Instructions to use ninja/Sentiment_Analysis with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ninja/Sentiment_Analysis with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="ninja/Sentiment_Analysis")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("ninja/Sentiment_Analysis") model = AutoModelForSequenceClassification.from_pretrained("ninja/Sentiment_Analysis") - Notebooks
- Google Colab
- Kaggle
Upload BertForSequenceClassification
Browse files- config.json +3 -1
config.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"_name_or_path": "bert-base-cased",
|
| 3 |
"architectures": [
|
| 4 |
-
"
|
| 5 |
],
|
| 6 |
"attention_probs_dropout_prob": 0.1,
|
| 7 |
"classifier_dropout": null,
|
|
@@ -622,6 +622,8 @@
|
|
| 622 |
"num_hidden_layers": 12,
|
| 623 |
"pad_token_id": 0,
|
| 624 |
"position_embedding_type": "absolute",
|
|
|
|
|
|
|
| 625 |
"transformers_version": "4.42.3",
|
| 626 |
"type_vocab_size": 2,
|
| 627 |
"use_cache": true,
|
|
|
|
| 1 |
{
|
| 2 |
"_name_or_path": "bert-base-cased",
|
| 3 |
"architectures": [
|
| 4 |
+
"BertForSequenceClassification"
|
| 5 |
],
|
| 6 |
"attention_probs_dropout_prob": 0.1,
|
| 7 |
"classifier_dropout": null,
|
|
|
|
| 622 |
"num_hidden_layers": 12,
|
| 623 |
"pad_token_id": 0,
|
| 624 |
"position_embedding_type": "absolute",
|
| 625 |
+
"problem_type": "single_label_classification",
|
| 626 |
+
"torch_dtype": "float32",
|
| 627 |
"transformers_version": "4.42.3",
|
| 628 |
"type_vocab_size": 2,
|
| 629 |
"use_cache": true,
|