Commit
•
9a8df92
1
Parent(s):
041d2fc
Update README.md (#1)
Browse files- Update README.md (f61de924c92d97d001a8ef1e9311fa983de6f79c)
Co-authored-by: Samuele Colombo <FinancialSupport@users.noreply.huggingface.co>
README.md
CHANGED
|
@@ -36,6 +36,15 @@ This is the model card of a 🤗 transformers model that has been pushed on the
|
|
| 36 |
- **License:** cc-by-nc-sa-4.0
|
| 37 |
- **Finetuned from model:** [Minerva-3B-base-v1.0](https://huggingface.co/sapienzanlp/Minerva-3B-base-v1.0), developed by [Sapienza NLP](https://nlp.uniroma1.it) in collaboration with [Future Artificial Intelligence Research (FAIR)](https://fondazione-fair.it/) and [CINECA](https://www.cineca.it/)
|
| 38 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 39 |
|
| 40 |
### Sample Code
|
| 41 |
|
|
|
|
| 36 |
- **License:** cc-by-nc-sa-4.0
|
| 37 |
- **Finetuned from model:** [Minerva-3B-base-v1.0](https://huggingface.co/sapienzanlp/Minerva-3B-base-v1.0), developed by [Sapienza NLP](https://nlp.uniroma1.it) in collaboration with [Future Artificial Intelligence Research (FAIR)](https://fondazione-fair.it/) and [CINECA](https://www.cineca.it/)
|
| 38 |
|
| 39 |
+
## Evaluation
|
| 40 |
+
|
| 41 |
+
For a detailed comparison of model performance, check out the [Leaderboard for Italian Language Models](https://huggingface.co/spaces/FinancialSupport/open_ita_llm_leaderboard).
|
| 42 |
+
|
| 43 |
+
Here's a breakdown of the performance metrics:
|
| 44 |
+
| Metric | hellaswag_it acc_norm | arc_it acc_norm | m_mmlu_it 5-shot acc | Average |
|
| 45 |
+
|:----------------------------|:----------------------|:----------------|:---------------------|:--------|
|
| 46 |
+
| **Accuracy Normalized** | 0.5187 | 0.3045 | 0.2612 | 0.361 |
|
| 47 |
+
|
| 48 |
|
| 49 |
### Sample Code
|
| 50 |
|