meta-llama

/

Llama-3.1-8B-Instruct

like 3.58k

Follow

Meta Llama 24.3k

I tried to do

from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-3.1-8B-Instruct")

chat = [
  {"role": "user", "content": "Hello, how are you?"},
  {"role": "assistant", "content": "I'm doing great. How can I help you today?"},
  {"role": "user", "content": "I'd like to show off how chat templating works!"},
]

print(tokenizer.apply_chat_template(chat,tokenize=False))

Output:

<|begin_of_text|><|start_header_id|>system<|end_header_id|>

Cutting Knowledge Date: December 2023
Today Date: 26 Jul 2024

<|eot_id|><|start_header_id|>user<|end_header_id|>

Hello, how are you?<|eot_id|><|start_header_id|>assistant<|end_header_id|>

I'm doing great. How can I help you today?<|eot_id|><|start_header_id|>user<|end_header_id|>

I'd like to show off how chat templating works!<|eot_id|>

Why am I getting dates during the tokenization process? This may impact the performance during fine-tuning the model for custom task. Also the date 26 Jul is not updated too.