Added app.py and Dockerfile

Dockerfile

@@ -1,8 +1,14 @@
-FROM python:3.9
+FROM python:3.10
 
 WORKDIR /app
-COPY . /app
 
+# Install dependencies
+COPY requirements.txt .
 RUN pip install -r requirements.txt
 
-CMD ["python", "app.py"]
+# Copy app files
+COPY . .
+
+# Expose port & run app
+EXPOSE 7860
+CMD ["python", "app.py"]

MedAI-LLM/README.md

@@ -0,0 +1,10 @@
+---
+title: MedAI LLM
+emoji: 🏆
+colorFrom: purple
+colorTo: gray
+sdk: docker
+pinned: false
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -1,12 +1,24 @@
 from flask import Flask, request, jsonify
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
 
 app = Flask(__name__)
 
+# Load base model and tokenizer
+MODEL_NAME = "meta-llama/Llama-2-7b-chat-hf"  # Change this to your base model
+tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
+model = AutoModelForCausalLM.from_pretrained(MODEL_NAME, torch_dtype=torch.float16, device_map="auto")
+
 @app.route("/predict", methods=["POST"])
 def predict():
-    data = request.get_json()
-    user_input = data.get("input", "")
-    response = f"Generated text for: {user_input}"  # Dummy response
+    data = request.json
+    input_text = data.get("text", "")
+
+    # Tokenize input
+    inputs = tokenizer(input_text, return_tensors="pt").to("cuda")
+    outputs = model.generate(**inputs, max_length=200)
+    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+
     return jsonify({"response": response})
 
 if __name__ == "__main__":

requirements.txt

@@ -1,3 +1,6 @@
 flask
 torch
 transformers
+gunicorn
+gradio
+