Update config.json

config.json

@@ -1,375 +1,375 @@
-{
-  "_name_or_path": "microsoft/Florence-2-base-ft",
-  "architectures": [
-    "Florence2ForConditionalGeneration"
-  ],
-  "auto_map": {
-    "AutoConfig": "microsoft/Florence-2-base-ft--configuration_florence2.Florence2Config",
-    "AutoModelForCausalLM": "microsoft/Florence-2-base-ft--modeling_florence2.Florence2ForConditionalGeneration"
-  },
-  "bos_token_id": 2,
-  "eos_token_id": 1,
-  "id2label": {
-    "0": "LABEL_0",
-    "1": "LABEL_1",
-    "2": "LABEL_2",
-    "3": "LABEL_3",
-    "4": "LABEL_4",
-    "5": "LABEL_5",
-    "6": "LABEL_6",
-    "7": "LABEL_7",
-    "8": "LABEL_8",
-    "9": "LABEL_9",
-    "10": "LABEL_10",
-    "11": "LABEL_11",
-    "12": "LABEL_12",
-    "13": "LABEL_13",
-    "14": "LABEL_14",
-    "15": "LABEL_15",
-    "16": "LABEL_16",
-    "17": "LABEL_17",
-    "18": "LABEL_18",
-    "19": "LABEL_19",
-    "20": "LABEL_20",
-    "21": "LABEL_21",
-    "22": "LABEL_22",
-    "23": "LABEL_23",
-    "24": "LABEL_24",
-    "25": "LABEL_25",
-    "26": "LABEL_26",
-    "27": "LABEL_27",
-    "28": "LABEL_28",
-    "29": "LABEL_29",
-    "30": "LABEL_30",
-    "31": "LABEL_31",
-    "32": "LABEL_32",
-    "33": "LABEL_33",
-    "34": "LABEL_34",
-    "35": "LABEL_35",
-    "36": "LABEL_36",
-    "37": "LABEL_37",
-    "38": "LABEL_38",
-    "39": "LABEL_39",
-    "40": "LABEL_40",
-    "41": "LABEL_41",
-    "42": "LABEL_42",
-    "43": "LABEL_43",
-    "44": "LABEL_44",
-    "45": "LABEL_45",
-    "46": "LABEL_46",
-    "47": "LABEL_47",
-    "48": "LABEL_48",
-    "49": "LABEL_49",
-    "50": "LABEL_50",
-    "51": "LABEL_51",
-    "52": "LABEL_52",
-    "53": "LABEL_53",
-    "54": "LABEL_54",
-    "55": "LABEL_55",
-    "56": "LABEL_56",
-    "57": "LABEL_57",
-    "58": "LABEL_58",
-    "59": "LABEL_59",
-    "60": "LABEL_60",
-    "61": "LABEL_61",
-    "62": "LABEL_62",
-    "63": "LABEL_63",
-    "64": "LABEL_64",
-    "65": "LABEL_65",
-    "66": "LABEL_66"
-  },
-  "ignore_index": -100,
-  "is_encoder_decoder": true,
-  "label2id": {
-    "LABEL_0": 0,
-    "LABEL_1": 1,
-    "LABEL_10": 10,
-    "LABEL_11": 11,
-    "LABEL_12": 12,
-    "LABEL_13": 13,
-    "LABEL_14": 14,
-    "LABEL_15": 15,
-    "LABEL_16": 16,
-    "LABEL_17": 17,
-    "LABEL_18": 18,
-    "LABEL_19": 19,
-    "LABEL_2": 2,
-    "LABEL_20": 20,
-    "LABEL_21": 21,
-    "LABEL_22": 22,
-    "LABEL_23": 23,
-    "LABEL_24": 24,
-    "LABEL_25": 25,
-    "LABEL_26": 26,
-    "LABEL_27": 27,
-    "LABEL_28": 28,
-    "LABEL_29": 29,
-    "LABEL_3": 3,
-    "LABEL_30": 30,
-    "LABEL_31": 31,
-    "LABEL_32": 32,
-    "LABEL_33": 33,
-    "LABEL_34": 34,
-    "LABEL_35": 35,
-    "LABEL_36": 36,
-    "LABEL_37": 37,
-    "LABEL_38": 38,
-    "LABEL_39": 39,
-    "LABEL_4": 4,
-    "LABEL_40": 40,
-    "LABEL_41": 41,
-    "LABEL_42": 42,
-    "LABEL_43": 43,
-    "LABEL_44": 44,
-    "LABEL_45": 45,
-    "LABEL_46": 46,
-    "LABEL_47": 47,
-    "LABEL_48": 48,
-    "LABEL_49": 49,
-    "LABEL_5": 5,
-    "LABEL_50": 50,
-    "LABEL_51": 51,
-    "LABEL_52": 52,
