Commit
•
16fafb6
1
Parent(s):
cc64495
Update README.md
Browse files
README.md
CHANGED
|
@@ -8,8 +8,13 @@ library_name: transformers
|
|
| 8 |
pipeline_tag: text-generation
|
| 9 |
tags:
|
| 10 |
- text-generation-inference
|
|
|
|
| 11 |
---
|
| 12 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13 |
**Dolphin-2.2-yi-34b-200k**, **Nous-Capybara-34B**, **Tess-M-v1.4**, **Airoboros-3_1-yi-34b-200k**, **PlatYi-34B-200K-Q**, and **Una-xaberius-34b-v1beta** merged with a new, experimental implementation of "dare ties" via mergekit.
|
| 14 |
|
| 15 |
Quantized with the git version of exllamav2 with 200 rows (400K tokens) on a long Orca-Vicuna format chat, a selected sci fi story and a fantasy story. This should hopefully yield better chat/storytelling performance than the short, default wikitext quantization.
|
|
|
|
| 8 |
pipeline_tag: text-generation
|
| 9 |
tags:
|
| 10 |
- text-generation-inference
|
| 11 |
+
- merge
|
| 12 |
---
|
| 13 |
|
| 14 |
+
### Obsolete, see https://huggingface.co/brucethemoose/Yi-34B-200K-DARE-merge-v5
|
| 15 |
+
|
| 16 |
+
***
|
| 17 |
+
|
| 18 |
**Dolphin-2.2-yi-34b-200k**, **Nous-Capybara-34B**, **Tess-M-v1.4**, **Airoboros-3_1-yi-34b-200k**, **PlatYi-34B-200K-Q**, and **Una-xaberius-34b-v1beta** merged with a new, experimental implementation of "dare ties" via mergekit.
|
| 19 |
|
| 20 |
Quantized with the git version of exllamav2 with 200 rows (400K tokens) on a long Orca-Vicuna format chat, a selected sci fi story and a fantasy story. This should hopefully yield better chat/storytelling performance than the short, default wikitext quantization.
|