Zero-Shot Classification Models

Model · Zero-shot classification

nli-deberta-v3-small

Joshua

https://huggingface.co/cross-encoder/nli-deberta-v3-small with ONNX weights to be compatible with Transformers.js. If you haven't already, you can install the Transformers.js JavaScript library from NPM using: Note: Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using Optimum and structuring your repo like this one (with ONNX weights located in a subfolder named onnx).

Model · Zero-shot classification

chinese-decision-0.8b-gguf

Quincyqiang

中文概率决策模型的 GGUF 版本：llama.cpp 推理，CPU 即可部署 各尺寸、部署格式与外部模型对比。2B BF16 与 2B Q80 均已公开发布并完成 CJ-Bench 全量评测：2B 整体准确率更高，0.8B 更小更快，部分法律判断与金融评分任务仍是 0.8B 更好。 本仓库是 Chinese Decision 0.8B 的 GGUF 格式导出，用于 llama.cpp / llama-cpp-python 推理。 原版模型是一个中文决策模型：给定上下文和一组固定候选项（单题 2–26 个；类别更多的 choice 问题可用服务端的 /v1/tournament 分组淘汰），一次前向直接返回每个候选项的概率，不生成任何 token。支持 noul（是/否）、choice（单选）、score（有序等级）三种题型，覆盖通用、医疗、法律、金融四个领域。模型能力、训练细节与应用案例见原版模型卡。 GGUF 版本的特点： - 无需 PyTorch 和 GPU：llama-cpp-python 即可在 CPU 上运行，也可用 CUDA 版 llama.cpp 跑在 GPU 上。 - 体积约为原版的一半：Q80 为 812 MB，原版 safetensors 为 1.50 GB。 - 内存占用更低：同一台服务器上，CPU 推理进程峰值内存 2.19 GiB，Transformers FP32 为 7.44 GiB。 - 精度基本不变：CJ-Bench 全量 307,900 条上，准确率、NLL、ECE、Brier 的变化都在千分之一以内。…

Model · Zero-shot classification

chinese-decision-0.8b

Quincyqiang

各尺寸、部署格式与外部模型对比。2B BF16 与 2B Q80 均已公开发布并完成 CJ-Bench 全量评测：2B 整体准确率更高，0.8B 更小更快，部分法律判断与金融评分任务仍是 0.8B 更好。 Chinese Decision 是一个面向中文场景的轻量级决策模型。它不聊天、不生成文本，只做一件事：给定上下文和一组固定候选项，返回每个候选项的概率。 - 一次前向，零输出 token：读取最后位置上候选字母 A–Z 的 logits，softmax 后即为概率。 - 三种题型：noul（是/否）、choice（单选）、score（有序等级，返回期望分值）。 以下截图来自我们的测试平台 Decision Studio，后端运行的就是本模型（step 10000）。这些场景采用同一种设计：业务规则写在代码里，决策模型只负责给出概率。 每张工单在一次请求里同时问 6 个问题：类别（choice），严重程度和情绪（score），是否可复现、是否要求退款、是否有流失风险（noul）。不管后续用不用得上都一并提问，省去多次往返。路由规则写在代码里，根据这些概率决定工单派给哪个队列；类别置信度低于 0.5 时转人工复核。截图中 8 张工单 × 6 个问题共 48 次决策，用时 285 ms。 推荐同时安装 flash-linear-attention，它为 Qwen3.5 的线性注意力层提供高效 kernel： Hugging Face： ModelScope： decisionconfig.json 中的温度只在 softmax 前缩放…

Model · Zero-shot classification

finecat-nli-v2-l

Lee Miller

This model is a fine-tune of jhu-clsp/ettin-encoder-400m, trained on the dleemiller/FineCat-NLI-Reason dataset, a compilation of several high-quality NLI data sources with quality screening and reduction of easy samples in the training split. Also includes additional NLI, fact verification and long document sources (2.05M pairs in total). The training uses logit distillation from an NLI finetune of Qwen3.8-27B. \begin{equation} \mathcal{L} = \alpha \cdot \mathcal{L}{\text{CE}}(z^{(s)}, y) + \beta \cdot T^2 \cdot \mathrm{KL}\left(\sigma(z^{(t)}/T) \,\|\, \sigma(z^{(s)}/T)\right) \end{equation} where \\(z^{(s)}\\) and \\(z^{(t)}\\) are the student and teacher logits, \\(y\\) are the ground…

