Upload 2 files

added_tokens.json

@@ -0,0 +1,205 @@
+{
+  "<mask>": 256203,
+  "ace_Arab": 256001,
+  "ace_Latn": 256002,
+  "acm_Arab": 256003,
+  "acq_Arab": 256004,
+  "aeb_Arab": 256005,
+  "afr_Latn": 256006,
+  "ajp_Arab": 256007,
+  "aka_Latn": 256008,
+  "als_Latn": 256162,
+  "amh_Ethi": 256009,
+  "apc_Arab": 256010,
+  "arb_Arab": 256011,
+  "ars_Arab": 256012,
+  "ary_Arab": 256013,
+  "arz_Arab": 256014,
+  "asm_Beng": 256015,
+  "ast_Latn": 256016,
+  "awa_Deva": 256017,
+  "ayr_Latn": 256018,
+  "azb_Arab": 256019,
+  "azj_Latn": 256020,
+  "bak_Cyrl": 256021,
+  "bam_Latn": 256022,
+  "ban_Latn": 256023,
+  "bel_Cyrl": 256024,
+  "bem_Latn": 256025,
+  "ben_Beng": 256026,
+  "bho_Deva": 256027,
+  "bjn_Arab": 256028,
+  "bjn_Latn": 256029,
+  "bod_Tibt": 256030,
+  "bos_Latn": 256031,
+  "bug_Latn": 256032,
+  "bul_Cyrl": 256033,
+  "cat_Latn": 256034,
+  "ceb_Latn": 256035,
+  "ces_Latn": 256036,
+  "cjk_Latn": 256037,
+  "ckb_Arab": 256038,
+  "crh_Latn": 256039,
+  "cym_Latn": 256040,
+  "dan_Latn": 256041,
+  "deu_Latn": 256042,
+  "dik_Latn": 256043,
+  "dyu_Latn": 256044,
+  "dzo_Tibt": 256045,
+  "ell_Grek": 256046,
+  "eng_Latn": 256047,
+  "epo_Latn": 256048,
+  "est_Latn": 256049,
+  "eus_Latn": 256050,
+  "ewe_Latn": 256051,
+  "fao_Latn": 256052,
+  "fij_Latn": 256054,
+  "fin_Latn": 256055,
+  "fon_Latn": 256056,
+  "fra_Latn": 256057,
+  "fur_Latn": 256058,
+  "fuv_Latn": 256059,
+  "gaz_Latn": 256135,
+  "gla_Latn": 256060,
+  "gle_Latn": 256061,
+  "glg_Latn": 256062,
+  "grn_Latn": 256063,
+  "guj_Gujr": 256064,
+  "hat_Latn": 256065,
+  "hau_Latn": 256066,
+  "heb_Hebr": 256067,
+  "hin_Deva": 256068,
+  "hne_Deva": 256069,
+  "hrv_Latn": 256070,
+  "hun_Latn": 256071,
+  "hye_Armn": 256072,
+  "ibo_Latn": 256073,
+  "ilo_Latn": 256074,
+  "ind_Latn": 256075,
+  "isl_Latn": 256076,
+  "ita_Latn": 256077,
+  "jav_Latn": 256078,
+  "jpn_Jpan": 256079,
+  "kab_Latn": 256080,
+  "kac_Latn": 256081,
+  "kam_Latn": 256082,
+  "kan_Knda": 256083,
+  "kas_Arab": 256084,
+  "kas_Deva": 256085,
+  "kat_Geor": 256086,
+  "kaz_Cyrl": 256089,
+  "kbp_Latn": 256090,
+  "kea_Latn": 256091,
+  "khk_Cyrl": 256122,
+  "khm_Khmr": 256092,
+  "kik_Latn": 256093,
+  "kin_Latn": 256094,
+  "kir_Cyrl": 256095,
+  "kmb_Latn": 256096,
+  "kmr_Latn": 256099,
+  "knc_Arab": 256087,
+  "knc_Latn": 256088,
+  "kon_Latn": 256097,
+  "kor_Hang": 256098,
+  "lao_Laoo": 256100,
+  "lij_Latn": 256102,
+  "lim_Latn": 256103,
+  "lin_Latn": 256104,
+  "lit_Latn": 256105,
+  "lmo_Latn": 256106,
+  "ltg_Latn": 256107,
+  "ltz_Latn": 256108,
+  "lua_Latn": 256109,
+  "lug_Latn": 256110,
+  "luo_Latn": 256111,
+  "lus_Latn": 256112,
+  "lvs_Latn": 256101,
+  "mag_Deva": 256113,
+  "mai_Deva": 256114,
+  "mal_Mlym": 256115,
+  "mar_Deva": 256116,
+  "min_Latn": 256117,
+  "mkd_Cyrl": 256118,
+  "mlt_Latn": 256120,
+  "mni_Beng": 256121,
+  "mos_Latn": 256123,
+  "mri_Latn": 256124,
+  "mya_Mymr": 256126,
+  "nld_Latn": 256127,
+  "nno_Latn": 256128,
+  "nob_Latn": 256129,
+  "npi_Deva": 256130,
+  "nso_Latn": 256131,
+  "nus_Latn": 256132,
+  "nya_Latn": 256133,
+  "oci_Latn": 256134,
+  "ory_Orya": 256136,
+  "pag_Latn": 256137,
+  "pan_Guru": 256138,
+  "pap_Latn": 256139,
+  "pbt_Arab": 256143,
+  "pes_Arab": 256053,
+  "plt_Latn": 256119,
+  "pol_Latn": 256140,
+  "por_Latn": 256141,
+  "prs_Arab": 256142,
+  "quy_Latn": 256144,
+  "ron_Latn": 256145,
+  "run_Latn": 256146,
+  "rus_Cyrl": 256147,
+  "sag_Latn": 256148,
+  "san_Deva": 256149,
+  "sat_Beng": 256150,
+  "scn_Latn": 256151,
+  "shn_Mymr": 256152,
+  "sin_Sinh": 256153,
+  "slk_Latn": 256154,
+  "slv_Latn": 256155,
+  "smo_Latn": 256156,
+  "sna_Latn": 256157,
+  "snd_Arab": 256158,
+  "som_Latn": 256159,
+  "sot_Latn": 256160,
+  "spa_Latn": 256161,
+  "srd_Latn": 256163,
+  "srp_Cyrl": 256164,
+  "ssw_Latn": 256165,
+  "sun_Latn": 256166,
+  "swe_Latn": 256167,
+  "swh_Latn": 256168,
+  "szl_Latn": 256169,
+  "tam_Taml": 256170,
+  "taq_Latn": 256177,
+  "taq_Tfng": 256178,
+  "tat_Cyrl": 256171,
+  "tel_Telu": 256172,
+  "tgk_Cyrl": 256173,
+  "tgl_Latn": 256174,
+  "tha_Thai": 256175,
+  "tir_Ethi": 256176,
+  "tpi_Latn": 256179,
+  "tsn_Latn": 256180,
+  "tso_Latn": 256181,
+  "tuk_Latn": 256182,
+  "tum_Latn": 256183,
+  "tur_Latn": 256184,
+  "twi_Latn": 256185,
+  "tzm_Tfng": 256186,
+  "uig_Arab": 256187,
+  "ukr_Cyrl": 256188,
+  "umb_Latn": 256189,
+  "urd_Arab": 256190,
+  "uzn_Latn": 256191,
+  "vec_Latn": 256192,
+  "vie_Latn": 256193,
+  "war_Latn": 256194,
+  "wol_Latn": 256195,
+  "xho_Latn": 256196,
+  "ydd_Hebr": 256197,
+  "yor_Latn": 256198,
+  "yue_Hant": 256199,
+  "zho_Hans": 256200,
+  "zho_Hant": 256201,
+  "zsm_Latn": 256125,
+  "zul_Latn": 256202
+}

