Update README.md
Browse files
README.md
CHANGED
@@ -34,6 +34,32 @@ GGML files are for CPU + GPU inference using [llama.cpp](https://github.com/gger
|
|
34 |
* [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/orca_mini_13B-GGML)
|
35 |
* [Unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/psmathur/orca_mini_13b)
|
36 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
37 |
<!-- compatibility_ggml start -->
|
38 |
## Compatibility
|
39 |
|
|
|
34 |
* [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/orca_mini_13B-GGML)
|
35 |
* [Unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/psmathur/orca_mini_13b)
|
36 |
|
37 |
+
## Prompt template: Alpaca with system message
|
38 |
+
|
39 |
+
|
40 |
+
```
|
41 |
+
### System:
|
42 |
+
You are an AI assistant that follows instruction extremely well. Help as much as you can.
|
43 |
+
|
44 |
+
### User:
|
45 |
+
prompt
|
46 |
+
|
47 |
+
### Response
|
48 |
+
```
|
49 |
+
or
|
50 |
+
```
|
51 |
+
### System:
|
52 |
+
You are an AI assistant that follows instruction extremely well. Help as much as you can.
|
53 |
+
|
54 |
+
### User:
|
55 |
+
prompt
|
56 |
+
|
57 |
+
### Input
|
58 |
+
input
|
59 |
+
|
60 |
+
### Response
|
61 |
+
```
|
62 |
+
|
63 |
<!-- compatibility_ggml start -->
|
64 |
## Compatibility
|
65 |
|