From 5ca49c93b1b5b89979ff5a99c5fdb1f97ff81983 Mon Sep 17 00:00:00 2001 From: Daya Guo <40300434+guoday@users.noreply.github.com> Date: Fri, 2 Feb 2024 10:42:46 +0800 Subject: [PATCH] Update eos token id --- README.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index c8a2ebf..2c1e8a2 100644 --- a/README.md +++ b/README.md @@ -135,8 +135,8 @@ messages=[ { 'role': 'user', 'content': "write a quick sort algorithm in python."} ] inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to(model.device) -# 32021 is the id of <|EOT|> token -outputs = model.generate(inputs, max_new_tokens=512, do_sample=False, top_k=50, top_p=0.95, num_return_sequences=1, eos_token_id=32021) +# tokenizer.eos_token_id is the id of <|EOT|> token +outputs = model.generate(inputs, max_new_tokens=512, do_sample=False, top_k=50, top_p=0.95, num_return_sequences=1, eos_token_id=tokenizer.eos_token_id) print(tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True)) ``` This code will output the following result: