Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
DaertML
/
phi-1_5-nf4-fp16compute-doublequant-BNB
like
0
Text Generation
Transformers
PyTorch
mixformer-sequential
custom_code
Model card
Files
Files and versions
Community
Train
Use this model
main
phi-1_5-nf4-fp16compute-doublequant-BNB
1 contributor
History:
2 commits
DaertML
ADD doublequant 4 bit quantization of phi 1.5B model
18d7875
about 1 year ago
.gitattributes
Safe
1.52 kB
initial commit
about 1 year ago
added_tokens.json
Safe
1.08 kB
ADD doublequant 4 bit quantization of phi 1.5B model
about 1 year ago
config.json
Safe
923 Bytes
ADD doublequant 4 bit quantization of phi 1.5B model
about 1 year ago
generation_config.json
Safe
69 Bytes
ADD doublequant 4 bit quantization of phi 1.5B model
about 1 year ago
merges.txt
Safe
456 kB
ADD doublequant 4 bit quantization of phi 1.5B model
about 1 year ago
pytorch_model.bin
Safe
pickle
Detected Pickle imports (3)
"collections.OrderedDict"
,
"torch.FloatStorage"
,
"torch._utils._rebuild_tensor_v2"
What is a pickle import?
5.67 GB
LFS
ADD doublequant 4 bit quantization of phi 1.5B model
about 1 year ago
special_tokens_map.json
Safe
99 Bytes
ADD doublequant 4 bit quantization of phi 1.5B model
about 1 year ago
tokenizer.json
Safe
2.11 MB
ADD doublequant 4 bit quantization of phi 1.5B model
about 1 year ago
tokenizer_config.json
Safe
237 Bytes
ADD doublequant 4 bit quantization of phi 1.5B model
about 1 year ago
vocab.json
Safe
798 kB
ADD doublequant 4 bit quantization of phi 1.5B model
about 1 year ago