Create app.py

app.py

@@ -0,0 +1,32 @@
+import gradio as gr
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+# Load tokenizer and model
+tokenizer = AutoTokenizer.from_pretrained("TuringsSolutions/LegalGemmaV1", trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained("TuringsSolutions/LegalGemmaV1", trust_remote_code=True)
+
+def predict(prompt, temperature, max_tokens):
+    inputs = tokenizer(prompt, return_tensors="pt")
+    outputs = model.generate(
+        **inputs,
+        max_new_tokens=max_tokens,
+        temperature=temperature
+    )
+    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    return response
+
+# Create Gradio interface
+iface = gr.Interface(
+    fn=predict, 
+    inputs=[
+        gr.Textbox(lines=2, placeholder="Enter your prompt here..."),
+        gr.Slider(minimum=0.1, maximum=1.0, value=0.7, label="Temperature"),
+        gr.Slider(minimum=10, maximum=200, value=50, step=10, label="Number of Output Tokens")
+    ], 
+    outputs="text",
+    title="Gemma 2 2B Law Case Management Model",
+    description="A model to assist with law case management. Adjust the temperature and number of output tokens as needed."
+)
+
+# Launch the Gradio app
+iface.launch()