Update README.md

README.md

@@ -99,10 +99,7 @@ model_id = "ibleducation/ibl-neural-edu-content-7B"
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 model = AutoModelForCausalLM.from_pretrained(
   model_id,
-  use_flash_attention_2=True,
-  torch_dtype=torch.bfloat16,
   device_map="auto",
-  trust_remote_code=True
 )
 pipeline = transformers.pipeline(
     "text-generation",
@@ -115,10 +112,7 @@ response = pipeline(prompt)
 print(response['generated_text'])
 ```
 
-> In cases where the runtime gpu does not support flash attention, `use_flash_attention_2` can be ignored
-> though at a possible performance cost
-
-**Important** - Use the prompt template below for ibl-tutoring-7B-128k :
+**Important** - Use the prompt template below:
 ```
 <s>[INST]{prompt}[/INST] 
 ```