Update README.md

README.md

@@ -42,7 +42,7 @@ generate_text = pipeline(
 )
 
 res = generate_text(
-    "Why is drinking water so healthy?",
+    "日本で一番高い山は富士山ですが、二番目に高い山は？",
     min_new_tokens=2,
     max_new_tokens=256,
     do_sample=False,
@@ -57,11 +57,11 @@ print(res[0]["generated_text"])
 You can print a sample prompt after the preprocessing step to see how it is feed to the tokenizer:
 
 ```python
-print(generate_text.preprocess("Why is drinking water so healthy?")["prompt_text"])
+print(generate_text.preprocess("日本で一番高い山は富士山ですが、二番目に高い山は？")["prompt_text"])
 ```
 
 ```bash
-<|prompt|>Why is drinking water so healthy?<|endoftext|><|answer|>
+<|prompt|>日本で一番高い山は富士山ですが、二番目に高い山は？<|endoftext|><|answer|>
 ```
 
 Alternatively, if you prefer to not use `trust_remote_code=True` you can download [h2oai_pipeline.py](h2oai_pipeline.py), store it alongside your notebook, and construct the pipeline yourself from the loaded model and tokenizer:
@@ -85,7 +85,7 @@ model = AutoModelForCausalLM.from_pretrained(
 generate_text = H2OTextGenerationPipeline(model=model, tokenizer=tokenizer)
 
 res = generate_text(
-    "Why is drinking water so healthy?",
+    "日本で一番高い山は富士山ですが、二番目に高い山は？",
     min_new_tokens=2,
     max_new_tokens=256,
     do_sample=False,
@@ -106,7 +106,7 @@ from transformers import AutoModelForCausalLM, AutoTokenizer
 model_name = "yukismd/JapaneseQuizChatbot_v1"  # either local folder or huggingface model name
 # Important: The prompt needs to be in the same format the model was trained with.
 # You can find an example prompt in the experiment logs.
-prompt = "<|prompt|>How are you?<|endoftext|><|answer|>"
+prompt = "<|prompt|>日本で一番高い山は富士山ですが、二番目に高い山は？<|endoftext|><|answer|>"
 
 tokenizer = AutoTokenizer.from_pretrained(model_name, use_fast=True)
 model = AutoModelForCausalLM.from_pretrained(model_name)