Commit
•
246fbd2
1
Parent(s):
077cd4f
Upload ./README.md with huggingface_hub
Browse files
README.md
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: cc-by-nc-4.0
|
| 3 |
+
---
|
| 4 |
+
### exl2 quant (measurement.json in main branch)
|
| 5 |
+
---
|
| 6 |
+
### check revisions for quants
|
| 7 |
+
---
|
| 8 |
+
|
| 9 |
+
|
| 10 |
+
A model trained on a dataset of 1.35 million rows of Yahoo Answers Q and A. ( https://huggingface.co/datasets/community-datasets/yahoo_answers_topics ) It does not chat well and will fall apart at longer contexts, but it does give unique responses.
|
| 11 |
+
It also believes the year is 2006... so yea, have fun!
|
| 12 |
+
|
| 13 |
+
Model uses ChatML formatting and works "best" with single round QA. System prompt is "You are a helpful assistant."
|
| 14 |
+
|
| 15 |
+
|
| 16 |
+
|