Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: llama2
|
3 |
+
language:
|
4 |
+
- en
|
5 |
+
---
|
6 |
+
|
7 |
+
# WinterGoddess-1.4x-70B-L2 IQ2-GGUF
|
8 |
+
|
9 |
+
## Description
|
10 |
+
IQ2-GGUF quants of [sophosympatheia/Aurora-Nights-70B-v1.0](https://huggingface.co/sophosympatheia/Aurora-Nights-70B-v1.0)
|
11 |
+
|
12 |
+
Unlike regular GGUF quants this uses important matrix similar to Quip# to keep the quant from degrading too much even at 2bpw allowing you to run larger models on less powerful machines.
|
13 |
+
|
14 |
+
***NOTE:*** As of uploading these this llamacpp can run these quants but i am unsure what guis like oobabooga / koboldcpp can run them.
|
15 |
+
|
16 |
+
[More info](https://github.com/ggerganov/llama.cpp/pull/4897)
|
17 |
+
|
18 |
+
|
19 |
+
# Models
|
20 |
+
|
21 |
+
Models: [IQ2-XS](), [IQ2-XXS]()
|
22 |
+
|
23 |
+
Regular GGUF Quants: [Here](https://huggingface.co/TheBloke/WinterGoddess-1.4x-70B-L2-GGUF)
|
24 |
+
|
25 |
+
## Prompt Format
|
26 |
+
|
27 |
+
Unclear
|
28 |
+
|
29 |
+
|
30 |
+
## Contact
|
31 |
+
Kooten on discord
|