Text Classification Models

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/Qwen3-4B-Base at revision 906504ac4b72e133a613011318afd8206fb5e8ec. 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/Qwen3-4B-Base at revision 906bfd4b4dc7f14ee4320094d8b41684abff8539 (training run s88-v1mid-H100-20261015-113727; lr 1e-4 (fp16, 1 GPU), 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 single-token…

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/Qwen3-1.7B-Base at revision ea980cb0a6c2ae4b936e82123acc929f1cec04c1. 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…

Fine-tune of convaiinnovations/laya-multilingual (Apache-2.0) for prompt-injection and jailbreak detection. The base model is mmBERT, vocab 256k. Code: 3p3r/sentinel-laya. The English checkpoint is a different model: 3p3r/sentinel-laya. This revision starts from the inject-label checkpoint and adds a round on 3p3r/short-role-attacks, a synthetic English and German set of short role swaps and short orders, each with a benign twin. The five evaluation sets below were not part of training. Noul temperature is 2.2534, kept from the first revision. Threshold is 0.5. Positive class: jailbreak or prompt injection. Metric: Binary F1. Same prompts as the English card, one RTX 3090, batch size 64.…

Model · Text classification

Sieve-9B-Plus

Sthānika AI

Sieve-9B-Plus is a decision model from the Sieve family. You give it a piece of text or JSON (the state) and typed questions, and it returns a calibrated probability for every option of every question. It reads the state once, scores the options directly, and never generates text. It is a LoRA adapter (rank 32) and a pointer head on Qwen/Qwen3.5-9B (revision c2022362), and it stores one calibration temperature per question category. The code is at - Backbone. Only the text part of Qwen3.5-9B is used; the model cannot produce text. - Readout. A pointer head scores the end of each option against the decision point. A calibrated softmax gives the probabilities. - Isolation. Each question runs…

Sift is an AI-assisted SMS scam screening project designed to help international students review unfamiliar English messages. This repository contains its primary classification model, a trained scikit-learn pipeline that predicts Normal (0) or Scam (1) and outputs a score for the Scam class. The original labeled dataset has 500 examples: 250 Scam and 250 Normal. It includes SMS-style messages, adapted messages, and some source material from other communication channels; not every example was an independently observed real-world SMS. Normal: 238 synthetic or adapted examples based on official information from organizations, including ANZ, ITV, U.S. Bank, O2, and Unity Bank, plus 12…

Model · Text classification

snd_sentiment_analysis

Danish Mahdi

This repository contains a fine-tuned XLM-RoBERTa Base model for 3-class sentiment classification in Sindhi. The model predicts one of the following labels: - positive - neutral - negative This model is intended for research, experimentation, and lightweight production prototyping on Sindhi-language sentiment analysis tasks. It may be useful for short-text classification such as reviews, feedback, and social-media snippets. It should not be used as the only basis for high-stakes decisions. Performance can vary by domain, dialect, and writing style, and human review is recommended when errors could affect people or organizations. The saved model artifacts in this repository report the…

Model · Text classification

Solomon

Doccy Health

A LoRA adapter and trained answer heads for Qwen/Qwen3.8-27B that turn a document plus a set of structured questions into one probability per decision, each with a retrieval pointer to where the support for it plausibly sits in the source. It does not generate text. Give it a document once and ask structured questions against it. Each answer comes back as a probability, and with source spans beside it. The answer is read from the whole document; the spans are a separate word-overlap search over the source text. They are a pointer to where the support probably is, not the passage the answer came from — Evidence spans, below, measures the difference. There is no chat, no reasoning trace and…

Model · Text classification

SourceCodeAuthorCheck-SLM-10M

Anthony Assi

A ~10 million parameter Small Language Model (SLM) Transformer designed for binary classification to detect whether Python source code was written by a human or generated by AI. The model was trained on a dataset of human-written code extracted from GitHub (Q3 2017 and prior) and synthetic AI-generated code mimicking Q3 2026 generative AI paradigms. You can test the model interactively without writing any code by visiting our Gradio Web UI Space. To use this model locally, you must include the model architecture class in your script before loading the weights. Once the class is defined, you can automatically pull the weights from Hugging Face and run inference cleanly using this helper…

