Create app.py

app.py

@@ -0,0 +1,14 @@
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM
+from transformers import TFAutoModel
+
+tokenizer = AutoTokenizer.from_pretrained(
+  'kakaobrain/kogpt', revision='KoGPT6B-ryan1.5b-float16',  # or float32 version: revision=KoGPT6B-ryan1.5b
+  bos_token='[BOS]', eos_token='[EOS]', unk_token='[UNK]', pad_token='[PAD]', mask_token='[MASK]'
+)
+model = AutoModelForCausalLM.from_pretrained(
+  'kakaobrain/kogpt', revision='KoGPT6B-ryan1.5b-float16',  # or float32 version: revision=KoGPT6B-ryan1.5b
+  pad_token_id=tokenizer.eos_token_id,
+  torch_dtype='auto', low_cpu_mem_usage=True
+).to(device='cuda', non_blocking=True)
+_ = model.eval()