Upload 12 files

args.json

@@ -0,0 +1 @@
+{"model_name": "multicoptic/entire_clean_corpus", "src_language": "cop", "tgt_language": "eng", "max_input_length": 128, "max_target_length": 128}

config.json

@@ -0,0 +1,76 @@
+{
+  "_name_or_path": "megalaa/mul-cop-en-norm-group-greekified",
+  "activation_dropout": 0.0,
+  "activation_function": "swish",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "MarianMTModel"
+  ],
+  "attention_dropout": 0.0,
+  "bad_words_ids": [
+    [
+      64171
+    ]
+  ],
+  "bos_token_id": 0,
+  "classif_dropout": 0.0,
+  "classifier_dropout": 0.0,
+  "custom_pipelines": {
+    "coptic-english-translation": {
+      "default": {
+        "model": {
+          "pt": "megalaa/mul-cop-en-norm-group-greekified"
+        }
+      },
+      "impl": "__main__.CopticEnglishPipeline",
+      "pt": [
+        "AutoModelForSeq2SeqLM"
+      ],
+      "tf": [],
+      "type": "text"
+    }
+  },
+  "d_model": 512,
+  "decoder_attention_heads": 8,
+  "decoder_ffn_dim": 2048,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 64171,
+  "decoder_vocab_size": 64172,
+  "dropout": 0.1,
+  "encoder_attention_heads": 8,
+  "encoder_ffn_dim": 2048,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 0,
+  "extra_pos_embeddings": 64172,
+  "forced_eos_token_id": 0,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "max_length": 512,
+  "max_position_embeddings": 512,
+  "model_type": "marian",
+  "normalize_before": false,
+  "normalize_embedding": false,
+  "num_beams": 6,
+  "num_hidden_layers": 6,
+  "pad_token_id": 64171,
+  "scale_embedding": true,
+  "share_encoder_decoder_embeddings": true,
+  "static_position_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.1",
+  "use_cache": true,
+  "vocab_size": 64172
+}

generation_config.json

@@ -0,0 +1,16 @@
+{
+  "bad_words_ids": [
+    [
+      64171
+    ]
+  ],
+  "bos_token_id": 0,
+  "decoder_start_token_id": 64171,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "max_length": 512,
+  "num_beams": 6,
+  "pad_token_id": 64171,
+  "renormalize_logits": true,
+  "transformers_version": "4.38.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a656385a4934e92523f0cd16f6b0657571813f44650db8ebaecd902af1057b84
+size 308263984

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,38 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "64171": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "separate_vocabs": false,
+  "source_lang": "mul",
+  "sp_model_kwargs": {},
+  "target_lang": "eng",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}

train_config.json

@@ -0,0 +1 @@
+{"job_hash": "bb4b305756099fe6c9aaa35d10bd9c1c", "evaluation_strategy": "steps", "learning_rate": 5e-05, "per_device_train_batch_size": 96, "per_device_eval_batch_size": 96, "weight_decay": 0, "save_total_limit": 4, "num_train_epochs": 12, "num_train_steps": null, "predict_with_generate": true, "eval_steps": 238, "logging_steps": 50, "label_smoothing_factor": 0, "commit_hash": "e045ea0"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f298dfdadef22f93696233852cbe958659770927b0d88d4771e749a33ef7bfd
+size 4603