{ "_name_or_path": "google/flan-t5-small", "architectures": [ "T5ForSequenceClassification" ], "classifier_dropout": 0.0, "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", "finetuning_task": "text-classification", "id2label": { "0": "0", "1": "1", "2": "10", "3": "11", "4": "12", "5": "13", "6": "14", "7": "15", "8": "16", "9": "17", "10": "18", "11": "19", "12": "2", "13": "20", "14": "21", "15": "22", "16": "23", "17": "24", "18": "25", "19": "26", "20": "27", "21": "28", "22": "29", "23": "3", "24": "30", "25": "31", "26": "32", "27": "33", "28": "34", "29": "35", "30": "36", "31": "37", "32": "38", "33": "39", "34": "4", "35": "40", "36": "41", "37": "42", "38": "43", "39": "44", "40": "45", "41": "46", "42": "47", "43": "48", "44": "49", "45": "5", "46": "50", "47": "51", "48": "52", "49": "53", "50": "54", "51": "55", "52": "56", "53": "57", "54": "58", "55": "59", "56": "6", "57": "60", "58": "61", "59": "62", "60": "63", "61": "64", "62": "65", "63": "66", "64": "67", "65": "68", "66": "69", "67": "7", "68": "70", "69": "71", "70": "72", "71": "73", "72": "74", "73": "75", "74": "76", "75": "77", "76": "78", "77": "79", "78": "8", "79": "80", "80": "81", "81": "82", "82": "83", "83": "84", "84": "85", "85": "86", "86": "87", "87": "88", "88": "89", "89": "9", "90": "90", "91": "91", "92": "92", "93": "93", "94": "94", "95": "95", "96": "96", "97": "97", "98": "98", "99": "99" }, "initializer_factor": 1.0, "is_encoder_decoder": true, "is_gated_act": true, "label2id": { "0": 0, "1": 1, "10": 2, "11": 3, "12": 4, "13": 5, "14": 6, "15": 7, "16": 8, "17": 9, "18": 10, "19": 11, "2": 12, "20": 13, "21": 14, "22": 15, "23": 16, "24": 17, "25": 18, "26": 19, "27": 20, "28": 21, "29": 22, "3": 23, "30": 24, "31": 25, "32": 26, "33": 27, "34": 28, "35": 29, "36": 30, "37": 31, "38": 32, "39": 33, "4": 34, "40": 35, "41": 36, "42": 37, "43": 38, "44": 39, "45": 40, "46": 41, "47": 42, "48": 43, "49": 44, "5": 45, "50": 46, "51": 47, "52": 48, "53": 49, "54": 50, "55": 51, "56": 52, "57": 53, "58": 54, "59": 55, "6": 56, "60": 57, "61": 58, "62": 59, "63": 60, "64": 61, "65": 62, "66": 63, "67": 64, "68": 65, "69": 66, "7": 67, "70": 68, "71": 69, "72": 70, "73": 71, "74": 72, "75": 73, "76": 74, "77": 75, "78": 76, "79": 77, "8": 78, "80": 79, "81": 80, "82": 81, "83": 82, "84": 83, "85": 84, "86": 85, "87": 86, "88": 87, "89": 88, "9": 89, "90": 90, "91": 91, "92": 92, "93": 93, "94": 94, "95": 95, "96": 96, "97": 97, "98": 98, "99": 99 }, "layer_norm_epsilon": 1e-06, "model_type": "t5", "n_positions": 512, "num_decoder_layers": 8, "num_heads": 6, "num_layers": 8, "output_past": true, "pad_token_id": 0, "problem_type": "single_label_classification", "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: " } }, "tie_word_embeddings": false, "torch_dtype": "float32", "transformers_version": "4.39.0.dev0", "use_cache": true, "vocab_size": 32128 }