-    "LABEL_53": 53,
-    "LABEL_54": 54,
-    "LABEL_55": 55,
-    "LABEL_56": 56,
-    "LABEL_57": 57,
-    "LABEL_58": 58,
-    "LABEL_59": 59,
-    "LABEL_6": 6,
-    "LABEL_60": 60,
-    "LABEL_61": 61,
-    "LABEL_62": 62,
-    "LABEL_63": 63,
-    "LABEL_64": 64,
-    "LABEL_65": 65,
-    "LABEL_66": 66,
-    "LABEL_7": 7,
-    "LABEL_8": 8,
-    "LABEL_9": 9
-  },
-  "model_type": "florence2",
-  "pad_token_id": 0,
-  "projection_dim": 768,
-  "text_config": {
-    "_name_or_path": "",
-    "activation_dropout": 0.1,
-    "activation_function": "gelu",
-    "add_bias_logits": false,
-    "add_cross_attention": false,
-    "add_final_layer_norm": false,
-    "architectures": null,
-    "attention_dropout": 0.1,
-    "bad_words_ids": null,
-    "begin_suppress_tokens": null,
-    "bos_token_id": 0,
-    "chunk_size_feed_forward": 0,
-    "classif_dropout": 0.1,
-    "classifier_dropout": 0.0,
-    "cross_attention_hidden_size": null,
-    "d_model": 768,
-    "decoder_attention_heads": 12,
-    "decoder_ffn_dim": 3072,
-    "decoder_layerdrop": 0.0,
-    "decoder_layers": 6,
-    "decoder_start_token_id": 2,
-    "diversity_penalty": 0.0,
-    "do_sample": false,
-    "dropout": 0.1,
-    "early_stopping": true,
-    "encoder_attention_heads": 12,
-    "encoder_ffn_dim": 3072,
-    "encoder_layerdrop": 0.0,
-    "encoder_layers": 6,
-    "encoder_no_repeat_ngram_size": 0,
-    "eos_token_id": 2,
-    "exponential_decay_length_penalty": null,
-    "finetuning_task": null,
-    "forced_bos_token_id": 0,
-    "forced_eos_token_id": 2,
-    "gradient_checkpointing": false,
-    "id2label": {
-      "0": "LABEL_0",
-      "1": "LABEL_1",
-      "2": "LABEL_2"
-    },
-    "init_std": 0.02,
-    "is_decoder": false,
-    "is_encoder_decoder": true,
-    "label2id": {
-      "LABEL_0": 0,
-      "LABEL_1": 1,
-      "LABEL_2": 2
-    },
-    "length_penalty": 1.0,
-    "max_length": 20,
-    "max_position_embeddings": 1024,
-    "min_length": 0,
-    "model_type": "florence2_language",
-    "no_repeat_ngram_size": 3,
-    "normalize_before": false,
-    "num_beam_groups": 1,
-    "num_beams": 3,
-    "num_hidden_layers": 6,
-    "num_return_sequences": 1,
-    "output_attentions": false,
-    "output_hidden_states": false,
-    "output_scores": false,
-    "pad_token_id": 1,
-    "prefix": null,
-    "problem_type": null,
-    "pruned_heads": {},
-    "remove_invalid_values": false,
-    "repetition_penalty": 1.0,
-    "return_dict": true,
-    "return_dict_in_generate": false,
-    "scale_embedding": false,
-    "sep_token_id": null,
-    "suppress_tokens": null,
-    "task_specific_params": null,
-    "temperature": 1.0,
-    "tf_legacy_loss": false,
-    "tie_encoder_decoder": false,
-    "tie_word_embeddings": true,
-    "tokenizer_class": null,
-    "top_k": 50,
-    "top_p": 1.0,
-    "torch_dtype": null,
-    "torchscript": false,
-    "typical_p": 1.0,
-    "use_bfloat16": false,
-    "use_cache": true,
-    "vocab_size": 51289
-  },
-  "torch_dtype": "float32",
-  "transformers_version": "4.41.2",
-  "vision_config": {
