Create app.py

app.py

@@ -0,0 +1,20 @@
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+import gradio as gr
+
+model_id = "HuggingFaceH4/zephyr-7b-beta"  # يدعم العربية بشكل جيد
+
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(
+    model_id,
+    device_map="auto",
+    torch_dtype=torch.float16
+)
+
+def chat_fn(message, history):
+    inputs = tokenizer(message, return_tensors="pt").to("cuda")
+    output = model.generate(**inputs, max_new_tokens=200, pad_token_id=tokenizer.eos_token_id)
+    response = tokenizer.decode(output[0], skip_special_tokens=True)
+    return response
+
+gr.ChatInterface(fn=chat_fn, title="مساعد عربي تجريبي").launch()