Upload Qwen3ForCausalLM
610ae28 verified - 1.52 kB initial commit
- 5.17 kB Upload Qwen3ForCausalLM
- 1.33 kB Upload Qwen3ForCausalLM
- 117 Bytes Upload Qwen3ForCausalLM
pytorch_model.bin Detected Pickle imports (16)
- "torch.device",
- "torchao.quantization.quant_api._int8_symm_per_token_reduced_range_quant",
- "torch.BFloat16Storage",
- "torchao.dtypes.affine_quantized_tensor.AffineQuantizedTensor",
- "torch._tensor._rebuild_from_type_v2",
- "torchao.quantization.quant_primitives.ZeroPointDomain",
- "collections.OrderedDict",
- "torch._utils._rebuild_wrapper_subclass",
- "torchao.quantization.linear_activation_quantized_tensor.LinearActivationQuantizedTensor",
- "torch.serialization._get_layout",
- "torch.CharStorage",
- "torch.int8",
- "torchao.dtypes.utils.PlainLayout",
- "torch.bfloat16",
- "torchao.dtypes.uintx.plain_layout.PlainAQTTensorImpl",
- "torch._utils._rebuild_tensor_v2"
How to fix it?
753 MB Upload Qwen3ForCausalLM