Commit
•
d3d62d3
1
Parent(s):
1f203bc
Update README.md
Browse files
README.md
CHANGED
|
@@ -27,7 +27,7 @@ This model is based on Qwen2-0.5b, and is governed by the Apache-2.0
|
|
| 27 |
|
| 28 |
The base model has 128k context, and the full-weight fine-tuning was with 16k sequence length.
|
| 29 |
|
| 30 |
-
Due to the complexities of fine tuning smaller models on datasets created by/for larger models - we removed
|
| 31 |
|
| 32 |
|
| 33 |
example:
|
|
|
|
| 27 |
|
| 28 |
The base model has 128k context, and the full-weight fine-tuning was with 16k sequence length.
|
| 29 |
|
| 30 |
+
Due to the complexities of fine tuning smaller models on datasets created by/for larger models - we removed coding, function calling and systemchat-multilingual datasets when tuning these models.
|
| 31 |
|
| 32 |
|
| 33 |
example:
|