Text Classification Models

A family of six models that detect lashon hara in text shown on screen. Each model lives in its own folder with its own README. All six give the same kind of answer: lashonhara or notlashonhara, in English and Hebrew, for messages from short chats to long emails. They tell real lashon hara apart from look-alikes that are permitted, such as direct constructive criticism, warnings that protect someone from harm (to'eles), honest references, and discussion of the laws themselves. A screening aid, not a halachic ruling. A rav should decide real questions. pc, mobile-legacy, server and server-small are Apache 2.0. mobile-flash and mobile-lite are under the LFM Open License v1.0 (see the LICENSE…

Model · Text classification

laya

Convai Innovations

Multilingual, non-autoregressive System 1 decision model. Give it a state (text, email, ticket, or JSON) and typed questions; it returns typed answers with mathematically calibrated probabilities in a single forward pass (~33 ms) across 100+ languages. Trained with reinforcement learning against strictly proper scoring rules (RLCD), so reporting honest probabilities is the only way to maximise reward. It never generates text, so there is nothing to parse and nothing to hallucinate. This repo holds all three checkpoints and is the hub for the family. The English checkpoint is at the repo root; the other two are bundled subfolders, and only the one you request is downloaded: pip install -U…

The Laya System One decision model, exported to ONNX fp32 and packaged for Verdict -- a high-performance serving engine for System One decision models. Serve it with one command: Pick the image that matches the host. The -v mounts cache the model, so only the first run downloads it. Add -e VERDICTUSEMODELSCOPE=1 and use sgyaqing/laya to fetch from ModelScope instead of the hub; add -e HFENDPOINT=https://hf-mirror.com if the hub is slow or unreachable. Endpoints: the standard decision protocols POST /v1/systemone and POST /v1/decisions, native POST /v1/choice | /v1/score | /v1/noul, plus an OpenAI-compatible layer (/v1/chat/completions, /v1/models). Measured on one machine (RTX 4090, AMD…

Laya typed decisions on Apple Silicon, running on the Core AI runtime — the successor to Core ML. This is a.aimodel asset exported from via Apple's coreai-torch bridge. It outputs choice / score / noul probabilities (and RL action logits) with zero generated tokens and no PyTorch, Core ML, Transformers, or cloud API at inference time. macOS 27+ (Core AI runtime), Python 3.10+. Validated on M3 Max / macOS 27.2. Validate the download end-to-end (all three specializations, timing, contract checks): Snake demo with the model (terminal game, reuses the laya-coreml UI + safety shield; automatically uses the B3 asset when present for ~2x game throughput): ~3× faster per pass than the fastest Core…

Laya typed decisions on Apple Silicon, using CPU + GPU. This is a portable Core ML bundle for laya-coreml, converted from convaiinnovations/laya. It outputs choice, score, and noul probabilities with zero generated tokens. Inference needs no PyTorch, Transformers, MLX, remote code, or cloud API. Apple Silicon, macOS 15+, Python 3.11–3.13. Tested on M3 Max / macOS 27.2. To download explicitly and then run entirely offline: Use laya.load("aac6fef/laya-coreml", localfilesonly=True) for a cached snapshot or pass a local directory. Use revision=" " to pin a remote revision. This FP16 export retains the original model architecture and decision schema. The enumerated-length GPU export is the…

Two ONNX exports of Laya-multilingual (322M parameters, built on mmBERT) used by Laya-Heart, a texting copilot for couples that runs on your own computer. Laya reads the partner's message and answers short card questions with probabilities ("Does 没事 really mean it's fine?", a danger level from 1 to 10, a hidden safety question). Both run with onnxruntime and Laya's laya-ts runtime, exactly as the app runs them. Practice exam written and labelled by teacher B (Qwen3-32B-AWQ, a different model family from the teacher that wrote the training chats). One command in the repository recomputes every number from the raw answers, or re-runs both models: npm run reproduce / npm run reproduce…

Model · Text classification

laya-kvp10k-noul

Sothiara Em

A fine-tuned Laya model (Convai Innovations, 421M, ModernBERT-large backbone) that answers one typed noul question: does a value correctly match its key label? (e.g. firstname = John → true, firstname = 1992 → false). Fine-tuned on the IBM KVP-10K dataset via the pre-parsed community mirror (OCR pre-extracted; no OCR step needed). This is the v2 (remediated) release: document-level 80/10/10 data partitioning, mixed-class frozen test set, calib-split temperature fitting, and a frozen category-stratified release gate. It supersedes the v1 release pre-remediation, historical artifact). Laya is a non-autoregressive decision model: you give it a state (text/dict) plus typed questions (choice…

