Create app.py

app.py

@@ -0,0 +1,35 @@
+import gradio as gr
+from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
+
+MODEL_NAME = "TinyLlama/TinyLlama-1.1B-Chat-v1.0"
+
+tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
+model = AutoModelForCausalLM.from_pretrained(MODEL_NAME, device_map="auto")
+
+generator = pipeline("text-generation", model=model, tokenizer=tokenizer)
+
+def generate_text(prompt, max_new_tokens, temperature, top_p):
+    result = generator(
+        prompt,
+        max_new_tokens=int(max_new_tokens),
+        do_sample=True,
+        temperature=float(temperature),
+        top_p=float(top_p),
+    )[0]["generated_text"]
+    return result
+
+with gr.Blocks(title="TinyLlama Chat") as demo:
+    gr.Markdown("## TinyLlama Chat\nگوش به زنگ م.")
+    with gr.Row():
+        prompt = gr.Textbox(label="Prompt", lines=4, placeholder="مثال: درباره گل‌های آفریقا بگو...")
+    with gr.Row():
+        max_new_tokens = gr.Slider(16, 512, value=150, step=1, label="max_new_tokens")
+        temperature = gr.Slider(0.1, 1.5, value=0.7, step=0.05, label="temperature")
+        top_p = gr.Slider(0.1, 1.0, value=0.9, step=0.05, label="top_p")
+    btn = gr.Button("جواب بده")
+    output = gr.Textbox(label="یاور : ", lines=10)
+
+    btn.click(generate_text, [prompt, max_new_tokens, temperature, top_p], output)
+
+if __name__ == "__main__":
+    demo.launch()