english-amr2text-model / config.json
acelikyurek's picture
first commit
f5f2f27
{
"_name_or_path": "google/flan-t5-large",
"architectures": [
"T5ForConditionalGeneration"
],
"classifier_dropout": 0.0,
"d_ff": 2816,
"d_kv": 64,
"d_model": 1024,
"decoder_start_token_id": 0,
"dense_act_fn": "gelu_new",
"dropout_rate": 0.1,
"eos_token_id": 1,
"feed_forward_proj": "gated-gelu",
"initializer_factor": 1.0,
"is_encoder_decoder": true,
"is_gated_act": true,
"layer_norm_epsilon": 1e-06,
"model_type": "t5",
"n_positions": 512,
"num_decoder_layers": 24,
"num_heads": 16,
"num_layers": 24,
"output_past": true,
"pad_token_id": 0,
"relative_attention_max_distance": 128,
"relative_attention_num_buckets": 32,
"task_specific_params": {
"translation_amr_to_text": {
"corpus_dir": "/workspace/amrlib-graph-to-text-english/amrlib/data/tdata_generate_xfm",
"custom_save_checkpoint": true,
"eval_batch_size": 8,
"eval_fn": "dev.txt.features.nowiki",
"eval_use_tense": true,
"first_eval_epoch": 0,
"max_in_len": 512,
"max_out_len": 512,
"max_train_graph_len": 512,
"max_train_sent_len": 90,
"model_name_or_path": "google/flan-t5-large",
"save_at_end": true,
"save_tokenizer": false,
"train_fn": "train.txt.features.nowiki.tdata"
}
},
"tie_word_embeddings": false,
"torch_dtype": "float32",
"transformers_version": "4.41.2",
"use_cache": true,
"vocab_size": 32128
}