Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- Solar
|
5 |
+
- Mistral
|
6 |
+
- Roleplay
|
7 |
+
---
|
8 |
+
|
9 |
+
# DaringLotus-10.7B 6bpw EXL2
|
10 |
+
|
11 |
+
## Description
|
12 |
+
EXL2 quant of [BlueNipples/DaringLotus-10.7B](https://huggingface.co/BlueNipples/DaringLotus-10.7B)
|
13 |
+
|
14 |
+
-6bpw should be comfortable on 12 gb with 8k context
|
15 |
+
-4bpw might just fit on 8gb of vram at 4k context
|
16 |
+
if yo have more ram get the 8bpw
|
17 |
+
|
18 |
+
|
19 |
+
## Other quants:
|
20 |
+
EXL2: [8bpw](https://huggingface.co/Kooten/DaringLotus-8bpw-exl2), [6bpw](https://huggingface.co/Kooten/DaringLotus-6bpw-exl2), [5bpw](https://huggingface.co/Kooten/DaringLotus-5bpw-exl2), [4bpw](https://huggingface.co/Kooten/DaringLotus-4bpw-exl2)
|
21 |
+
|
22 |
+
|
23 |
+
## Prompt Format
|
24 |
+
### Alpaca:
|
25 |
+
I am not entirely certain of this but i think alpaca is correct for this model
|
26 |
+
|
27 |
+
```
|
28 |
+
Below is an instruction that describes a task. Write a response that appropriately completes the request.
|
29 |
+
|
30 |
+
### Instruction:
|
31 |
+
{prompt}
|
32 |
+
|
33 |
+
### Input:
|
34 |
+
{input}
|
35 |
+
|
36 |
+
### Response:
|
37 |
+
|
38 |
+
```
|
39 |
+
|
40 |
+
## Contact
|
41 |
+
Kooten on discord
|