Update README.md (#5)

- Update README.md (4409dd776fb4484cb7b8c76768ad8d4d035a51a8)

README.md

@@ -111,7 +111,10 @@ print(tokenizer.decode(outputs[0]))
 from transformers import AutoTokenizer, AutoModelForCausalLM
 
 tokenizer = AutoTokenizer.from_pretrained("google/gemma-2-9b-it")
-model = AutoModelForCausalLM.from_pretrained("google/gemma-2-9b-it", device_map="auto", torch_dtype=torch.bfloat16)
+model = AutoModelForCausalLM.from_pretrained(
+    "google/gemma-2-9b-it",
+    device_map="auto",
+    torch_dtype=torch.bfloat16)
 
 input_text = "Write me a poem about Machine Learning."
 input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
@@ -129,8 +132,7 @@ from transformers import AutoTokenizer, AutoModelForCausalLM
 tokenizer = AutoTokenizer.from_pretrained("google/gemma-2-9b-it")
 model = AutoModelForCausalLM.from_pretrained(
     "google/gemma-2-9b-it",
-    device_map="auto"
-)
+    device_map="auto")
 
 input_text = "Write me a poem about Machine Learning."
 input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
@@ -150,7 +152,9 @@ from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
 quantization_config = BitsAndBytesConfig(load_in_8bit=True)
 
 tokenizer = AutoTokenizer.from_pretrained("google/gemma-2-9b-it")
-model = AutoModelForCausalLM.from_pretrained("google/gemma-2-9b-it", quantization_config=quantization_config)
+model = AutoModelForCausalLM.from_pretrained(
+    "google/gemma-2-9b-it",
+    quantization_config=quantization_config)
 
 input_text = "Write me a poem about Machine Learning."
 input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
@@ -168,7 +172,9 @@ from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
 quantization_config = BitsAndBytesConfig(load_in_4bit=True)
 
 tokenizer = AutoTokenizer.from_pretrained("google/gemma-2-9b-it")
-model = AutoModelForCausalLM.from_pretrained("google/gemma-2-9b-it", quantization_config=quantization_config)
+model = AutoModelForCausalLM.from_pretrained(
+    "google/gemma-2-9b-it",
+    quantization_config=quantization_config)
 
 input_text = "Write me a poem about Machine Learning."
 input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
@@ -211,8 +217,7 @@ tokenizer = AutoTokenizer.from_pretrained(model_id)
 model = AutoModelForCausalLM.from_pretrained(
     model_id,
     device_map="cuda",
-    torch_dtype=dtype,
-)
+    torch_dtype=dtype,)
 
 chat = [
     { "role": "user", "content": "Write a hello world program" },