bfloat and less tokens

app.py

@@ -1,13 +1,14 @@
 import gradio as gr
 from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
 
 model_name = "AddieFoote0/arithmetic-300M-reference"
-model = AutoModelForCausalLM.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16)
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 
 def generate_response(prompt):
     inputs = tokenizer(prompt, return_tensors="pt")
-    outputs = model.generate(**inputs, max_new_tokens=50, temperature=0.7)
+    outputs = model.generate(**inputs, max_new_tokens=20, temperature=1.0)
     return tokenizer.decode(outputs[0], skip_special_tokens=True)
 
 iface = gr.Interface(