1 contributor

History: 2 commits

bobox

KL divergence loss layers selfdistill....Multi step multi task training.

869170b verified 6 months ago

1_Pooling
KL divergence loss layers selfdistill....Multi step multi task training. 6 months ago
.gitattributes

1.52 kB

initial commit 6 months ago
README.md

408 kB

KL divergence loss layers selfdistill....Multi step multi task training. 6 months ago
added_tokens.json

23 Bytes

KL divergence loss layers selfdistill....Multi step multi task training. 6 months ago
config.json

879 Bytes

KL divergence loss layers selfdistill....Multi step multi task training. 6 months ago
config_sentence_transformers.json

195 Bytes

KL divergence loss layers selfdistill....Multi step multi task training. 6 months ago
modules.json

229 Bytes

KL divergence loss layers selfdistill....Multi step multi task training. 6 months ago
pytorch_model.bin
Detected Pickle imports (3)
- "torch.FloatStorage",
- "collections.OrderedDict",
- "torch._utils._rebuild_tensor_v2"
What is a pickle import?
565 MB
LFS

KL divergence loss layers selfdistill....Multi step multi task training. 6 months ago
sentence_bert_config.json

53 Bytes

KL divergence loss layers selfdistill....Multi step multi task training. 6 months ago
special_tokens_map.json

970 Bytes

KL divergence loss layers selfdistill....Multi step multi task training. 6 months ago
spm.model

2.46 MB
LFS

KL divergence loss layers selfdistill....Multi step multi task training. 6 months ago
tokenizer.json

8.65 MB

KL divergence loss layers selfdistill....Multi step multi task training. 6 months ago
tokenizer_config.json

1.48 kB

KL divergence loss layers selfdistill....Multi step multi task training. 6 months ago

Detected Pickle imports (3)