Upload model

config.json

@@ -1,33 +1,24 @@
 {
-  "_name_or_path": "./models/cont_alt/best_model",
-  "activation_dropout": 0.1,
+  "_name_or_path": "/models/final_all_unfrozen/best_model",
   "architectures": [
-    "VisionEncoderDecoderModel"
+    "EncoderDecoderModel"
   ],
-  "attention_dropout": 0.1,
-  "bos_token_id": 0,
   "decoder": {
-    "_name_or_path": "",
-    "activation_dropout": 0.0,
-    "activation_function": "gelu",
+    "_name_or_path": "FacebookAI/xlm-roberta-base",
     "add_cross_attention": true,
-    "architectures": null,
-    "attention_dropout": 0.0,
+    "architectures": [
+      "XLMRobertaForMaskedLM"
+    ],
+    "attention_probs_dropout_prob": 0.1,
     "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": 768,
-    "d_model": 1024,
-    "decoder_attention_heads": 16,
-    "decoder_ffn_dim": 4096,
-    "decoder_layerdrop": 0.0,
-    "decoder_layers": 12,
-    "decoder_start_token_id": 2,
+    "classifier_dropout": null,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
     "diversity_penalty": 0.0,
     "do_sample": false,
-    "dropout": 0.1,
     "early_stopping": false,
     "encoder_no_repeat_ngram_size": 0,
     "eos_token_id": 2,
@@ -35,31 +26,39 @@
     "finetuning_task": null,
     "forced_bos_token_id": null,
     "forced_eos_token_id": null,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.1,
+    "hidden_size": 768,
     "id2label": {
       "0": "LABEL_0",
       "1": "LABEL_1"
     },
-    "init_std": 0.02,
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
     "is_decoder": true,
     "is_encoder_decoder": false,
     "label2id": {
       "LABEL_0": 0,
       "LABEL_1": 1
     },
-    "layernorm_embedding": true,
+    "layer_norm_eps": 1e-05,
     "length_penalty": 1.0,
     "max_length": 20,
-    "max_position_embeddings": 512,
+    "max_position_embeddings": 514,
     "min_length": 0,
-    "model_type": "trocr",
+    "model_type": "xlm-roberta",
     "no_repeat_ngram_size": 0,
+    "num_attention_heads": 12,
     "num_beam_groups": 1,
     "num_beams": 1,
+    "num_hidden_layers": 12,
     "num_return_sequences": 1,
     "output_attentions": false,
     "output_hidden_states": false,
+    "output_past": true,
     "output_scores": false,
     "pad_token_id": 1,
+    "position_embedding_type": "absolute",
     "prefix": null,
     "problem_type": null,
     "pruned_heads": {},
@@ -67,7 +66,6 @@
     "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,
@@ -80,43 +78,43 @@
     "top_p": 1.0,
     "torch_dtype": null,
     "torchscript": false,
+    "type_vocab_size": 1,
     "typical_p": 1.0,
     "use_bfloat16": false,
-    "use_cache": false,
-    "use_learned_position_embeddings": true,
-    "vocab_size": 632
+    "use_cache": true,
+    "vocab_size": 1024
   },
   "decoder_start_token_id": 0,
-  "dropout": 0.1,
   "encoder": {
-    "_name_or_path": "",
+    "_name_or_path": "colesimmons/xlm-roberta-sumerian-glyphs",
     "add_cross_attention": false,
-    "architectures": null,
-    "attention_probs_dropout_prob": 0.0,
+    "architectures": [
+      "XLMRobertaForMaskedLM"
+    ],
+    "attention_probs_dropout_prob": 0.15,
     "bad_words_ids": null,
     "begin_suppress_tokens": null,
-    "bos_token_id": null,
+    "bos_token_id": 0,
     "chunk_size_feed_forward": 0,
+    "classifier_dropout": null,
     "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,
+    "eos_token_id": 2,
     "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_dropout_prob": 0.15,
     "hidden_size": 768,
     "id2label": {
       "0": "LABEL_0",
       "1": "LABEL_1"
     },
-    "image_size": 384,
     "initializer_range": 0.02,
     "intermediate_size": 3072,
     "is_decoder": false,
@@ -125,27 +123,27 @@
       "LABEL_0": 0,
       "LABEL_1": 1
     },
-    "layer_norm_eps": 1e-12,
+    "layer_norm_eps": 1e-05,
     "length_penalty": 1.0,
     "max_length": 20,
+    "max_position_embeddings": 514,
     "min_length": 0,
-    "model_type": "vit",
+    "model_type": "xlm-roberta",
     "no_repeat_ngram_size": 0,
     "num_attention_heads": 12,
     "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_past": true,
     "output_scores": false,
-    "pad_token_id": null,
-    "patch_size": 16,
+    "pad_token_id": 1,
+    "position_embedding_type": "absolute",
     "prefix": null,
     "problem_type": null,
     "pruned_heads": {},
-    "qkv_bias": false,
     "remove_invalid_values": false,
     "repetition_penalty": 1.0,
     "return_dict": true,
@@ -160,17 +158,17 @@
     "tokenizer_class": null,
     "top_k": 50,
     "top_p": 1.0,
-    "torch_dtype": null,
+    "torch_dtype": "float32",
     "torchscript": false,
+    "type_vocab_size": 1,
     "typical_p": 1.0,
-    "use_bfloat16": false
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 640
   },
-  "eos_token_id": 2,
   "is_encoder_decoder": true,
-  "model_type": "vision-encoder-decoder",
+  "model_type": "encoder-decoder",
   "pad_token_id": 1,
-  "processor_class": "TrOCRProcessor",
-  "tie_word_embeddings": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.41.0"
+  "transformers_version": "4.41.1"
 }

generation_config.json

@@ -1,9 +1,7 @@
 {
   "_from_model_config": true,
   "bos_token_id": 0,
-  "decoder_start_token_id": 2,
   "eos_token_id": 2,
   "pad_token_id": 1,
-  "transformers_version": "4.41.0",
-  "use_cache": false
+  "transformers_version": "4.41.1"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:217a48143c297db57cb4ede3af1c00c8a47acec12ca1f1b60ead4a997f3116d8
-size 1132449976
+oid sha256:c413f33d46356b77d25ebc48902faa99379ecad2e7ffd186a24a3957d99d7dff
+size 806992280