Model · Zero-shot classification

matilda-jev-v1.5

Maincode

A BF16 JEV decision model with a 255-option readout. This is the highest-scoring checkpoint in the completed MATILDA JEV experiments as of 9 October 2026: Decision Index 63.47 (0.3 public suite). The model accepts a state and one or more decision questions. It supports choice, noul (probability of true), and ordinal score. Inference is one forward pass per question; the model has no text-generation head and does not generate a chain of thought. The LoRA updates are already merged into the weights. No adapter merge is required. Use Python 3.12 or newer and install PyTorch for your accelerator. The validated cluster environment uses PyTorch 2.14.0, Transformers 5.17.0, and an AMD Instinct…

Model · Zero-shot classification

finecat-nli-v2-xl

Lee Miller

This model is a fine-tune of jhu-clsp/ettin-encoder-1b, trained on the dleemiller/FineCat-NLI-Reason dataset, a compilation of several high-quality NLI data sources with quality screening and reduction of easy samples in the training split. Also includes additional NLI, fact verification and long document sources (2.05M pairs in total). The training uses logit distillation from an NLI finetune of Qwen3.8-27B. \begin{equation} \mathcal{L} = \alpha \cdot \mathcal{L}{\text{CE}}(z^{(s)}, y) + \beta \cdot T^2 \cdot \mathrm{KL}\left(\sigma(z^{(t)}/T) \,\|\, \sigma(z^{(s)}/T)\right) \end{equation} where \\(z^{(s)}\\) and \\(z^{(t)}\\) are the student and teacher logits, \\(y\\) are the ground…

Model · Zero-shot classification

Vela-2.0-0.3B

vLLM Semantic Router

Open Foundation Routing Models Routing decisions. Safety checks. Precise text spans. Vela 2.0 brings routing questions and span-level decisions into one model interface. Supply your options, labels and rubrics at request time; ask about the request, its context and the answer together. The 0.3B is the family's compact multilingual encoder, with an 8,192-token input budget and Torch or ONNX inference on CPU or GPU. 1. Route with your own criteria. Choose a route, check a policy condition, assign a score or select multiple labels. 2. Locate the text behind a signal. Return spans of personal information and unsupported claims with character offsets and probabilities. 3. Ask across the whole…

Model · Zero-shot classification

siddhanto-bangla-english-banglish

Kazal Chandra Barman

Siddhanto (সিদ্ধান্ত, "decision") is a fine-tune of convaiinnovations/laya-multilingual (mmBERT-base, 322M params) for open-domain typed decisions over Bangla, English and Banglish (romanized Bangla / code-switched) conversational text. It is not a fixed-label classifier. It implements Laya's typed choice / noul / score interface: at request time you supply the question and its options (any schema, any domain), and the model returns a calibrated probability distribution over exactly those options — no retraining or head-swapping needed to add a new label set. Fine-tuned on ~268k typed-decision examples drawn from: - An internal 56-intent OTA (travel-agency) synthetic corpus…

Model · Zero-shot classification

Vela-2.0-4B

vLLM Semantic Router

Open Foundation Routing Models Routing decisions. Safety checks. Precise text spans. The balanced hybrid member of Vela 2.0: strong multilingual safety and general decisions, with router and open-label spans through one interface. Define options, labels and rubrics at request time. Ask multiple named questions about a request, context and answer, and receive structured decisions with the text spans that support your workflow. 1. Balanced routing capability. Safety macro AUC of 0.921 across 14 public sets, alongside open-label extraction and general decisions. 2. Routing and safety together. Use one request for routing, prompt-attack checks, PII and unsupported-claim detection. 3. Decisions…

