Llama Factory Finetuning

[yaosheng-zhang]

Reminder

• I have read the above rules and searched the existing issues.

System Info

How to add some characters to the tokenizer before fine-tuning, similar to tokenizer.add_tokens([“<vul_start>”, “<vul_end>”])

Reproduction

Put your message here.

Others

No response

[hiyouga]

--new_special_tokens <vul_start>,<vul_end>

[yaosheng-zhang]

how to add tokens to the llama-factory when operating it on the visualization platform.