Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
medmekk
/
Llama-3.1-8B-Instruct-ao-autoquant
like
0
Text Generation
PyTorch
8 languages
llama
torchao-my-repo
facebook
meta
llama-3
torchao
arxiv:
2204.05149
License:
llama3.1
Model card
Files
Files and versions
Community
main
Llama-3.1-8B-Instruct-ao-autoquant
Ctrl+K
Ctrl+K
1 contributor
History:
2 commits
medmekk
HF Staff
Upload folder using huggingface_hub
fd70730
verified
11 days ago
.gitattributes
Safe
1.57 kB
Upload folder using huggingface_hub
11 days ago
README.md
Safe
44.5 kB
Upload folder using huggingface_hub
11 days ago
chat_template.jinja
Safe
4.61 kB
Upload folder using huggingface_hub
11 days ago
config.json
Safe
1.03 kB
Upload folder using huggingface_hub
11 days ago
pytorch_model-00001-of-00004.bin
pickle
Detected Pickle imports (21)
"torch.BFloat16Storage"
,
"torch._utils._rebuild_wrapper_subclass"
,
"torchao.quantization.autoquant.AQGemliteInt4G64WeightOnlyQuantizedLinearWeight"
,
"torchao.quantization.autoquant.AQInt8DynamicallyQuantizedLinearWeight"
,
"torchao.quantization.autoquant.AQBFloat16LinearWeight"
,
"torchao.quantization.autoquant.AQInt4G64WeightOnlyQuantizedLinearWeight"
,
"torchao.quantization.autoquant.AQInt8WeightOnlyQuantizedLinearWeight"
,
"torch.serialization._get_layout"
,
"torch.bfloat16"
,
"torchao.quantization.autoquant.AQFloat8PerTensorScalingDynamicallyQuantizedLinearWeight"
,
"torch._utils._rebuild_tensor_v2"
,
"torchao.quantization.autoquant.AQFloat8WeightOnlyQuantizedLinearWeight"
,
"torchao.quantization.autoquant.AQInt8WeightOnlyQuantizedLinearWeight2"
,
"torchao.quantization.autoquant.AQDefaultLinearWeight"
,
"torch.device"
,
"torchao.quantization.autoquant.AQFloat8PerRowScalingDynamicallyQuantizedLinearWeight"
,
"collections.OrderedDict"
,
"torchao.quantization.autoquant.AQFloat16LinearWeight"
,
"torchao.quantization.autoquant.AQFloat32LinearWeight"
,
"torchao.quantization.autoquant.AutoQuantizableLinearWeight"
,
"torch._tensor._rebuild_from_type_v2"
How to fix it?
4.98 GB
LFS
Upload folder using huggingface_hub
11 days ago
pytorch_model-00002-of-00004.bin
pickle
Detected Pickle imports (21)
"torch.device"
,
"torchao.quantization.autoquant.AQFloat16LinearWeight"
,
"torch.serialization._get_layout"
,
"torchao.quantization.autoquant.AQInt8WeightOnlyQuantizedLinearWeight2"
,
"torch._tensor._rebuild_from_type_v2"
,
"torchao.quantization.autoquant.AQFloat32LinearWeight"
,
"torchao.quantization.autoquant.AQGemliteInt4G64WeightOnlyQuantizedLinearWeight"
,
"torch._utils._rebuild_wrapper_subclass"
,
"collections.OrderedDict"
,
"torchao.quantization.autoquant.AQInt4G64WeightOnlyQuantizedLinearWeight"
,
"torchao.quantization.autoquant.AQBFloat16LinearWeight"
,
"torchao.quantization.autoquant.AQFloat8PerRowScalingDynamicallyQuantizedLinearWeight"
,
"torchao.quantization.autoquant.AQInt8DynamicallyQuantizedLinearWeight"
,
"torch._utils._rebuild_tensor_v2"
,
"torchao.quantization.autoquant.AQDefaultLinearWeight"
,
"torchao.quantization.autoquant.AutoQuantizableLinearWeight"
,
"torch.bfloat16"
,
"torch.BFloat16Storage"
,
"torchao.quantization.autoquant.AQInt8WeightOnlyQuantizedLinearWeight"
,
"torchao.quantization.autoquant.AQFloat8WeightOnlyQuantizedLinearWeight"
,
"torchao.quantization.autoquant.AQFloat8PerTensorScalingDynamicallyQuantizedLinearWeight"
How to fix it?
