HuggingFaceH4

/

SmolLM3-3B-QAT-Baseline-Q

like 0

Follow

Hugging Face H4 1.41k

• "torch._tensor._rebuild_from_type_v2",
• "torch.device",
• "torchao.dtypes.uintx.plain_layout.PlainAQTTensorImpl",
• "torchao.dtypes.affine_quantized_tensor.AffineQuantizedTensor",
• "torch.CharStorage",
• "torch.bfloat16",
• "torch._utils._rebuild_tensor_v2",
• "torch.serialization._get_layout",
• "torch.int8",
• "torch._utils._rebuild_wrapper_subclass",
• "torch.BFloat16Storage",
• "torchao.quantization.linear_activation_quantized_tensor.LinearActivationQuantizedTensor",
• "collections.OrderedDict",
• "torchao.dtypes.utils.PlainLayout",
• "torchao.quantization.quant_api._int8_asymm_per_token_quant",
• "torchao.quantization.quant_primitives.ZeroPointDomain"

How to fix it?