Model · Text classification

laya-multilingual

Convai Innovations

Non-autoregressive System 1 decision model covering 100+ languages. Give it a state (text, email, ticket, or JSON) and typed questions; it returns typed answers with probabilities in a single forward pass. No text generation, so nothing to parse and nothing to hallucinate. Part of the Laya family — use this checkpoint for anything that is not English. Since laya 0.3.13 the default Router() keeps both english and this checkpoint resident, so a mixed workload no longer swaps checkpoints on every language change. For a server, load them up front so even the first request of each language is just a forward pass: router.attach("multilingual", agent) registers an Agent you already built, so a…

Non-autoregressive System 1 decision model covering 100+ languages. Give it a state (text, email, ticket, or JSON) and typed questions; it returns typed answers with probabilities in a single forward pass. No text generation, so nothing to parse and nothing to hallucinate. Part of the Laya family — use this checkpoint for anything that is not English. The default Router() keeps both english and this checkpoint resident, so a mixed workload no longer swaps checkpoints on every language change. For a server, load them up front so even the first request of each language is just a forward pass: router.attach("multilingual", agent) registers an Agent you already built, so a process that loaded…

The Laya Multilingual System One decision model (mmBERT-base, 100+ languages), exported to ONNX fp32 and packaged for Verdict -- a high-performance serving engine for System One decision models. Serve it with one command: Pick the image that matches the host. The -v mounts cache the model, so only the first run downloads it. Add -e VERDICTUSEMODELSCOPE=1 and use sgyaqing/laya-multilingual to fetch from ModelScope instead of the hub; add -e HFENDPOINT=https://hf-mirror.com if the hub is slow or unreachable. For English-only workloads, use verdict-models/laya. Endpoints: the standard decision protocols POST /v1/systemone and POST /v1/decisions, native POST /v1/choice | /v1/score | /v1/noul…

Laya typed decisions on Apple Silicon, using CPU + GPU. This is a portable Core ML bundle for laya-coreml, converted from convaiinnovations/laya-multilingual. It outputs choice, score, and noul probabilities with zero generated tokens. Inference needs no PyTorch, Transformers, MLX, remote code, or cloud API. Apple Silicon, macOS 15+, Python 3.11–3.13. Tested on M3 Max / macOS 27.2. To download explicitly and then run entirely offline: Use laya.load("aac6fef/laya-multilingual-coreml", localfilesonly=True) for a cached snapshot or pass a local directory. Use revision=" " to pin a remote revision. This FP16 export retains the original model architecture and decision schema. The…

Laya typed decisions on Apple Silicon, using CPU + Neural Engine. This is a portable Core ML bundle for laya-coreml, converted from convaiinnovations/laya-multilingual. It outputs choice, score, and noul probabilities with zero generated tokens. Inference needs no PyTorch, Transformers, MLX, remote code, or cloud API. Apple Silicon, macOS 15+, Python 3.11–3.13. Tested on M3 Max / macOS 27.2. To download explicitly and then run entirely offline: Use laya.load("aac6fef/laya-multilingual-coreml-ane", localfilesonly=True) for a cached snapshot or pass a local directory. Use revision=" " to pin a remote revision. This FP16 conversion retains the original trained parameters. The ANE graph's host…

Laya typed decisions on Apple Silicon, using CPU + Neural Engine. This is a portable Core ML bundle for laya-coreml, converted from convaiinnovations/laya-multilingual. It outputs choice, score, and noul probabilities with zero generated tokens. Inference needs no PyTorch, Transformers, MLX, remote code, or cloud API. Apple Silicon, macOS 15+, Python 3.11–3.13. Tested on M3 Max / macOS 27.2. To download explicitly and then run entirely offline: Use laya.load("aac6fef/laya-multilingual-coreml-ane-w8", localfilesonly=True) for a cached snapshot or pass a local directory. Use revision=" " to pin a remote revision. This is a separately identified 8-bit grouped K-means weight-palette variant.…

