Text Generation
Transformers
Safetensors
llama
text-generation-inference
mfromm commited on
Commit
476b34a
·
verified ·
1 Parent(s): c2b4289

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +0 -1
README.md CHANGED
@@ -106,7 +106,6 @@ model = AutoModelForCausalLM.from_pretrained(
106
  model_name,
107
  trust_remote_code=True,
108
  torch_dtype=torch.bfloat16,
109
- attn_implementation="flash_attention_2",
110
  )
111
  model = model.to(device).eval()
112
  tokenizer = AutoTokenizer.from_pretrained(
 
106
  model_name,
107
  trust_remote_code=True,
108
  torch_dtype=torch.bfloat16,
 
109
  )
110
  model = model.to(device).eval()
111
  tokenizer = AutoTokenizer.from_pretrained(