Closed yeonju7kim closed 7 months ago
https://github.com/Alpha-VLLM/LLaMA2-Accessory/blob/32f9a9ebbaccfa5a1cda95bc3172f6129a8680f7/accessory/data/alpaca.py#L223C1-L224C65
In this code, it looks like the model only uses the first conversation. I found the same thing in LLaMA-adapter repository.
https://github.com/OpenGVLab/LLaMA-Adapter/issues/123
Is there any reason why the model only uses the first conversation?
SPHINX use multi-turn conversation.
We use this dataset for fine-tuning: https://github.com/Alpha-VLLM/LLaMA2-Accessory/blob/32f9a9ebbaccfa5a1cda95bc3172f6129a8680f7/accessory/data/conversation/dataset.py
https://github.com/Alpha-VLLM/LLaMA2-Accessory/blob/32f9a9ebbaccfa5a1cda95bc3172f6129a8680f7/accessory/data/alpaca.py#L223C1-L224C65
In this code, it looks like the model only uses the first conversation. I found the same thing in LLaMA-adapter repository.
https://github.com/OpenGVLab/LLaMA-Adapter/issues/123
Is there any reason why the model only uses the first conversation?