pszemraj commited on
Commit
374785c
1 Parent(s): 1546be8

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -3
README.md CHANGED
@@ -41,7 +41,7 @@ inference:
41
  do_sample: True
42
  top_p: 0.95
43
  top_k: 20
44
- temperature: 0.5
45
  repetition_penalty: 3.5
46
 
47
  ---
@@ -55,11 +55,14 @@ It achieves the following results on the evaluation set:
55
 
56
  ## Model description
57
 
58
- - it is a splendid model
 
 
59
 
60
  ## Intended uses & limitations
61
 
62
- - [ai-msgbot](https://github.com/pszemraj/ai-msgbot)
 
63
 
64
  ## Training and evaluation data
65
 
 
41
  do_sample: True
42
  top_p: 0.95
43
  top_k: 20
44
+ temperature: 0.3
45
  repetition_penalty: 3.5
46
 
47
  ---
 
55
 
56
  ## Model description
57
 
58
+ - a basic dialogue model for conversation. It can be used as a chatbot.
59
+ - check out a [simple demo here](https://huggingface.co/spaces/ethzanalytics/dialogue-demo)
60
+
61
 
62
  ## Intended uses & limitations
63
 
64
+ - usage is designed for integrating with this repo: [ai-msgbot](https://github.com/pszemraj/ai-msgbot)
65
+ - the main specific information to know is that the model generates whole conversations between two entities, `person alpha` and `person beta`. These entity names are used functionally as custom `<bos>` tokens to extract when one response ends and another begins.
66
 
67
  ## Training and evaluation data
68