Create app.py

app.py

@@ -0,0 +1,55 @@
+import gradio as gr
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
+from threading import Thread
+
+MODEL_ID = "ministral/Ministral-3b-instruct"
+
+# ===== Load model & tokenizer =====
+tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
+model = AutoModelForCausalLM.from_pretrained(
+    MODEL_ID,
+    torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32,
+    device_map="auto"
+)
+
+# ===== Streaming Chat Function =====
+def chat_stream(message, history):
+    prompt = ""
+    for user, bot in history:
+        prompt += f"<|user|>\n{user}\n<|assistant|>\n{bot}\n"
+    prompt += f"<|user|>\n{message}\n<|assistant|>\n"
+
+    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+
+    streamer = TextIteratorStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
+    generation_kwargs = dict(
+        **inputs,
+        streamer=streamer,
+        max_new_tokens=256,
+        temperature=0.7,
+        do_sample=True,
+        top_p=0.9,
+    )
+    thread = Thread(target=model.generate, kwargs=generation_kwargs)
+    thread.start()
+
+    partial_text = ""
+    for token in streamer:
+        partial_text += token
+        yield partial_text
+
+# ===== Gradio UI =====
+with gr.Blocks(title="Ministral 3B Chat") as demo:
+    gr.Markdown("## 🧠 Ministral 3B Instruct — Chat Demo\nLightweight model for Hugging Face Spaces.")
+    chatbot = gr.Chatbot(height=400)
+    msg = gr.Textbox(placeholder="متن خودت رو بنویس و Enter بزن...", label="پیام شما")
+
+    def respond(message, chat_history):
+        response = chat_stream(message, chat_history)
+        return response, chat_history + [(message, "")]
+
+    msg.submit(chat_stream, [msg, chatbot], chatbot)
+
+demo.queue(max_size=32, concurrency_count=1)
+demo.launch()