Instructions to use typeform/mobilebert-uncased-mnli with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use typeform/mobilebert-uncased-mnli with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("zero-shot-classification", model="typeform/mobilebert-uncased-mnli")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("typeform/mobilebert-uncased-mnli") model = AutoModelForSequenceClassification.from_pretrained("typeform/mobilebert-uncased-mnli") - Inference
- Notebooks
- Google Colab
- Kaggle
David Chu commited on
Commit ·
f8f2f7f
1
Parent(s): 4f8ce95
Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language: en
|
| 3 |
+
pipeline_tag: zero-shot-classification
|
| 4 |
+
tags:
|
| 5 |
+
- mobilebert
|
| 6 |
+
datasets:
|
| 7 |
+
- multi_nli
|
| 8 |
+
metrics:
|
| 9 |
+
- accuracy
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devices
|
| 13 |
+
|
| 14 |
+
This model is the Multi-Genre Natural Language Inference (MNLI) fine-turned version of the [uncased MobileBERT model](https://huggingface.co/google/mobilebert-uncased).
|