Closed sevenandseven closed 3 months ago
logger.info("Resize model embeddings to fit tokenizer") base_model.resize_token_embeddings(tokenzier_vocab_size)
“Okay, thank you for your reply.”
Using your method, new problems have emerged.
手动改词表了吗?没改词表的话不会报tokenzier_vocab_size > model_vocab_size的问题,把transformers降级到4.28.1
没有手动改词表,就是用的工程的run_pt使用的txt数据,对base模型进行二次微调的。我试试降低版本。
Describe the Question
Please provide a clear and concise description of what the question is.
Hello, during the process of using LORA to fine-tune the chatglm3 base model, an inconsistency problem between the model vocabulary and the tokenization vocabulary occurred during the merging process. How can I solve this?