Commit
•
2a5cbf2
1
Parent(s):
fe48a35
Update README.md
Browse files
README.md
CHANGED
|
@@ -20,6 +20,8 @@ To produce a valuable model, we follow the same procedure proposed in: https://a
|
|
| 20 |
We use default script parameters and select a sample of 100,000 examples in the Italian language. We decided to sample data from the Filtered Oscar Dataset for
|
| 21 |
the Italian Language released by Sarti.
|
| 22 |
|
|
|
|
|
|
|
| 23 |
- **Developed by:** Pierpaolo Basile, Pierluigi Cassotti, Marco Polignano, Lucia Siciliani, Giovanni Semeraro. Department of Computer Science, University of Bari Aldo Moro, Italy
|
| 24 |
- **Model type:** BLOOM
|
| 25 |
- **Language(s) (NLP):** Italian
|
|
|
|
| 20 |
We use default script parameters and select a sample of 100,000 examples in the Italian language. We decided to sample data from the Filtered Oscar Dataset for
|
| 21 |
the Italian Language released by Sarti.
|
| 22 |
|
| 23 |
+
**It is important to underline that when you use the adapted LLM is necessary to use the tokenizer of the adapted model.**
|
| 24 |
+
|
| 25 |
- **Developed by:** Pierpaolo Basile, Pierluigi Cassotti, Marco Polignano, Lucia Siciliani, Giovanni Semeraro. Department of Computer Science, University of Bari Aldo Moro, Italy
|
| 26 |
- **Model type:** BLOOM
|
| 27 |
- **Language(s) (NLP):** Italian
|