Update app.py

app.py

@@ -1,27 +1,8 @@
-import gradio as gr
-from transformers import AutoModelForCausalLM, AutoTokenizer
-import torch
+import os
+from transformers import AutoTokenizer, AutoModelForCausalLM
 
 model_name = "openai-community/gpt-oss-20b"
+hf_token = os.getenv("HF_TOKEN")  # Reads from Space secret
 
-tokenizer = AutoTokenizer.from_pretrained(model_name)
-model = AutoModelForCausalLM.from_pretrained(
-    model_name,
-    torch_dtype=torch.float16,
-    device_map="auto"
-)
-
-def chat(message, history):
-    inputs = tokenizer(message, return_tensors="pt").to(model.device)
-    outputs = model.generate(
-        **inputs,
-        max_length=200,
-        do_sample=True,
-        temperature=0.7,
-        top_p=0.9
-    )
-    reply = tokenizer.decode(outputs[0], skip_special_tokens=True)
-    return reply
-
-iface = gr.ChatInterface(fn=chat)
-iface.launch()
+tokenizer = AutoTokenizer.from_pretrained(model_name, use_auth_token=hf_token)
+model = AutoModelForCausalLM.from_pretrained(model_name, use_auth_token=hf_token)