Update README.md
Browse files
README.md
CHANGED
@@ -20,18 +20,12 @@ Original model: https://huggingface.co/mistral-community/Mixtral-8x22B-v0.1
|
|
20 |
|
21 |
## Prompt format
|
22 |
|
23 |
-
|
24 |
-
|
25 |
-
```
|
26 |
-
<s> [INST] <<SYS>>
|
27 |
-
{system_prompt}
|
28 |
-
<</SYS>>
|
29 |
-
|
30 |
-
{prompt} [/INST] </s>
|
31 |
-
```
|
32 |
|
33 |
## Download a file (not the whole branch) from below:
|
34 |
|
|
|
|
|
35 |
| Filename | Quant type | File Size | Description |
|
36 |
| -------- | ---------- | --------- | ----------- |
|
37 |
| [Mixtral-8x22B-v0.1-Q5_K_M.gguf](https://huggingface.co/bartowski/Mixtral-8x22B-v0.1-GGUF/blob/main/Mixtral-8x22B-v0.1-Q5_K_M-00001-of-00005.gguf) | Q5_K_M | 99.96GB | High quality, *recommended*. |
|
|
|
20 |
|
21 |
## Prompt format
|
22 |
|
23 |
+
This is a base model with no prompt format.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
24 |
|
25 |
## Download a file (not the whole branch) from below:
|
26 |
|
27 |
+
This is a very large model and has been split into parts to upload. Recent versions of llamacpp allow you to load part 1 and the rest will load as well. Make sure you download all parts of the chosen size.
|
28 |
+
|
29 |
| Filename | Quant type | File Size | Description |
|
30 |
| -------- | ---------- | --------- | ----------- |
|
31 |
| [Mixtral-8x22B-v0.1-Q5_K_M.gguf](https://huggingface.co/bartowski/Mixtral-8x22B-v0.1-GGUF/blob/main/Mixtral-8x22B-v0.1-Q5_K_M-00001-of-00005.gguf) | Q5_K_M | 99.96GB | High quality, *recommended*. |
|