Zero-Shot Classification
Transformers
Safetensors
English
modernbert
text-classification
instruct
natural-language-inference
nli
Instructions to use tasksource/ModernBERT-large-nli with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use tasksource/ModernBERT-large-nli with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("zero-shot-classification", model="tasksource/ModernBERT-large-nli")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("tasksource/ModernBERT-large-nli") model = AutoModelForSequenceClassification.from_pretrained("tasksource/ModernBERT-large-nli", device_map="auto") - Inference
- Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -31,6 +31,8 @@ It is very good at reasoning tasks (better than llama 3.1 8B Instruct on ANLI an
|
|
| 31 |
| glue/wnli | 0.64 |
|
| 32 |
| glue/mrpc | 0.81 |
|
| 33 |
| glue/qqp | 0.87 |
|
|
|
|
|
|
|
| 34 |
| super_glue/boolq | 0.66 |
|
| 35 |
| super_glue/cb | 0.86 |
|
| 36 |
| super_glue/multirc | 0.9 |
|
|
@@ -69,8 +71,6 @@ It is very good at reasoning tasks (better than llama 3.1 8B Instruct on ANLI an
|
|
| 69 |
| recast_white/dpr | 0.84 |
|
| 70 |
| add_one_rte | 0.94 |
|
| 71 |
| paws/labeled_final | 0.96 |
|
| 72 |
-
| glue/cola | 0.87 |
|
| 73 |
-
| glue/sst2 | 0.96 |
|
| 74 |
| pragmeval/pdtb | 0.56 |
|
| 75 |
| lex_glue/scotus | 0.58 |
|
| 76 |
| lex_glue/ledgar | 0.85 |
|
|
|
|
| 31 |
| glue/wnli | 0.64 |
|
| 32 |
| glue/mrpc | 0.81 |
|
| 33 |
| glue/qqp | 0.87 |
|
| 34 |
+
| glue/cola | 0.87 |
|
| 35 |
+
| glue/sst2 | 0.96 |
|
| 36 |
| super_glue/boolq | 0.66 |
|
| 37 |
| super_glue/cb | 0.86 |
|
| 38 |
| super_glue/multirc | 0.9 |
|
|
|
|
| 71 |
| recast_white/dpr | 0.84 |
|
| 72 |
| add_one_rte | 0.94 |
|
| 73 |
| paws/labeled_final | 0.96 |
|
|
|
|
|
|
|
| 74 |
| pragmeval/pdtb | 0.56 |
|
| 75 |
| lex_glue/scotus | 0.58 |
|
| 76 |
| lex_glue/ledgar | 0.85 |
|