Create app.py

app.py

@@ -0,0 +1,27 @@
+import gradio as gr
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+
+# Define the model name and cache path
+model_name = 'MohamedRashad/Arabic-Orpo-Llama-3-8B-Instruct'
+
+# Load the tokenizer and model
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name).to("cuda" if torch.cuda.is_available() else "cpu")
+
+# Add a pad token if it does not exist
+if tokenizer.pad_token is None:
+    tokenizer.pad_token = tokenizer.eos_token
+
+def generate_response(input_text):
+    inputs = tokenizer(input_text, return_tensors='pt', padding=True, truncation=True, max_length=512)
+    inputs = {key: value.to("cuda" if torch.cuda.is_available() else "cpu") for key, value in inputs.items()}
+    
+    with torch.no_grad():
+        outputs = model.generate(inputs['input_ids'], attention_mask=inputs['attention_mask'], max_length=50)
+    
+    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    return response
+
+interface = gr.Interface(fn=generate_response, inputs="text", outputs="text")
+interface.launch(share=True)