yhavinga's picture
Update config.json
eead863
raw
history blame
857 Bytes
{
"_name_or_path": "yhavinga/t5-v1.1-large-dutch-cased-2",
"architectures": [
"T5ForConditionalGeneration"
],
"d_ff": 2816,
"d_kv": 64,
"d_model": 1024,
"decoder_start_token_id": 0,
"dropout_rate": 0.1,
"eos_token_id": 1,
"feed_forward_proj": "gated-gelu",
"gradient_checkpointing": false,
"initializer_factor": 1.0,
"is_encoder_decoder": true,
"layer_norm_epsilon": 1e-06,
"model_type": "t5",
"num_decoder_layers": 24,
"num_heads": 16,
"num_layers": 24,
"output_past": true,
"pad_token_id": 0,
"relative_attention_num_buckets": 32,
"tie_word_embeddings": false,
"torch_dtype": "float32",
"transformers_version": "4.13.0",
"use_cache": true,
"vocab_size": 32103,
"no_repeat_ngram_size": 3,
"num_beams": 6,
"num_beam_groups": 2,
"min_length": 75,
"max_length": 142,
"length_penalty": 1.2
}