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

Jump to bottom

評価用LLMと被評価LLMの temperature の調整 #117

Merged
merged 2 commits into from
May 11, 2024
Merged

評価用LLMと被評価LLMの temperature の調整 #117

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
3ca4e65
:art: 回答にブレが出ないように temperature を調整
keitakn May 11, 2024
e1e2e6d
:art: 評価用LLMのtemperatureはできるだけ小さい値が望ましいので0に設定
keitakn May 11, 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
4 changes: 2 additions & 2 deletions src/infrastructure/repository/openai/openai_cat_message_repository.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -53,7 +53,7 @@ async def generate_message_for_guest_user(
model="gpt-3.5-turbo-1106",
messages=regenerated_messages,
stream=True,
temperature=0.7,
temperature=0.1,
user=user,
)

Expand Down Expand Up @@ -120,7 +120,7 @@ async def _might_regenerate_messages_contain_tools_results_exec(
response = await self.client.chat.completions.create(
model="gpt-3.5-turbo-1106",
messages=copied_messages,
temperature=0.7,
temperature=0,
user=str(dto.get("user_id")),
tools=tools_params,
tool_choice="auto",
Expand Down
2 changes: 1 addition & 1 deletion ...e/repository/openai/openai_cat_message_repository/test_generate_message_for_guest_user.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -163,7 +163,7 @@ async def test_generate_message_for_guest_user(
evaluation_response = await async_open_ai.chat.completions.create(
model="gpt-4-turbo",
messages=[{"role": "system", "content": evaluation_prompt}],
temperature=0.1,
temperature=0,
user=dto.get("user_id"),
response_format={"type": "json_object"},
)
Expand Down
Loading