Update README.md

README.md

@@ -147,7 +147,7 @@ import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer
 device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 model = AutoModelForCausalLM.from_pretrained(
-    "OuteAI/Lite-Oute-2-Mamba2Attn-Instruct",
+    "OuteAI/Lite-Oute-2-Mamba2Attn-Base",
     # To allow custom modeling files
     trust_remote_code=True,
 
@@ -155,7 +155,7 @@ model = AutoModelForCausalLM.from_pretrained(
     # attn_implementation="flash_attention_2", 
 )
 model.to(device)
-tokenizer = AutoTokenizer.from_pretrained("OuteAI/Lite-Oute-2-Mamba2Attn-Instruct")
+tokenizer = AutoTokenizer.from_pretrained("OuteAI/Lite-Oute-2-Mamba2Attn-Base")
 
 def generate_response(message: str, temperature: float = 0.2, repetition_penalty: float = 1.12) -> str:
     # Convert message to PyTorch tensors