Update README.md

README.md

@@ -1,3 +1,7 @@
+---
+base_model:
+- microsoft/Phi-3.5-vision-instruct
+---
 
 ## Creation
 
@@ -28,11 +32,4 @@ recipe = QuantizationModifier(
 SAVE_DIR = MODEL_ID.split("/")[1] + "-FP8-Dynamic"
 oneshot(model=model, recipe=recipe, output_dir=SAVE_DIR)
 processor.save_pretrained(SAVE_DIR)
-
-# Confirm generations of the quantized model look sane.
-print("========== SAMPLE GENERATION ==============")
-input_ids = processor(text="Hello my name is", return_tensors="pt").input_ids.to("cuda")
-output = model.generate(input_ids, max_new_tokens=20)
-print(processor.decode(output[0]))
-print("==========================================")
 ```