ByT5_g2g / config.json
sp1r05's picture
Upload T5ForConditionalGeneration
ab53207 verified
raw
history blame
860 Bytes
{
"_name_or_path": "/home/sp1r05/Documents/gsoc/gr-nlp-toolkit/gr_nlp_toolkit/tmp/ByT5-TV",
"architectures": [
"T5ForConditionalGeneration"
],
"d_ff": 3584,
"d_kv": 64,
"d_model": 1472,
"decoder_start_token_id": 0,
"dense_act_fn": "gelu_new",
"dropout_rate": 0.1,
"eos_token_id": 1,
"feed_forward_proj": "gated-gelu",
"gradient_checkpointing": false,
"initializer_factor": 1.0,
"is_encoder_decoder": true,
"is_gated_act": true,
"layer_norm_epsilon": 1e-06,
"model_type": "t5",
"num_decoder_layers": 4,
"num_heads": 6,
"num_layers": 12,
"pad_token_id": 0,
"relative_attention_max_distance": 128,
"relative_attention_num_buckets": 32,
"tie_word_embeddings": false,
"tokenizer_class": "ByT5Tokenizer",
"torch_dtype": "float32",
"transformers_version": "4.30.2",
"use_cache": true,
"vocab_size": 384
}