Upload 9 files

config.json

@@ -1,16 +1,17 @@
 {
-  "_name_or_path": "microsoft/trocr-base-stage1",
+  "_name_or_path": "microsoft/trocr-base-handwritten",
   "architectures": [
     "VisionEncoderDecoderModel"
   ],
   "decoder": {
     "_name_or_path": "",
     "activation_dropout": 0.0,
-    "activation_function": "relu",
+    "activation_function": "gelu",
     "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,
@@ -27,6 +28,7 @@
     "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,
@@ -41,10 +43,10 @@
       "LABEL_0": 0,
       "LABEL_1": 1
     },
-    "layernorm_embedding": false,
+    "layernorm_embedding": true,
     "length_penalty": 1.0,
     "max_length": 20,
-    "max_position_embeddings": 1024,
+    "max_position_embeddings": 512,
     "min_length": 0,
     "model_type": "trocr",
     "no_repeat_ngram_size": 0,
@@ -62,21 +64,23 @@
     "repetition_penalty": 1.0,
     "return_dict": true,
     "return_dict_in_generate": false,
-    "scale_embedding": true,
+    "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": false,
+    "tie_word_embeddings": true,
     "tokenizer_class": null,
     "top_k": 50,
     "top_p": 1.0,
     "torch_dtype": null,
     "torchscript": false,
-    "transformers_version": "4.12.5",
+    "typical_p": 1.0,
     "use_bfloat16": false,
     "use_cache": false,
-    "use_learned_position_embeddings": false,
+    "use_learned_position_embeddings": true,
     "vocab_size": 50265
   },
   "decoder_start_token_id": 0,
@@ -87,6 +91,7 @@
     "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,
@@ -95,7 +100,9 @@
     "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,
@@ -141,8 +148,10 @@
     "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,
@@ -150,19 +159,20 @@
     "top_p": 1.0,
     "torch_dtype": null,
     "torchscript": false,
-    "transformers_version": "4.12.5",
+    "typical_p": 1.0,
     "use_bfloat16": false
   },
   "eos_token_id": 2,
   "is_encoder_decoder": true,
   "length_penalty": 2.0,
-  "max_length": 10,
+  "max_length": 64,
   "model_type": "vision-encoder-decoder",
   "no_repeat_ngram_size": 3,
   "num_beams": 4,
   "pad_token_id": 1,
+  "processor_class": "TrOCRProcessor",
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
-  "transformers_version": null,
+  "transformers_version": "4.32.1",
   "vocab_size": 50265
 }

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 0,
+  "decoder_start_token_id": 0,
+  "early_stopping": true,
+  "eos_token_id": 2,
+  "length_penalty": 2.0,
+  "max_length": 64,
+  "no_repeat_ngram_size": 3,
+  "num_beams": 4,
+  "pad_token_id": 1,
+  "transformers_version": "4.32.1",
+  "use_cache": false
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7616590322292667a9236be8811f1fd731264455df71ce3cee71752f71c90bd0
+size 2667049975

preprocessor_config.json

@@ -0,0 +1,22 @@
+{
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "ViTImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 384,
+    "width": 384
+  }
+}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18ec62351d5433a370ad266920c37e02540712b11d0f694abcf1c91a9ddb86b4
-size 1539649667
+oid sha256:d71cfba588a3059e92e4e4045978fa552e7d94773f78ce87cfbf6c6b0d604415
+size 1335854221

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6bda2751f95a66ee4a22b3ad21795225c1e7a41e2a49ee94036634d40fc6328
+size 14575

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41832dedf57a243e88a5dd568de84f293bb695cd3e7de2787177db6ba2f2c0d7
+size 627

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c993f98f6063ff0cb800e08f158acc0ebb2d3c2af87fa0034b7129d0443e01b
+size 4219