Jev directory
CommunityJev Models & Reimplementations
Jev History Corpus
Hugging Face dataset of synthetic conversational question-and-answer pairs about Jev internals, covering pointer-head scoring, replay-source counts, slot-selection ladders, and model lineage. English text, 10K-100K rows, Apache-2.0, tagged for fine-tuning and knowledge injection.
- Reading time
- 2 min
- Published by
- Community
- Added
- Nov 2026
Highlights
- Hosted on Hugging Face as juiceb0xc0de/jev-history-corpus under an Apache-2.0 license.
- English text dataset sized between 10K and 100K rows.
- Listed tasks are question answering and text generation.
- Rows are conversational user/assistant pairs about Jev internals.
- Tagged synthetic, fine-tuning, knowledge-injection, canary, training-diagnostics, and post-cutoff.
Questions about this entry
Short answers drawn from the linked project or page.
It is published on Hugging Face under the namespace juiceb0xc0de, at the dataset path juiceb0xc0de/jev-history-corpus. The page provides a dataset card, file listing, and data studio view alongside the community tab.
The dataset card lists the license as apache-2.0. That is the only licensing information given in the provided material; check the card itself for any additional terms before redistributing the rows.
The card reports a size band of 10K to 100K rows. The exact row count is not stated in the provided material, so treat the band as the sizing figure when planning a fine-tuning or knowledge-injection run.
The dataset is text-only and its listed language is English. Modalities are given as Text, with no audio, image, or video components described on the card.
Rows are conversational user/assistant pairs about Jev internals. Examples in the digest cover pointer-head option scoring, replay-source counts across versions, the slot-selection ladder for causal and non-causal models, model lineage, and the autoresearch loop.
The card lists Question Answering and Text Generation as the tasks. The rows are formatted as conversational message lists with user and assistant roles, which suits supervised fine-tuning and knowledge-injection style training.
The card tags it synthetic, fine-tuning, knowledge-injection, canary, training-diagnostics, and post-cutoff. These tags describe how the corpus is intended to be used rather than any runtime or serving capability.
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
Apache-2.0 Hugging Face repository for RSI-JEV-27b, a 27B multimodal decision model based on Qwen3.8-27B that answers supplied multiple-choice questions over images, returning a selected option and probabilities for all options in one forward pass.
Jev Models & Reimplementations#open-models#benchmark#calibration
Community
Open-weight vision-language judge that takes a task instruction plus 10 frames of a robot manipulation attempt and predicts success or failure with calibrated probabilities in a single forward pass. Released with inference code and a 20,628-prediction evaluation set.
Jev Models & ReimplementationsArticle#arxiv#open-models#evaluation
Community
Hugging Face dataset of Qwen3.6-35B-A3B-FP8 state/action embeddings for contrastive post-training on the Jev Decision Index's entailment and verification train splits: ANLI, ContractNLI, NLI4CT, HoVer and RAGTruth.
Jev Models & Reimplementations#open-models#calibration#research
Community
PostHog's reasoning Jev-style classifier with a diffusion drafter, reporting higher accuracy than Kev-9B and hosted Jev on held-out and JevBench tiers.
Jev Models & Reimplementations#community#evaluation#open-models
Community
PostHog/jeevesPython
PostHog/jeevesPythonHugging Face dataset of Jev-shaped retrieval and classification decisions built from MM-BRIGHT, holding Qwen3.6-35B-A3B-FP8 state, action, and hard-negative embeddings for post-training CLM heads.
Jev Models & Reimplementations#open-models#benchmark#evaluation
Community
Hugging Face dataset that renders HoVer claim-verification items as Jev Decision Index retrieval and classification requests, with Qwen3.6-35B-A3B-FP8 state, action, and hard-negative embeddings for post-training CLM heads.
Jev Models & Reimplementations#classification#benchmark#open-models
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.