Commit
•
0825072
1
Parent(s):
9ea2367
Update README.md (#5)
Browse files- Update README.md (3bf936099ef81dc24c9c9fc231a2d17d4f6fb672)
Co-authored-by: Dan Saattrup Nielsen <saattrupdan@users.noreply.huggingface.co>
README.md
CHANGED
|
@@ -1,5 +1,6 @@
|
|
| 1 |
---
|
| 2 |
license: other
|
|
|
|
| 3 |
---
|
| 4 |
<!-- header start -->
|
| 5 |
<div style="width: 100%;">
|
|
@@ -96,4 +97,4 @@ A preliminary evaluation of the model quality is conducted by creating a set of
|
|
| 96 |
|
| 97 |
## Major updates of weights v1.1
|
| 98 |
- 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.
|
| 99 |
-
- 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%;">
|
|
|
|
| 97 |
|
| 98 |
## Major updates of weights v1.1
|
| 99 |
- 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.
|
| 100 |
+
- Fix the supervised fine-tuning loss computation for better model quality.
|