medmekk
/

llama-3.2-1b-float8-torchao

Model card Files Files and versions

llama-3.2-1b-float8-torchao

3.53 GB

1 contributor

History: 2 commits

medmekk's picture

medmekk HF Staff

Upload folder using huggingface_hub

a8beee1 verified 22 days ago

.gitattributes

1.52 kB

initial commit 22 days ago
config.json

1.41 kB

Upload folder using huggingface_hub 22 days ago
generation_config.json

188 Bytes

Upload folder using huggingface_hub 22 days ago
model.safetensors

2.03 GB
xet

Upload folder using huggingface_hub 22 days ago
pytorch_model.bin
Detected Pickle imports (14)
- "torch._utils._rebuild_tensor_v2",
- "torch.bfloat16",
- "torch.storage.UntypedStorage",
- "torch.FloatStorage",
- "torch.serialization._get_layout",
- "collections.OrderedDict",
- "torch._utils._rebuild_wrapper_subclass",
- "torchao.quantization.quantize_.common.kernel_preference.KernelPreference",
- "torch.BFloat16Storage",
- "torch._tensor._rebuild_from_type_v2",
- "torch.float8_e4m3fn",
- "torch.device",
- "torch._utils._rebuild_tensor_v3",
- "torchao.quantization.Float8Tensor"
How to fix it?
1.5 GB
xet

Upload folder using huggingface_hub 22 days ago