TheBloke commited on
Commit
c97bd17
·
1 Parent(s): dd66c47

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +18 -0
README.md CHANGED
@@ -29,6 +29,24 @@ It is the result of quantising to 4bit using [GPTQ-for-LLaMa](https://github.com
29
  * [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/airoboros-13B-1.1-GGML)
30
  * [Unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/TheBloke/airoboros-13B-1.1-fp16)
31
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
32
  ## How to easily download and use this model in text-generation-webui
33
 
34
  Please make sure you're using the latest version of text-generation-webui
 
29
  * [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/airoboros-13B-1.1-GGML)
30
  * [Unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/TheBloke/airoboros-13B-1.1-fp16)
31
 
32
+ ## Prompt example
33
+
34
+ Please see the base Airoboros model README below, or by [going to the original model](https://huggingface.co/jondurbin/airoboros-13b-gpt4-1.1), for more details.
35
+ ```
36
+ BEGININPUT
37
+ BEGINCONTEXT
38
+ url: https://some.web.site/123
39
+ date: 2023-06-01
40
+ ... other metdata ...
41
+ ENDCONTEXT
42
+ [insert your text blocks here]
43
+ ENDINPUT
44
+ [add as many other blocks, in the exact same format]
45
+ BEGININSTRUCTION
46
+ [insert your instruction(s). The model was tuned with single questions, paragraph format, lists, etc.]
47
+ ENDINSTRUCTION
48
+ ```
49
+
50
  ## How to easily download and use this model in text-generation-webui
51
 
52
  Please make sure you're using the latest version of text-generation-webui