Kevin99z commited on
Commit
bd3d3be
·
1 Parent(s): dc8aff5

Upload ChatgptRec

Browse files
Files changed (1) hide show
  1. config.json +15 -0
config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "WEIGHT_DIMENSIONS": {},
3
+ "answer_mask": "<movie>",
4
+ "answer_type": "movie",
5
+ "backup_prompt": {
6
+ "content": " It look like the previous response is a a template with some <movie> mask. Now please fills in with actual names of movie. Your answer should be formatted as a string separated by comma. For example if there are three <movie> in the template, and you want to fill them with \"Inception\", \"The Matrix\", and \"The Dark Knight\", then your answer should be formatted as: \"\"\"Inception,The Matrix,The Dark Knight\"\"\" Do not include anything except the formatted string.",
7
+ "role": "user"
8
+ },
9
+ "model_name": "gpt-4",
10
+ "prompt": {
11
+ "content": " It look like your previous response is a a template with some <movie> mask. Now please fills in with actual names of movie. Your answer should be formatted as a json object with a link to the movies wiki page so that I could directly parse it. For example if there are two <movie> in the template, and you want to fill them with \"Inception\" and \"The Matrix\", then your answer should be formatted as follows: [{\"name\": \"Inception\", \"uri\": \"https://en.wikipedia.org/wiki/Inception\"}, {\"name\": \"The Matrix\", \"uri\": \"https://en.wikipedia.org/wiki/The_Matrix\"}] The returned object should has the same number of movie as in your previous response. Do not include anything outside the json object.",
12
+ "role": "user"
13
+ },
14
+ "transformers_version": "4.33.2"
15
+ }