model

app.py

@@ -4,8 +4,8 @@ import torch
 import numpy as np
 from transformers import AutoTokenizer, AutoModelForSequenceClassification
 
-tokenizer = AutoTokenizer.from_pretrained("oeg/roberta-finetuned-CPV_Spanish")
-model = AutoModelForSequenceClassification.from_pretrained("oeg/roberta-finetuned-CPV_Spanish")
+tokenizer = AutoTokenizer.from_pretrained("model")
+model = AutoModelForSequenceClassification.from_pretrained("model")
 
 cpv = pd.read_csv("cpv.csv")
 df = pd.read_csv("code-desc.csv")

model/config.json

@@ -0,0 +1,123 @@
+{
+  "_name_or_path": "PlanTL-GOB-ES/roberta-base-bne",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "03",
+    "1": "09",
+    "2": "14",
+    "3": "15",
+    "4": "16",
+    "5": "18",
+    "6": "19",
+    "7": "22",
+    "8": "24",
+    "9": "30",
+    "10": "31",
+    "11": "32",
+    "12": "33",
+    "13": "34",
+    "14": "35",
+    "15": "37",
+    "16": "38",
+    "17": "39",
+    "18": "41",
+    "19": "42",
+    "20": "43",
+    "21": "44",
+    "22": "45",
+    "23": "48",
+    "24": "50",
+    "25": "51",
+    "26": "55",
+    "27": "60",
+    "28": "63",
+    "29": "64",
+    "30": "65",
+    "31": "66",
+    "32": "70",
+    "33": "71",
+    "34": "72",
+    "35": "73",
+    "36": "75",
+    "37": "76",
+    "38": "77",
+    "39": "79",
+    "40": "80",
+    "41": "85",
+    "42": "90",
+    "43": "92",
+    "44": "98"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "03": 0,
+    "09": 1,
+    "14": 2,
+    "15": 3,
+    "16": 4,
+    "18": 5,
+    "19": 6,
+    "22": 7,
+    "24": 8,
+    "30": 9,
+    "31": 10,
+    "32": 11,
+    "33": 12,
+    "34": 13,
+    "35": 14,
+    "37": 15,
+    "38": 16,
+    "39": 17,
+    "41": 18,
+    "42": 19,
+    "43": 20,
+    "44": 21,
+    "45": 22,
+    "48": 23,
+    "50": 24,
+    "51": 25,
+    "55": 26,
+    "60": 27,
+    "63": 28,
+    "64": 29,
+    "65": 30,
+    "66": 31,
+    "70": 32,
+    "71": 33,
+    "72": 34,
+    "73": 35,
+    "75": 36,
+    "76": 37,
+    "77": 38,
+    "79": 39,
+    "80": 40,
+    "85": 41,
+    "90": 42,
+    "92": 43,
+    "98": 44
+  },
+  "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",
+  "problem_type": "multi_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.16.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50262
+}

model/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec3b704a4ba9c6b5a13fd4000da3684ea15e1d9f446da3b7a008ab1e702ed3fd
+size 498797101

model/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}}

model/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": false, "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"}, "trim_offsets": true, "max_len": 512, "special_tokens_map_file": null, "name_or_path": "PlanTL-GOB-ES/roberta-base-bne", "tokenizer_class": "RobertaTokenizer"}

model/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de5181bca1f3a92e7db43208603a46f084990047a8236f7ddce2a6fa818dd85b
+size 3055