| { | |
| "_name_or_path": "lmqg_output/trimmed_qa/mt5-small-trimmed-ru-120000-ruquad-qa/best_model", | |
| "add_prefix": false, | |
| "architectures": [ | |
| "MT5ForConditionalGeneration" | |
| ], | |
| "d_ff": 1024, | |
| "d_kv": 64, | |
| "d_model": 512, | |
| "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": "mt5", | |
| "num_decoder_layers": 8, | |
| "num_heads": 6, | |
| "num_layers": 8, | |
| "pad_token_id": 0, | |
| "relative_attention_max_distance": 128, | |
| "relative_attention_num_buckets": 32, | |
| "tie_word_embeddings": false, | |
| "tokenizer_class": "T5Tokenizer", | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.26.1", | |
| "use_cache": true, | |
| "vocab_size": 120002, | |
| "vocabtrimmer": { | |
| "mining_config": { | |
| "dataset": "vocabtrimmer/mc4_validation", | |
| "dataset_column": "text", | |
| "dataset_name": "ru", | |
| "dataset_split": "validation", | |
| "language": "ru", | |
| "min_frequency": 2, | |
| "target_vocab_size": 120000 | |
| }, | |
| "stats": { | |
| "compression_rate_embedding": 47.97890545035824, | |
| "compression_rate_full": 55.61493153260948, | |
| "parameter_size_embedding/raw": 256114688, | |
| "parameter_size_embedding/trimmed": 122881024, | |
| "parameter_size_full/raw": 300176768, | |
| "parameter_size_full/trimmed": 166943104, | |
| "vocab_size/raw": 250112, | |
| "vocab_size/trimmed": 120001 | |
| } | |
| } | |
| } | |