medmekk
/

Meta-Llama-3-8B-quantized-int4_weight_only

Model card Files Files and versions Community

Meta-Llama-3-8B-quantized-int4_weight_only

1 contributor

History: 2 commits

medmekk's picture

medmekk HF staff

Upload folder using huggingface_hub

5c25d06 verified 3 months ago

.gitattributes

1.52 kB

initial commit 3 months ago
config.json

908 Bytes

Upload folder using huggingface_hub 3 months ago
generation_config.json

177 Bytes

Upload folder using huggingface_hub 3 months ago
pytorch_model-00001-of-00002.bin
Detected Pickle imports (14)
- "torchao.dtypes.affine_quantized_tensor.TensorCoreTiledLayoutType",
- "torchao.dtypes.affine_quantized_tensor.TensorCoreTiledAQTLayout",
- "torch.device",
- "torch._utils._rebuild_tensor_v2",
- "torch._utils._rebuild_wrapper_subclass",
- "torch.bfloat16",
- "torch.int32",
- "torch._tensor._rebuild_from_type_v2",
- "torch.IntStorage",
- "collections.OrderedDict",
- "torch.BFloat16Storage",
- "torch.serialization._get_layout",
- "torchao.quantization.quant_primitives.ZeroPointDomain",
- "torchao.dtypes.affine_quantized_tensor.AffineQuantizedTensor"
How to fix it?
4.76 GB
LFS

Upload folder using huggingface_hub 3 months ago
pytorch_model-00002-of-00002.bin
Detected Pickle imports (3)
- "torch.BFloat16Storage",
- "torch._utils._rebuild_tensor_v2",
- "collections.OrderedDict"
What is a pickle import?
1.05 GB
LFS

Upload folder using huggingface_hub 3 months ago
pytorch_model.bin.index.json

23.9 kB

Upload folder using huggingface_hub 3 months ago