HuggingFaceTB
/

SmolVLM2-256M-Video-Instruct

Video-Text-to-Text

image-text-to-text

Inference Endpoints

Model card Files Files and versions Community

orrzohar commited on 2 days ago

Commit

eb77138

·

verified ·

1 Parent(s): e083124

update readme dtype

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -95,7 +95,7 @@ inputs = processor.apply_chat_template(
     tokenize=True,
     return_dict=True,
     return_tensors="pt",
-).to(model.device)
 generated_ids = model.generate(**inputs, do_sample=False, max_new_tokens=64)
 generated_texts = processor.batch_decode(

     tokenize=True,
     return_dict=True,
     return_tensors="pt",
+).to(model.device, dtype=torch.bfloat16)
 generated_ids = model.generate(**inputs, do_sample=False, max_new_tokens=64)
 generated_texts = processor.batch_decode(