m-polignano-uniba
commited on
Update README.md
Browse files
README.md
CHANGED
@@ -245,11 +245,11 @@ The 🌟**ANITA project**🌟 *(**A**dvanced **N**atural-based interaction for t
|
|
245 |
|
246 |
## Specifications
|
247 |
|
248 |
-
- **Model developers
|
249 |
-
- **Variations
|
250 |
-
- **Input
|
251 |
-
- **Output
|
252 |
-
- **Model Architecture
|
253 |
- **Context length**: 8K, 8192.
|
254 |
<hr>
|
255 |
|
|
|
245 |
|
246 |
## Specifications
|
247 |
|
248 |
+
- **Model developers**: Ph.D. Marco Polignano - University of Bari Aldo Moro, Italy
|
249 |
+
- **Variations**: The model release has been **supervised fine-tuning (SFT)** using **QLoRA** in the 4bit version, on a long list of instruction-based datasets. **ORPO** approach over the *mlabonne/orpo-dpo-mix-40k* dataset is used to align with human preferences for helpfulness and safety.
|
250 |
+
- **Input**: Models input text only.
|
251 |
+
- **Output**: Models generate text and code only.
|
252 |
+
- **Model Architecture**: *Llama 3 architecture*.
|
253 |
- **Context length**: 8K, 8192.
|
254 |
<hr>
|
255 |
|