Laya typed decisions on Apple Silicon, using CPU + GPU. This is a portable Core ML bundle for laya-coreml, converted from convaiinnovations/laya-multilingual. It outputs choice, score, and noul probabilities with zero generated tokens. Inference needs no PyTorch, Transformers, MLX, remote code, or cloud API. Apple Silicon, macOS 15+, Python 3.11–3.13. Tested on M3 Max / macOS 27.2. To download explicitly and then run entirely offline: Use laya.load("aac6fef/laya-multilingual-coreml-snake", localfilesonly=True) for a cached snapshot or pass a local directory. Use revision=" " to pin a remote revision. This FP16 export retains the original model architecture and decision schema. The…

Model · Text classification

laya-nextflow-nfcore

PrimeOmicX LLC

Laya v3 is an ultra-fast, local System-1 Decision Engine fine-tuned on top of ModernBERT-Large for Nextflow DSL2 and the nf-core bioinformatics ecosystem. It is designed to make zero-latency, high-accuracy architectural decisions in autonomous pipeline compilers (such as Codaris), resolving complex setup questions without burning LLM tokens. Evaluated across 40 realistic Nextflow architecture tasks

Model · Text classification

laya-onnx

weXare

An unofficial ONNX export of convaiinnovations/laya, the open-source "System One" decision model by Convai Innovations, made to run client-side with ONNX Runtime Web on WebGPU or WebAssembly. Laya takes a state and typed questions and scores every option in one forward pass. It returns calibrated probabilities, not generated text. This is the default model of @wexare/laya-web (source), which loads it automatically: sha256 of layafp16.onnx: b2125c7a1044e78807ee718ff4e65c9892b6b55aeeeee64f31fffffd76871b0a Batch, sequence and option count are all dynamic. Masked option slots return -1e4. Turning logits into answers (per-option-count temperature, softmax, confidence) follows the reference laya…

Model · Text classification

laya-pdpa-onnx-v4-32k

MY

ONNX export of Suarify/laya-pdpa-my-v4 — a Malaysian PDPA classifier for call transcripts. Ten typed questions per call: eight yes/no classes, one ordered severity, one choice for who disclosed. Exported with torch.onnx.export(dynamo=True), opset 17, external data. Accuracy is over all 960 held-out decisions (96 rows × 10 questions), by argmax, against a majority-class baseline of 72.8%. Parity of the fp32 export against the PyTorch checkpoint is 1.07e-05 max absolute logit difference across batches 1, 3, 8 and 16. fp32 and q4f16 both score 825/960. That identical total is a coincidence of to 10.15 absolute logit difference, and the flips happen to break 23 each way. The disagreements are…

Model · Text classification

laya-pt-es-typed

Telepatia

This checkpoint fine-tunes convaiinnovations/laya-multilingual for native choice, score, and noul decisions in Portuguese and Spanish. It keeps the original 322M-parameter mmBERT architecture. It adds no inference component and does not generate text. It returns typed answers and probabilities in one forward pass. This is a text model. Inference takes a textual state plus typed questions. The second training stage used text decisions derived from public speech corpora, but this checkpoint does not accept audio by itself. The separate audio projector is not included. The official Laya SDK defines these primitives as follows: - choice: selects one key from a runtime-defined criteria object.…

Classifies GitHub issues written in any language as bug, feature, question or docs. A fine-tune of Laya multilingual (mmBERT-base) used by the laya-triage GitHub Action for non-English issues, next to the English model laya-triage-en. The same 500 NLBSE'23 validation issues, machine-translated with NLLB-200 into 13 languages. Accuracy (±3 points per language): laya-triage and Jev are within noise of each other across languages; both are far ahead of the untuned base. Translations can flatter a model trained on translations, so we also checked real issues: on 367 non-English issues opened in 2026 (never seen, written by people, not translated) accuracy went from 47.1% to 65.7%. Use it…

Model · Text classification

laya-typed-decisions

Convai Innovations

Non-autoregressive System 1 decision model, fine-tuned on the typed-decisions workflows: agent-trace observability, customer service, invoice processing and security incidents. Part of the Laya family. 400 test cases, 2,000 decisions, measured on the official test split. +3.9 points over Jev's published 0.727, above the 0.735 teacher ceiling, with 2.4x better Brier and 1.6x better score MAE. Jev figures are third-party published, not measured here — there is no TypeSafe API access in this project, and sample sizes and prompts differ. Treat the comparison as indicative. Router will not select this checkpoint automatically unless you construct it with autotaskdetection=True — it is…

