Commit
ยท
c4eef06
1
Parent(s):
bad6273
Update README.md
Browse files
README.md
CHANGED
@@ -16,13 +16,22 @@ tags:
|
|
16 |
|
17 |
Model Card for Loquace-12B
|
18 |
|
19 |
-
# Loquace ๐ฎ๐น An Italian instruction finetuned
|
20 |
|
21 |
## Model Description
|
22 |
|
23 |
Loquace-12B is the first 12B italian Large Language Model trained using QLoRa on a large dataset of 102k question/answer pairs
|
24 |
exclusively in Italian.
|
25 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
26 |
## Usage
|
27 |
|
28 |
|
|
|
16 |
|
17 |
Model Card for Loquace-12B
|
18 |
|
19 |
+
# Loquace ๐ฎ๐น An exclusively Italian speaking, instruction finetuned, Large Language model. ๐ฎ๐น
|
20 |
|
21 |
## Model Description
|
22 |
|
23 |
Loquace-12B is the first 12B italian Large Language Model trained using QLoRa on a large dataset of 102k question/answer pairs
|
24 |
exclusively in Italian.
|
25 |
|
26 |
+
|
27 |
+
Loquace-12B is part of the big Loquace family:
|
28 |
+
|
29 |
+
https://huggingface.co/cosimoiaia/Loquace-70m - Based on pythia-70m
|
30 |
+
https://huggingface.co/cosimoiaia/Loquace-410m - Based on pythia-410m
|
31 |
+
https://huggingface.co/cosimoiaia/Loquace-7B - Based on Falcon-7B, the most performing model of it's class.
|
32 |
+
https://huggingface.co/cosimoiaia/Loquace-12B - Based on pythia-12B
|
33 |
+
https://huggingface.co/cosimoiaia/Loquace-20B - Based on gpt-neox-20B
|
34 |
+
|
35 |
## Usage
|
36 |
|
37 |
|