OuteAI
/

Lite-Oute-2-Mamba2Attn-250M-Instruct

Model card Files Files and versions Community

edwko commited on 30 days ago

Commit

d123cee

•

1 Parent(s): 2d1186b

Update README.md

Files changed (1) hide show

README.md +2 -1

README.md CHANGED Viewed

@@ -220,7 +220,8 @@ model = AutoModelForCausalLM.from_pretrained(
     trust_remote_code=True,
     # If you have installed flash attention 2
-    # attn_implementation="flash_attention_2",
 )
 model.to(device)
 tokenizer = AutoTokenizer.from_pretrained("OuteAI/Lite-Oute-2-Mamba2Attn-Instruct")

     trust_remote_code=True,
     # If you have installed flash attention 2
+    # attn_implementation="flash_attention_2",
+    # torch_dtype=torch.bfloat16,
 )
 model.to(device)
 tokenizer = AutoTokenizer.from_pretrained("OuteAI/Lite-Oute-2-Mamba2Attn-Instruct")