Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# MiquMaid-v1-70B 6bpw
|
| 2 |
+
|
| 3 |
+
## Description
|
| 4 |
+
Exllama quant of [NeverSleep/MiquMaid-v1-70B](https://huggingface.co/NeverSleep/MiquMaid-v1-70B)
|
| 5 |
+
|
| 6 |
+
## Other quants:
|
| 7 |
+
EXL2: [6bpw](https://huggingface.co/Kooten/MiquMaid-v1-70B-6bpw-exl2), [5bpw](https://huggingface.co/Kooten/MiquMaid-v1-70B-5bpw-exl2), [4bpw](https://huggingface.co/Kooten/MiquMaid-v1-70B-4bpw-exl2), [3.5bpw](https://huggingface.co/Kooten/MiquMaid-v1-70B-3.5bpw-exl2), [3bpw](https://huggingface.co/Kooten/MiquMaid-v1-70B-3bpw-exl2), [2.4bpw](https://huggingface.co/Kooten/MiquMaid-v1-70B-2.4bpw-exl2)
|
| 8 |
+
|
| 9 |
+
2.4bpw is probably the most you can fit in a 24gb card
|
| 10 |
+
|
| 11 |
+
GGUF:
|
| 12 |
+
[2bit Imatrix GGUF](https://huggingface.co/Kooten/MiquMaid-v1-70B-IQ2-GGUF)
|
| 13 |
+
|
| 14 |
+
### Custom format:
|
| 15 |
+
```
|
| 16 |
+
### Instruction:
|
| 17 |
+
{system prompt}
|
| 18 |
+
|
| 19 |
+
### Input:
|
| 20 |
+
{input}
|
| 21 |
+
|
| 22 |
+
### Response:
|
| 23 |
+
{reply}
|
| 24 |
+
```
|
| 25 |
+
|
| 26 |
+
## Contact
|
| 27 |
+
Kooten on discord
|
| 28 |
+
|
| 29 |
+
[ko-fi.com/kooten](https://ko-fi.com/kooten)
|