upload model

args.json

@@ -0,0 +1,24 @@
+{
+    "custom_vocab_files": [
+        "/home/usuaris/veu/casimiro.pio.carrino/projects/corpus-utils-lm/corpora/bio/biomedical-clinical.txt"
+    ],
+    "vocab_name": "bio-biomedical-clinical-vocab-52k",
+    "tokenizer": "bbpe",
+    "lowercase": false,
+    "vocab_size": 52000,
+    "min_frequency": 10,
+    "extra_tokens": [],
+    "limit_alphabet": 1000,
+    "no_show_progress": false,
+    "strip_accents": false,
+    "no_handle_chinese_chars": false,
+    "no_clean_text": false,
+    "reserve_tokens": 0,
+    "use_tokenizers": false,
+    "no_fairseq": false,
+    "files": [
+        "/home/usuaris/veu/casimiro.pio.carrino/projects/corpus-utils-lm/corpora/bio/biomedical-clinical.txt"
+    ],
+    "output_root_path": "/home/usuaris/veu/casimiro.pio.carrino/projects/corpus-utils-lm/output/model-ready_output/bio-biomedical-clinical-vocab-52k-2021-04-26-0955-3a71-240f",
+    "commit_hash": "3a7116cf776527c411869becbe6fad8b9e3f5e56"
+}

config.json

@@ -0,0 +1,25 @@
+{
+  "architectures": [
+    "RobertaForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.4.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 52000
+}

process.log

@@ -0,0 +1,8 @@
+Executing train_tokenizer.py
+------------------------------
+training bbpe tokenizer
+Initialize an empty tokenizer
+training
+saving model tokenizer to /home/usuaris/veu/casimiro.pio.carrino/projects/corpus-utils-lm/output/model-ready_output/bio-biomedical-clinical-vocab-52k-2021-04-26-0955-3a71-240f/train_tokenizer_output/train-tokenizer-2021-04-26-1009-3a71-e9ca
+saving pretrained to /home/usuaris/veu/casimiro.pio.carrino/projects/corpus-utils-lm/output/model-ready_output/bio-biomedical-clinical-vocab-52k-2021-04-26-0955-3a71-240f/train_tokenizer_output/train-tokenizer-2021-04-26-1009-3a71-e9ca
+saving config to /home/usuaris/veu/casimiro.pio.carrino/projects/corpus-utils-lm/output/model-ready_output/bio-biomedical-clinical-vocab-52k-2021-04-26-0955-3a71-240f/train_tokenizer_output/train-tokenizer-2021-04-26-1009-3a71-e9ca

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e0c8d7bb348e40327b7c38eb6995c74d5c64345bc4ab9b3deff58e7359f15f7
+size 504420627

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": true, "errors": "replace", "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "max_len": 512, "special_tokens_map_file": null, "name_or_path": "/home/usuaris/veu/casimiro.pio.carrino/projects/corpus-utils-lm/output/model-ready_output/bio-biomedical-clinical-vocab-52k-2021-04-26-0955-3a71-240f/train_tokenizer_output/train-tokenizer-2021-04-26-1009-3a71-e9ca"}