Instructions to use Wolverine001/bert_finetuned_senti with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Wolverine001/bert_finetuned_senti with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="Wolverine001/bert_finetuned_senti")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("Wolverine001/bert_finetuned_senti") model = AutoModelForSequenceClassification.from_pretrained("Wolverine001/bert_finetuned_senti", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download classification_report.json from Wolverine001/bert_finetuned_senti: direct link, hf CLI and curl.
- Browser
- Download file 802 Bytes
-
https://huggingface.co/Wolverine001/bert_finetuned_senti/resolve/main/classification_report.json
- Command line
-
hf download hf://Wolverine001/bert_finetuned_senti/classification_report.json
-
curl -L -o classification_report.json https://huggingface.co/Wolverine001/bert_finetuned_senti/resolve/main/classification_report.json
802 Bytes
| { | |
| "accuracy": 0.6095, | |
| "metrics": { | |
| "negative": { | |
| "precision": 0.82, | |
| "recall": 0.29, | |
| "f1-score": 0.42, | |
| "support": 1001 | |
| }, | |
| "neutral": { | |
| "precision": 0.51, | |
| "recall": 0.89, | |
| "f1-score": 0.65, | |
| "support": 1430 | |
| }, | |
| "positive": { | |
| "precision": 0.85, | |
| "recall": 0.54, | |
| "f1-score": 0.66, | |
| "support": 1103 | |
| }, | |
| "macro_avg": { | |
| "precision": 0.73, | |
| "recall": 0.57, | |
| "f1-score": 0.58, | |
| "support": 3534 | |
| }, | |
| "weighted_avg": { | |
| "precision": 0.7, | |
| "recall": 0.61, | |
| "f1-score": 0.59, | |
| "support": 3534 | |
| } | |
| } | |
| } |