Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
Muennighoff
/
SGPT-2.7B-weightedmean-msmarco-specb-bitfit
like
3
Sentence Similarity
sentence-transformers
PyTorch
gpt_neo
feature-extraction
mteb
Eval Results
Inference Endpoints
arxiv:
2202.08904
Model card
Files
Files and versions
Community
2
Train
Deploy
Use this model
main
SGPT-2.7B-weightedmean-msmarco-specb-bitfit
1 contributor
History:
10 commits
Muennighoff
Update README.md
44ec091
over 1 year ago
1_Pooling
Add SGPT-2.7B-weightedmean-msmarco-specb-bitfit
almost 3 years ago
evaluation
Format MTEB evaluation
about 2 years ago
.gitattributes
Safe
1.18 kB
initial commit
almost 3 years ago
README.md
Safe
65.5 kB
Update README.md
over 1 year ago
added_tokens.json
Safe
32 Bytes
Add SGPT-2.7B-weightedmean-msmarco-specb-bitfit
almost 3 years ago
config.json
Safe
1.52 kB
Better model with bs=256
over 2 years ago
config_sentence_transformers.json
Safe
123 Bytes
Better model with bs=256
over 2 years ago
merges.txt
Safe
456 kB
Add SGPT-2.7B-weightedmean-msmarco-specb-bitfit
almost 3 years ago
modules.json
Safe
229 Bytes
Add SGPT-2.7B-weightedmean-msmarco-specb-bitfit
almost 3 years ago
pytorch_model-00001-of-00002.bin
Safe
pickle
Detected Pickle imports (4)
"torch._utils._rebuild_tensor_v2"
,
"torch.ByteStorage"
,
"collections.OrderedDict"
,
"torch.FloatStorage"
What is a pickle import?
10 GB
LFS
Better model with bs=256
over 2 years ago
pytorch_model-00002-of-00002.bin
Safe
pickle
Detected Pickle imports (4)
"collections.OrderedDict"
,
"torch.ByteStorage"
,
"torch.FloatStorage"
,
"torch._utils._rebuild_tensor_v2"
What is a pickle import?
743 MB
LFS
Better model with bs=256
over 2 years ago
pytorch_model.bin.index.json
Safe
32.8 kB
LFS
Better model with bs=256
over 2 years ago
sentence_bert_config.json
Safe
53 Bytes
Add SGPT-2.7B-weightedmean-msmarco-specb-bitfit
almost 3 years ago
special_tokens_map.json
Safe
120 Bytes
Add SGPT-2.7B-weightedmean-msmarco-specb-bitfit
almost 3 years ago
tokenizer.json
Safe
2.11 MB
Better model with bs=256
over 2 years ago
tokenizer_config.json
Safe
658 Bytes
Better model with bs=256
over 2 years ago
vocab.json
Safe
798 kB
Add SGPT-2.7B-weightedmean-msmarco-specb-bitfit
almost 3 years ago