roberta_small_mlm_from_scratch

RoBERTa-small을 Codenet데이터로 pre_train한 가중치입니다.

How to use

from transformers import AutoTokenizer, AutoModelForSequenceClassification
tok = AutoTokenizer.from_pretrained("hosung1/roberta_small_mlm_from_scratch")
mdl = AutoModelForSequenceClassification.from_pretrained("hosung1/roberta_small_mlm_from_scratch")

Downloads last month: 4

Safetensors

Model size

35.9M params

Tensor type

F32