Add initial gradio setup

app.py

@@ -10,7 +10,7 @@ def generate(prompt, seq_len, temperature, filter_thres, model):
         num_tokens=50304, dim=1024, depth=24, dim_head=128, heads=8, flash_attn=False, qk_rmsnorm = False,
     ).to(device)
 
-    model.load('./palm_410m_8k_v0.pt', map_location=torch.device('cpu'))
+    model.load('./palm_410m_8k_v0.pt', device)
 
     tokenizer = AutoTokenizer.from_pretrained("EleutherAI/gpt-neox-20b")