This model is a conversion of MoritzLaurer/roberta-base-zeroshot-v2.0-c to ONNX format using the Optimum library.
wazn-2b-v0.1 is an open-weight model for zero-shot classification from Numidlabs, released under Apache License 2.0. Its published files total 172.9 MB.
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.
Parameters—
Context—
Weights172.9 MB
Licenseapache-2.0
AccessOpen weights
Monthly Downloads—
Model Card
By Numidlabs, published under apache-2.0, revision 869e2f1ad096.
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.
Read Numidlabs's full model card
Wazn is a decision model: given a context, optional rules and an instruction, it 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.
Use
pip install "wazn-experimental[server]"
wazn-experimental serve --model numidlabs/wazn-2b-v0.1
from wazn_experimental import Client, Request, Instruction, Label
request = Request(
context="My running shoes arrived in the wrong size. Can I swap them?",
instructions=[Instruction(
"Which team should handle this?",
labels=[Label("returns", "Exchanges, refunds, wrong or damaged items"),
Label("shipping", "Delivery status, delays, lost packages"),
Label("billing", "Charges, invoices, payment problems")],
)],
)
print(Client().predict(request).answer)
Model
- Backbone:
Qwen/Qwen3.5-2B-Baseat revisionb1485b2fa6dfa1287294f269f5fb618e03d52d7c, loaded from the hub (not in this repo) - This repo: the head (43,214,082 parameters: relational judge, NONE gate, tag embeddings, LoRA adapters)
- Token budgets: 8192 prefix tokens, 640 tokens per label
Limitations
TODO: known weak spots, training data summary, evaluation results.
License
The head weights are released under Apache-2.0. The backbone keeps its own
license; see Qwen/Qwen3.5-2B-Base.
Identity and Version
- Repository
- numidlabs/wazn-2b-v0.1
- Publisher
- Numidlabs
- Task
- Zero-shot classification
- Modality
- Text
- Library
- wazn-experimental
- Parameters
- Not stated by the source
- Languages
- Not stated by the source
- Revision
- 869e2f1ad0963ba5df6e31b0181e2372b0c5d304
- First published
- 2026-10-02
- Last updated
- 2026-10-03
Files and Weights
4 files, 172.9 MB in total. The weights are 1 file totalling 172.9 MB in safetensors.
Weights1 file · 172.9 MB
Configuration1 file · 1.1 KB
Documentation1 file · 1.6 KB
Repository1 file · 1.5 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| head.safetensors | Weights | 172.9 MB | f44029fec318 |
| config.json | Configuration | 1.1 KB | — |
| README.md | Documentation | 1.6 KB | — |
| .gitattributes | Repository | 1.5 KB | — |
License and Download
- License
- apache-2.0
- Access
- Open weights, no gate
- Download size
- 172.9 MB
Download from Numidlabs
Released by Numidlabs through its official repository on Hugging Face. Read the license.
Built From
- Derived from Qwen/Qwen3.5-2B-Base
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 172.9 MB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About wazn-2b-v0.1
Can I use wazn-2b-v0.1 commercially?
Yes. wazn-2b-v0.1 is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.
Similar Models
https://huggingface.co/facebook/bart-large-mnli 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).
distilbart-mnli is the distilled version of bart-large-mnli created using the No Teacher Distillation technique proposed for BART summarisation by Huggingface, here. We just copy alternating layers from bart-large-mnli and finetune more on the same data. This is a very simple and effective technique, as we can see the performance drop is very little. Detailed performace trade-offs will be posted in this sheet. If you want to train these models yourself, clone the distillbart-mnli repo and follow the steps below Clone and install transformers from source Download MNLI data Create student model Start fine-tuning You can find the logs of these trained models in this wandb project.
distilbart-mnli is the distilled version of bart-large-mnli created using the No Teacher Distillation technique proposed for BART summarisation by Huggingface, here. We just copy alternating layers from bart-large-mnli and finetune more on the same data. This is a very simple and effective technique, as we can see the performance drop is very little. Detailed performace trade-offs will be posted in this sheet. If you want to train these models yourself, clone the distillbart-mnli repo and follow the steps below Clone and install transformers from source Download MNLI data Create student model Start fine-tuning You can find the logs of these trained models in this wandb project.
https://huggingface.co/typeform/mobilebert-uncased-mnli 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).
https://huggingface.co/cross-encoder/nli-deberta-v3-xsmall 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).