Upload model

config.json

@@ -0,0 +1,299 @@
+{
+  "_name_or_path": "text_recognizer_final/checkpoint-2000",
+  "architectures": [
+    "LangVisionEncoderDecoderModel"
+  ],
+  "decoder": {
+    "_name_or_path": "",
+    "activation_dropout": 0.0,
+    "activation_function": "gelu",
+    "add_cross_attention": true,
+    "add_final_layer_norm": true,
+    "architectures": [
+      "MBartForCausalLM"
+    ],
+    "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": null,
+    "d_expert": 1024,
+    "d_model": 1024,
+    "decoder_attention_heads": 16,
+    "decoder_ffn_dim": 4096,
+    "decoder_layerdrop": 0.0,
+    "decoder_layers": 7,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout": 0.1,
+    "early_stopping": false,
+    "encoder_attention_heads": 16,
+    "encoder_ffn_dim": 4096,
+    "encoder_layerdrop": 0.0,
+    "encoder_layers": 12,
+    "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": 2,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "init_std": 0.02,
+    "is_decoder": true,
+    "is_encoder_decoder": false,
+    "kv_heads": 4,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "langs": {
+      "af": 65539,
+      "am": 65540,
+      "ar": 65541,
+      "as": 65542,
+      "az": 65543,
+      "be": 65544,
+      "bg": 65545,
+      "bn": 65546,
+      "br": 65547,
+      "bs": 65548,
+      "ca": 65549,
+      "cs": 65550,
+      "cy": 65551,
+      "da": 65552,
+      "de": 65553,
+      "el": 65554,
+      "en": 65555,
+      "eo": 65556,
+      "es": 65557,
+      "et": 65558,
+      "eu": 65559,
+      "fa": 65560,
+      "fi": 65561,
+      "fr": 65562,
+      "fy": 65563,
+      "ga": 65564,
+      "gd": 65565,
+      "gl": 65566,
+      "gu": 65567,
+      "ha": 65568,
+      "he": 65569,
+      "hi": 65570,
+      "hr": 65571,
+      "hu": 65572,
+      "hy": 65573,
+      "id": 65574,
+      "is": 65575,
+      "it": 65576,
+      "ja": 65577,
+      "jv": 65578,
+      "ka": 65579,
+      "kk": 65580,
+      "km": 65581,
+      "kn": 65582,
+      "ko": 65583,
+      "ku": 65584,
+      "ky": 65585,
+      "la": 65586,
+      "lo": 65587,
+      "lt": 65588,
+      "lv": 65589,
+      "mg": 65590,
+      "mk": 65591,
+      "ml": 65592,
+      "mn": 65593,
+      "mr": 65594,
+      "ms": 65595,
+      "my": 65596,
+      "ne": 65597,
+      "nl": 65598,
+      "no": 65599,
+      "om": 65600,
+      "or": 65601,
+      "pa": 65602,
+      "pl": 65603,
+      "ps": 65604,
+      "pt": 65605,
+      "ro": 65606,
+      "ru": 65607,
+      "sa": 65608,
+      "sd": 65609,
+      "si": 65610,
+      "sk": 65611,
+      "sl": 65612,
+      "so": 65613,
+      "sq": 65614,
+      "sr": 65615,
+      "su": 65616,
+      "sv": 65617,
+      "sw": 65618,
+      "ta": 65619,
+      "te": 65620,
+      "th": 65621,
+      "tl": 65622,
+      "tr": 65623,
+      "ug": 65624,
+      "uk": 65625,
+      "ur": 65626,
+      "uz": 65627,
+      "vi": 65628,
+      "xh": 65629,
+      "yi": 65630,
+      "zh": 65631
+    },
+    "length_penalty": 1.0,
+    "max_length": 256,
+    "max_position_embeddings": 1536,
+    "min_length": 0,
+    "model_type": "mbart",
+    "moe_layers": [
+      3
+    ],
+    "no_repeat_ngram_size": 0,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_decoder_layers": 6,
+    "num_hidden_layers": 12,
+    "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": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": "float32",
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "use_moe": true,
+    "vocab_size": 65792
+  },
+  "decoder_start_token_id": 1,
+  "encoder": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": [
+      "DonutSwinModel"
+    ],
+    "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,
+    "depths": [
+      2,
+      2,
+      14,
+      2
+    ],
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "drop_path_rate": 0.1,
+    "early_stopping": false,
+    "embed_dim": 128,
+    "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,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.0,
+    "hidden_size": 1024,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "image_size": [
+      196,
+      896
+    ],
+    "initializer_range": 0.02,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "mlp_ratio": 4.0,
+    "model_type": "donut-swin",
+    "no_repeat_ngram_size": 0,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_channels": 3,
+    "num_heads": [
+      4,
+      8,
+      16,
+      32
+    ],
+    "num_layers": 4,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "patch_size": 4,
+    "path_norm": true,
+    "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": "float32",
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_2d_embeddings": false,
+    "use_absolute_embeddings": true,
+    "use_bfloat16": false,
+    "window_size": 7
+  },
+  "is_encoder_decoder": true,
+  "model_type": "vision-encoder-decoder",
+  "pad_token_id": 0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.36.2"
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "forced_eos_token_id": 2,
+  "max_length": 512,
+  "pad_token_id": 1,
+  "transformers_version": "4.36.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:922fd2283c7a9fafcc171b4840cf19aab4a70a890ec350adc832a8be9846b7ac
+size 1048833584