-    "_name_or_path": "",
-    "add_cross_attention": false,
-    "architectures": null,
-    "bad_words_ids": null,
-    "begin_suppress_tokens": null,
-    "bos_token_id": null,
-    "chunk_size_feed_forward": 0,
-    "cross_attention_hidden_size": null,
-    "decoder_start_token_id": null,
-    "depths": [
-      1,
-      1,
-      9,
-      1
-    ],
-    "dim_embed": [
-      128,
-      256,
-      512,
-      1024
-    ],
-    "diversity_penalty": 0.0,
-    "do_sample": false,
-    "drop_path_rate": 0.1,
-    "early_stopping": false,
-    "enable_checkpoint": false,
-    "encoder_no_repeat_ngram_size": 0,
-    "eos_token_id": null,
-    "exponential_decay_length_penalty": null,
-    "finetuning_task": null,
-    "forced_bos_token_id": null,
-    "forced_eos_token_id": null,
-    "id2label": {
-      "0": "LABEL_0",
-      "1": "LABEL_1"
-    },
-    "image_feature_source": [
-      "spatial_avg_pool",
-      "temporal_avg_pool"
-    ],
-    "image_pos_embed": {
-      "max_pos_embeddings": 50,
-      "type": "learned_abs_2d"
-    },
-    "is_decoder": false,
-    "is_encoder_decoder": false,
-    "label2id": {
-      "LABEL_0": 0,
-      "LABEL_1": 1
-    },
-    "length_penalty": 1.0,
-    "max_length": 20,
-    "min_length": 0,
-    "model_type": "",
-    "no_repeat_ngram_size": 0,
-    "num_beam_groups": 1,
-    "num_beams": 1,
-    "num_groups": [
-      4,
-      8,
-      16,
-      32
-    ],
-    "num_heads": [
-      4,
-      8,
-      16,
-      32
-    ],
-    "num_return_sequences": 1,
-    "output_attentions": false,
-    "output_hidden_states": false,
-    "output_scores": false,
-    "pad_token_id": null,
-    "patch_padding": [
-      3,
-      1,
-      1,
-      1
-    ],
-    "patch_prenorm": [
-      false,
-      true,
-      true,
-      true
-    ],
-    "patch_size": [
-      7,
-      3,
-      3,
-      3
-    ],
-    "patch_stride": [
-      4,
-      2,
-      2,
-      2
-    ],
-    "prefix": null,
-    "problem_type": null,
-    "projection_dim": 768,
-    "pruned_heads": {},
-    "remove_invalid_values": false,
-    "repetition_penalty": 1.0,
-    "return_dict": true,
-    "return_dict_in_generate": false,
-    "sep_token_id": null,
-    "suppress_tokens": null,
-    "task_specific_params": null,
-    "temperature": 1.0,
-    "tf_legacy_loss": false,
-    "tie_encoder_decoder": false,
-    "tie_word_embeddings": true,
-    "tokenizer_class": null,
-    "top_k": 50,
-    "top_p": 1.0,
-    "torch_dtype": null,
-    "torchscript": false,
-    "typical_p": 1.0,
-    "use_bfloat16": false,
-    "visual_temporal_embedding": {
-      "max_temporal_embeddings": 100,
-      "type": "COSINE"
-    },
-    "window_size": 12
-  },
-  "vocab_size": 51289
-}
+{
+  "_name_or_path": "microsoft/Florence-2-base-ft",
+  "architectures": [
+    "Florence2ForConditionalGeneration"
+  ],
+  "auto_map": {
+    "AutoConfig": "microsoft/Florence-2-base-ft--configuration_florence2.Florence2Config",
+    "AutoModelForCausalLM": "microsoft/Florence-2-base-ft--modeling_florence2.Florence2ForConditionalGeneration"
