Upload 7 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "/home/etutubalina/graph_entity_linking/huggingface_models/xlm-roberta-base",
+  "architectures": [
+    "XLMRobertaModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "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": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.24.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

model_description.tsv

@@ -0,0 +1,50 @@
+train_dir	/home/etutubalina/graph_entity_linking/pos_pairs_graph_data/2020AB/ENG_SPA_POR_FRE_JPN_RUS_DUT_GER_ITA_CZE_SWE_KOR_LAV_HUN_CHI_NOR_POL_TUR_EST_FIN_SCR_UKR_GRE_DAN_BAQ_HEB_MULTILINGUAL_ALL_LANGUAGES_MAP_TO_ENG_20_20_20_FULL
+validate	False
+output_dir	/home/etutubalina/graph_entity_linking/results/pretrained_graphsapbert/2020AB/768_0.2_FINAL_NEIGHBORS_MS_LOSS_ALL_LANGUAGES/GAT_DGI_MULTILINGUAL_NO_LOOPS_MAP_ENG_20_20_20/
+gat_num_outer_layers	1
+gat_num_inner_layers	3
+gat_num_hidden_channels	768
+gat_num_neighbors	[3]
+gat_num_att_heads	2
+gat_dropout_p	0.3
+gat_attention_dropout_p	0.1
+gat_use_relational_features	False
+use_rel_or_rela	rel
+graph_loss_weight	1.0
+dgi_loss_weight	0.1
+remove_selfloops	True
+text_loss_weight	1.0
+intermodal_loss_weight	1.0
+use_intermodal_miner	True
+intermodal_miner_margin	0.2
+freeze_neighbors	False
+apply_text_loss_to_all_neighbors	False
+modality_distance	sapbert
+intermodal_loss_type	sapbert
+intermodal_strategy	None
+use_detached_text	False
+remove_activations	False
+common_hard_pairs	False
+fuse_unimodal_embeddings	False
+cross_fusion	False
+inmodal_fusion	False
+global_fusion	False
+fusion_text_weight	None
+max_length	32
+use_cuda	True
+learning_rate	2e-05
+weight_decay	0.01
+batch_size	256
+num_epochs	1
+amp	True
+parallel	True
+random_seed	42
+loss	ms_loss
+use_miner	True
+miner_margin	0.2
+type_of_triplets	all
+agg_mode	cls
+text_encoder	/home/etutubalina/graph_entity_linking/huggingface_models/xlm-roberta-base/
+dataloader_num_workers	0
+save_every_N_epoch	1
+model_checkpoint_path	None

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04f2bdac1ad7417622e153e86efe3e0bbe2675e65b8c7a6006cd22c424b188df
+size 1112241265

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 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62c24cdc13d4c9952d63718d6c9fa4c287974249e16b7ade6d5a85e7bbb75626
+size 17082660

tokenizer_config.json

@@ -0,0 +1,20 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 512,
+  "name_or_path": "/home/etutubalina/graph_entity_linking/huggingface_models/xlm-roberta-base",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}