Update README.md

README.md

@@ -118,7 +118,7 @@ transformers>=5.6.0
 from transformers import AutoModelForCausalLM, AutoTokenizer
 import torch
 
-model_path = "tencent/Hy-MT2-30B-A3B"
+model_path = "tencent/Hy-MT2-7B-FP8"
 
 # Load tokenizer
 tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
@@ -161,7 +161,7 @@ uv pip install --editable . --torch-backend=auto
 Start the vLLM server:
 
 ```bash
-vllm serve tencent/Hy-MT2-30B-A3B --tensor-parallel-size 1
+vllm serve tencent/Hy-MT2-7B-FP8 --tensor-parallel-size 1
 ```
 
 ### sglang
@@ -178,7 +178,7 @@ pip3 install -e "python"
 Launch SGLang server:
 
 ```bash
-python3 -m sglang.launch_server --model tencent/Hy-MT2-30B-A3B --tp 1
+python3 -m sglang.launch_server --model tencent/Hy-MT2-7B-FP8 --tp 1
 ```
 
 ### llama_cpp