Update README.md

README.md

@@ -11,16 +11,14 @@ tags:
 - phi-3
 - phi-3-mini
 - italian
-base_model: unsloth/Phi-3-mini-4k-instruct-bnb-4bit
-datasets:
-- mchl-labs/stambecco_data_it
+base_model: microsoft/Phi-3-mini-4k-instruct
 ---
 
 # Uploaded  model
 
-- **Developed by:** walid-iguider
-- **License:** cc-by-nc-sa-4.0
-- **Finetuned from model :** unsloth/Phi-3-mini-4k-instruct-bnb-4bit
+- **Developed by:** Enzo Pio Palmisano
+- **License:** mit
+- **Finetuned from model :** microsoft/Phi-3-mini-4k-instruct
 
 
 ## Evaluation
@@ -30,7 +28,7 @@ For a detailed comparison of model performance, check out the [Leaderboard for I
 Here's a breakdown of the performance metrics:
 | Metric                      | hellaswag_it acc_norm | arc_it acc_norm | m_mmlu_it 5-shot acc | Average |
 |:----------------------------|:----------------------|:----------------|:---------------------|:--------|
-| **Accuracy Normalized**     | 0.5841                | 0.4414        | 0.5389              | 0.5214  |
+| **Accuracy Normalized**     | 0.6088                | 0.4440          | X                    | X       |
 
 ---
 
@@ -73,8 +71,4 @@ question = """Quale è la torre più famosa di Parigi?"""
 answer = generate_answer(question)
 print(answer)
 ```
----
-
-This model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
-
-[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
+---