main commit

Dockerfile

@@ -0,0 +1,17 @@
+# Use Python 3.10.6 image
+FROM python:3.10
+
+# Set the working directory in the container
+WORKDIR /app
+
+# Copy the requirements file
+COPY requirements.txt .
+
+# Install dependencies
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Copy the rest of your application files
+COPY . .
+
+# Command to run your FastAPI app
+CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7860"]

hate_speech_distilbert/config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "distilbert/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"
+  },
+  "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,
+  "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": "4.48.2",
+  "vocab_size": 30522
+}

hate_speech_distilbert/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68032af24f1dddf2e2e69ef3adbd13a0fc225c29faa4a1e9ea84ed8cc5dc90c7
+size 267835644

hate_speech_distilbert/special_tokens_map.json

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

hate_speech_distilbert/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": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

hate_speech_distilbert/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:155a78e5aee35bfe5f0e466f5868f64b857215bb4a148b7d0cdf4555dc3e2d94
+size 5304

main.py

@@ -0,0 +1,38 @@
+from fastapi import FastAPI
+from pydantic import BaseModel
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+import torch
+
+# Load model and tokenizer
+MODEL_PATH = "./hate_speech_distilbert"  # Update with actual path
+model = AutoModelForSequenceClassification.from_pretrained(MODEL_PATH)
+tokenizer = AutoTokenizer.from_pretrained(MODEL_PATH)
+
+# Label Mapping
+LABELS = {
+    0: "Hate Speech",
+    1: "Offensive Language",
+    2: "NOT Hate Speech"
+}
+
+app = FastAPI()
+
+class TextRequest(BaseModel):
+    text: str
+
+@app.get("/")
+def greet_json():
+    return {"Hello": "World!"}
+
+@app.post("/predict")
+async def predict(request: TextRequest):
+    inputs = tokenizer(request.text, return_tensors="pt", truncation=True, padding=True)
+    with torch.no_grad():
+        outputs = model(**inputs)
+    prediction = torch.argmax(outputs.logits, dim=1).item()
+    return {"prediction": LABELS[prediction]}
+
+# Example Usage
+if __name__ == "__main__":
+    import uvicorn
+    uvicorn.run(app, host="0.0.0.0", port=8000)