Upload processor
6ef756e
verified
-
1.57 kB
Upload processor
-
5.17 kB
Upload Qwen2_5_VLForConditionalGeneration
-
605 Bytes
Upload processor
-
1.02 kB
Upload processor
-
3 kB
Upload Qwen2_5_VLForConditionalGeneration
-
214 Bytes
Upload Qwen2_5_VLForConditionalGeneration
-
1.67 MB
Upload processor
-
575 Bytes
Upload processor
pytorch_model.bin
Detected Pickle imports (15)
- "torch.device",
- "torch.BFloat16Storage",
- "torch.CharStorage",
- "torch.serialization._get_layout",
- "torchao.dtypes.utils.PlainLayout",
- "torchao.dtypes.uintx.plain_layout.PlainAQTTensorImpl",
- "torch.LongStorage",
- "collections.OrderedDict",
- "torch.bfloat16",
- "torch._utils._rebuild_tensor_v2",
- "torchao.quantization.quant_primitives.ZeroPointDomain",
- "torch._utils._rebuild_wrapper_subclass",
- "torch.int8",
- "torch._tensor._rebuild_from_type_v2",
- "torchao.dtypes.affine_quantized_tensor.AffineQuantizedTensor"
How to fix it?
4.75 GB
Upload Qwen2_5_VLForConditionalGeneration
-
613 Bytes
Upload processor
-
11.4 MB
Upload processor
-
4.73 kB
Upload processor
-
1.73 kB
Upload processor
-
2.78 MB
Upload processor