Update README.md

README.md

@@ -214,7 +214,7 @@ class EosListStoppingCriteria(StoppingCriteria):
         return self.eos_sequence in last_ids
 
 # Initialize the model with automatic device mapping
-llm = pipeline("text-generation", model="yentinglin/Llama-3-Taiwan-70B-Instruct-rc1", device_map="auto")
+llm = pipeline("text-generation", model="yentinglin/Llama-3-Taiwan-70B-Instruct", device_map="auto")
 tokenizer = llm.tokenizer
 
 # Define a conversation example
@@ -258,7 +258,7 @@ docker run \
   -p "${PORT}:8000" \
   --ipc=host \
   vllm/vllm-openai:v0.4.0.post1 \
-  --model "yentinglin/Llama-3-Taiwan-70B-Instruct-rc1" \
+  --model "yentinglin/Llama-3-Taiwan-70B-Instruct" \
   -tp "${NUM_GPUS}"
 ```
 
@@ -277,7 +277,7 @@ client = OpenAI(
 )
 
 chat_response = client.chat.completions.create(
-    model="yentinglin/Llama-3-Taiwan-70B-Instruct-rc1",
+    model="yentinglin/Llama-3-Taiwan-70B-Instruct",
     messages=[
         {"role": "system", "content": "You are a helpful assistant."},
         {"role": "user", "content": "Tell me a joke."},