latest

app.py

@@ -1,64 +0,0 @@
-# app.py
-import torch
-import joblib
-from transformers import BertTokenizer
-from torch.nn.functional import softmax
-
-# Load the tokenizer
-tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
-
-# Device configuration
-device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
-
-# Load your saved model
-model = joblib.load('model.joblib')
-model.to(device)
-model.eval()
-
-# Class names corresponding to the labels
-class_names = ["JAILBREAK", "INJECTION", "PHISHING", "SAFE"]
-
-def preprocess(text):
-    # Tokenize the input text
-    encoding = tokenizer(
-        text,
-        truncation=True,
-        padding=True,
-        max_length=128,
-        return_tensors='pt'
-    )
-    return encoding
-
-def inference(model_inputs):
-    """
-    This function will be called for every inference request.
-    """
-    try:
-        # Get the text input
-        text = model_inputs.get('text', None)
-        if text is None:
-            return {'message': 'No text provided for inference.'}
-
-        # Preprocess the text
-        encoding = preprocess(text)
-        input_ids = encoding['input_ids'].to(device)
-        attention_mask = encoding['attention_mask'].to(device)
-
-        # Perform inference
-        with torch.no_grad():
-            outputs = model(input_ids, attention_mask=attention_mask)
-            logits = outputs.logits
-            probabilities = softmax(logits, dim=-1)
-            confidence, predicted_class = torch.max(probabilities, dim=-1)
-
-        # Prepare the response
-        predicted_label = class_names[predicted_class.item()]
-        confidence_score = confidence.item()
-
-        return {
-            'classification': predicted_label,
-            'confidence': confidence_score
-        }
-
-    except Exception as e:
-        return {'error': str(e)}

config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3
+  },
+  "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": "4.44.2",
+  "vocab_size": 30522
+}

model.joblib → label_mapping.joblib

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0b21b9462a2a3b8a360588252e9cacf970a03502a4b9f964548d09213295ca2
-size 1122320204
+oid sha256:8ebe0c69f1c4ae5bd54fa3fa15e087b52dd6eb9ec51f725d3de59ee783580001
+size 66

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2371fa66c3e53554ee383aa353152665cf37173974a083dd0b02a5a1dd684af4
+size 267838720

model_pruned_quantized.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebaebf589930938493f6bfb60e87963f0af6013f0450fa64a3d99a1a5ed44ab6
+size 138717586

requirements.txt

@@ -1,4 +0,0 @@
-# requirements.txt
-torch
-transformers
-joblib

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 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}