Upload folder using huggingface_hub

config.json

@@ -1,12 +1,19 @@
 {
+  "_name_or_path": "microsoft/trocr-small-handwritten",
   "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": 8,
     "d_model": 8,
@@ -14,41 +21,149 @@
     "decoder_ffn_dim": 8,
     "decoder_layerdrop": 0.0,
     "decoder_layers": 2,
+    "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": 64044
   },
   "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": 8,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
     "image_size": 384,
     "initializer_range": 0.02,
     "intermediate_size": 8,
+    "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": 2,
+    "num_beam_groups": 1,
+    "num_beams": 1,
     "num_channels": 3,
     "num_hidden_layers": 2,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
     "patch_size": 16,
-    "pooler_act": "tanh",
-    "pooler_output_size": 384,
-    "qkv_bias": 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": null,
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false
   },
   "eos_token_id": 2,
   "is_encoder_decoder": true,
   "model_type": "vision-encoder-decoder",
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.53.3"
+  "transformers_version": "4.45.0"
 }

generation_config.json

@@ -4,6 +4,6 @@
   "decoder_start_token_id": 2,
   "eos_token_id": 2,
   "pad_token_id": 1,
-  "transformers_version": "4.53.3",
+  "transformers_version": "4.45.0",
   "use_cache": false
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7134459482ae786a1d10ea8e14df9824849792c7d43968095f00ceab520cc6e2
-size 4193512
+oid sha256:25be9f958467fa618b9465e6561a0022bd95b5c187f2d1b9084f4acd8e46a7c7
+size 4179976

tokenizer_config.json

@@ -42,10 +42,9 @@
     }
   },
   "bos_token": "<s>",
-  "clean_up_tokenization_spaces": false,
+  "clean_up_tokenization_spaces": true,
   "cls_token": "<s>",
   "eos_token": "</s>",
-  "extra_special_tokens": {},
   "mask_token": "<mask>",
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<pad>",