We pre-train ELECTRA small on the TLMD dataset, with over 40 million tokens.
Contained are trained Flax and PyTorch models.
The hyperparameters corresponding to model sizes mentioned above are as follows:
(L = number of layers; AH = number of attention heads; HS = hidden size; FFN = feedforward network dimension; P = number of parameters; Seq = maximum sequence length.)
- Downloads last month