DeBERTa-ST-AllLayers-v3.1 / config_sentence_transformers.json
bobox's picture
KL divergence loss layers selfdistill....Multi step multi task training.
a232ba1 verified
raw
history blame
No virus
195 Bytes
{
"__version__": {
"sentence_transformers": "3.0.1",
"transformers": "4.42.3",
"pytorch": "2.1.2"
},
"prompts": {},
"default_prompt_name": null,
"similarity_fn_name": null
}