This model is a conversion of MoritzLaurer/roberta-base-zeroshot-v2.0-c to ONNX format using the Optimum library.
Open-weight model · Zero-shot classification
distilbert-base-uncased-mnli
by Joshua Xenova/distilbert-base-uncased-mnli
https://huggingface.co/typeform/distilbert-base-uncased-mnli with ONNX weights to be compatible with Transformers.js.
Parameters—
Context512
Weights923.9 MB
License—
AccessOpen weights
Monthly Downloads5.1k
Model Card
https://huggingface.co/typeform/distilbert-base-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).
Excerpt from the card by Joshua.
Configuration
- Architecture
- DistilBertForSequenceClassification
- Context length (tokens)
- 512
- Vocabulary size
- 30,522
- Model type
- distilbert
Identity and Version
- Repository
- Xenova/distilbert-base-uncased-mnli
- Publisher
- Joshua
- Task
- Zero-shot classification
- Modality
- Text
- Library
- transformers.js
- Parameters
- Not stated by the source
- Languages
- Not stated by the source
- Revision
- fddd480db7392a87114a6813c6acb5ede13ff4ee
- First published
- 2023-05-02
- Last updated
- 2025-07-11
Files and Weights
15 files, 924.9 MB in total. The weights are 8 files totalling 923.9 MB in onnx.
Weights8 files · 923.9 MB
Configuration2 files · 878 B
Tokenizer3 files · 943.3 KB
Documentation1 file · 1.2 KB
Repository1 file · 1.5 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| onnx/model.onnx | Weights | 268.0 MB | 145d2bb1a82d |
| onnx/model_bnb4.onnx | Weights | 122.0 MB | f71c227ffa84 |
| onnx/model_fp16.onnx | Weights | 134.1 MB | 6990c8a005d7 |
| onnx/model_int8.onnx | Weights | 67.3 MB | ebfda67883e5 |
| onnx/model_q4.onnx | Weights | 124.6 MB | 1aab657f487b |
| onnx/model_q4f16.onnx | Weights | 73.0 MB | bad834ed796d |
| onnx/model_quantized.onnx | Weights | 67.6 MB | 5b7e374d8d1e |
| onnx/model_uint8.onnx | Weights | 67.3 MB | 3992b5404256 |
| config.json | Configuration | 753 B | — |
| special_tokens_map.json | Configuration | 125 B | — |
| README.md | Documentation | 1.2 KB | — |
| .gitattributes | Repository | 1.5 KB | — |
| tokenizer.json | Tokenizer | 711.4 KB | — |
| tokenizer_config.json | Tokenizer | 372 B | — |
| vocab.txt | Tokenizer | 231.5 KB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 923.9 MB
Download from Joshua
Released by Joshua through its official repository on Hugging Face.
Built From
- Derived from typeform/distilbert-base-uncased-mnli
- Quantized from typeform/distilbert-base-uncased-mnli
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 923.9 MB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About distilbert-base-uncased-mnli
What is distilbert-base-uncased-mnli's context length?
512 tokens, from the maximum position embeddings in its published configuration.
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).