Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Add support for Gemma chat template #1530

Merged
merged 3 commits into from
Apr 21, 2024
Merged

Add support for Gemma chat template #1530

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
3b866c9
Add support for Gemma chat template
Haoxiang-Wang Apr 17, 2024
675d68c
Update fschat version to include its newest support for Gemma chat style
Haoxiang-Wang Apr 17, 2024
9471994
pin fastchat to current HEAD
winglian Apr 17, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion requirements.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,7 +28,7 @@ scipy
scikit-learn==1.2.2
pynvml
art
fschat==0.2.36
fschat @ git+https://github.com/lm-sys/FastChat.git@5095615810cf613dba7f27dd155f571fcff976d8
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Would it be possible to use a version instead of commit?

Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Screenshot 2024-04-21 at 4 55 02 PM unfortunately, fastchat hasn't cut a release in a while too.

gradio==3.50.2
tensorboard

Expand Down
8 changes: 8 additions & 0 deletions src/axolotl/monkeypatch/fastchat_conversation_turns.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -123,6 +123,14 @@ def get_turns( # pylint: disable=too-many-return-statements
else:
yield role, ""
return
if self.sep_style == SeparatorStyle.GEMMA:
if self.system_message:
raise ValueError("Gemma chat template does not support system messages")
for i, (role, message) in enumerate(self.messages):
prefix = "<bos>" if i == 0 else ""
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I am a bit confused about this. I don't think you need to add bos manually like this. Axolotl should prepend it.

Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

since this is Gemma specific, and this function doesn't have access to the tokenizer, I think this is fine for now. in other formats in this function, we have literal "" strings.

message_str = message if message else ""
yield prefix + "<start_of_turn>" + role + "\n", message_str + "<end_of_turn>\n"
return
if 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
Expand Down
Loading