Files changed (1) hide show
  1. README.md +12 -6
README.md CHANGED
@@ -2,11 +2,17 @@
2
  license: creativeml-openrail-m
3
  language:
4
  - en
5
- thumbnail:
6
  tags:
7
  - text generation
8
  - conversational
9
  inference: false
 
 
 
 
 
 
10
  ---
11
 
12
  # Pygmalion 6B
@@ -38,22 +44,22 @@ We provide a notebook with a Gradio UI for playing around with the model without
38
  The model can be used as a regular text generation model, but it'll perform best if the input prompt adheres to the following format:
39
 
40
  ```
41
- [CHARACTER]'s Persona: [A few sentences about the character you want the model to play]
42
  <START>
43
  [DIALOGUE HISTORY]
44
  You: [Your input message here]
45
  [CHARACTER]:
46
  ```
47
 
48
- Where `[CHARACTER]` is, as you can probably guess, the name of the character you want the model to portray, `<START>` should be used verbatim as a delimiter token to separate persona and scenario data from the dialogue, and `[DIALOGUE HISTORY]` is chat history so the model can have some conversational context to draw from. Ideally it'll be pairs of messages like:
49
 
50
  ```
51
- [CHARACTER]: [some dialogue here]
52
- You: [your response to the dialogue above]
53
  ```
54
 
55
  Apart from chat history, you can also just add example conversations in `[DIALOGUE HISTORY]` to show how the character should speak - ideally at the beginning, so it doesn't get confused as to what's conversation history vs. character definition.
56
 
57
  ## Known issues
58
 
59
- We haven't played around with the model enough to enumerate them. Feel free to give us some feedback!
 
2
  license: creativeml-openrail-m
3
  language:
4
  - en
5
+ thumbnail: null
6
  tags:
7
  - text generation
8
  - conversational
9
  inference: false
10
+ datasets:
11
+ - fka/awesome-chatgpt-prompts
12
+ metrics:
13
+ - accuracy
14
+ library_name: allennlp
15
+ pipeline_tag: text-classification
16
  ---
17
 
18
  # Pygmalion 6B
 
44
  The model can be used as a regular text generation model, but it'll perform best if the input prompt adheres to the following format:
45
 
46
  ```
47
+ [evfra de tershaav]'s Persona: [the leader of the angara resistance on aya, a pragmatic man with a tradgic past. ]
48
  <START>
49
  [DIALOGUE HISTORY]
50
  You: [Your input message here]
51
  [CHARACTER]:
52
  ```
53
 
54
+ Where `[evfra]` is, as you can probably guess, the name of the character you want the model to portray, `<START>` should be used verbatim as a delimiter token to separate persona and scenario data from the dialogue, and `[DIALOGUE HISTORY]` is chat history so the model can have some conversational context to draw from. Ideally it'll be pairs of messages like:
55
 
56
  ```
57
+ [evfra]: [what do you want human]
58
+ You: [i stuttered to respond to his agitated question" im here from the nexus to br your map maker]
59
  ```
60
 
61
  Apart from chat history, you can also just add example conversations in `[DIALOGUE HISTORY]` to show how the character should speak - ideally at the beginning, so it doesn't get confused as to what's conversation history vs. character definition.
62
 
63
  ## Known issues
64
 
65
+ We haven't played around with the model enough to enumerate them. Feel free to give us some feedback!