ms on an M1 Max. GGUF builds (BF16 / Q80 / Q4KM) for LM Studio and llama.cpp: chaoliangUNSW/Jev-Style-Qwen3.5-2B-Decision-GGUF Everything below is measured on data the model never trained on, with the probabilities exactly as the released weights produce them (no post-processing). - Calibrated out of the box. An ECE of 0.017 on 1,500 examples is statistically indistinguishable from a perfectly calibrated model…
Open weights
apache-2.0
1.9B parameters
262,144 tokens
mlx
Website: jevstyle.com — all JevStyle decision models, benchmarks and quickstart in one place. A Jev-style decision model for classification, routing and typed choices. Give it a state, a question and a list of options; one prefill returns a selected option with calibrated probabilities. Download this build: model.safetensors. The repository also includes its calibration, inference client and evaluation records. 81.20% macro accuracy on the fixed English reference panel, compared with 76.68% for v1 and 75.09% for English Laya. The results below use the CUDA reference structure: 11 real-label task groups, 3,277 decisions, equal task weights, and the same 3,100-record calibration split.…
Open weights
apache-2.0
1.9B parameters
262,144 tokens
mlx
Website: jevstyle.com — all JevStyle decision models, benchmarks and quickstart in one place. A Jev-style decision model for classification, routing and typed choices. Give it a state, a question and a list of options; one prefill returns a selected option with calibrated probabilities. Download this build: model.safetensors. The repository also includes its calibration, inference client and evaluation records. 81.20% macro accuracy on the fixed English reference panel, compared with 76.68% for v1 and 75.09% for English Laya. The results below use the CUDA reference structure: 11 real-label task groups, 3,277 decisions, equal task weights, and the same 3,100-record calibration split.…
Open weights
apache-2.0
1.9B parameters
262,144 tokens
transformers
Model · Text generation
IFML
A masked diffusion language model adapted from Qwen3.5-2B. The backbone is hybrid: only its attention layers are made bidirectional, and the Gated DeltaNet layers stay causal. This is a base model, with no instruction tuning. Paper: dQwen3.5: Hybrid-Attention Diffusion Language Models. Code: https://github.com/AntonXue/dQwen Needs a CUDA GPU and transformers>=5.13 (tested with torch 2.7.1+cu128, flash-linear-attention 0.5.1). generate decodes the whole canvas at once, committing positions above a confidence threshold (tau=0.9); pass blocklength=32 for left-to-right block decoding, or tau=None, stepsperblock=k for a fixed budget. The 50B-token checkpoint from the paper is…
Open weights
apache-2.0
1.9B parameters
262,144 tokens
transformers
VNPen is MewBaka Studio's visual-novel model series. The writer edition is for script writing, de-AI rewriting, and generating example scenes from a mood brief. Output format is one script line per line: speaker：text, with narration written as 旁白：. The base Qwen/Qwen3.5-2B is multimodal. Its checkpoint carries 297 model.visual. tensors (a depth-24 / hidden-1024 / patch-16 ViT) and 15 mtp. tensors for multi-token prediction. This project is text-only. In transformers, AutoModelForCausalLM on a qwen35 config builds Qwen35ForCausalLM over a Qwen35TextConfig — so the vision weights were never loaded at any point: not for training, not for merging, not for saving. Verified on the published…
Open weights
apache-2.0
1.9B parameters
262,144 tokens
transformers
FP8 version of ThinkLess-2B: 8-bit floating-point weights and activations, 2.5 GB (bf16: 4.3 GB), with near-identical accuracy. Made with llm-compressor (FP8DYNAMIC: per-channel FP8 weights, dynamic per-token FP8 activations, no calibration data). The output head, vision tower and MTP heads stay in 16-bit. The differences are within the 95% confidence intervals, and answers stay just as short (cut-offs ≤ 1%). FP8 compute needs a GPU with FP8 support (NVIDIA Hopper or Ada, e.g. H100, L4, RTX 40-series); vLLM loads the compressed-tensors format directly. Use Qwen3.5's thinking-mode sampling (temperature 1.0, top-p 0.95, top-k 20, presence penalty 1.5). A 4-bit AWQ version of ThinkLess-2B was…
Open weights
apache-2.0
1.9B parameters
262,144 tokens
transformers
