Commit
•
b17b8fb
1
Parent(s):
0d9bcbb
Update README.md
Browse files
README.md
CHANGED
|
@@ -31,6 +31,8 @@ This model is based on Qwen2-1.5b, and is governed by the Apache-2.0
|
|
| 31 |
|
| 32 |
The base model has 128k context, and the full-weight fine-tuning was with 16k sequence length.
|
| 33 |
|
|
|
|
|
|
|
| 34 |
|
| 35 |
example:
|
| 36 |
|
|
|
|
| 31 |
|
| 32 |
The base model has 128k context, and the full-weight fine-tuning was with 16k sequence length.
|
| 33 |
|
| 34 |
+
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.
|
| 35 |
+
|
| 36 |
|
| 37 |
example:
|
| 38 |
|