Instructions to use hubert233/GPTFuzz with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use hubert233/GPTFuzz with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="hubert233/GPTFuzz")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("hubert233/GPTFuzz") model = AutoModelForSequenceClassification.from_pretrained("hubert233/GPTFuzz") - Inference
- Notebooks
- Google Colab
- Kaggle
Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
---
|
| 4 |
+
Official repo of [GPTFuzzer](https://github.com/sherdencooper/GPTFuzz). This model is a finetuned Roberta model to classify the toxicity of response, trained on a manually labeled dataset (see in [finetuning data](https://github.com/sherdencooper/GPTFuzz/tree/master/datasets/responses_labeled))
|