🌐 AI搜索 & 代理 主页
Skip to content

Allow for users to pass in a quantization config #1269

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
SilasMarvin merged 1 commit into from
Jan 3, 2024
Merged

Allow for users to pass in a quantization config #1269

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
Allow for users to pass in a quantization config
  • Loading branch information
@SilasMarvin
SilasMarvin committed Jan 3, 2024
commit 6417c83256ad6750aff0ec3fa681696028a2d80a
20 changes: 15 additions & 5 deletions pgml-extension/src/bindings/transformers/transformers.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -41,6 +41,7 @@
PegasusTokenizer,
TrainingArguments,
Trainer,
GPTQConfig
)
import threading

Expand Down Expand Up @@ -279,7 +280,13 @@ def __init__(self, model_name, **kwargs):
elif self.task == "summarization" or self.task == "translation":
self.model = AutoModelForSeq2SeqLM.from_pretrained(model_name, **kwargs)
elif self.task == "text-generation" or self.task == "conversational":
self.model = AutoModelForCausalLM.from_pretrained(model_name, **kwargs)
# See: https://huggingface.co/docs/transformers/main/quantization
if "quantization_config" in kwargs:
quantization_config = kwargs.pop("quantization_config")
quantization_config = GPTQConfig(**quantization_config)
self.model = AutoModelForCausalLM.from_pretrained(model_name, quantization_config=quantization_config, **kwargs)
else:
self.model = AutoModelForCausalLM.from_pretrained(model_name, **kwargs)
else:
raise PgMLException(f"Unhandled task: {self.task}")

Expand Down Expand Up @@ -409,10 +416,13 @@ def create_pipeline(task):
else:
try:
pipe = StandardPipeline(model_name, **task)
except TypeError:
# some models fail when given "device" kwargs, remove and try again
task.pop("device")
pipe = StandardPipeline(model_name, **task)
except TypeError as error:
if "device" in task:
# some models fail when given "device" kwargs, remove and try again
task.pop("device")
pipe = StandardPipeline(model_name, **task)
else:
raise error
return pipe


Expand Down