Upload 7 files

app.py

@@ -0,0 +1,58 @@
+import gradio as gr
+import torch
+import torch.nn as nn
+from transformers import BertModel, BertTokenizer
+
+# define the labels for the mutli-classification model
+class_names = ['Negative', 'Neutral', 'Positive']
+
+# Build the Sentiment Classifier class 
+class SentimentClassifier(nn.Module):
+    # Constructor class 
+    def __init__(self, n_classes):
+        super(SentimentClassifier, self).__init__()
+        self.bert = BertModel.from_pretrained('lothritz/LuxemBERT')
+        self.drop = nn.Dropout(p=0.3)
+        self.out = nn.Linear(self.bert.config.hidden_size, n_classes)
+    
+    # Forward propagaion class
+    def forward(self, input_ids, attention_mask):
+        _, pooled_output = self.bert(
+          input_ids=input_ids,
+          attention_mask=attention_mask,
+            return_dict=False
+        )
+        #  Add a dropout layer 
+        output = self.drop(pooled_output)
+        return self.out(output)
+# load the CNN binary classification model
+model = SentimentClassifier(len(class_names))
+model.load_state_dict(torch.load('model/pytorch_model.bin'))
+tokenizer = BertTokenizer.from_pretrained('./model/')
+
+def encode(text):
+    encoded_text = tokenizer.encode_plus(
+        text,
+        max_length=50,
+        add_special_tokens=True,
+        return_token_type_ids=False,
+        pad_to_max_length=True,
+        return_attention_mask=True,
+        return_tensors='pt',
+    )
+    return encoded_text
+
+def classify(text):
+    encoded_comment = encode(text)
+    input_ids = encoded_comment['input_ids']
+    attention_mask = encoded_comment['attention_mask']
+
+    output = model(input_ids, attention_mask)
+    _, prediction = torch.max(output, dim=1)
+    
+    return class_names[prediction]
+
+demo = gr.Interface(fn=classify, inputs="text", outputs="text", title="Sentiment Analyser", description="Text classifer for Luxembourgish")
+
+
+demo.launch()

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "neojex/testing",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 514,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.29.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bb586ffd8105810b89040e6cd3147af150aebbd2232b63a64f10f1eb574c196
+size 436427573

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1585bd57bdff40999fba176b024c23515bef076536ee57f6033a20efe9335422
+size 3899