Upload 7 files

app.py

@@ -0,0 +1,31 @@
+import torch
+import transformers
+from transformers import DistilBertTokenizerFast
+from transformers import DistilBertForSequenceClassification
+import gradio as gr
+
+# Load the pre-trained tokenizer
+tokenizer = DistilBertTokenizerFast.from_pretrained('./model_save/',local_files_only=True)
+
+# Load the pre-trained DilBERT model
+model = DistilBertForSequenceClassification.from_pretrained('./model_save/',local_files_only=True)
+model.eval()
+
+# Define a predict function
+def predict(text):
+    encoding=tokenizer(text,return_tensors='pt')
+    input_ids, attention_mask = encoding['input_ids'],encoding['attention_mask']
+    outputs = model(input_ids,attention_mask=attention_mask)
+    logits = outputs['logits']
+    pred_label = torch.argmax(logits,1)[0]
+    return 'Positive' if pred_label > 0.5 else 'Negative'
+
+# Initialize the Gradio interface
+title = "Write a movie review"
+description = "Enter a review for a movie you've seen.  This tool will try to guess whether your review is positive or negative."
+gr.Interface(fn=predict, 
+             inputs="text",
+             outputs="label",
+             title = title,
+             description = description,
+              ).launch()

model_save/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.20.1",
+  "vocab_size": 30522
+}

model_save/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a619cd8c20b321c9442a77f080497fbc1d94e9340eab738fa80fd7b280086ea
+size 267854321

model_save/special_tokens_map.json

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

model_save/tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "name_or_path": "distilbert-base-uncased",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}