Update README.md
Browse files
README.md
CHANGED
@@ -27,9 +27,8 @@ New files inference up to 10% faster without any quality reduction.
|
|
27 |
- Main files are based on v1.1 release
|
28 |
- See changelog below
|
29 |
- Use prompt template: ```HUMAN: <prompt> ASSISTANT: <response>```
|
30 |
-
- Uncensored files are based on v0 release
|
31 |
- Use prompt template: ```### User: <prompt> ### Assistant: <response>```
|
32 |
-
- PR #896 was used for q4_0. Everything else is latest as of upload time.
|
33 |
|
34 |
### Quantization
|
35 |
Several quantization methods are supported. They differ in the resulting model disk size and inference speed.
|
|
|
27 |
- Main files are based on v1.1 release
|
28 |
- See changelog below
|
29 |
- Use prompt template: ```HUMAN: <prompt> ASSISTANT: <response>```
|
30 |
+
- Uncensored files are based on a modified v0 release
|
31 |
- Use prompt template: ```### User: <prompt> ### Assistant: <response>```
|
|
|
32 |
|
33 |
### Quantization
|
34 |
Several quantization methods are supported. They differ in the resulting model disk size and inference speed.
|