Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
medmekk
/
Qwen2.5-0.5B-Instruct-ao-float8wo
like
0
Text Generation
Transformers
PyTorch
English
qwen2
feature-extraction
torchao-my-repo
chat
conversational
text-generation-inference
torchao
arxiv:
2407.10671
License:
apache-2.0
Model card
Files
Files and versions
Community
1
Train
Deploy
Use this model
main
Qwen2.5-0.5B-Instruct-ao-float8wo
Ctrl+K
Ctrl+K
1 contributor
History:
2 commits
medmekk
HF Staff
Upload folder using huggingface_hub
efd354d
verified
about 1 month ago
.gitattributes
Safe
1.57 kB
Upload folder using huggingface_hub
about 1 month ago
README.md
Safe
5.41 kB
Upload folder using huggingface_hub
about 1 month ago
added_tokens.json
Safe
605 Bytes
Upload folder using huggingface_hub
about 1 month ago
config.json
Safe
1.11 kB
Upload folder using huggingface_hub
about 1 month ago
merges.txt
Safe
1.67 MB
Upload folder using huggingface_hub
about 1 month ago
pytorch_model.bin
pickle
Detected Pickle imports (15)
"torch._utils._rebuild_wrapper_subclass"
,
"collections.OrderedDict"
,
"torch._utils._rebuild_tensor_v2"
,
"torchao.dtypes.floatx.float8_layout.Float8Layout"
,
"torch.BFloat16Storage"
,
"torchao.dtypes.affine_quantized_tensor.AffineQuantizedTensor"
,
"torch.storage.UntypedStorage"
,
"torchao.quantization.quant_primitives.ZeroPointDomain"
,
"torch.bfloat16"
,
"torch.serialization._get_layout"
,
"torch._tensor._rebuild_from_type_v2"
,
"torchao.dtypes.floatx.float8_layout.Float8AQTTensorImpl"
,
"torch._utils._rebuild_tensor_v3"
,
"torch.float8_e4m3fn"
,
"torch.device"
How to fix it?
631 MB
LFS
Upload folder using huggingface_hub
about 1 month ago
special_tokens_map.json
Safe
613 Bytes
Upload folder using huggingface_hub
about 1 month ago
tokenizer.json
Safe
11.4 MB
LFS
Upload folder using huggingface_hub
about 1 month ago
tokenizer_config.json
Safe
7.34 kB
Upload folder using huggingface_hub
about 1 month ago
vocab.json
Safe
2.78 MB
Upload folder using huggingface_hub
about 1 month ago