Update README.md

README.md

@@ -46,7 +46,20 @@ import torch
 from transformers import AutoTokenizer, AutoModelForCausalLM
 
 tokenizer = AutoTokenizer.from_pretrained("pfnet/nekomata-14b-pfn-qfin", trust_remote_code=True)
+
+
+# Use GPU with bf16 (recommended for supported devices)
+# model = AutoModelForCausalLM.from_pretrained("pfnet/nekomata-14b-pfn-qfin", device_map="auto", trust_remote_code=True, bf16=True)
+
+# Use GPU with fp16
+# model = AutoModelForCausalLM.from_pretrained("pfnet/nekomata-14b-pfn-qfin", device_map="auto", trust_remote_code=True, fp16=True)
+
+# Use CPU
+# model = AutoModelForCausalLM.from_pretrained("pfnet/nekomata-14b-pfn-qfin", device_map="cpu", trust_remote_code=True)
+
+# Automatically select device and precision
 model = AutoModelForCausalLM.from_pretrained("pfnet/nekomata-14b-pfn-qfin", device_map="auto", trust_remote_code=True)
+
 text = "日本銀行は"
 input_ids = tokenizer(text, return_tensors="pt").input_ids
 with torch.no_grad():