Laya typed decisions on Apple Silicon, using CPU + GPU. This is a portable Core ML bundle for laya-coreml, converted from convaiinnovations/laya-typed-decisions. It outputs choice, score, and noul probabilities with zero generated tokens. Inference needs no PyTorch, Transformers, MLX, remote code, or cloud API. Apple Silicon, macOS 15+, Python 3.11–3.13. Tested on M3 Max / macOS 27.2. To download explicitly and then run entirely offline: Use laya.load("aac6fef/laya-typed-decisions-coreml", localfilesonly=True) for a cached snapshot or pass a local directory. Use revision=" " to pin a remote revision. This FP16 export retains the original model architecture and decision schema. The…

This repository provides a ONNX converted and quantized version of meta-llama/Llama-Prompt-Guard-2-22M - Meta LLaMA – Foundation model powering the classifier - Hugging Face Transformers – Model and tokenizer loading - ONNX – Model export and runtime format - ONNX Runtime – Efficient inference backend We use jackhhao/jailbreak-classification for the evaluation (train+test) You can find the full source code, CLI tools, and evaluation scripts in the official GitHub repository.

A LoRA adapter for Qwen/Qwen3.5-4B that makes typed decisions about a document in one forward pass and returns calibrated probabilities over the options: a System-1 decision engine, fast judgment rather than generated reasoning. Served with the code at github.com/tuantong/loupe-serving, which reads the answer from the next-token probabilities of the option labels; nothing is generated. An exact average (model soup) of LoRA adapters on the attention, linear-attention and MLP projections of all 32 layers (three seeds of one recipe, a continuation of that recipe on written rationales, and a run whose targets include a second teacher), stored as one rank-96 adapter. Merge it into the base…

This is the model card of a transformers model that has been pushed on the Hub. Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. Use the code below to get started with the model. Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).

Model klasifikasi teks klinis multi-task berbasis Medical-IndoBERT (Domain-Adaptive Pretrained) yang disempurnakan melalui Supervised Fine-Tuning (SFT) dengan arsitektur Dual-Head: 1. Head 1 (ICD-10): Klasifikasi Diagnosis Klinis Primer (WHO ICD-10). 2. Head 2 (INA-CBGs): Prediksi Kelompok Tarif Casemix Klaim (Kemenkes RI / UNU-IIGH Casemix). Senior atau peneliti dapat langsung menguji model ini menggunakan kode berikut: Dataset dan bobot dikembangkan sesuai regulasi perlindungan data medis UU PDP No. 27/2022. Rekam Medis (Nomor Rekam Medis, No. SEP, Nama Pasien) telah dideidentifikasi dan disimpan di repositori privat terpisah.

A calibrated typed-decision model: give it a state (text, ticket, policy, JSON) and a typed question — choice, boolean, or rubric score — and it returns a probability for every option in a single forward pass (~24 ms). No generation, no parsing, nothing to hallucinate. 12 of 13 subsets exceed Bespoke Nimble-9B — a model 2.2× its size — same prompt format, same scoring protocol. The primary suite: BoolQ, MultiNLI, PAWS, PubMedQA, SQuAD-2, VitaminC, Civil Comments, Aegis 2.0, MASSIVE (en/de), HelpSteer-2, SummEval (consistency / relevance). Every item human-labeled; byte-reproducible (manifest-locked ids + sha256); same protocol as the Bespoke Nimble evaluation. Wins: verification-style noul…

Model · Text classification

MiniCPM5-2B-pjev-LoRA

Adrian Ciprian Iancu

A one-token decision model you can switch on per request, on the MiniCPM5-2B server you already run. Kailune-AI/pjev-2b is a strong typed-decision model: give it a state, a question and lettered options, and it returns a calibrated probability for every option in a single forward pass. It ships as a full merged model (about 2.7 GB in Q80). If your agent already serves openbmb/MiniCPM5-2B for chat, a second full model costs VRAM you probably do not have. This repository re-expresses pjev-2b as a rank-64 LoRA over the stock MiniCPM5-2B weights. Load it once next to the chat model, turn it on only for decision requests, and pay about 200 MB of VRAM instead of 2.7 GB. Measured on a private…

This is the model card of a transformers model that has been pushed on the Hub. Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. Use the code below to get started with the model. Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).

