Instructions to use sms1097/retrieval_model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use sms1097/retrieval_model with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="sms1097/retrieval_model")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("sms1097/retrieval_model") model = AutoModelForSequenceClassification.from_pretrained("sms1097/retrieval_model", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -4,5 +4,11 @@ datasets:
|
|
| 4 |
- sms1097/self_rag_tokens_train_data
|
| 5 |
---
|
| 6 |
|
| 7 |
-
# Retrieval
|
| 8 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
- sms1097/self_rag_tokens_train_data
|
| 5 |
---
|
| 6 |
|
| 7 |
+
# Retrieval Model
|
| 8 |
+
|
| 9 |
+
This generates the `Retrieve` token as descirbed in Self-RAG.
|
| 10 |
+
|
| 11 |
+
We are testing to see if a retrieved document is relevant to the user input of our language model.
|
| 12 |
+
|
| 13 |
+
The expected input to the model is just a query posed to the language model.
|
| 14 |
+
|