Hugging Face's logo

TheBloke
/
orca_mini_7B-GGML

Transformers
English
Model card Files Community
2
TheBloke commited on
Commit
246420a
•
1 Parent(s): 8e32b70

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -5
README.md CHANGED
@@ -41,8 +41,7 @@ GGML files are for CPU + GPU inference using [llama.cpp](https://github.com/gger
41
  * [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/orca_mini_7B-GGML)
42
  * [Unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/psmathur/orca_mini_7b)
43
 
44
- ## Prompt template: Alpaca with system message
45
-
46
 
47
  ```
48
  ### System:
@@ -51,7 +50,7 @@ You are an AI assistant that follows instruction extremely well. Help as much as
51
  ### User:
52
  prompt
53
 
54
- ### Response
55
  ```
56
  or
57
  ```
@@ -61,10 +60,10 @@ You are an AI assistant that follows instruction extremely well. Help as much as
61
  ### User:
62
  prompt
63
 
64
- ### Input
65
  input
66
 
67
- ### Response
68
  ```
69
 
70
  <!-- compatibility_ggml start -->
 
41
  * [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/orca_mini_7B-GGML)
42
  * [Unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/psmathur/orca_mini_7b)
43
 
44
+ ## Prompt template:
 
45
 
46
  ```
47
  ### System:
 
50
  ### User:
51
  prompt
52
 
53
+ ### Response:
54
  ```
55
  or
56
  ```
 
60
  ### User:
61
  prompt
62
 
63
+ ### Input:
64
  input
65
 
66
+ ### Response:
67
  ```
68
 
69
  <!-- compatibility_ggml start -->