Update app.py

app.py

@@ -1,3 +1,4 @@
+import gradio as gr
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
 model_id = "INTERX/Qwen2.5-GenX-14B"
@@ -5,17 +6,12 @@ model_id = "INTERX/Qwen2.5-GenX-14B"
 tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
 model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", torch_dtype="auto", trust_remote_code=True)
 
-prompt = "Spiega il processo di stampaggio a iniezione."
-messages = [{"role": "user", "content": prompt}]
+def chat(prompt):
+    messages = [{"role": "user", "content": prompt}]
+    tokenized_chat = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors='pt').to(model.device)
+    generated_ids = model.generate(tokenized_chat, max_new_tokens=512)
+    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
+    return response
 
-tokenized_chat = tokenizer.apply_chat_template(
-    messages,
-    tokenize=True,
-    add_generation_prompt=True,
-    return_tensors='pt'
-).to(model.device)
+gr.Interface(fn=chat, inputs="text", outputs="text", title="Qwen2.5-GenX-14B Chat").launch()
 
-generated_ids = model.generate(tokenized_chat, max_new_tokens=512)
-
-response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
-print(response)