{ "d_model": null, "device": "cpu", "model_kwargs": {}, "model_name": "LPTM2", "patch_len": 8, "patch_stride_len": 8, "seq_len": 512, "t5_config": { "architectures": [ "T5ForConditionalGeneration" ], "attn_implementation": null, "d_ff": 2816, "d_kv": 64, "d_model": 1024, "decoder_start_token_id": 0, "dropout_rate": 0.1, "eos_token_id": 1, "feed_forward_proj": "gated-gelu", "initializer_factor": 1.0, "is_encoder_decoder": 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, "tie_word_embeddings": false, "use_cache": true, "vocab_size": 32128 }, "task_name": "reconstruction", "transformer_backbone": "google/flan-t5-large", "transformer_type": "encoder_only" }