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

Feat/custom chat template #1233

Open
wants to merge 6 commits into
base: main
Choose a base branch
from
Open

Feat/custom chat template #1233

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
62d48d7
feat: custom chat template
komninoschatzipapas Jan 30, 2024
f60044f
fix: custom_chat_template
komninoschatzipapas Jan 30, 2024
7ac8a79
docs: fix chat_templates
komninoschatzipapas Jan 30, 2024
9247380
fix: custom_chat_template priority
komninoschatzipapas Jan 30, 2024
3434e36
docs: more conventional chat template for custom_chat_template
komninoschatzipapas Jan 30, 2024
23c1f5d
docs: wrap custom_chat_template string
komninoschatzipapas Jan 30, 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: 2 additions & 0 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -615,6 +615,8 @@ rl:
chat_template: chatml
# Changes the default system message
default_system_message: You are a helpful assistant. Please give a long and detailed answer. # Currently only supports chatml.
# A custom chat template in Jinja format. Will overwrite `chat_template` and `default_system_message`
Copy link
Collaborator

Choose a reason for hiding this comment

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

"May overwrite the default system message" since you could design the chat template to accept one.

custom_chat_template: "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>' + 'assistant' + '\n' }}{% endif %}"
# Axolotl attempts to save the dataset as an arrow after packing the data together so
# subsequent training attempts load faster, relative path
dataset_prepared_path: data/last_run_prepared
Expand Down
4 changes: 3 additions & 1 deletion src/axolotl/utils/models.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -218,7 +218,9 @@ def load_tokenizer(cfg):
LOG.debug(f"PAD: {tokenizer.pad_token_id} / {tokenizer.pad_token}")
LOG.debug(f"UNK: {tokenizer.unk_token_id} / {tokenizer.unk_token}")

if cfg.chat_template:
if cfg.custom_chat_template:
tokenizer.chat_template = cfg.custom_chat_template
Copy link
Collaborator

Choose a reason for hiding this comment

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

similar to the chatml replacement, we could consider some sort of standardized string in the chat template that could be replaced based on the configuration.

elif cfg.chat_template:
chat_template_string = chat_templates(cfg.chat_template)
if cfg.default_system_message and cfg.chat_template == "chatml":
chat_template_string = chat_template_string.replace(
Expand Down