Zero-Shot Classification
Transformers
ONNX
Safetensors
English
GLiClass
text classification
zero-shot
small language models
RAG
sentiment analysis
Instructions to use knowledgator/gliclass-base-v1.0-init with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use knowledgator/gliclass-base-v1.0-init with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("zero-shot-classification", model="knowledgator/gliclass-base-v1.0-init")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("knowledgator/gliclass-base-v1.0-init", dtype="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -51,7 +51,7 @@ for result in results:
|
|
| 51 |
Below, you can see the F1 score on several text classification datasets. All tested models were not fine-tuned on those datasets and were tested in a zero-shot setting.
|
| 52 |
| Model | IMDB | AG_NEWS | Emotions |
|
| 53 |
|-----------------------------|------|---------|----------|
|
| 54 |
-
| [gliclass-base-v1.0 (
|
| 55 |
| [gliclass-small-v1.0 (144 M)](https://huggingface.co/knowledgator/gliclass-small-v1.0) | 0.8650 | 0.6805 | 0.4664 |
|
| 56 |
| [Bart-large-mnli (407 M)](https://huggingface.co/facebook/bart-large-mnli) | 0.89 | 0.6887 | 0.3765 |
|
| 57 |
| [Deberta-base-v3 (184 M)](https://huggingface.co/cross-encoder/nli-deberta-v3-base) | 0.85 | 0.6455 | 0.5095 |
|
|
|
|
| 51 |
Below, you can see the F1 score on several text classification datasets. All tested models were not fine-tuned on those datasets and were tested in a zero-shot setting.
|
| 52 |
| Model | IMDB | AG_NEWS | Emotions |
|
| 53 |
|-----------------------------|------|---------|----------|
|
| 54 |
+
| [gliclass-base-v1.0 (186 M)](https://huggingface.co/knowledgator/gliclass-base-v1.0) | 0.8650 | 0.6837 | 0.4749 |
|
| 55 |
| [gliclass-small-v1.0 (144 M)](https://huggingface.co/knowledgator/gliclass-small-v1.0) | 0.8650 | 0.6805 | 0.4664 |
|
| 56 |
| [Bart-large-mnli (407 M)](https://huggingface.co/facebook/bart-large-mnli) | 0.89 | 0.6887 | 0.3765 |
|
| 57 |
| [Deberta-base-v3 (184 M)](https://huggingface.co/cross-encoder/nli-deberta-v3-base) | 0.85 | 0.6455 | 0.5095 |
|