Model · Text classification

Neo

TokenAI

TokenAI is a non-profit startup founded in 2025 by Assem Sabry, based in Alexandria, Egypt. The Neo model, source code, training data, documentation, and related materials are owned by TokenAI. Neo is a compact TokenAI System One decision model for selecting actions from a declared candidate set. It reads English application context and a typed decision schema, then returns calibrated outputs for choice, score, and noul in one encoder forward pass. It is not a conversational or free-form text-generation model. Training dataset: tokenaii/Neo-dataset — https://huggingface.co/datasets/tokenaii/Neo-dataset It contains the complete project source code, training code, synthetic-data generation…

Model · Text classification

noah-decide-v06-research

Beinex.ai

Noah-Decide is a 0.6B-parameter decision model from Beinex AI. You give it a situation (the state), a question and a set of options. It returns a calibrated probability for each option. In certified mode, the model returns the set of options it cannot rule out. When that set is not exactly one option, it escalates to a human. Licence: CC BY-NC 4.0. It is free for research and other non-commercial use; commercial use needs a licence from Beinex. The base model, Qwen3-0.6B, is Apache-2.0. - Base model. Qwen3-0.6B, fully fine-tuned and then blended back towards the base weights (60% fine-tuned, 40% base). The blend ratio was chosen on held-out decision types. - Option order does not matter.…

OD-1 is an open System One decision model: give it a state (text or JSON) and typed questions (choice, noul = yes/no, score = ordinal) and it returns every answer from one forward pass, with full probability distributions including an explicit NOTANSWERABLE outcome. The request/response shape follows the Jev / TypeSafe /v1/systemone wire format. Backbone: Qwen/Qwen3.5-0.8B (Apache-2.0) with typed answer heads read at marker tokens, early-exit heads (layers 6/12/18), and a CLM-style contrastive shortlist head for questions with more than 24 options. Trained with SFT + distillation from Qwen3.5-27B-FP8 (never a compared system), RLCD-style proper-score calibration, an abstention utility…

OD-1 is an open System One decision model: give it a state (text or JSON) and typed questions (choice, noul = yes/no, score = ordinal) and it returns every answer from one forward pass, with full probability distributions including an explicit NOTANSWERABLE outcome. The request/response shape follows the Jev / TypeSafe /v1/systemone wire format. Backbone: Qwen/Qwen3.5-0.8B (Apache-2.0) with typed answer heads read at marker tokens, early-exit heads (layers 6/12/18), and a CLM-style contrastive shortlist head for questions with more than 24 options. Trained with SFT + distillation from Qwen3.5-27B-FP8 (never a compared system), RLCD-style proper-score calibration, an abstention utility…

OD-1 is an open System One decision model: give it a state (text or JSON) and typed questions (choice, noul = yes/no, score = ordinal) and it returns every answer from one forward pass, with full probability distributions including an explicit NOTANSWERABLE outcome. The request/response shape follows the Jev / TypeSafe /v1/systemone wire format. Backbone: Qwen/Qwen3.5-0.8B (Apache-2.0) with typed answer heads read at marker tokens, early-exit heads (layers 6/12/18), and a CLM-style contrastive shortlist head for questions with more than 24 options. Trained with SFT + distillation from Qwen3.5-27B-FP8 (never a compared system), RLCD-style proper-score calibration, an abstention utility…

Model · Text classification

opendecision-agent

Luiz Eduardo

A small, auditable classifier that predicts what an assistant should do next in a task-oriented conversation. Given the current state, it returns one action from a fixed vocabulary with a probability for each, so an agent can act alone when it is confident and hand the decision to a person when it is not. It ships with a decision policy (config.toml) that blocks impossible actions and sets a minimum confidence per action. Direct use. Decide the next step of a conversational agent (ask, search, present options, confirm, execute, end the conversation), route uncertain decisions to human review, and log decisions with feedback to collect training data. Out of scope. Executing irreversible…

Model · Text classification

opendecision-flights

Luiz Eduardo

A small, auditable classifier that predicts the next step of an agent that helps find flight tickets. Given the current state, it returns one action from a fixed vocabulary with a probability for each, so an agent can act alone when it is confident and hand the decision to a person when it is not. It ships with a decision policy (config.toml) that blocks impossible actions and sets a minimum confidence per action. Direct use. Decide the next step of a conversational agent (ask, search, present options, confirm, execute, end the conversation), route uncertain decisions to human review, and log decisions with feedback to collect training data. Out of scope. Executing irreversible actions…

Model · Text classification

openjev-v5-0.8b

Rodney Lafuente-Mercado

This is an unchanged mirror of AlexWortega's pretrained OpenJev v5 0.8B model, published so adapters can identify and load this specific base without confusing it with the 2B and 4B models in the upstream repository. All model, tokenizer, and configuration files are byte-for-byte copies. I did not train this base model. The source is AlexWortega/openjev, qwen3.5-0.8b-nli-v5, pinned to revision 552759daad712f1af6c4c13dabcb1e047886fc9c. OpenJev turns the Qwen3.5-0.8B backbone into a three-class natural language inference classifier. Credit for the base model and its training belongs to AlexWortega and the Qwen team. See the upstream model card for the method and reported evaluations. The…