Model · Zero-shot classification

Vela-2.0-9B

vLLM Semantic Router

Open Foundation Routing Models Routing decisions. Safety checks. Precise text spans. The largest hybrid member of Vela 2.0: high-accuracy multilingual routing, long-document PII and hallucination detection, with open-label spans through one interface. Define options, labels and rubrics at request time. Ask multiple named questions about a request, context and answer, and receive structured decisions with the text spans that support your workflow. 1. High-accuracy decisions. A 41.63 Jev Decision Index with optional Noul calibration, plus 0.989 AUC on unseen prompt-attack families. 2. Routing and safety together. Use one request for routing, prompt-attack checks, PII and unsupported-claim…

Model · Zero-shot classification

Vela-2.0-0.8B

vLLM Semantic Router

Open Foundation Routing Models Routing decisions. Safety checks. Precise text spans. The compact hybrid member of Vela 2.0: a 756M-parameter model for multilingual routing, safety checks and span-level decisions through one interface. Define options, labels and rubrics at request time. Ask multiple named questions about a request, context and answer, and receive structured decisions with the text spans that support your workflow. 1. Compact deployment. About 3 GB of GPU memory for FP32 parameters, with a 16,384-token input limit. 2. Routing and safety together. Use one request for routing, prompt-attack checks, PII and unsupported-claim detection. 3. Decisions at span resolution. Return…

Bobcat Flash 1.2 · Bobcat Flash 1.2 FP8 · Try it in the Space · Code on GitHub Bobcat Flash is the fast tier of Bobcat, a typed-decision model. You send a state (text or JSON) and questions whose possible answers you define in the request; Flash returns a probability for every answer you named, and nothing else. It never generates text: it reads the logits of the offered candidates at the first answer position of one forward pass, and the host builds a closed JSON reply from your own names. An answer can be wrong, but it cannot be malformed. This repository, sanghwa-na/bobcat-flash-1.2, holds Bobcat Flash 1.2 as ready-to-serve BF16 weights on google/gemma-4-26B-A4B-it (Apache-2.0) at…

A pre-quantized FP8 checkpoint of Bobcat Flash 1.2, the fast tier of the typed-decision model Bobcat: you send a state and questions whose answers you name, and it returns a probability for every answer you named; it never generates text. Evaluation, training data, limitations and the full license notes are on the main card, This repository, sanghwa-na/bobcat-flash-1.2-fp8, is the BF16 weights of sanghwa-na/bobcat-flash-1.2 quantized to FP8 (27.2 GB, FP8DYNAMIC, every expert included): float8e4m3fn weights with one scale per output channel, activations quantized per token at run time, in the compressed-tensors format that vLLM loads as it is. It is the checkpoint the Bobcat Flash Space…

Model · Zero-shot classification

chinese-decision-2b

Quincyqiang

Chinese Decision 是一个面向中文场景的轻量级决策模型。它不聊天、不生成文本：给定上下文和一组固定候选项，一次前向直接返回每个候选项的概率，适合意图识别、工单分流、内容审核、数据打标、给模型输出打分、智能体动作选择等"有限选项判断"任务。 - 一次前向，零输出 token：读取最后位置上候选字母 A–Z 的 logits，softmax 后即为概率。 - 三种题型：noul（是/否）、choice（单选）、score（有序等级，返回期望分值）。 - 系列中准确率最高：CJ-Bench 全量整体 ACC 84.11%，医疗 / 法律 / 金融平均 78.25%，比 chinese-decision-0.8b 分别高 1.01 / 1.35 个百分点。 - 概率经过校准：附带在独立校准划分上拟合的温度，整体 ECE 0.64%。 更新于 2026-10-17。BF16 合并模型已完成全量 CJ-Bench、保存/重载和实际 HTTP 三题型/双路由验证，并已在 Hugging Face 与 ModelScope 公开发布。由本模型直接转换的 Q80 GGUF 也已完成全量 CJ-Bench 对照，见 2B Q80 模型卡。 训练数据版本 a3963a61f71e00051a80721e587d720d8926e8e7。最终 adapter SHA256 为 9b55e8eda00997544b76fa945d890605c3acae4199041c197ef5a09275142a7c；合并权重 SHA256 为…

