Jev directory
CommunityJev Models & Reimplementations
Eikos-27B
caiovicentino's 27B decision model applies a stated policy to the facts and returns calibrated probabilities for trading-rule cases: order limits, margin, wash sales, KYC and AML, in English and Portuguese with a 4B browser demo.
- Reading time
- 2 min
- Published by
- Community
- Author
- caiovicentino1
- Last verified
- Oct 2026
Used inJev for Finance & Fintech
- Platforms
- Browser
- Capabilities
- Open sourceRuns locally
Highlights
- Applies a stated policy to the facts and returns calibrated probabilities, per the model card's description.
- Documented decision areas include order limits, margin, wash sales, KYC and AML.
- English and Portuguese are named, alongside a 4B browser demo.
- The 27B checkpoint is published on Hugging Face under caiovicentino1.
Watch out
The model card text was largely unreadable on 2026-10-15: the fetched page content was a chat-template dump, so this entry is grounded on the card's title and meta description only. No benchmarks, pricing, hardware requirements or licence terms could be verified from the digest.
Questions about this entry
Short answers drawn from the linked project or page.
A 27B decision model from caiovicentino that applies a stated policy to the facts and returns calibrated probabilities, aimed at trading-rule cases such as order limits, margin, wash sales, KYC and AML.
The card's summary lists order limits, margin, wash sales, KYC and AML. It returns probabilities rather than free text, so an application can act or escalate on a threshold.
The summary names English and Portuguese. No other language coverage is documented in the digest, and the fetched page text contained no language table.
Yes, the card mentions a 4B browser demo alongside the 27B model. The digest did not include details of that demo because the fetched page text was a chat-template dump.
The digest does not state pricing, hardware requirements or licence terms for this checkpoint. Those details were not readable in the fetched page text, so check the model card directly.
The meta description says the probabilities are calibrated, but the digest contains no evaluation tables or calibration error figures, so validate the model's probabilities on your own cases before gating decisions on them.
The model card is published by caiovicentino1 on Hugging Face, described as caiovicentino's model. The digest gives no company, licence or repository details beyond that.
Reactions & coverage
Posts, threads, and videos about this entry from around the web.
X: Both Jev 1.13 and 1.14 score 29 of 30 on 30 Turkish buyer and seller messages
More Jev resources like this
HAL-X AI's 322M non-autoregressive decision model returns calibrated answers in one forward pass of about 10 ms, with native number, excerpt and citation outputs beyond Jev's choice, noul and score types. Apache-2.0, post-trained in 18 languages.
Jev Models & Reimplementations#community#catalog-import#madewithjev
Community
An Apache-2.0 0.8B decision model that returns calibrated probabilities for yes/no, choice and score questions on CPU. Distributed as GGUF for llama.cpp and served behind a Jev-style /v1/systemone API, so existing Jev clients mostly need only a new base URL.
Jev Models & Reimplementations#community#gguf#local-inference
Community
kouhxp/gutsyHTML
kouhxp/gutsyHTMLOpen, CPU-sized Jev-style decision model: give it a situation, a question and options, and Decima returns calibrated probabilities in roughly 20-50 ms per decision as int8 ONNX, with no GPU, no API key and nothing leaving the machine.
Jev Models & Reimplementations#community#catalog-import#cobanov
Community
amyrmahdy/decimaPython
amyrmahdy/decimaPythonGestalt Labs' Jeff is a LoRA adapter on Qwen3-4B-Instruct-2507 that answers Jev-style choice, noul and score questions with labels and probabilities instead of prose, runs locally, and ships a train-your-own guide; on 9,730 fact-checking examples it trails Jev 1.13.0 on accuracy (0.8183 vs 0.8283).
Jev Models & Reimplementations#community#catalog-import#madewithjev
Community
Mapika's open decision model is a 1.9B Qwen3.5-2B fine-tune that returns a probability for every option of every typed question in one forward pass, with no generated text. v11 adds a rank-64 LoRA stage and reports 0.577 on the JevBench public hard tier, up from v10's 0.459.
Jev Models & Reimplementations#community#catalog-import#madewithjev
Community
A CPU port of SemIf with a web UI: JEV-CPU loads Qwen3-0.6B in float32 and reads a decision from its option logits in about a second, across eight domains from support to incident severity, with no GPU.
Jev Models & Reimplementations#community#catalog-import#madewithjev
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.