5 GB
LFS
Upload folder using huggingface_hub
11 days ago
pytorch_model-00003-of-00004.bin
pickle
Detected Pickle imports (21)
"torch.BFloat16Storage"
,
"torchao.quantization.autoquant.AQInt4G64WeightOnlyQuantizedLinearWeight"
,
"torchao.quantization.autoquant.AQGemliteInt4G64WeightOnlyQuantizedLinearWeight"
,
"torchao.quantization.autoquant.AQBFloat16LinearWeight"
,
"torchao.quantization.autoquant.AQFloat32LinearWeight"
,
"torch.bfloat16"
,
"torch._utils._rebuild_wrapper_subclass"
,
"torchao.quantization.autoquant.AQFloat8PerRowScalingDynamicallyQuantizedLinearWeight"
,
"torchao.quantization.autoquant.AQFloat16LinearWeight"
,
"torch._utils._rebuild_tensor_v2"
,
"torchao.quantization.autoquant.AQFloat8PerTensorScalingDynamicallyQuantizedLinearWeight"
,
"torch.serialization._get_layout"
,
"torchao.quantization.autoquant.AQDefaultLinearWeight"
,
"torchao.quantization.autoquant.AQInt8WeightOnlyQuantizedLinearWeight2"
,
"torchao.quantization.autoquant.AQFloat8WeightOnlyQuantizedLinearWeight"
,
"torch._tensor._rebuild_from_type_v2"
,
"torchao.quantization.autoquant.AutoQuantizableLinearWeight"
,
"torch.device"
,
"torchao.quantization.autoquant.AQInt8DynamicallyQuantizedLinearWeight"
,
"torchao.quantization.autoquant.AQInt8WeightOnlyQuantizedLinearWeight"
,
"collections.OrderedDict"
How to fix it?
4.92 GB
LFS
Upload folder using huggingface_hub
11 days ago
pytorch_model-00004-of-00004.bin
pickle
Detected Pickle imports (21)
"torch.BFloat16Storage"
,
"torch._utils._rebuild_wrapper_subclass"
,
"torchao.quantization.autoquant.AQGemliteInt4G64WeightOnlyQuantizedLinearWeight"
,
"torchao.quantization.autoquant.AQInt8DynamicallyQuantizedLinearWeight"
,
"torchao.quantization.autoquant.AQBFloat16LinearWeight"
,
"torchao.quantization.autoquant.AQInt4G64WeightOnlyQuantizedLinearWeight"
,
"torchao.quantization.autoquant.AQInt8WeightOnlyQuantizedLinearWeight"
,
"torch.serialization._get_layout"
,
"torch.bfloat16"
,
"torchao.quantization.autoquant.AQFloat8PerTensorScalingDynamicallyQuantizedLinearWeight"
,
"torch._utils._rebuild_tensor_v2"
,
"torchao.quantization.autoquant.AQFloat8WeightOnlyQuantizedLinearWeight"
,
"torchao.quantization.autoquant.AQInt8WeightOnlyQuantizedLinearWeight2"
,
"torchao.quantization.autoquant.AQDefaultLinearWeight"
,
"torch.device"
,
"torchao.quantization.autoquant.AQFloat8PerRowScalingDynamicallyQuantizedLinearWeight"
,
"collections.OrderedDict"
,
"torchao.quantization.autoquant.AQFloat16LinearWeight"
,
"torchao.quantization.autoquant.AQFloat32LinearWeight"
,
"torchao.quantization.autoquant.AutoQuantizableLinearWeight"
,
"torch._tensor._rebuild_from_type_v2"
How to fix it?
117 MB
LFS
Upload folder using huggingface_hub
11 days ago
pytorch_model.bin.index.json
Safe
22.2 kB
Upload folder using huggingface_hub
11 days ago
special_tokens_map.json
Safe
296 Bytes
Upload folder using huggingface_hub
11 days ago
tokenizer.json
Safe
17.2 MB
LFS
Upload folder using huggingface_hub
11 days ago
tokenizer_config.json
Safe
50.5 kB
Upload folder using huggingface_hub
11 days ago