OpenJevX is an open-weight, non-autoregressive System One decision model specialized from Laya, which uses answerdotai/ModernBERT-large plus a dynamic typed-decision head. It accepts runtime-defined choice, score, and noul questions and returns calibrated probabilities in one forward pass. It is compatible with the TypeSafe Jev /v1/systemone request shape through the OpenJevX server. - CUDA p50 latency per five-question case: 22.8 ms The benchmark uses the untouched 400-case, 2,000-decision test split from LocalLLaMA/typed-decisions. Training uses only its 1,200-case train split. OpenJevX is a derivative of Laya by ConvAI Innovations and ModernBERT by Answer.AI and LightOn. Laya and…

Model · Text classification

OpenThai-SystemOne-Ollama

iApp Technology

OpenThai-SystemOne is an open Thai + English System One decision model (0.8B, Apache-2.0). It does not generate text: given a state (text or JSON) and typed questions it returns probabilities: choice between named options, noul (yes/no) and score on an ordered scale. This repo is its Ollama build for Ollama's System One API (POST /v1/systemone, Ollama ≥ 0.35), the same API Ollama serves Nimble and Tev1 with. Everything runs on your machine; no API key. The curl example below uses the hf.co name; with the ollama.com pull, use "model": "iapp/openthai-systemone". (Probabilities rounded. The whole request is part of every question's prompt, so the same question can score slightly differently…

Model · Text classification

parallax-2-preview

Parallax Labs

Parallax 2 Preview is the first public look at Parallax Labs' upcoming Parallax-2 model. It's a 4B finetune of Qwen 3.5, trained specifically to reason through problems carefully, like a frontier model would. Parallax-2-preview is a 4B parameter finetune designed to demonstrate structured reasoning at small scale. It uses the reasoning style of frontier models, while remaining fast enough to run on consumer hardware. Parallax 2 Preview is intended for reasoning-heavy tasks where a short, direct answer isn't the goal. Suitable for further finetuning into reasoning-focused applications, education tools, or as a component in multi-model pipelines where structured reasoning is the required…

Model · Text classification

phishing-scam-detector-base-ONNX

ONNX Community

This is an ONNX version of Horizon-Labs/phishing-scam-detector-base. It was automatically converted and uploaded using this Hugging Face Space. See the pipeline documentation for text-classification: https://huggingface.co/docs/transformers.js/api/pipelines#modulepipelines.TextClassificationPipeline Flags phishing, scams and spam in emails, SMS, chat and social-media messages in many languages. Three labels: - fraud: phishing (fake bank, delivery, account or tax messages with links), scams (prizes, investment and crypto schemes, fake jobs, "hi mum, new number", romance, advance fee), requests for passwords, one-time codes or payment details, malware lures; - spam: unwanted advertising and…

Model · Text classification

phishing_spam_jev_like_classifier

Ayush

A fine-tuned DistilBERT sequence classifier for binary email triage: legitimate and spam. It is a prototype trained and evaluated on a historical SpamAssassin corpus. It is not a phishing or malware detector and should not be treated as a complete email security system. Use as an experimental text-only aid to sort historical or otherwise appropriately reviewed email into ham/spam queues. Route uncertain, empty, or unsupported inputs to human review. Do not use the output as the sole basis for blocking senders, taking account actions, or making other consequential decisions. This model does not authenticate senders, inspect attachments, resolve or visit links, verify SPF/DKIM/DMARC, or…

Model · Text classification

Phocinae-Largha-150M-v1

Phocinae

Tiny model. Big decisions. — 小海豹，大决断。· 一斑见全豹，一点定全局。 斑海豹 Largha, the spotted seal: a 144.3M bilingual decision model (150M-class) for structured decisions — one forward pass per decision, on your own hardware. Not a chat model: it takes a state plus a list of typed questions (noul yes/no · choice pick-one · score 2–10) and returns calibrated answers with confidence, robust to option reordering. The official runtime is phocinae-server: a local FastAPI service (127.0.0.1 only) that loads these weights with a pure PyTorch forward (no extra runtime needed). Full spec: docs/protocol.md. answers values: noul = bool · choice = 0-based option index · score = integer 2–10. Errors: 422 (unknown…

