LoneStriker
commited on
Commit
•
28d75ae
1
Parent(s):
6027400
Added note on repetition penalty setting
Browse files
README.md
CHANGED
@@ -9,7 +9,7 @@ datasets:
|
|
9 |
# Fine-tune of Y-34B with Spicyboros-3.1
|
10 |
One epoch of fine tuning with @jondurbin's SpicyBoros-3.1 dataset. 4.65bpw should fit on a single 3090/4090, 5.0bpw, 6.0bpw, and 8.0bpw will require more than one GPU 24 GB VRAM GPU.
|
11 |
|
12 |
-
**Please note
|
13 |
|
14 |
# Original Yi-34B Model Card Below
|
15 |
<div align="center">
|
|
|
9 |
# Fine-tune of Y-34B with Spicyboros-3.1
|
10 |
One epoch of fine tuning with @jondurbin's SpicyBoros-3.1 dataset. 4.65bpw should fit on a single 3090/4090, 5.0bpw, 6.0bpw, and 8.0bpw will require more than one GPU 24 GB VRAM GPU.
|
11 |
|
12 |
+
**Please note:** you may have to turn down repetition penalty to 1.0. The model seems to get into "thesaurus" mode sometimes without this change.
|
13 |
|
14 |
# Original Yi-34B Model Card Below
|
15 |
<div align="center">
|