+  },
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8",
+    "9": "LABEL_9",
+    "10": "LABEL_10",
+    "11": "LABEL_11",
+    "12": "LABEL_12",
+    "13": "LABEL_13",
+    "14": "LABEL_14",
+    "15": "LABEL_15",
+    "16": "LABEL_16",
+    "17": "LABEL_17",
+    "18": "LABEL_18",
+    "19": "LABEL_19",
+    "20": "LABEL_20",
+    "21": "LABEL_21",
+    "22": "LABEL_22",
+    "23": "LABEL_23",
+    "24": "LABEL_24",
+    "25": "LABEL_25",
+    "26": "LABEL_26",
+    "27": "LABEL_27",
+    "28": "LABEL_28",
+    "29": "LABEL_29",
+    "30": "LABEL_30",
+    "31": "LABEL_31",
+    "32": "LABEL_32",
+    "33": "LABEL_33",
+    "34": "LABEL_34",
+    "35": "LABEL_35",
+    "36": "LABEL_36",
+    "37": "LABEL_37",
+    "38": "LABEL_38",
+    "39": "LABEL_39",
+    "40": "LABEL_40",
+    "41": "LABEL_41",
+    "42": "LABEL_42",
+    "43": "LABEL_43",
+    "44": "LABEL_44",
+    "45": "LABEL_45",
+    "46": "LABEL_46",
+    "47": "LABEL_47",
+    "48": "LABEL_48",
+    "49": "LABEL_49",
+    "50": "LABEL_50",
+    "51": "LABEL_51",
+    "52": "LABEL_52",
+    "53": "LABEL_53",
+    "54": "LABEL_54",
+    "55": "LABEL_55",
+    "56": "LABEL_56",
+    "57": "LABEL_57",
+    "58": "LABEL_58",
+    "59": "LABEL_59",
+    "60": "LABEL_60",
+    "61": "LABEL_61",
+    "62": "LABEL_62",
+    "63": "LABEL_63",
+    "64": "LABEL_64",
+    "65": "LABEL_65",
+    "66": "LABEL_66"
+  },
+  "ignore_index": -100,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "LABEL_11": 11,
+    "LABEL_12": 12,
+    "LABEL_13": 13,
+    "LABEL_14": 14,
+    "LABEL_15": 15,
+    "LABEL_16": 16,
+    "LABEL_17": 17,
+    "LABEL_18": 18,
+    "LABEL_19": 19,
+    "LABEL_2": 2,
+    "LABEL_20": 20,
+    "LABEL_21": 21,
+    "LABEL_22": 22,
+    "LABEL_23": 23,
+    "LABEL_24": 24,
+    "LABEL_25": 25,
+    "LABEL_26": 26,
+    "LABEL_27": 27,
+    "LABEL_28": 28,
+    "LABEL_29": 29,
+    "LABEL_3": 3,
+    "LABEL_30": 30,
+    "LABEL_31": 31,
+    "LABEL_32": 32,
+    "LABEL_33": 33,
+    "LABEL_34": 34,
+    "LABEL_35": 35,
+    "LABEL_36": 36,
+    "LABEL_37": 37,
+    "LABEL_38": 38,
+    "LABEL_39": 39,
+    "LABEL_4": 4,
+    "LABEL_40": 40,
+    "LABEL_41": 41,
+    "LABEL_42": 42,
+    "LABEL_43": 43,
+    "LABEL_44": 44,
+    "LABEL_45": 45,
+    "LABEL_46": 46,
+    "LABEL_47": 47,
+    "LABEL_48": 48,
+    "LABEL_49": 49,
+    "LABEL_5": 5,
+    "LABEL_50": 50,
+    "LABEL_51": 51,
+    "LABEL_52": 52,
+    "LABEL_53": 53,
+    "LABEL_54": 54,
+    "LABEL_55": 55,
+    "LABEL_56": 56,
+    "LABEL_57": 57,
+    "LABEL_58": 58,
+    "LABEL_59": 59,
+    "LABEL_6": 6,
+    "LABEL_60": 60,
+    "LABEL_61": 61,
+    "LABEL_62": 62,
+    "LABEL_63": 63,
+    "LABEL_64": 64,
+    "LABEL_65": 65,
+    "LABEL_66": 66,
+    "LABEL_7": 7,
+    "LABEL_8": 8,
+    "LABEL_9": 9
+  },
+  "model_type": "florence2",
+  "pad_token_id": 0,
+  "projection_dim": 768,
+  "text_config": {
+    "_name_or_path": "",
+    "activation_dropout": 0.1,
+    "activation_function": "gelu",
+    "add_bias_logits": false,
+    "add_cross_attention": false,
