saanikat commited on
Commit
8943500
·
1 Parent(s): 787b39b

config files

Browse files
README.md CHANGED
@@ -11,16 +11,19 @@ This repository hosts three pre-trained models desgined for metadata attribute s
11
  - label_encoder_bedbase.pkl # Unqiue label values derived from training data, model classifies the output into these labels for BEDBASE schema
12
  - model_bedbase.pth # BEDBASE schema trained model
13
  - vectorizer_bedbase.pkl # CountVectorizer instance from the `scikit-learn` library for Bag of Words encoding used as input to the model
 
14
  /encode
15
  - encode_schema_design.yaml #ENCODE schema
16
  - label_encoder_encode.pkl # Unqiue label values derived from training data, model classifies the output into these labels for ENCODE schema
17
  - model_encode.pth # ENCODE schema trained model
18
  - vectorizer_encode.pkl # CountVectorizer instance from the `scikit-learn` library for Bag of Words encoding used as input to the model
 
19
  /fairtracks
20
  - fairtracks_schema_design.yaml # FAIRTRACKS schema
21
  - label_encoder_fairtracks.pkl # Unqiue label values derived from training data, model classifies the output into these labels for FAIRTRACKS schema
22
  - model_fairtracks.pth #FAIRTRACKS schema trained model
23
  - vectorizer_fairtracks.pkl # CountVectorizer instance from the `scikit-learn` library for Bag of Words encoding used as input to the model
 
24
  ```
25
 
26
  ### Usage
@@ -43,4 +46,5 @@ To add a schema model:
43
  - label_encoder_new_schema.pkl
44
  - model_new_schema.pth
45
  - vectorizer_new_schema.pkl
 
46
  ```
 
11
  - label_encoder_bedbase.pkl # Unqiue label values derived from training data, model classifies the output into these labels for BEDBASE schema
12
  - model_bedbase.pth # BEDBASE schema trained model
13
  - vectorizer_bedbase.pkl # CountVectorizer instance from the `scikit-learn` library for Bag of Words encoding used as input to the model
14
+ - config_bedbase.yaml # Config file with model parameters
15
  /encode
16
  - encode_schema_design.yaml #ENCODE schema
17
  - label_encoder_encode.pkl # Unqiue label values derived from training data, model classifies the output into these labels for ENCODE schema
18
  - model_encode.pth # ENCODE schema trained model
19
  - vectorizer_encode.pkl # CountVectorizer instance from the `scikit-learn` library for Bag of Words encoding used as input to the model
20
+ - config_encode.yaml # Config file with model parameters
21
  /fairtracks
22
  - fairtracks_schema_design.yaml # FAIRTRACKS schema
23
  - label_encoder_fairtracks.pkl # Unqiue label values derived from training data, model classifies the output into these labels for FAIRTRACKS schema
24
  - model_fairtracks.pth #FAIRTRACKS schema trained model
25
  - vectorizer_fairtracks.pkl # CountVectorizer instance from the `scikit-learn` library for Bag of Words encoding used as input to the model
26
+ - config_fairtracks.yaml # Config file with model parameters
27
  ```
28
 
29
  ### Usage
 
46
  - label_encoder_new_schema.pkl
47
  - model_new_schema.pth
48
  - vectorizer_new_schema.pkl
49
+ - config_new_schema.yaml
50
  ```
bedbase/config_bedbase.yaml ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ params:
2
+ input_size_bow: 13708
3
+ embedding_size: 384
4
+ hidden_size: 32
5
+ output_size: 12
6
+ dropout_prob: 0.113
encode/config_encode.yaml ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ params:
2
+ input_size_bow: 10459
3
+ embedding_size: 384
4
+ hidden_size: 32
5
+ output_size: 18
6
+ dropout_prob: 0.113
fairtracks/config_fairtracks.yaml ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ params:
2
+ input_size_bow: 13617
3
+ embedding_size: 384
4
+ hidden_size: 32
5
+ output_size: 15
6
+ dropout_prob: 0.113