jerryzh168
/

Meta-Llama-3-8B-torchao-int4_weight_only-gs_64

Model card Files Files and versions Community

Meta-Llama-3-8B-torchao-int4_weight_only-gs_64

1 contributor

History: 2 commits

jerryzh168's picture

Upload folder using huggingface_hub

034cab2 verified 19 days ago

.gitattributes

1.52 kB

initial commit 19 days ago
README.md

691 Bytes

Upload folder using huggingface_hub 19 days ago
config.json

930 Bytes

Upload folder using huggingface_hub 19 days ago
pytorch_model.bin
Detected Pickle imports (14)
- "torch.serialization._get_layout",
- "torchao.dtypes.affine_quantized_tensor.AffineQuantizedTensor",
- "torch._utils._rebuild_wrapper_subclass",
- "torch.IntStorage",
- "torch._tensor._rebuild_from_type_v2",
- "torch.BFloat16Storage",
- "torchao.dtypes.affine_quantized_tensor.TensorCoreTiledLayoutType",
- "torch.int32",
- "torch._utils._rebuild_tensor_v2",
- "torch.bfloat16",
- "torch.device",
- "torchao.quantization.quant_primitives.ZeroPointDomain",
- "torchao.dtypes.affine_quantized_tensor.TensorCoreTiledAQTLayout",
- "collections.OrderedDict"
How to fix it?
4.98 GB
LFS

Upload folder using huggingface_hub 19 days ago