| { | |
| "_name_or_path": "Intel/nq_fid_lfqa_early_exit", | |
| "architectures": [ | |
| "FiDT5" | |
| ], | |
| "conf_head_type": "2layer", | |
| "d_ff": 3072, | |
| "d_kv": 64, | |
| "d_model": 768, | |
| "decoder_early_exit_type": null, | |
| "decoder_passage_filter": null, | |
| "decoder_start_token_id": 0, | |
| "dense_act_fn": "relu", | |
| "distil_from_last": false, | |
| "distil_from_last_temp": 1, | |
| "dropout_rate": 0.1, | |
| "eos_token_id": 1, | |
| "feed_forward_proj": "relu", | |
| "initializer_factor": 1.0, | |
| "is_encoder_decoder": true, | |
| "is_gated_act": false, | |
| "layer_norm_epsilon": 1e-06, | |
| "model_type": "t5", | |
| "n_positions": 512, | |
| "num_decoder_layers": 12, | |
| "num_heads": 12, | |
| "num_layers": 12, | |
| "output_past": true, | |
| "pad_token_id": 0, | |
| "relative_attention_max_distance": 128, | |
| "relative_attention_num_buckets": 32, | |
| "share_conf_heads": true, | |
| "task_specific_params": { | |
| "summarization": { | |
| "early_stopping": true, | |
| "length_penalty": 2.0, | |
| "max_length": 200, | |
| "min_length": 30, | |
| "no_repeat_ngram_size": 3, | |
| "num_beams": 4, | |
| "prefix": "summarize: " | |
| }, | |
| "translation_en_to_de": { | |
| "early_stopping": true, | |
| "max_length": 300, | |
| "num_beams": 4, | |
| "prefix": "translate English to German: " | |
| }, | |
| "translation_en_to_fr": { | |
| "early_stopping": true, | |
| "max_length": 300, | |
| "num_beams": 4, | |
| "prefix": "translate English to French: " | |
| }, | |
| "translation_en_to_ro": { | |
| "early_stopping": true, | |
| "max_length": 300, | |
| "num_beams": 4, | |
| "prefix": "translate English to Romanian: " | |
| } | |
| }, | |
| "torch_dtype": "float32", | |
| "train_conf_heads": true, | |
| "transformers_version": "4.16.2", | |
| "use_cache": true, | |
| "use_decoder_heads": false, | |
| "use_shared_decoder_lm_head": true, | |
| "vocab_size": 32128 | |
| } | |