config.json

@@ -0,0 +1,173 @@
+{
+  "_name_or_path": "ocrmodel-small-printed-V2/checkpoint-37640",
+  "architectures": [
+    "VisionEncoderDecoderModel"
+  ],
+  "decoder": {
+    "_name_or_path": "",
+    "activation_dropout": 0.0,
+    "activation_function": "relu",
+    "add_cross_attention": true,
+    "architectures": null,
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 0,
+    "chunk_size_feed_forward": 0,
+    "classifier_dropout": 0.0,
+    "cross_attention_hidden_size": 384,
+    "d_model": 256,
+    "decoder_attention_heads": 8,
+    "decoder_ffn_dim": 1024,
+    "decoder_layerdrop": 0.0,
+    "decoder_layers": 6,
+    "decoder_start_token_id": 2,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout": 0.1,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 2,
+    "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"
+    },
+    "init_std": 0.02,
+    "is_decoder": true,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layernorm_embedding": true,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 512,
+    "min_length": 0,
+    "model_type": "trocr",
+    "no_repeat_ngram_size": 0,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "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": true,
+    "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": false,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": false,
+    "use_learned_position_embeddings": true,
+    "vocab_size": 256204
+  },
+  "decoder_start_token_id": 0,
+  "encoder": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_probs_dropout_prob": 0.0,
+    "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,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "encoder_stride": 16,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.0,
+    "hidden_size": 384,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "image_size": 384,
+    "initializer_range": 0.02,
+    "intermediate_size": 1536,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-12,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "deit",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 6,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_channels": 3,
+    "num_hidden_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "patch_size": 16,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "qkv_bias": true,
+    "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
+  },
+  "eos_token_id": 2,
+  "is_encoder_decoder": true,
+  "max_length": 64,
+  "model_type": "vision-encoder-decoder",
+  "pad_token_id": 1,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.1",
+  "vocab_size": 256204
+}