upload tokenizer
abf7d7b
verified
-
1.57 kB
upload tokenizer
-
5.17 kB
upload quantized model
-
707 Bytes
upload tokenizer
-
1.57 kB
upload quantized model
-
117 Bytes
upload quantized model
-
1.67 MB
upload tokenizer
pytorch_model.bin
Detected Pickle imports (21)
- "torch.Size",
- "torch._utils._rebuild_wrapper_subclass",
- "torchao.quantization.linear_activation_quantized_tensor.LinearActivationQuantizedTensor",
- "torchao.quantization.quant_api._input_activation_quant_func_fp8",
- "torchao.dtypes.floatx.float8_layout.Float8AQTTensorImpl",
- "torchao.quantization.quant_primitives.ZeroPointDomain",
- "collections.OrderedDict",
- "torchao.dtypes.affine_quantized_tensor.AffineQuantizedTensor",
- "torchao.float8.inference.Float8MMConfig",
- "torch.storage.UntypedStorage",
- "torch.BFloat16Storage",
- "torch.bfloat16",
- "torch.float8_e4m3fn",
- "torch._tensor._rebuild_from_type_v2",
- "torch._utils._rebuild_tensor_v3",
- "torch._utils._rebuild_tensor_v2",
- "torch.device",
- "torch.FloatStorage",
- "torchao.dtypes.floatx.float8_layout.Float8Layout",
- "torch.serialization._get_layout",
- "torchao.quantization.granularity.PerTensor"
How to fix it?
752 MB
upload quantized model
-
616 Bytes
upload tokenizer
-
11.4 MB
upload tokenizer
-
9.71 kB
upload tokenizer
-
2.78 MB
upload tokenizer