nm-testing
/

paligemma-3b-mix-224-FP8-dynamic

compressed-tensors

Model card Files Files and versions

mgoin commited on Oct 29, 2024

Commit

7d826dc

·

verified ·

1 Parent(s): b548a46

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -29,7 +29,7 @@ recipe = QuantizationModifier(
 )
 # Apply quantization and save to disk in compressed-tensors format.
-SAVE_DIR = MODEL_ID.split("/")[1] + "-FP8-Dynamic"
 oneshot(model=model, recipe=recipe, output_dir=SAVE_DIR)
 processor.save_pretrained(SAVE_DIR)
 ```

 )
 # Apply quantization and save to disk in compressed-tensors format.
+SAVE_DIR = MODEL_ID.split("/")[1] + "-FP8-dynamic"
 oneshot(model=model, recipe=recipe, output_dir=SAVE_DIR)
 processor.save_pretrained(SAVE_DIR)
 ```