Model · Zero-shot classification

chinese-decision-2b-gguf

Quincyqiang

Chinese Decision 2B 的 CPU 部署包，保留相同提示、候选概率计算与校准温度。 本仓库是 Chinese Decision 2B 的 GGUF Q80 导出，用于 llama.cpp / llama-cpp-python 推理。原版是一个中文决策模型：给定上下文和一组固定候选项（单题 2–26 个；类别更多的 choice 问题可用服务端的 /v1/tournament 分组淘汰），一次前向直接返回每个候选项的概率，不生成任何 token；支持 noul（是/否）、choice（单选）、score（有序等级）三种题型，覆盖通用、医疗、法律、金融四个领域。 - 无需 PyTorch 和 GPU：llama-cpp-python 即可在 CPU 上运行，也可用 CUDA 版 llama.cpp 跑在 GPU 上。 - 体积约为原版的一半：Q80 为 2.01 GB，原版 safetensors 为 3.76 GB。 - 内存占用更低：同一台服务器上，CPU 推理进程内存观测最大值 3.34 GiB，Transformers FP32 为 11.74 GiB。 - 精度基本不变：CJ-Bench 全量 307,900 条上准确率 84.1094%（BF16 交付版 84.1107%），首选项一致率 99.00%。 - 接口不变：与 BF16 版共用提示编译器、温度和 HTTP 接口，可直接接入 Decision Studio。 2026-10-17 完成量化、文件校验、CPU / HTTP 检查与 CJ-Bench 全量对照，并在 Hugging Face 与…

Model · Zero-shot classification

d3-edge

vLLM Semantic Router

d3-edge is the 0.6B multimodal foundation decision model of Decision 3.0, the decision models of vLLM Semantic Router. Give it an input (text or JSON, optionally with images) and the questions you need answered: pick one of several options, say yes or no, or rate on a scale. It answers them all in one call and returns a probability for every answer, without generating text. - Jev Decision Index 0.3, public suite: 30.55, measured with the official 0.3 kit on the released weights: all 140,178 public requests answered, none unsupported. - +13.9 on the public suite over Decision 2.0 (its 0.6B model: 16.68 on the board), ahead in all five areas. Images go before the text of the request, each…

Model · Zero-shot classification

d3-lite

vLLM Semantic Router

d3-lite is the 0.8B multimodal foundation decision model of Decision 3.0, the decision models of vLLM Semantic Router. Give it an input (text or JSON, optionally with images) and the questions you need answered: pick one of several options, say yes or no, or rate on a scale. It answers them all in one call and returns a probability for every answer, without generating text. - Jev Decision Index 0.3, public suite: 36.94, measured with the official 0.3 kit on the released weights: all 140,178 public requests answered, none unsupported. - +16.4 on the public suite over Decision 2.0 (its 0.8B model: 20.57 on the board), ahead in all five areas. Images go before the text of the request, each…

Model · Zero-shot classification

d3-nano

vLLM Semantic Router

d3-nano is the 2B multimodal foundation decision model of Decision 3.0, the decision models of vLLM Semantic Router. Give it an input (text or JSON, optionally with images) and the questions you need answered: pick one of several options, say yes or no, or rate on a scale. It answers them all in one call and returns a probability for every answer, without generating text. - Jev Decision Index 0.3, public suite: 42.14, measured with the official 0.3 kit on the released weights: all 140,178 public requests answered, none unsupported. - +12.1 on the public suite over Decision 2.0 (its 2B model: 30.05 on the board), ahead in all five areas. Images go before the text of the request, each read at…

Model · Zero-shot classification

d3-oQ4e

Jun Kim

This model was quantized using oQ (oMLX v0.7.1) mixed-precision quantization with Improved oQe Quantization (jundot/omlx#4385). A mixed-precision MLX checkpoint of vllm-sr/d3, the 27B multimodal decision model of Decision 3.0 from vLLM Semantic Router, built on Qwen/Qwen3.8-27B. It reads text or JSON with optional images and videos and returns a probability for every option of choice, yes/no and score questions without generating text. It includes the language backbone, the vision encoder and the code readout. The code readout (readout.safetensors, FP32) and decisionconfig.json are copied unchanged from the source. oMLX serves this checkpoint through POST /v1/systemone; Decision 3.0 support…