An offline English and Hinglish command interpreter for home devices and registered industrial/robotics devices. It converts one instruction into a catalog-validated JSON intent. The package includes a trained 87,181-byte action model, a 1,002,414-device SQLite catalog, a Python API, an HTTP service, a browser playground, Docker files, and reproducible training and evaluation data. The runtime was previously packaged locally as edge-command-docker-v3-ui. The system resolves device names through explicit identifiers, aliases and SQLite FTS5 search. It prioritizes action patterns and capability checks, with a stored count-based unigram/bigram classifier for the fallback scoring path. The…

Model · Text classification

szl-triage-linear-development-v1

SZL Holdings

NOTPROMOTABLE. No production admission or runtime integration. This is a newly trained, independently implemented six-class Python softmax classifier with 744 train-only features. It is a custom JSON weight format, not a Transformers checkpoint or a hosted inference endpoint. The complete study source, original weights, records, negative control and sealed thresholds are distributed from immutable Git blobs. SOURCEBINDING.json lists their hashes; unsigned hashes require trust in the declared canonical source. The fixed seed 11 study trained on 527 engine-labelled rows, excluding 101 held rows. On the previously exposed 42-row development challenge, joint label/state accuracy was 8/42…

Maps free text (a patent abstract, for example) to ranked International Patent Classification symbols. Every IPC entry is embedded from its full ancestor path and the query is scored against the hierarchy (path support, beam by best subtree score). This repository is a custom Inference Endpoints handler (handler.py). Deploy it as level is one of section, class, subclass, group, subgroup or auto. The response is a list of {symbol, canonical, level, score, similarity, title, path}. Contents: scheme/ (titles and hierarchy), index/ (vectors, parquet), text2ipc/ (the package, vendored), text2ipc.json (which index to serve). Data: IPC scheme master files by WIPO; Portuguese titles from INPI…

This model was fine-tuned on the AG News dataset (fancyzhx/agnews) for four-class news topic classification: The dataset was divided into 108,000 training examples, 12,000 validation examples, and 7,600 test examples. A random seed of 42 was used. This model is intended for English news topic classification into the four AG News categories: World, Sports, Business, and Sci/Tech. It was developed for educational purposes and experimentation with BERT adaptation methods. The model is trained on English news data and may not generalize well to other domains or languages. It only supports the four categories present in AG News. Performance on real-world data may differ from the reported…

Model · Text classification

Toxic-Not-Toxic

Saber Bounehas

This model is a fine-tuned version of distilroberta-base on the None dataset. It achieves the following results on the evaluation set: The following hyperparameters were used during training: - learningrate: 5e-05 - trainbatchsize: 8 - evalbatchsize: 8 - lrschedulertype: linear - numepochs: 10 - Transformers 5.19.0 - Pytorch 2.14.1 - Datasets 5.1.0 - Tokenizers 0.23.2

Model · Text classification

tsukiai-laya

Tsukihime

This repository contains the fine-tuned and metadata-prompt-tuned Laya Decision Gate for the Tsukiai Agent Pipeline. Evaluating on 600 held-out test examples

Model · Text classification

typed-decisions-minilm-l6-specialist

Adaptive Classifier

A specialist for the Typed Decisions (workflow, question) on a frozen sentence-transformers/all-MiniLM-L6-v2 encoder, 20 heads in total. Each head takes the rendered state, the question text and its options, and returns a probability distribution over the question's labels. This is not zero-shot. It was fitted on the 1,200-case train split of Typed Decisions and is scored on the 400-case test split. Per the benchmark's own rules it is a specialist, and should not be compared with generalist models that answer unseen question schemas. "This run" is the model in this repository, fitted and scored from the public dataset with adaptive-classifier 0.2.0 on Apple MPS, and scored by the benchmark…

Epochs: 5; Batch size: 32; Optimizer: AdamW; Max input token length: 256.

