How to merge the bias item of c_attn = nn.Linear(config.hidden_size, 3 * self.projection_size) into LLama?

#2
by songkq - opened

Hello, could you please share how to merge the bias item of c_attn = nn.Linear(config.hidden_size, 3 * self.projection_size) into LLama?

This model was forked from https://huggingface.co./JosephusCheung/Qwen-LLaMAfied-7B-Chat , I only changed the tokenizer. I don't have weight convert script either. You can ask JosephusCheung for help.

OK. Thanks.

This model was forked from https://huggingface.co./JosephusCheung/Qwen-LLaMAfied-7B-Chat , I only changed the tokenizer. I don't have weight convert script either. You can ask JosephusCheung for help.

songkq changed discussion status to closed

Sign up or log in to comment