t5-tiny-nl6-finnish / config.json
aapot
Add 20k train step and HF flax model
0998a82
raw history blame
No virus
683 Bytes
{
"_name_or_path": "./",
"architectures": [
"T5ForConditionalGeneration"
],
"d_ff": 1024,
"d_kv": 64,
"d_model": 256,
"decoder_start_token_id": 0,
"dropout_rate": 0.1,
"eos_token_id": 1,
"feed_forward_proj": "gated-gelu",
"initializer_factor": 1.0,
"is_encoder_decoder": true,
"layer_norm_epsilon": 1e-06,
"model_type": "t5",
"n_positions": 512,
"num_decoder_layers": 6,
"num_heads": 4,
"num_layers": 6,
"output_past": true,
"pad_token_id": 0,
"relative_attention_max_distance": 128,
"relative_attention_num_buckets": 32,
"tie_word_embeddings": false,
"transformers_version": "4.18.0",
"use_cache": true,
"vocab_size": 32128
}