Model · Text classification

pplx-decider-v1-27b-EXL3

ramGPT

EXL3 4.00 bpw conversion of perplexity-ai/pplx-decider-v1-27b. pplx-decider-v1-27b does not use the normal LM-head token-generation path for its final answer. It produces a hidden state and applies the model's custom readout.safetensors decision head to obtain option probabilities. The repository therefore includes pplxdeciderexl3.py, which registers the model architecture and performs the custom decision readout. This model is not recommended for standard TabbyAPI usage. A local smoke test with TabbyAPI and ExLlamaV3 1.5.2 failed during startup with: More importantly, simply registering the architecture is not sufficient for normal /v1/chat/completions behavior: TabbyAPI's standard…

Creator, Sole Author & Lead Architect: Alan Canto Architecture: ModernBERT-large (System 1 Non-Autoregressive Decision Engine) Hardware Runtime: Trained, fine-tuned, and certified locally on NVIDIA GeForce RTX 3050 Attribution: Conceived, engineered, and published by Alan Canto. All rights reserved. ProKope 421M (named after the classical Stoic concept of disciplined, measured progress and operational mastery) is a high-speed, non-autoregressive System 1 decision model engineered by Alan Canto. Unlike autoregressive language models (which incur significant token latency, JSON parsing errors, and hallucination loops), ProKope 421M processes structured input states in a single forward pass…

A fast, multilingual classifier that flags prompt injection and jailbreak attempts, both in user messages (direct) and in untrusted content an AI agent reads: emails, web pages, documents, RAG chunks, and tool/API outputs (indirect). their clean counterparts, so it looks for instructions aimed at the AI, not for scary words. - Low false-alarm rate on look-alike benign text: 92.9% on NotInject, 99.2% on OR-Bench-hard. half the size and the same decisions as fp32 on our checks), transformers.js. Labels: SAFE (0) and INJECTION (1). This is the same convention as protectai/deberta-v3-base-prompt-injection-v2, so the model is a drop-in replacement in code and tools built for that one. INJECTION…

A compact multilingual detector for prompt injection and jailbreak attempts (large language model guardrails). Given any user prompt, tool output, or document excerpt, it outputs the probability that the text is an attack on the LLM's instructions. Existing public injection detectors are either English-only (e.g. protectai's deberta models) or released under licenses many organizations cannot use (Meta's PromptGuard line). This model is permissively licensed, works in 17 languages, ships with its multilingual training corpus and is evaluated against a public baseline on shared test sets. Recommended threshold: 0.50 — conservative default (EN precision 0.83 on the attack test, safe-prompt…

A fast, multilingual classifier that flags prompt injection and jailbreak attempts, both in user messages (direct) and in untrusted content an AI agent reads: emails, web pages, documents, RAG chunks, and tool/API outputs (indirect). their clean counterparts, so it looks for instructions aimed at the AI, not for scary words. - Low false-alarm rate on look-alike benign text: 89.7% on NotInject, 99.5% on OR-Bench-hard. half the size and the same decisions as fp32 on our checks), transformers.js. Labels: SAFE (0) and INJECTION (1). This is the same convention as protectai/deberta-v3-base-prompt-injection-v2, so the model is a drop-in replacement in code and tools built for that one. INJECTION…

Model · Text classification

Quorum-Reader-Qwen3-4B-Adapter

DataAgent

A LoRA adapter for Qwen/Qwen3-4B — the in-context reader of the Quorum 24-shot intent-classification ensemble. Given 24 retrieved examples in the prompt (no weight update), it scores every candidate label in a single forward pass. Combined (geometric mean) with a frozen BAAI/bge-large-en-v1.5 nearest-neighbour over the same 24 examples, the ensemble reaches 0.932 on Banking77 (full 3,080 test) — above the closed API Jev's 0.924 at Jev's own 24-shot protocol. In our study a further configuration (per-class descriptions + a calibration-selected combination) reached 0.938 and significantly beat Jev on a paired McNemar test LoRA (r = 64) on Qwen/Qwen3-4B, fine-tuned on a mixture of public…

This is an experimental, CPU-only Go classifier for three claims expressed in English or Korean development comments. One fixed semantic-contrast data continuation reduced mean three-head cross-entropy on a newly sealed AI-reference research evaluation from 0.996490 to 0.860646, compared with a fixed float continuation control. The paired difference was −0.135844, with a 95% lineage-bootstrap interval of [−0.154294, −0.117779]. The prespecified research-progress conditions were met. The general stratum got worse: its candidate-minus-control CE difference was +0.023867. Completion hints remain unqualified, and these AI-reference results do not establish human agreement, private-work…

