Skip to content

Support multiple chat templates - step 1 #1396

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 5 commits into from
May 9, 2024
Merged

Support multiple chat templates - step 1 #1396

Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
6b36976
Support multiple chat templates - step 1
CISC Apr 27, 2024
27c3235
Merge branch 'main' into multiple-chat-templates-part1
abetlen May 8, 2024
a5a45ea
register chat templates to self.chat_formats instead of globally
CISC May 8, 2024
223d798
Merge branch 'main' into multiple-chat-templates-part1
abetlen May 9, 2024
a5b2efc
Don't expose internal chat handlers yet
abetlen May 9, 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
50 changes: 28 additions & 22 deletions llama_cpp/llama.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -378,6 +378,7 @@ def __init__(

self.chat_format = chat_format
self.chat_handler = chat_handler
self._chat_handlers: Dict[str, llama_chat_format.LlamaChatCompletionHandler] = {}

self.draft_model = draft_model

Expand Down Expand Up @@ -409,10 +410,33 @@ def __init__(
if self.verbose:
print(f"Model metadata: {self.metadata}", file=sys.stderr)

eos_token_id = int(self.metadata.get("tokenizer.ggml.eos_token_id", self.token_eos()))
bos_token_id = int(self.metadata.get("tokenizer.ggml.bos_token_id", self.token_bos()))

eos_token = self._model.token_get_text(eos_token_id)
bos_token = self._model.token_get_text(bos_token_id)

# Unfortunately the llama.cpp API does not return metadata arrays, so we can't get template names from tokenizer.chat_templates
template_choices = dict((name[10:], template) for name, template in self.metadata.items() if name.startswith("tokenizer.chat_template."))

if "tokenizer.chat_template" in self.metadata:
template_choices["chat_template.default"] = self.metadata["tokenizer.chat_template"]

if self.verbose and template_choices:
print(f"Available chat formats from metadata: {', '.join(template_choices.keys())}", file=sys.stderr)

for name, template in template_choices.items():
self._chat_handlers[name] = llama_chat_format.Jinja2ChatFormatter(
template=template,
eos_token=eos_token,
bos_token=bos_token,
stop_token_ids=[eos_token_id],
).to_chat_handler()

if (
self.chat_format is None
and self.chat_handler is None
and "tokenizer.chat_template" in self.metadata
and "chat_template.default" in template_choices
):
chat_format = llama_chat_format.guess_chat_format_from_gguf_metadata(
self.metadata
Expand All @@ -423,30 +447,12 @@ def __init__(
if self.verbose:
print(f"Guessed chat format: {chat_format}", file=sys.stderr)
else:
template = self.metadata["tokenizer.chat_template"]
try:
eos_token_id = int(self.metadata["tokenizer.ggml.eos_token_id"])
except:
eos_token_id = self.token_eos()
try:
bos_token_id = int(self.metadata["tokenizer.ggml.bos_token_id"])
except:
bos_token_id = self.token_bos()

eos_token = self._model.token_get_text(eos_token_id)
bos_token = self._model.token_get_text(bos_token_id)

if self.verbose:
print(f"Using gguf chat template: {template}", file=sys.stderr)
print(f"Using gguf chat template: {template_choices['chat_template.default']}", file=sys.stderr)
print(f"Using chat eos_token: {eos_token}", file=sys.stderr)
print(f"Using chat bos_token: {bos_token}", file=sys.stderr)

self.chat_handler = llama_chat_format.Jinja2ChatFormatter(
template=template,
eos_token=eos_token,
bos_token=bos_token,
stop_token_ids=[eos_token_id],
).to_chat_handler()
self.chat_format = "chat_template.default"

if self.chat_format is None and self.chat_handler is None:
self.chat_format = "llama-2"
Expand Down Expand Up @@ -1719,7 +1725,7 @@ def create_chat_completion(
Returns:
Generated chat completion or a stream of chat completion chunks.
"""
handler = self.chat_handler or llama_chat_format.get_chat_completion_handler(
handler = self.chat_handler or self._chat_handlers.get(self.chat_format) or llama_chat_format.get_chat_completion_handler(
self.chat_format
)
return handler(
Expand Down