Update README.md

README.md

@@ -65,7 +65,7 @@ sampling_params = SamplingParams(max_tokens=8192)
 # If you want to divide the GPU requirement over multiple devices, please add *e.g.* `tensor_parallel=2`
 llm = LLM(model=model_name, tokenizer_mode="mistral", config_format="mistral", load_format="mistral")
 
-prompt = "How many often does the letter r occur in Mistral?"
+prompt = "How often does the letter r occur in Mistral?"
 
 messages = [
     {
@@ -105,7 +105,7 @@ curl --location 'http://<your-node-url>:8000/v1/chat/completions' \
     "messages": [
       {
         "role": "user",
-        "content": "How many often does the letter r occur in Mistral?"
+        "content": "How often does the letter r occur in Mistral?"
       }
     ]
 }'
@@ -159,7 +159,7 @@ from mistral_common.protocol.instruct.request import ChatCompletionRequest
 tokenizer = MistralTokenizer.from_file(f"{mistral_models_path}/tokenizer.model.v3")
 model = Transformer.from_folder(mistral_models_path)
 
-completion_request = ChatCompletionRequest(messages=[UserMessage(content="How many often does the letter r occur in Mistral?")])
+completion_request = ChatCompletionRequest(messages=[UserMessage(content="How often does the letter r occur in Mistral?")])
 
 tokens = tokenizer.encode_chat_completion(completion_request).tokens