Pruned version of XLM-R

config.json

@@ -0,0 +1,145 @@
+{
+  "_name_or_path": "Unbabel/XLM-R-19L",
+  "architectures": [
+    "XLMRobertaModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 19,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "pruned_heads": {
+    "0": [
+      12,
+      5,
+      6,
+      14
+    ],
+    "1": [
+      13,
+      12,
+      5,
+      15
+    ],
+    "2": [
+      8,
+      9,
+      10,
+      13
+    ],
+    "3": [
+      9,
+      10,
+      4,
+      12
+    ],
+    "4": [
+      8,
+      9,
+      3,
+      13
+    ],
+    "5": [
+      2,
+      3,
+      4,
+      12
+    ],
+    "6": [
+      0,
+      9,
+      3,
+      12
+    ],
+    "7": [
+      0,
+      9,
+      2,
+      15
+    ],
+    "8": [
+      0,
+      8,
+      3,
+      13
+    ],
+    "9": [
+      0,
+      15,
+      14,
+      7
+    ],
+    "10": [
+      0,
+      1,
+      11,
+      12
+    ],
+    "11": [
+      11,
+      15,
+      6,
+      7
+    ],
+    "12": [
+      8,
+      10,
+      3,
+      14
+    ],
+    "13": [
+      8,
+      2,
+      4,
+      5
+    ],
+    "14": [
+      0,
+      9,
+      11,
+      14
+    ],
+    "15": [
+      8,
+      3,
+      4,
+      6
+    ],
+    "16": [
+      8,
+      10,
+      2,
+      3
+    ],
+    "17": [
+      0,
+      8,
+      12,
+      6
+    ],
+    "18": [
+      0,
+      8,
+      15,
+      7
+    ]
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.10.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec41283958021ae27302632a773f8ded70b8f049373de7cabe903b5d9ff0fd21
+size 1744352085

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "sp_model_kwargs": {}, "model_max_length": 512, "special_tokens_map_file": null, "tokenizer_file": "/mnt/shared/home/ricardorei/.cache/huggingface/transformers/7766c86e10505ed9b39af34e456480399bf06e35b36b8f2b917460a2dbe94e59.a984cf52fc87644bd4a2165f1e07e0ac880272c1e82d648b4674907056912bd7", "name_or_path": "xlm-roberta-large", "tokenizer_class": "XLMRobertaTokenizer"}