Skip to content

Script to call MLX LM with Google flan t5 #58

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

Open
emmagarr wants to merge 3 commits into
base: main
Choose a base branch
from
+23 −0
Open

Script to call MLX LM with Google flan t5 #58

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
0cb1536
script to call mlx with google flan t5
emmagarr Dec 10, 2024
b4984a0
added command line arguments
emmagarr Dec 10, 2024
a17fdcd
script to call mlx lm with flan t5
emmagarr Dec 10, 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
23 changes: 23 additions & 0 deletions ml_mdm/language_models/call_mlx_lm.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,23 @@
from typing import Optional
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
import argparse

def call_mlx_lm(input_text: str, model_name: Optional[str] = "google/flan-t5-base") -> str:
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForSeq2SeqLM.from_pretrained(model_name)

input_ids = tokenizer.encode(input_text, return_tensors="pt")
output_ids = model.generate(input_ids)

output_text = tokenizer.decode(output_ids[0], skip_special_tokens=True)
return output_text

@luke-carlson luke-carlson Dec 11, 2024

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

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

this is still using pytorch, tested by checking print(type(output_ids)) and they were still pytorch tensors.

You could essentially copy in the T5 class + loading logic from https://github.com/ml-explore/mlx-examples/blob/main/t5/t5.py


# command line arguments
if __name__ == "__main__":
parser = argparse.ArgumentParser()
parser.add_argument("--input_text", type=str, required=True)
parser.add_argument("--model", type=str, default="google/flan-t5-base")
args = parser.parse_args()

output_text = call_mlx_lm(args.input_text, args.model)
print(output_text)