uratori-ja-2b is a Japanese decision model. Given a text state (for example a source document and a claim) and one or more typed questions, it returns a probability distribution over the allowed answers in a single forward pass, without generating text. Three question types are supported: noul (yes/no), choice (pick one of 2 to 8 labelled options) and score (an ordinal scale with 2 to 10 levels). It is trained for three jobs: checking whether a claim or an answer is supported by supplied evidence (grounding), comparing two documents (contradictions, meaning-changing edits, added claims) and judging retrieval results and answers in a RAG pipeline (relevance, sufficiency, faithfulness). The…

uratori-ja-310m is a Japanese decision model. Given a text state (for example a source document and a claim) and one or more typed questions, it returns a probability distribution over the allowed answers in a single forward pass, without generating text. Three question types are supported: noul (yes/no), choice (pick one of 2 to 8 labelled options) and score (an ordinal scale with 2 to 10 levels). It is trained for three jobs: checking whether a claim or an answer is supported by supplied evidence (grounding), comparing two documents (contradictions, meaning-changing edits, added claims) and judging retrieval results and answers in a RAG pipeline (relevance, sufficiency, faithfulness). The…

uratori-ja-4b is a Japanese decision model. Given a text state (for example a source document and a claim) and one or more typed questions, it returns a probability distribution over the allowed answers in a single forward pass, without generating text. Three question types are supported: noul (yes/no), choice (pick one of 2 to 8 labelled options) and score (an ordinal scale with 2 to 10 levels). It is trained for three jobs: checking whether a claim or an answer is supported by supplied evidence (grounding), comparing two documents (contradictions, meaning-changing edits, added claims) and judging retrieval results and answers in a RAG pipeline (relevance, sufficiency, faithfulness). The…

Model · Text classification

valnivo-router-small

Valnivo Labs

intfloat/multilingual-e5-small fine-tuned by Valnivo Labs as a classifier over the Valnivo copilot's fixed library of answers: it returns the id of an explanation, a screen or a fixed refusal, and nothing else. Trained only on questions written for that purpose — never on anybody's data. 8-bit ONNX (onnx/modelquantized.onnx) for transformers.js; the input is prefixed query: as for e5. ONNX Runtime's WebAssembly is copied under ort/. It gives no financial advice and is not a general model: outside the Valnivo app its labels mean nothing.

Model · Text classification

vega-08b-public-intents

Nandakishor M

Inference on a single T4, end to end, in the browser. 800 million or 4 billion parameters. A 73,728-token context. Images. Running on your own hardware. That combination is the point: a decision model small enough to sit inside your own process, that can read a whole contract in one pass and look at a picture, and that still beats a hosted reference model on the tasks below. A new architecture with its own training and calibration method. The language model inside it is frozen and never trained; everything learned lives in a small physics engine on top of it. Both are in this repository and take the same code path. The 0.8B sits at the root because that is where it has always been; the 4B…

Sentiment (negative / neutral / positive) for Vietnamese student feedback about university courses. PhoBERT-base fine-tuned on UIT-VSFC with diacritic and teencode augmentation and, at every step, trained to give a real informally typed comment the label a frozen teacher gives its normalized form. Real typing changes 12% of its labels, against 18% for the same model without that training. Shipped as the ONNX FP32 graph the ViFeedback service runs, plus the PyTorch checkpoint it was exported from. Code, evaluation protocol and every number below: https://github.com/ThanhDatVN/ViFeedback-NLP-Service The model expects pyvi word-segmented, lowercase text (giảngviên nhiệttình), at most 96…

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

Zircon-0.6B-v2-mlx

Fahrenheit Research

Zircon v2 is a 0.6B-parameter decision model from Fahrenheit Research. It runs fully on-device on Apple silicon. You give it an email, a message or a pending task plus a set of options, and it returns a calibrated probability for each option in under 50 ms per decision. (1) MacBook Pro (Apple M5), 8-bit weights, median. Speed varies by hardware. (2) Fahrenheit Research internal testing, September 2026, on held-out emails not seen in training. (3) Fahrenheit Research internal testing, September 2026. 400 cases (2,000 decisions) from the public LocalLLaMA typed-decisions test set. (4) Fahrenheit Research internal testing, September 2026, on game seeds not seen in training. Built on Qwen3-0.6B…