bartowski commited on
Commit
a90a1cd
1 Parent(s): 4ec2d62

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -9
README.md CHANGED
@@ -20,18 +20,12 @@ Original model: https://huggingface.co/mistral-community/Mixtral-8x22B-v0.1
20
 
21
  ## Prompt format
22
 
23
- No chat template specified so default is used. This may be incorrect, check original model card for details.
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*. |