Jev directory
CommunityJev Models & Reimplementations
Workmagic Jev Decision Qwen3 8B Sft V2
Hugging Face LoRA adapter from workmagicio, fine-tuned from Qwen/Qwen3-8B and tagged decision-model and typed-decisions. Published under library anyjev with safetensors weights for English text generation.
- Reading time
- 1 min
- Published by
- Community
- Added
- Nov 2026
Highlights
- LoRA adapter tagged stage2, fine-tuned from Qwen/Qwen3-8B.
- Repo tags include decision-model, typed-decisions, tacit, and anyjev.
- Safetensors weights, English language, text-generation pipeline.
- Public and ungated, with zero downloads and zero likes when the metadata was captured.
- Chat template handles Qwen3-style tool calls and an optional thinking block.
Questions about this entry
Short answers drawn from the linked project or page.
A Hugging Face model repository published by workmagicio. It is a LoRA adapter tagged stage2, decision-model, and typed-decisions, listed under the library name anyjev.
Qwen/Qwen3-8B. The repository metadata lists it both as base_model and as base_model:adapter, and the architecture tag is qwen3.
Safetensors. The repository is tagged with the safetensors library, alongside the anyjev library name and the qwen3 architecture tag.
No. The metadata shows private false and gated false, and no inference provider was enabled for it at the time of listing.
English, with the text-generation pipeline tag and a conversational tag. The repository is also tagged region:us.
The chat template includes Qwen3-style tool handling, rendering function signatures inside tools tags and emitting calls inside tool_call tags, plus an optional thinking block controlled by enable_thinking.
Zero downloads and zero likes when the metadata was captured. The repository was created and last modified on 2026-11-01.
Reactions & coverage
Posts, threads, and videos about this entry from around the web.
X: Standard One SH (StandardThinking)
LinkedIn: What multimodal decision models actually change, and what they do not.
LinkedInJevDirectory.org
Hacker News: Decision Index 0.2.1 scores open reproductions of Jev on a frozen suite.
jackbravo4 pointsDecision Index 0.2.1 – 70 open reproductions of TypeSafe Jev's Decision ModelRead the thread on Hacker NewsHacker News: Pointer to a DiffusionGemma plus vLLM tutorial for a Jev-shaped classifier.
1 pointHow to build a Jev-style classifier with DiffusionGemma and vLLMRead the thread on Hacker NewsMore Jev resources like this
LoRA fine-tune of Qwen/Qwen3-8B published by workmagicio and tagged as a Jev decision model for typed decisions. Distributed in safetensors under the anyjev library name, with an English conversational text-generation pipeline.
Jev Models & Reimplementations#open-models#lora#qwen3
Community
A LoRA plus 24-slot decision head over Qwen3.8-27B from Ming Xu's train-jev project: it serves TypeSafe's System One API with 0.851 Kev transfer-v4 accuracy and ECE 0.053, and needs an 80 GB GPU.
Jev Models & Reimplementations#community#open-models#local
Community
A 24 GB-GPU alternative from the train-jev project: Qwen3.5-4B plus a rank-16 LoRA and 24-slot decision head scoring 0.647 PK accuracy, 40.4 Decision Index and 43 ms p50 latency, ahead of Kev-4B at the same size.
Jev Models & Reimplementations#community#open-models#local
Community
A LoRA fine-tune of Strands Decider 2B that rates jokes on seven comedy traits, answering each as a typed yes/no question with a probability; an unofficial fan project that cannot write jokes and is not endorsed by Conan O'Brien.
Jev Models & Reimplementations#community#open-models#humor
Community
Torchcast AI's 4B text decision model on Qwen3.5-4B returns yes/no probabilities, choice distributions and ordinal score distributions through a TypeSafe-compatible API, reading option letters in one forward pass under CC BY-NC 4.0.
Jev Models & Reimplementations#community#open-models#typed-decisions
Community
StartLux's 9B Instant decision model as GGUF for llama.cpp: Q8_0 (9.53 GB) measures DecisionPivot 53.2 against 50.6 for Q4_K_M and 53.2 for BF16 on vLLM, returning one-forward-pass typed-question probabilities.
Jev Models & Reimplementations#community#open-models#quantized
Community
From the Jev guides
Original write-ups on what this entry is for.
From the Jev AI model community
Posts from builders shipping with Jev right now.