Update README.md
30b47e8 verified - 1.52 kB initial commit
- 1.37 kB Update README.md
- 1.66 kB Add TorchAO quantized quantized-microsoft/Phi-4-mini-flash-reasoning
- 1.48 kB Add TorchAO quantized quantized-microsoft/Phi-4-mini-flash-reasoning
- 207 Bytes Add TorchAO quantized quantized-microsoft/Phi-4-mini-flash-reasoning
- 917 kB Add TorchAO quantized quantized-microsoft/Phi-4-mini-flash-reasoning
pytorch_model-00001-of-00004.bin Detected Pickle imports (16)
- "torch.bfloat16",
- "torch.BFloat16Storage",
- "torch.serialization._get_layout",
- "torchao.dtypes.utils.PlainLayout",
- "torchao.quantization.linear_activation_quantized_tensor.LinearActivationQuantizedTensor",
- "torch._utils._rebuild_tensor_v2",
- "torchao.quantization.quant_primitives.ZeroPointDomain",
- "torchao.dtypes.uintx.plain_layout.PlainAQTTensorImpl",
- "torch._tensor._rebuild_from_type_v2",
- "torchao.quantization.quant_api._int8_symm_per_token_reduced_range_quant",
- "torchao.dtypes.affine_quantized_tensor.AffineQuantizedTensor",
- "torch.CharStorage",
- "torch.device",
- "torch._utils._rebuild_wrapper_subclass",
- "torch.int8",
- "collections.OrderedDict"
How to fix it?
4.84 GB Add TorchAO quantized quantized-microsoft/Phi-4-mini-flash-reasoning pytorch_model-00002-of-00004.bin Detected Pickle imports (16)
- "torch.BFloat16Storage",
- "torch.serialization._get_layout",
- "torchao.dtypes.utils.PlainLayout",
- "torchao.quantization.linear_activation_quantized_tensor.LinearActivationQuantizedTensor",
- "torch._utils._rebuild_tensor_v2",
- "torchao.quantization.quant_primitives.ZeroPointDomain",
- "torchao.dtypes.uintx.plain_layout.PlainAQTTensorImpl",
- "torch._tensor._rebuild_from_type_v2",
- "torch._utils._rebuild_wrapper_subclass",
- "torchao.dtypes.affine_quantized_tensor.AffineQuantizedTensor",
- "torch.CharStorage",
- "torchao.quantization.quant_api._int8_symm_per_token_reduced_range_quant",
- "torch.device",
- "torch.bfloat16",
- "torch.int8",
- "collections.OrderedDict"
How to fix it?
4.96 GB Add TorchAO quantized quantized-microsoft/Phi-4-mini-flash-reasoning pytorch_model-00003-of-00004.bin Detected Pickle imports (16)
- "torchao.quantization.quant_primitives.ZeroPointDomain",
- "torchao.dtypes.uintx.plain_layout.PlainAQTTensorImpl",
- "torch._utils._rebuild_wrapper_subclass",
- "collections.OrderedDict",
- "torch.CharStorage",
- "torch.BFloat16Storage",
- "torchao.quantization.linear_activation_quantized_tensor.LinearActivationQuantizedTensor",
- "torchao.dtypes.utils.PlainLayout",
- "torch._tensor._rebuild_from_type_v2",
- "torch.serialization._get_layout",
- "torch.bfloat16",
- "torch.device",
- "torch._utils._rebuild_tensor_v2",
- "torchao.quantization.quant_api._int8_symm_per_token_reduced_range_quant",
- "torch.int8",
- "torchao.dtypes.affine_quantized_tensor.AffineQuantizedTensor"
How to fix it?
4.86 GB Add TorchAO quantized quantized-microsoft/Phi-4-mini-flash-reasoning - 1.03 GB Add TorchAO quantized quantized-microsoft/Phi-4-mini-flash-reasoning
- 20.4 kB Add TorchAO quantized quantized-microsoft/Phi-4-mini-flash-reasoning
- 463 Bytes Add TorchAO quantized quantized-microsoft/Phi-4-mini-flash-reasoning
- 7.15 MB Add TorchAO quantized quantized-microsoft/Phi-4-mini-flash-reasoning
- 17.3 kB Add TorchAO quantized quantized-microsoft/Phi-4-mini-flash-reasoning
- 1.61 MB Add TorchAO quantized quantized-microsoft/Phi-4-mini-flash-reasoning