Model · Zero-shot classification

d3-oQ8e

Jun Kim

This model was quantized using oQ (oMLX v0.7.1) mixed-precision quantization with Improved oQe Quantization (jundot/omlx#4385). A mixed-precision MLX checkpoint of vllm-sr/d3, the 27B multimodal decision model of Decision 3.0 from vLLM Semantic Router, built on Qwen/Qwen3.8-27B. It reads text or JSON with optional images and videos and returns a probability for every option of choice, yes/no and score questions without generating text. It includes the language backbone, the vision encoder and the code readout. The code readout (readout.safetensors, FP32) and decisionconfig.json are copied unchanged from the source. oMLX serves this checkpoint through POST /v1/systemone; Decision 3.0 support…

d3-W4A16-G128-AWQ is an unofficial INT4 weight-only (W4A16) AWQ quantization of d3, the 27B multimodal foundation decision model of Decision 3.0. It takes the same inputs and questions as d3 and returns a probability for every answer, without generating text, with 16.5 GB of weights instead of 52 GB. - Keeps 97.76% of d3's answers on the 14,031 test requests of tasksource-jev-typed-decisions, with accuracy 83.09% against BF16's 83.25%. - 16.9 GB of GPU memory after loading instead of 52.3 GB, and 17.5 GB at the peak of the 20 longest of 1,000 text requests (up to 5,928 characters of state) on an MI300X. - Reads images and videos as d3 does: the vision tower is unchanged, and d3's example…

Model · Zero-shot classification

finecat-nli-ultra-l

Lee Miller

This model is a fine-tune of dmis-lab/UltraBERT-380M, trained on the dleemiller/FineCat-NLI-Reason dataset, a compilation of several high-quality NLI data sources with quality screening and reduction of easy samples in the training split. Also includes additional NLI, fact verification and long document sources (2.05M pairs in total). The training uses logit distillation from an NLI finetune of Qwen3.8-27B. \begin{equation} \mathcal{L} = \alpha \cdot \mathcal{L}{\text{CE}}(z^{(s)}, y) + \beta \cdot T^2 \cdot \mathrm{KL}\left(\sigma(z^{(t)}/T) \,\|\, \sigma(z^{(s)}/T)\right) \end{equation} where \\(z^{(s)}\\) and \\(z^{(t)}\\) are the student and teacher logits, \\(y\\) are the ground truth…

Model · Zero-shot classification

malkuth-2b

Sae Chan O

A small multilingual decision model for classification, with a focus on Korean. Given a text, a question, and a set of criteria, Malkuth returns probabilities over the possible choices instead of generating text. Malkuth-2B is a LoRA adapter trained on Kev and built on a frozen empero-ai/Qwen3.8-2B-Distill. It has 17.9M trainable parameters and a 65 MB adapter. - choice: select one of up to 255 options - noul: yes or no - score: select an ordered level Multiple questions can be evaluated against the same input. Questions are evaluated independently, so they cannot see each other's answers. Probabilities are temperature-calibrated on a held-out validation split. Malkuth is served through Kev…

Model · Zero-shot classification

malkuth-4b

Sae Chan O

A small multilingual decision model for classification, with a focus on Korean. Given a text, a question, and a set of criteria, Malkuth returns probabilities over the possible choices instead of generating text. Malkuth-4B is a LoRA adapter trained on Kev and built on a frozen Qwen/Qwen3.5-4B-Base. It has 33.8M trainable parameters and a 124 MB adapter. - choice: select one of up to 255 options - noul: yes or no - score: select an ordered level Multiple questions can be evaluated against the same input. Questions are evaluated independently, so they cannot see each other's answers. Probabilities are temperature-calibrated on a held-out validation split. Malkuth is served through Kev and…

Classify text in 30+ languages into any labels you choose, with no training. Use it with the transformers zero-shot-classification pipeline, like facebook/bart-large-mnli, but multilingual, smaller, and with an 8k-token context window (fine-tuned at up to 1,024 tokens). non-commercial sets). See Training. Part of Horizon Labs' open models (collection). Labels: notentailment (0) and entailment (1). For each candidate label the model scores whether the text entails "This example is {label}." (or your hypothesistemplate). Any NLI-style use works too: pass text and textpair to a text-classification pipeline. Accuracy, single-label (multilabel=False: the label with the highest entailment score…

