Instructions to use sms1097/relevant_model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use sms1097/relevant_model with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="sms1097/relevant_model")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("sms1097/relevant_model") model = AutoModelForSequenceClassification.from_pretrained("sms1097/relevant_model", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Relevant Model
|
| 2 |
+
|
| 3 |
+
This generates the `is_relevant` token as descirbed in Self-RAG.
|
| 4 |
+
|
| 5 |
+
We are testing to see if a retrieved document is relevant to the user input of our language model.
|
| 6 |
+
|
| 7 |
+
The expected input to the model is:
|
| 8 |
+
|
| 9 |
+
```
|
| 10 |
+
Instruction:\n{instruction}\nContext:\n{doc}
|
| 11 |
+
```
|