Upload 9 files

app.py

@@ -0,0 +1,59 @@
+# Gradio
+import gradio as gr
+
+# ML
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+import torch
+from typing import Tuple, Dict
+
+
+model_path = "./"
+tokenizer = AutoTokenizer.from_pretrained(model_path)
+model = AutoModelForSequenceClassification.from_pretrained(model_path)
+model.eval()
+
+reverse_label_mapping = {0: 'gpt-4.1-nano', 1: 'gpt-4.1', 2: 'o4-mini'}
+
+def route_query(query: str) -> Tuple[str, float, Dict[str, str]]:
+    """
+    Route query endpoint
+    """
+
+    if not query.strip():
+        return "Please enter a query", 0.0, {}
+    
+    
+    inputs = tokenizer(
+        query,
+        padding='max_length',
+        truncation=True,
+        max_length=128,
+        return_tensors='pt'
+    )
+    
+    with torch.no_grad():
+        outputs = model(**inputs)
+        predictions = torch.nn.functional.softmax(outputs.logits, dim=-1)
+        predicted_class = torch.argmax(predictions, dim=-1)
+        confidence = torch.max(predictions, dim=-1)[0]
+    
+    probs = predictions.cpu().numpy()[0]
+    probabilities = {reverse_label_mapping[i]: f"{prob:.3f}" for i, prob in enumerate(probs)}
+    recommended_model = reverse_label_mapping[predicted_class.item()]
+    
+    return recommended_model, f"{confidence.item():.3f}", probabilities
+
+iface = gr.Interface(
+    fn=route_query,
+    inputs=gr.Textbox(lines=2, placeholder="Enter your query here..."),
+    outputs=[
+        gr.Textbox(label="Recommended Model"),
+        gr.Textbox(label="Confidence"),
+        gr.JSON(label="All Probabilities")
+    ],
+    title="GPT Router Model",
+    description="Enter a query to get routing recommendation to the appropriate GPT model"
+)
+
+if __name__ == "__main__":
+    iface.launch()

config.json

@@ -0,0 +1,34 @@
+{
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.3,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "output_past": true,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.2",
+  "vocab_size": 28996
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc27a6a1ef282dfbbb5483e34b937c61b71adf685db6f70ab4f4cbe6c96663b0
+size 263147764

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 +1,56 @@
+{
+  "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": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "extra_special_tokens": {},
+  "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]"
+}

training_info.json

@@ -0,0 +1,9 @@
+{
+  "model_type": "distilbert",
+  "task": "classification",
+  "num_labels": 3,
+  "training_steps": 1224,
+  "learning_rate": 2e-05,
+  "batch_size": 16,
+  "epochs": 3
+}