Commit
•
94b7b75
1
Parent(s):
f854f89
Update README.md
Browse files
README.md
CHANGED
@@ -21,7 +21,10 @@ Model Card for Loquace-410m
|
|
21 |
An exclusively Italian speaking, instruction finetuned, Large Language model. 🇮🇹
|
22 |
|
23 |
The Loquace Italian LLM models family was created as a proof-of-concept to evaluate on how different model sizes can be fine-tuned using QLoRa on an instruct dataset
|
24 |
-
of a specific language.
|
|
|
|
|
|
|
25 |
|
26 |
## Model Description
|
27 |
|
|
|
21 |
An exclusively Italian speaking, instruction finetuned, Large Language model. 🇮🇹
|
22 |
|
23 |
The Loquace Italian LLM models family was created as a proof-of-concept to evaluate on how different model sizes can be fine-tuned using QLoRa on an instruct dataset
|
24 |
+
of a specific language.
|
25 |
+
|
26 |
+
The QLoRa (https://github.com/artidoro/qlora) method of fine-tuning significantly lower the resources requirements compared to any other methods available,
|
27 |
+
this allow to easily execute the process on significanly larger dataset while still using consumers GPUs and still achieve high accuracy.
|
28 |
|
29 |
## Model Description
|
30 |
|