Upload processor
42c6ad6 verified - 1.57 kB Upload processor
- 5.17 kB Upload Gemma3ForConditionalGeneration
- 35 Bytes Upload processor
- 1.62 kB Upload processor
- 2.49 kB Upload Gemma3ForConditionalGeneration
- 215 Bytes Upload Gemma3ForConditionalGeneration
- 570 Bytes Upload processor
- 70 Bytes Upload processor
pytorch_model.bin Detected Pickle imports (20)
- "torch.serialization._get_layout",
- "torchao.float8.inference.Float8MMConfig",
- "torch._tensor._rebuild_from_type_v2",
- "torch.BFloat16Storage",
- "torch.device",
- "torchao.dtypes.affine_quantized_tensor.AffineQuantizedTensor",
- "torchao.quantization.linear_activation_quantized_tensor.LinearActivationQuantizedTensor",
- "torch.bfloat16",
- "collections.OrderedDict",
- "torch._utils._rebuild_tensor_v2",
- "torchao.quantization.granularity.PerRow",
- "torchao.dtypes.floatx.float8_layout.Float8Layout",
- "torchao.dtypes.floatx.float8_layout.Float8AQTTensorImpl",
- "torch.FloatStorage",
- "torchao.quantization.quant_api._input_activation_quant_func_fp8",
- "torch._utils._rebuild_wrapper_subclass",
- "torchao.quantization.quant_primitives.ZeroPointDomain",
- "torch._utils._rebuild_tensor_v3",
- "torch.storage.UntypedStorage",
- "torch.float8_e4m3fn"
How to fix it?
4.99 GB Upload Gemma3ForConditionalGeneration - 662 Bytes Upload processor
- 33.4 MB Upload processor
- 4.69 MB Upload processor
- 1.16 MB Upload processor
