This model is a conversion of MoritzLaurer/roberta-base-zeroshot-v2.0-c to ONNX format using the Optimum library.
malkuth-4b is an open-weight model for zero-shot classification from Sae Chan O, released under Creative Commons Attribution-NonCommercial 4.0. Its published files total 155.2 MB.
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.
Parameters—
Context—
Weights135.2 MB
Licensecc-by-nc-4.0
AccessOpen weights
Monthly Downloads—
Model Card
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…
Excerpt from the card by Sae Chan O, licensed cc-by-nc-4.0.
Identity and Version
- Repository
- dhtocks/malkuth-4b
- Publisher
- Sae Chan O
- Task
- Zero-shot classification
- Modality
- Text
- Library
- peft
- Parameters
- Not stated by the source
- Languages
- en, ko, ja, zh, de, fr, es, hi
- Revision
- ba9221fcb1ff450fc51dcefffc8e034ed479630d
- First published
- 2026-09-24
- Last updated
- 2026-09-25
Files and Weights
9 files, 155.2 MB in total. The weights are 2 files totalling 135.2 MB in pt, safetensors.
Weights2 files · 135.2 MB
Configuration2 files · 3.4 KB
Tokenizer2 files · 20.0 MB
Documentation1 file · 4.9 KB
Other1 file · 7.8 KB
Repository1 file · 1.6 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| adapter_model.safetensors | Weights | 129.9 MB | 96b4f5a922af |
| head.pt | Weights | 5.2 MB | 8e3e63bf28a0 |
| adapter_config.json | Configuration | 1.3 KB | — |
| training_config.json | Configuration | 2.2 KB | — |
| README.md | Documentation | 4.9 KB | — |
| chat_template.jinja | Other | 7.8 KB | — |
| .gitattributes | Repository | 1.6 KB | — |
| tokenizer.json | Tokenizer | 20.0 MB | 06b9509352d2 |
| tokenizer_config.json | Tokenizer | 1.1 KB | — |
License and Download
- License
- cc-by-nc-4.0
- Access
- Open weights, no gate
- Download size
- 135.2 MB
Download from Sae Chan O
Released by Sae Chan O through its official repository on Hugging Face. Read the license.
Built From
- Adapter of Qwen/Qwen3.5-4B-Base
- Derived from Qwen/Qwen3.5-4B-Base
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 135.2 MB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About malkuth-4b
Can I use malkuth-4b commercially?
Not without separate permission. malkuth-4b is released under Creative Commons Attribution-NonCommercial 4.0. CC BY-NC 4.0 permits sharing and adapting with credit for non-commercial purposes only. Commercial use needs separate permission from the rights holder.
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).