Update README.md

README.md

@@ -23,7 +23,13 @@ This project is supported by [AWS LLM development support program](https://aws.a
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
+# For A100 or H100 GPU
 model = AutoModelForCausalLM.from_pretrained("stockmark/stockmark-13b", device_map="auto", torch_dtype=torch.bfloat16)
+
+# If you use a T4 or V100 GPU, please load a model in 8 bit with the below code.
+# To do so, you need to install `bitsandbytes` via `pip install bitsandbytes`.
+# model = AutoModelForCausalLM.from_pretrained("stockmark/stockmark-13b", device_map={"": 0}, load_in_8bit=True)
+
 tokenizer = AutoTokenizer.from_pretrained("stockmark/stockmark-13b")
 
 inputs = tokenizer("自然言語処理とは", return_tensors="pt").to(model.device)
@@ -39,9 +45,10 @@ output = tokenizer.decode(tokens[0], skip_special_tokens=True)
 print(output)
 ```
 
-## Example:
+## Examples:
 
-- LoRA tuning (in preparation): https://huggingface.co/stockmark/stockmark-13b/blob/main/notebooks/LoRA.ipynb
+- LoRA tuning: https://huggingface.co/stockmark/stockmark-13b/blob/main/notebooks/LoRA.ipynb
+- QLoRA tuning (in preparation): https://huggingface.co/stockmark/stockmark-13b/blob/main/notebooks/QLoRA.ipynb
 
 ## Training dataset