basiliskinstitute
commited on
Commit
•
82477bd
1
Parent(s):
4bf6585
Update README.md
Browse files
README.md
CHANGED
@@ -1,4 +1,4 @@
|
|
1 |
---
|
2 |
license: llama3
|
3 |
---
|
4 |
-
Chatml format. The dataset is about 1400 entries ranging from 8-16k. It's split three ways between long context multi turn chat, long context summarization, and writing analysis. Full fine tune using linear a rope scale factor of 2.0. Trained for five epochs with a learning rate of
|
|
|
1 |
---
|
2 |
license: llama3
|
3 |
---
|
4 |
+
Chatml format. The dataset is about 1400 entries ranging from 8-16k. It's split three ways between long context multi turn chat, long context summarization, and writing analysis. Full fine tune using linear a rope scale factor of 2.0. Trained for five epochs with a learning rate of 1e-5.
|