Instructions to use grounded-ai/phi3.5-hallucination-judge with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use grounded-ai/phi3.5-hallucination-judge with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("microsoft/Phi-3.5-mini-instruct") model = PeftModel.from_pretrained(base_model, "grounded-ai/phi3.5-hallucination-judge") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse filesshould return the formatted prompt instead of the input ? :)
README.md
CHANGED
|
@@ -46,7 +46,7 @@ def format_input(reference, query, response):
|
|
| 46 |
####END INFO####
|
| 47 |
Based on the information provided is the model output a hallucination? Respond with only "yes" or "no"
|
| 48 |
"""
|
| 49 |
-
return
|
| 50 |
|
| 51 |
text = format_input(reference="The apple mac has the best hardware",
|
| 52 |
query="What computer has the best software?",
|
|
|
|
| 46 |
####END INFO####
|
| 47 |
Based on the information provided is the model output a hallucination? Respond with only "yes" or "no"
|
| 48 |
"""
|
| 49 |
+
return prompt
|
| 50 |
|
| 51 |
text = format_input(reference="The apple mac has the best hardware",
|
| 52 |
query="What computer has the best software?",
|