+    "add_final_layer_norm": false,
+    "architectures": null,
+    "attention_dropout": 0.1,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 0,
+    "chunk_size_feed_forward": 0,
+    "classif_dropout": 0.1,
+    "classifier_dropout": 0.0,
+    "cross_attention_hidden_size": null,
+    "d_model": 768,
+    "decoder_attention_heads": 12,
+    "decoder_ffn_dim": 3072,
+    "decoder_layerdrop": 0.0,
+    "decoder_layers": 6,
+    "decoder_start_token_id": 2,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout": 0.1,
+    "early_stopping": true,
+    "encoder_attention_heads": 12,
+    "encoder_ffn_dim": 3072,
+    "encoder_layerdrop": 0.0,
+    "encoder_layers": 6,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 2,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": 0,
+    "forced_eos_token_id": 2,
+    "gradient_checkpointing": false,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1",
+      "2": "LABEL_2"
+    },
+    "init_std": 0.02,
+    "is_decoder": false,
+    "is_encoder_decoder": true,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1,
+      "LABEL_2": 2
+    },
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 1024,
+    "min_length": 0,
+    "model_type": "florence2_language",
+    "no_repeat_ngram_size": 3,
+    "normalize_before": false,
+    "num_beam_groups": 1,
+    "num_beams": 3,
+    "num_hidden_layers": 6,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 1,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "scale_embedding": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 51289
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "vision_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "depths": [
+      1,
+      1,
+      9,
+      1
+    ],
+    "dim_embed": [
+      128,
+      256,
+      512,
+      1024
+    ],
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "drop_path_rate": 0.1,
+    "early_stopping": false,
+    "enable_checkpoint": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "image_feature_source": [
+      "spatial_avg_pool",
+      "temporal_avg_pool"
+    ],
+    "image_pos_embed": {
+      "max_pos_embeddings": 50,
+      "type": "learned_abs_2d"
+    },
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "davit",
+    "no_repeat_ngram_size": 0,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_groups": [
+      4,
+      8,
+      16,
+      32
+    ],
+    "num_heads": [
+      4,
+      8,
+      16,
+      32
+    ],
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "patch_padding": [
+      3,
+      1,
+      1,
+      1
+    ],
+    "patch_prenorm": [
+      false,
+      true,
+      true,
+      true
+    ],
+    "patch_size": [
+      7,
+      3,
+      3,
+      3
+    ],
+    "patch_stride": [
+      4,
+      2,
+      2,
+      2
+    ],
+    "prefix": null,
+    "problem_type": null,
+    "projection_dim": 768,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "visual_temporal_embedding": {
+      "max_temporal_embeddings": 100,
+      "type": "COSINE"
+    },
+    "window_size": 12
+  },
+  "vocab_size": 51289
+}