r

app.py

@@ -1,37 +1,37 @@
 import ktrain
 from gradio import Interface, Parallel, TabbedInterface
 
-examples = [
+vs_examples = [
 	["I only get my kids the ones I got....I've turned down many so called 'vaccines'"], 
 	["In child protective services, further providing for definitions, for immunity from liability"], 
 	["Lol what? Measles is a real thing. Get vaccinated"]]
-title = "Vaccine Sentiment Task - VS2"
-desc = "Enter vaccine-related tweets to generate sentiment from 3 models (BERT, MentalBERT, PHS-BERT). Label 0='vaccine critical', 1='neutral', 2='vaccine supportive'. The three provided examples have true labels 0,1,2 respectively. For details about VS2, please refer to our paper (linked provided in the corresponding Hugging Face repository)."
+vs_title = "Vaccine Sentiment Task - VS2"
+vs_desc = "Enter vaccine-related tweets to generate sentiment from 3 models (BERT, MentalBERT, PHS-BERT). Label 0='vaccine critical', 1='neutral', 2='vaccine supportive'. The three provided examples have true labels 0,1,2 respectively. For details about VS2, please refer to our paper (linked provided in the corresponding Hugging Face repository)."
 
-predictor_bert = ktrain.load_predictor('bert')
-predictor_mental = ktrain.load_predictor('mentalbert')
-predictor_phs = ktrain.load_predictor('phsbert')
+vs_predictor_bert = ktrain.load_predictor('vs/bert')
+vs_predictor_mental = ktrain.load_predictor('vs/mentalbert')
+vs_predictor_phs = ktrain.load_predictor('vs/phsbert')
 
-def BERT(text):
-	results = predictor_bert.predict(str(text))
+def vs_BERT(text):
+	results = vs_predictor_bert.predict(str(text))
 	return str(results)
 	
-def MentalBERT(text):
-	results = predictor_mental.predict(str(text))
+def vs_MentalBERT(text):
+`	results = vs_predictor_mental.predict(str(text))
 	return str(results)
 	
-def PHSBERT(text):
-	results = predictor_phs.predict(str(text))
+def vs_PHSBERT(text):
+	results = vs_predictor_phs.predict(str(text))
 	return str(results)
 
-bert_io = Interface(fn=BERT, inputs="text", outputs="text")
-mental_io = Interface(fn=MentalBERT, inputs="text", outputs="text")
-phs_io = Interface(fn=PHSBERT, inputs="text", outputs="text")
+vs_bert_io = Interface(fn=vs_BERT, inputs="text", outputs="text")
+vs_mental_io = Interface(fn=vs_MentalBERT, inputs="text", outputs="text")
+vs_phs_io = Interface(fn=vs_PHSBERT, inputs="text", outputs="text")
 
-vs = Parallel(bert_io, mental_io, phs_io, 
-	examples=examples, 
-	title=title, 
-	description=desc,
+vs = Parallel(vs_bert_io, vs_mental_io, vs_phs_io, 
+	examples=vs_examples, 
+	title=vs_title, 
+	description=vs_desc,
 	theme="peach")
 	
 def model(text):
@@ -53,4 +53,4 @@ interface_names = ["Vaccine Sentiment Task",
 	"Stress Task",
 	"Other Health Related Task"]
 
-TabbedInterface(interfaces, interface_names).launch()
+TabbedInterface(interfaces, interface_names).launch()

vs/bert/config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.3.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

vs/bert/special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

vs/bert/tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2934646a4e63cab5a21ccf9be03db89abc30340c6575523cf29f3e226781d7eb
+size 438208876

vs/bert/tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "name_or_path": "bert-base-uncased"}

vs/mentalbert/config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "mental/mental-bert-base-uncased",
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.3.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

vs/mentalbert/special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

vs/mentalbert/tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acf08239b7cfbc73d117bfd5c1de52fe995055db0a53cd62ec250f9d9189c9ac
+size 438208876

vs/mentalbert/tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "mental/mental-bert-base-uncased", "tokenizer_class": "BertTokenizer"}

vs/phsbert/config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "publichealthsurveillance/PHS-BERT",
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "total_flos": 2232610412725615392,
+  "transformers_version": "4.3.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

vs/phsbert/special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

vs/phsbert/tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb80f58acee61b66be6469dd9ae943afa96caf25fc333bf67c0ebf2bac0a2f22
+size 1341096820

vs/phsbert/tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": null, "full_tokenizer_file": null, "name_or_path": "publichealthsurveillance/PHS-BERT", "do_basic_tokenize": true, "never_split": null}