Hugging Face's logo

TheBloke
/
orca_mini_13B-GPTQ

Text Generation
Transformers
Safetensors
English
llama
text-generation-inference
4-bit precision
gptq
Model card Files Community
5
TheBloke commited on
Commit
1ef5236
•
1 Parent(s): 06d96bc

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -4
README.md CHANGED
@@ -36,7 +36,7 @@ It is the result of quantising to 4bit using [GPTQ-for-LLaMa](https://github.com
36
  * [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/orca_mini_13B-GGML)
37
  * [Unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/psmathur/orca_mini_13b)
38
 
39
- ## Prompt template: Alpaca with system message
40
 
41
  ```
42
  ### System:
@@ -45,7 +45,7 @@ You are an AI assistant that follows instruction extremely well. Help as much as
45
  ### User:
46
  prompt
47
 
48
- ### Response
49
  ```
50
  or
51
  ```
@@ -55,10 +55,10 @@ You are an AI assistant that follows instruction extremely well. Help as much as
55
  ### User:
56
  prompt
57
 
58
- ### Input
59
  input
60
 
61
- ### Response
62
  ```
63
 
64
  ## How to easily download and use this model in text-generation-webui
 
36
  * [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/orca_mini_13B-GGML)
37
  * [Unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/psmathur/orca_mini_13b)
38
 
39
+ ## Prompt template:
40
 
41
  ```
42
  ### System:
 
45
  ### User:
46
  prompt
47
 
48
+ ### Response:
49
  ```
50
  or
51
  ```
 
55
  ### User:
56
  prompt
57
 
58
+ ### Input:
59
  input
60
 
61
+ ### Response:
62
  ```
63
 
64
  ## How to easily download and use this model in text-generation-webui