Skip to content

Fix conv_template of chinese alpaca 2 #2812

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

Merged
merrymercy merged 3 commits into from
Dec 24, 2023
Merged

Fix conv_template of chinese alpaca 2 #2812

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
225963f
add support for Chinese-LLaMA-Alpaca
zollty Nov 6, 2023
23489a2
Merge branch 'main' of https://github.com/zollty/FastChat
zollty Dec 13, 2023
4e223f7
Fix conv_template of chinese alpaca 2
zollty Dec 13, 2023
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
12 changes: 12 additions & 0 deletions fastchat/conversation.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -990,6 +990,18 @@ def get_conv_template(name: str) -> Conversation:
)
)

register_conv_template(
Conversation(
name="chinese-alpaca2",
system_template="[INST] <<SYS>>\n{system_message}\n<</SYS>>\n\n",
system_message="You are a helpful assistant. 你是一个乐于助人的助手。请你提供专业、有逻辑、内容真实、有价值的详细回复。",
roles=("[INST]", "[/INST]"),
sep_style=SeparatorStyle.LLAMA2,
sep=" ",
sep2=" </s><s>",
)
)

register_conv_template(
Conversation(
name="cutegpt",
Expand Down
2 changes: 1 addition & 1 deletion fastchat/model/model_adapter.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1760,7 +1760,7 @@ def load_model(self, model_path: str, from_pretrained_kwargs: dict):
return model, tokenizer

def get_default_conv_template(self, model_path: str) -> Conversation:
return get_conv_template("llama2-chinese")
return get_conv_template("chinese-alpaca2")


class VigogneAdapter(BaseModelAdapter):
Expand Down