Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
AminBH
/
Llama-3-8B-Quanto-2bit
like
0
Model card
Files
Files and versions
Community
main
Llama-3-8B-Quanto-2bit
1 contributor
History:
2 commits
AminBH
Upload Llama-3-8B-Quanto-2bit.pt with huggingface_hub
98832c3
verified
3 months ago
.gitattributes
1.52 kB
initial commit
3 months ago
Llama-3-8B-Quanto-2bit.pt
pickle
Detected Pickle imports (32)
"transformers.utils.quantization_config.QuantizationMethod"
,
"__builtin__.set"
,
"collections.OrderedDict"
,
"torch.FloatStorage"
,
"transformers.models.llama.modeling_llama.LlamaRotaryEmbedding"
,
"torch.nn.modules.sparse.Embedding"
,
"transformers.models.llama.modeling_llama.LlamaModel"
,
"torch.CharStorage"
,
"transformers.models.llama.modeling_llama.LlamaRMSNorm"
,
"torch._utils._rebuild_parameter"
,
"quanto.nn.qlinear.QLinear"
,
"torch._tensor._rebuild_from_type_v2"
,
"torch._utils._rebuild_wrapper_subclass"
,
"quanto.tensor.qbits.qbits.QBitsTensor"
,
"torch.serialization._get_layout"
,
"transformers.models.llama.modeling_llama.LlamaSdpaAttention"
,
"torch.nn.modules.container.ModuleList"
,
"transformers.quantizers.quantizer_quanto.QuantoHfQuantizer"
,
"torch.int8"
,
"torch._utils._rebuild_tensor_v2"
,
"torch.bfloat16"
,
"torch.ByteStorage"
,
"quanto.tensor.qbits.packed.PackedTensor"
,
"quanto.tensor.qtype.qtype"
,
"torch.device"
,
"torch.BFloat16Storage"
,
"torch.nn.modules.activation.SiLU"
,
"transformers.models.llama.modeling_llama.LlamaDecoderLayer"
,
"transformers.models.llama.configuration_llama.LlamaConfig"
,
"transformers.models.llama.modeling_llama.LlamaMLP"
,
"torch.uint8"
,
"transformers.utils.quantization_config.QuantoConfig"
How to fix it?
2.96 GB
LFS
Upload Llama-3-8B-Quanto-2bit.pt with huggingface_hub
3 months ago