Doctor-Shotgun
commited on
Commit
•
5f19259
1
Parent(s):
c2dabd4
Update README.md
Browse files
README.md
CHANGED
@@ -17,7 +17,7 @@ Note that all modules were trained, including 'gate'. There are some reports tha
|
|
17 |
|
18 |
Not extensively tested for quality, YMMV. Would try with temp ~1.5-2 and min-p of ~0.03-0.05 since mixtral does appear to be highly confident on its responses.
|
19 |
|
20 |
-
[EXL2 Quants](https://huggingface.co/Doctor-Shotgun/Mixtral-8x7B-Instruct-
|
21 |
|
22 |
## Usage:
|
23 |
The intended prompt format is the Alpaca instruction format of LimaRP v3:
|
|
|
17 |
|
18 |
Not extensively tested for quality, YMMV. Would try with temp ~1.5-2 and min-p of ~0.03-0.05 since mixtral does appear to be highly confident on its responses.
|
19 |
|
20 |
+
[EXL2 Quants](https://huggingface.co/Doctor-Shotgun/Mixtral-8x7B-Instruct-v0.1-limarp-exl2)
|
21 |
|
22 |
## Usage:
|
23 |
The intended prompt format is the Alpaca instruction format of LimaRP v3:
|