leonardlin
commited on
Commit
•
382729b
1
Parent(s):
1b5a059
Update README.md
Browse files
README.md
CHANGED
@@ -23,7 +23,7 @@ It also uses NEFTune, although the expected impact is neglible for this dataset.
|
|
23 |
|
24 |
While the 2e-5 model matched gpt-3.5-turbo performance, this 2e-6 version consistently edges it out, so I think it's fair to say that this model "beats" it.
|
25 |
|
26 |
-
While this is merely a test ablation on the road to `shisa-v2`, as the strongest commercially-usable open JA model benchmarked so far, this model may be of general interest.
|
27 |
|
28 |
|
29 |
## Performance
|
|
|
23 |
|
24 |
While the 2e-5 model matched gpt-3.5-turbo performance, this 2e-6 version consistently edges it out, so I think it's fair to say that this model "beats" it.
|
25 |
|
26 |
+
While this is merely a test ablation on the road to `shisa-v2`, as of its release (mid-May 2024), it's the strongest commercially-usable open JA model benchmarked so far, so this model may be of general interest.
|
27 |
|
28 |
|
29 |
## Performance
|