Update README.md

README.md

@@ -154,8 +154,8 @@ def generate(model, prompt, steps=128, gen_length=128, block_length=128, tempera
 
 
 device = 'cuda'
-model = AutoModel.from_pretrained('/mnt/dllm/fengqi/LLaDA-MoE-7B-A1B-Instruct-Release', trust_remote_code=True, torch_dtype=torch.bfloat16).to(device).eval()
-tokenizer = AutoTokenizer.from_pretrained('/mnt/dllm/fengqi/LLaDA-MoE-7B-A1B-Instruct-Release', trust_remote_code=True)
+model = AutoModel.from_pretrained('inclusionAI/LLaDA-MoE-7B-A1B-Instruct', trust_remote_code=True, torch_dtype=torch.bfloat16).to(device).eval()
+tokenizer = AutoTokenizer.from_pretrained('inclusionAI/LLaDA-MoE-7B-A1B-Instruct', trust_remote_code=True)
 
 prompt = "Lily can run 12 kilometers per hour for 4 hours. After that, she runs 6 kilometers per hour. How many kilometers can she run in 8 hours?"
 m = [