Upload 9 files

config.json

@@ -0,0 +1,35 @@
+{
+  "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"
+  },
+  "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,
+  "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": "4.52.2",
+  "vocab_size": 119547
+}

main.py

@@ -0,0 +1,46 @@
+import os
+import requests
+import zipfile
+import torch
+import logging
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+from fastapi import FastAPI, HTTPException
+from pydantic import BaseModel
+# Setup logging
+logging.basicConfig(level=logging.INFO)
+# Model location
+MODEL_DIR = "model"
+MODEL_ZIP_PATH = os.path.join(MODEL_DIR, "model.zip")
+MODEL_BLOB_URL = "https://brewtinkersa.blob.core.windows.net/models/models/model.zip"  
+# Download and unzip the model at startup
+def download_and_extract_model():
+    if not os.path.exists(MODEL_DIR):
+        os.makedirs(MODEL_DIR, exist_ok=True)
+    if not os.path.exists(os.path.join(MODEL_DIR, "config.json")):
+        logging.info("Downloading model from Azure Blob...")
+        response = requests.get(MODEL_BLOB_URL)
+        with open(MODEL_ZIP_PATH, "wb") as f:
+            f.write(response.content)
+        with zipfile.ZipFile(MODEL_ZIP_PATH, 'r') as zip_ref:
+            zip_ref.extractall(MODEL_DIR)
+        logging.info("Model extracted.")
+# Prepare model
+download_and_extract_model()
+tokenizer = AutoTokenizer.from_pretrained(MODEL_DIR)
+model = AutoModelForSequenceClassification.from_pretrained(MODEL_DIR)
+model.eval()
+# FastAPI setup
+app = FastAPI()
+class RequestData(BaseModel):
+    text: str
+@app.post("/predict")
+def predict(request: RequestData):
+    try:
+        inputs = tokenizer(request.text, return_tensors="pt", truncation=True, padding=True)
+        outputs = model(**inputs)
+        prediction = torch.argmax(outputs.logits, dim=1).item()
+        labels = {0: "negative", 1: "neutral", 2: "positive"}
+        return {"prediction": prediction, "label": labels.get(prediction, "unknown")}
+    except Exception as e:
+        logging.error(f"Prediction failed: {e}")
+        raise HTTPException(status_code=500, detail="Internal Server Error")

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:415b0ec2511d90bbf6cde090da6ac83efe984d2c0ee01b2e8e0365f461c1b48e
+size 541320452

requirements.txt

@@ -0,0 +1,7 @@
+fastapi
+uvicorn
+gunicorn
+transformers==4.40.1
+torch==2.2.2
+pydantic
+requests

special_tokens_map.json

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

startup.txt

@@ -0,0 +1 @@
+gunicorn -w 1 -k uvicorn.workers.UvicornWorker main:app

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "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_basic_tokenize": true,
+  "do_lower_case": false,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6944e414bd9f3407c056eb66183f1fb891f963418532191b86340e99157ffff2
+size 5304