feat(glm3): adapt to glm3 prompt #2620
Conversation
|
Thanks @silk55 for the contribution! We'd love to add support for ChatGLM3.
|
|
LGTM. |
|
Oh, I think system message after should add a \n |
|
hi there, check this: #2622 I think I follow the format |
| @@ -140,6 +140,17 @@ def get_prompt(self) -> str: | |||
| elif self.sep_style == SeparatorStyle.CHATGLM: | |||
| # source: https://huggingface.co/THUDM/chatglm-6b/blob/1d240ba371910e9282298d4592532d7f0f3e9f3e/modeling_chatglm.py#L1302-L1308 | |||
| # source2: https://huggingface.co/THUDM/chatglm2-6b/blob/e186c891cf64310ac66ef10a87e6635fa6c2a579/modeling_chatglm.py#L926 | |||
| if self.name == "chatglm3": | |||
There was a problem hiding this comment.
Could you put a link to the source here?
There was a problem hiding this comment.
Hi there,
since chatglm3 uses differenet chat format, I do not think we still need to use the 'CHATGLM' separator style and put a if condition to choice the chat format. But putting the chatglm3 chat format into 'CHATGLM' separator style make sense. I suggest an main contributer to dicide do we have to make an new separator style for it @merrymercy
There was a problem hiding this comment.
@silk55 could you add a source?
|
Hi @lucasjinreal @yanyang1024 @silk55 @ZeyuTeng96. You all added the ChatGLM-3 support (#2618, #2620, #2622). |
|
closed by #2622 |
https://huggingface.co/THUDM/chatglm3-6b/blob/fc3235f807ef5527af598c05f04f2ffd17f48bab/tokenization_chatglm.py#L184
added adaptation to chatglm3 new prompt