Upload files with `vila-upload`.

siglip_encoder.py

@@ -19,12 +19,16 @@ import torch.nn as nn
 import torch.nn.functional as F
 from accelerate.hooks import add_hook_to_module
 from einops import rearrange
-from s2wrapper import forward as multiscale_forward
+
 from transformers import AutoConfig, PretrainedConfig, PreTrainedModel, SiglipImageProcessor
 from transformers.image_processing_utils import BaseImageProcessor
-from transformers.integrations.deepspeed import is_deepspeed_zero3_enabled
 from transformers.models.siglip import SiglipVisionModel
 
+from s2wrapper import forward as multiscale_forward
+
+# from transformers.integrations.deepspeed import is_deepspeed_zero3_enabled
+def is_deepspeed_zero3_enabled():
+    return False
 
 class VisionTower(nn.Module):
     def __init__(self, vision_tower, args, delay_load=False):