Update README.md
#5
by
saattrupdan
- opened
README.md
CHANGED
|
@@ -1,5 +1,6 @@
|
|
| 1 |
---
|
| 2 |
license: other
|
|
|
|
| 3 |
---
|
| 4 |
<!-- header start -->
|
| 5 |
<div style="width: 100%;">
|
|
@@ -98,4 +99,4 @@ A preliminary evaluation of the model quality is conducted by creating a set of
|
|
| 98 |
|
| 99 |
## Major updates of weights v1.1
|
| 100 |
- Refactor the tokenization and separator. In Vicuna v1.1, the separator has been changed from `"###"` to the EOS token `"</s>"`. This change makes it easier to determine the generation stop criteria and enables better compatibility with other libraries.
|
| 101 |
-
- Fix the supervised fine-tuning loss computation for better model quality.
|
|
|
|
| 1 |
---
|
| 2 |
license: other
|
| 3 |
+
pipeline_tag: conversational
|
| 4 |
---
|
| 5 |
<!-- header start -->
|
| 6 |
<div style="width: 100%;">
|
|
|
|
| 99 |
|
| 100 |
## Major updates of weights v1.1
|
| 101 |
- Refactor the tokenization and separator. In Vicuna v1.1, the separator has been changed from `"###"` to the EOS token `"</s>"`. This change makes it easier to determine the generation stop criteria and enables better compatibility with other libraries.
|
| 102 |
+
- Fix the supervised fine-tuning loss computation for better model quality.
|