Classify text in 30+ languages into any labels you choose, with no training. Use it with the transformers zero-shot-classification pipeline, like facebook/bart-large-mnli, but multilingual, smaller, and with an 8k-token context window (fine-tuned at up to 1,024 tokens). non-commercial sets). See Training. Part of Horizon Labs' open models (collection). Labels: notentailment (0) and entailment (1). For each candidate label the model scores whether the text entails "This example is {label}." (or your hypothesistemplate). Any NLI-style use works too: pass text and textpair to a text-classification pipeline. Accuracy, single-label (multilabel=False: the label with the highest entailment score…

An open 0.6B "System One" decision model aligned with the public Jev HTTP contract: state + questions in, complete calibrated probability distributions out, zero autoregressive decoding. GLM-5.3-flash structured teacher distillation, CE + Brier, best-step selection and calibration-split temperature fitting. One RTX 4080 SUPER, ~65 min, full recipe in the repo. - Results (fixed held-out websites): choice top-1-in-positives 0.380 (test) / 0.500 (ood) vs uniform 0.089; noul accuracy 0.84 / Brier 0.142; real Jev-1.13 reaches 0.543 / 0.610 on the same questions. Or serve the Jev-compatible HTTP API: python -m openjev.serve --checkpoint-dir --port 8123. Full pipeline (data synthesis → streaming…

Model · Zero-shot classification

proof_v3

Falcons.ai

A single-pass, typed, calibrated decision model. Give it a state (text, code or JSON), one or more typed questions (choice, noul yes/no, score ordinal) and a closed set of options. It returns a calibrated probability for every option, from one encoder pass per question, however many options there are. This repository is both the model card and the developer guide: how to load it, test it, and use it as a decision component in an agentic system. The model has no generative component. It can only rank the options you give it, so it cannot produce text outside that set. All numbers come from this checkpoint's falcondecreport.json: one run, small preset, seed 42, MODE="scratch". Calibration is…

Variante plus (CC BY-NC 4.0, solo uso no comercial): ajustada con 15 datasets, varios de licencia no permisiva o no declarada. Para uso comercial existe tde-es-en-lite-v2 (MIT). Motor de decisiones tipadas (choice / score / noul) sobre un encoder bidireccional int8 de ~42,5 M de parámetros (43 MB), recortado a español e inglés. No genera texto: elige entre opciones que le das, puntúa una rúbrica o estima si una proposición se desprende de un texto, y devuelve probabilidades, con la opción de abstenerse. Corre en CPU, 1 hilo, sin GPU y sin Python en runtime, con el binario nativo tde (Rust). Código fuente (Apache-2.0) incluido en src/; repositorio de desarrollo: typed-decision-engine.…

VIYA reads Vietnamese text and returns typed decisions with calibrated confidence in a single forward pass. It does not generate text: you describe the question and the options in plain language, and VIYA scores every option. Options are free text, so you can add or rename them without retraining. - Vietnamese fact-checking. 87.6 macro-F1 on ViFactCheck with gold evidence (human: 84.9). When it has to find the evidence itself in the full article, it scores 78.7, ahead of Gemini 1.5 Flash, XLM-R large and Mistral 7B. - Full fact-checking pipeline. On ViWikiFC, VIYA finds the right evidence sentence and reaches the right verdict 75.7% of the time; the best published pipeline reaches 67.0%.…

The Von System One decision model (ModernBERT-large, 395M, English, 8192-token context), 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/von 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…

Model · Zero-shot classification

wazn-2b-v0.1

Numidlabs

returns a probability distribution over a set of labels you supply, each with an optional definition and few-shot examples. Nothing is generated. Experimental. For trying the model out, not for production. TODO: known weak spots, training data summary, evaluation results. The head weights are released under Apache-2.0. The backbone keeps its own license; see Qwen/Qwen3.5-2B-Base.