This original CPU-only Go classifier separately estimates response requests, current development work and completion reports. Each head has true/false/unknown classes. It generates no prose and never verifies task completion or authorizes application writes. This version is not operationally qualified. On 240 original AI-reviewed development rows, gated true proposals/correct were KO: response1/1, activity7/7, completion0/0 (undefined precision); EN: response6/6, activity6/6, completion3/4. Pooled completion precision was75%, below the frozen98% research floor. Unknown activity/completion references had only3 families per locale, below the minimum5. Few perfect proposals do not establish…

Model · Text classification

RubriX-8B

CobuildX AI

RubriX is a non-autoregressive rubric judge. Given a criterion, the rubric's level descriptions and a response (optionally with the conversation it answers), it returns a probability for every level in a single pass, with no text generation. Level descriptions are embedded once per rubric and cached, so the cost of each judgment does not grow with the number or length of the levels. Read more in the blog post: Introducing RubriX. One encoder, Qwen3-8B with this repository's LoRA adapter, embeds the input and each level description separately. Two projection heads map them into a shared space, and - sk = τ · cos(f(input), g(levelk)), with τ = 100 - p = softmax(s1 … sK) The model was trained…

Model · Text classification

s1-jev-cvltist

CVLT AI

A local, open, Jev-compatible "System One" decision model. s1-jev-cvltist is the name of this release model (project codename "system one", s1; the internal checkpoint id is s1-v6). Base: Qwen3.5-4B (Apache-2.0) · Adapter: LoRA r=16, α=32 · Context: 4096 Interface: the TypeSafe Jev wire spec (choice / score / noul) · Size: 124 MB adapter system one (s1) is a small decision model trained to answer Jev-style questions (choice, score, noul) over a free-form "state", returning calibrated probabilities rather than a bare answer. It is deliberately built on a general instruction base (Qwen3.5-4B) with a thin LoRA adapter, so it carries knowledge a purpose-built encoder can't, while the readout…

Model · Text classification

s1-jev-cvltist

A. E. E. Collier

A local, open, Jev-compatible "System One" decision model. s1-jev-cvltist is the name of this release model (project codename "system one", s1; the internal checkpoint id is s1-v6). Base: Qwen3.5-4B (Apache-2.0) · Adapter: LoRA r=16, α=32 · Context: 4096 Interface: the TypeSafe Jev wire spec (choice / score / noul) · Size: 124 MB adapter system one (s1) is a small decision model trained to answer Jev-style questions (choice, score, noul) over a free-form "state", returning calibrated probabilities rather than a bare answer. It is deliberately built on a general instruction base (Qwen3.5-4B) with a thin LoRA adapter, so it carries knowledge a purpose-built encoder can't, while the readout…

This is the model card of a transformers model that has been pushed on the Hub. Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. Use the code below to get started with the model. Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).

This is the model card of a transformers model that has been pushed on the Hub. Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. Use the code below to get started with the model. Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).

SCM ("Sovereign Classification Model", repository rev) makes typed, non-generative decisions in one forward pass: choice (pick one of K), noul (yes/no) and score (ordinal level) questions about a state. This repo holds a LoRA adapter only (adaptermodel.safetensors) for Qwen/Qwen3-14B-Base at revision 0b0bd3732e2c374d483664439ea334928b65f304. It is an experimental research release, not a production model. All options of one question are shown in one prompt as lettered lines; the model's score for an option is the next-token logit of its letter. Several option orders are scored and their per-order log-softmax over the letters is averaged, then renormalised to a probability vector. The exact…

SCM ("Sovereign Classification Model") makes typed decisions in one forward pass: choice (pick one of K), noul (yes/no) and score (ordinal level) questions about a text. This repo holds a LoRA adapter only for Qwen/Qwen3-14B-Base at revision 0b0bd3732e2c374d483664439ea334928b65f304 (training run s88-v1max-H100x2-20261015-113714; lr 5e-5 (bf16, 2 GPUs data-parallel), LoRA r=16 / alpha=32 on all attention and MLP projections, 16 questions per step, one epoch, prompts left-truncated at 3,072 tokens). It is not a production model. All options of one question appear in one prompt as labelled lines; the score of an option is the next-token logit of its label. Labels are A to T, then U to Z, then…