flan-t5-large-PLsql / config.json
MRNH's picture
Upload config.json with huggingface_hub
650408b
{
"vocab_size": 32107,
"d_model": 1024,
"d_kv": 64,
"d_ff": 2816,
"num_layers": 24,
"num_decoder_layers": 24,
"num_heads": 16,
"relative_attention_num_buckets": 32,
"relative_attention_max_distance": 128,
"dropout_rate": 0.1,
"classifier_dropout": 0.0,
"layer_norm_epsilon": 1e-06,
"initializer_factor": 1.0,
"feed_forward_proj": "gated-gelu",
"use_cache": true,
"dense_act_fn": "gelu_new",
"is_gated_act": true,
"return_dict": true,
"output_hidden_states": false,
"output_attentions": false,
"torchscript": false,
"torch_dtype": null,
"use_bfloat16": false,
"tf_legacy_loss": false,
"pruned_heads": {},
"tie_word_embeddings": false,
"is_encoder_decoder": true,
"is_decoder": false,
"cross_attention_hidden_size": null,
"add_cross_attention": false,
"tie_encoder_decoder": false,
"max_length": 20,
"min_length": 0,
"do_sample": false,
"early_stopping": false,
"num_beams": 1,
"num_beam_groups": 1,
"diversity_penalty": 0.0,
"temperature": 1.0,
"top_k": 50,
"top_p": 1.0,
"typical_p": 1.0,
"repetition_penalty": 1.0,
"length_penalty": 1.0,
"no_repeat_ngram_size": 0,
"encoder_no_repeat_ngram_size": 0,
"bad_words_ids": null,
"num_return_sequences": 1,
"chunk_size_feed_forward": 0,
"output_scores": false,
"return_dict_in_generate": false,
"forced_bos_token_id": null,
"forced_eos_token_id": null,
"remove_invalid_values": false,
"exponential_decay_length_penalty": null,
"suppress_tokens": null,
"begin_suppress_tokens": null,
"architectures": [
"T5ForConditionalGeneration"
],
"finetuning_task": null,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"tokenizer_class": null,
"prefix": null,
"bos_token_id": null,
"pad_token_id": 0,
"eos_token_id": 1,
"sep_token_id": null,
"decoder_start_token_id": 0,
"task_specific_params": null,
"problem_type": null,
"_name_or_path": "MRNH/flan-t5-large-PLsql",
"transformers_version": "4.33.3",
"model_type": "t5",
"n_positions": 512,
"output_past": true
}