{ "_name_or_path": "ckpts/gimlet", "architectures": [ "GraphT5TransformerForConditionalGeneration" ], "d_ff": 2048, "d_kv": 64, "d_model": 512, "decoder_start_token_id": 0, "dense_act_fn": "relu", "dropout_rate": 0.1, "eos_token_id": 1, "feed_forward_proj": "relu", "graph_args": { "apply_graphormer_init": true, "dropout": 0.0, "edge_type": "multi_hop", "encoder_attention_heads": 8, "encoder_embed_dim": 512, "encoder_layers": 6, "encoder_normalize_before": false, "graphonly_problem_type": "", "graphonly_readout": "mean", "loss_reduction_method": "token", "maskt2g": true, "max_nodes": 128, "multi_hop_max_dist": 5, "num_atoms": 4608, "num_classes": -1, "num_edge_dis": 128, "num_edges": 1536, "num_in_degree": 512, "num_out_degree": 512, "num_spatial": 512, "spatial_pos_max": 1024, "transformer_backbone": "gimlet" }, "initializer_factor": 1.0, "is_encoder_decoder": true, "is_gated_act": false, "layer_norm_epsilon": 1e-06, "loss_reduction_method": "token", "model_type": "t5", "n_positions": 512, "num_decoder_layers": 6, "num_heads": 8, "num_layers": 6, "output_past": true, "pad_token_id": 0, "relative_attention_max_distance": 128, "relative_attention_num_buckets": 32, "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", "transformers_version": "4.28.0.dev0", "use_cache": true, "vocab_size": 32100 }