10000 Add Google's Gemma formatting via `chat_format="gemma"` by alvarobartt · Pull Request #1210 · abetlen/llama-cpp-python · GitHub
[go: up one dir, main page]
Skip to content

Add Google's Gemma formatting via chat_format="gemma" #1210

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
merged 4 commits into from
Feb 23, 2024
Merged

Add Google's Gemma formatting via chat_format="gemma" #1210

Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
3bef2c2
Add Google's Gemma formatting via `chat_format="gemma"`
alvarobartt Feb 22, 2024
afd2869
Replace `raise ValueError` with `logger.debug`
alvarobartt Feb 23, 2024
fd1906d
Merge branch 'main' into main
alvarobartt Feb 23, 2024
f316d55
Merge branch 'main' into main
abetlen Feb 23, 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
21 changes: 21 additions & 0 deletions llama_cpp/llama_chat_format.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,6 +14,7 @@
import llama_cpp.llama_types as llama_types
import llama_cpp.llama_grammar as llama_grammar

from ._logger import logger
from ._utils import suppress_stdout_stderr, Singleton

### Common Chat Templates and Special Tokens ###
Expand Down Expand Up @@ -993,6 +994,26 @@ def format_saiga(
return ChatFormatterResponse(prompt=_prompt.strip())


# Chat format for Google's Gemma models, see more details and available models:
# https://huggingface.co/collections/google/gemma-release-65d5efbccdbb8c4202ec078b
@register_chat_format("gemma")
def format_gemma(
messages: List[llama_types.ChatCompletionRequestMessage],
**kwargs: Any,
) -> ChatFormatterResponse:
system_message = _get_system_message(messages)
if system_message is not None and system_message != "":
logger.debug(
"`role='system'` messages are not allowed on Google's Gemma models."
)
_roles = dict(user="<start_of_turn>user\n", assistant="<start_of_turn>model\n")
_sep = "<end_of_turn>\n"
_messages = _map_roles(messages, _roles)
_messages.append((_roles["assistant"], None))
_prompt = _format_no_colon_single(system_message="", messages=_messages, sep=_sep)
return ChatFormatterResponse(prompt=_prompt, stop=_sep)


# Tricky chat formats that require custom chat handlers


Expand Down
0