Update README.md

README.md

@@ -49,9 +49,9 @@ quant_scheme = "mxfp4"
 exclude_layers = ["lm_head", "*linear_attn.in_proj_ba", "*linear_attn.in_proj_qkvz","*mlp.gate", "*mlp.shared_expert_gate", "*self_attn.k_proj", "*self_attn.q_proj", "*self_attn.v_proj"]
 
 # Load model
+tokenizer = AutoTokenizer.from_pretrained(ckpt_path, trust_remote_code=True)
 model = AutoModelForCausalLM.from_pretrained(ckpt_path, torch_dtype="auto", device_map="auto")
 model.eval()
-tokenizer = AutoTokenizer.from_pretrained(ckpt_path, trust_remote_code=True)
 
 # Get quant config from template
 template = LLMTemplate.get(model.config.model_type)