Update app.py

app.py

@@ -1,17 +1,22 @@
 import gradio as gr
-from transformers import AutoModelForCausalLM, AutoTokenizer
+from transformers import AutoTokenizer, AutoModelForCausalLM
 
-model_id = "INTERX/Qwen2.5-GenX-14B"
+MODEL_ID = "INTERX/Qwen2.5-GenX-7B"
 
-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)
+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)
 
-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
+def chat(user_input):
+    messages = [{"role": "user", "content": user_input}]
+    inputs = 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()
+    output = model.generate(inputs, max_new_tokens=512)
+    response = tokenizer.decode(output[0], skip_special_tokens=True)
+    return response
 
+gr.Interface(fn=chat, inputs="text", outputs="text", title="Chat con Qwen2.5-GenX-7B").launch()