Deploy BERT Scorer

Dockerfile

@@ -0,0 +1,20 @@
+# Use Python 3.9
+FROM python:3.9-slim
+
+# Set working directory
+WORKDIR /app
+
+# Copy requirements and install
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Copy all files (Model + Code)
+COPY . .
+
+# Create a user to run the app (Security requirement for HF)
+RUN useradd -m -u 1000 user
+USER user
+ENV PATH="/home/user/.local/bin:$PATH"
+
+# Run the app on port 7860
+CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]

app.py

@@ -0,0 +1,52 @@
+import torch
+from fastapi import FastAPI
+from pydantic import BaseModel
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+
+# 1. Initialize API
+app = FastAPI()
+
+# 2. Define Request Model
+class PromptRequest(BaseModel):
+    prompt: str
+
+# 3. Load Model (Runs once at startup)
+# We use "." because the model files are now in the same folder as this script
+MODEL_DIR = "." 
+DEVICE = "cuda" if torch.cuda.is_available() else "cpu"
+
+print(f"Loading model on {DEVICE}...")
+try:
+    tokenizer = AutoTokenizer.from_pretrained(MODEL_DIR)
+    model = AutoModelForSequenceClassification.from_pretrained(MODEL_DIR).to(DEVICE)
+    model.eval()
+    print("✅ Model loaded successfully!")
+except Exception as e:
+    print(f"❌ Error loading model: {e}")
+    raise RuntimeError("Model failed to load")
+
+# 4. Define the Scoring Logic (The same math from your local script)
+def calculate_score(text):
+    inputs = tokenizer(text, return_tensors="pt", truncation=True, max_length=128).to(DEVICE)
+    with torch.no_grad():
+        outputs = model(**inputs)
+    
+    raw_score = outputs.logits.item()
+    
+    # Calibration Formula
+    if raw_score < 30:
+        final_score = raw_score - 20
+    else:
+        final_score = (raw_score - 30) * 3.33
+        
+    return round(max(0.0, min(100.0, final_score)), 2)
+
+# 5. Define the API Endpoint
+@app.post("/score")
+def get_score(request: PromptRequest):
+    score = calculate_score(request.prompt)
+    return {"score": score}
+
+@app.get("/")
+def home():
+    return {"status": "Model is running. Send POST request to /score"}

config.json

@@ -0,0 +1,32 @@
+{
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "regression",
+  "transformers_version": "4.57.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb8cef435e7d4a8e4892f21a1840881a0411a991c5c2fef76b11ce0bc960b54f
+size 437955572

requirements.txt

@@ -0,0 +1,6 @@
+fastapi
+uvicorn
+torch
+transformers
+safetensors
+pydantic

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": true,
+  "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": "BertTokenizer",
+  "unk_token": "[UNK]"
+}