Update README.md
Browse files
README.md
CHANGED
@@ -1,4 +1,21 @@
|
|
1 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
|
3 |
```bash
|
4 |
cd llama.cpp
|
|
|
1 |
+
This is the Q3_K_M GGUF port of the [lightblue/Karasu-Mixtral-8x22B-v0.1](https://huggingface.co/lightblue/Karasu-Mixtral-8x22B-v0.1) model.
|
2 |
+
|
3 |
+
|
4 |
+
### How to use
|
5 |
+
|
6 |
+
The easiest way to run this would be to download [LM Studio](https://lmstudio.ai/) and search for this model on the search bar.
|
7 |
+
|
8 |
+
Other ways to run this directly are using the llama.cpp package.
|
9 |
+
|
10 |
+
```bash
|
11 |
+
git clone https://github.com/ggerganov/llama.cpp
|
12 |
+
cd llama.cpp
|
13 |
+
make
|
14 |
+
huggingface-cli download lightblue/Karasu-Mixtral-8x22B-v0.1-gguf --local-dir /some/folder/
|
15 |
+
./main -m /some/folder/Karasu-Mixtral-8x22B-v0.1-Q3_K_M-00001-of-00005.gguf -p "<s>[INST] Tell me a really funny joke. No puns! [/INST]" -n 256 -e
|
16 |
+
```
|
17 |
+
|
18 |
+
### Commands to make this:
|
19 |
|
20 |
```bash
|
21 |
cd llama.cpp
|