Commit
•
9252d50
1
Parent(s):
d9f5b5c
Update README.md
Browse files
README.md
CHANGED
|
@@ -11,6 +11,12 @@ tags:
|
|
| 11 |
- merge
|
| 12 |
- Yi
|
| 13 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14 |
# Yi 34B Merge v8
|
| 15 |
|
| 16 |
A merge of several Yi 34B 200K models using the new DARE Ties method via mergekit, quantized with exllamav2 on ~300K tokens of a sci-fi story, a fantasy story, and a vicuna chat for optimal long context storywriting performance.
|
|
|
|
| 11 |
- merge
|
| 12 |
- Yi
|
| 13 |
---
|
| 14 |
+
|
| 15 |
+
# **NOTE: THIS QUANTIZATION IS BROKEN**
|
| 16 |
+
|
| 17 |
+
See: https://huggingface.co/brucethemoose/Yi-34B-200K-DARE-megamerge-v8-31bpw-exl2-fiction/discussions/4#65a5eb3aee220af178d28541
|
| 18 |
+
|
| 19 |
+
|
| 20 |
# Yi 34B Merge v8
|
| 21 |
|
| 22 |
A merge of several Yi 34B 200K models using the new DARE Ties method via mergekit, quantized with exllamav2 on ~300K tokens of a sci-fi story, a fantasy story, and a vicuna chat for optimal long context storywriting performance.
|