Upload 9 files

README.md

@@ -1,3 +1,36 @@
 ---
 license: openrail
+language:
+- en
+metrics:
+- accuracy
+pipeline_tag: text2text-generation
 ---
+
+This is a t5-small model trained on the wikidata5M dataset.
+
+This model was trained on tail and entity prediction in a knowledge graph using the graph's context represented by the node's neighborhood.
+
+Textual representation was obtained from wikidata entities and relation titles. Entity description was used to disambiguate if two entities had the same title. If still, no disambiguation was possible, we assigned unique numerical ids for such entities.
+
+The neighborhood for the input was obtained as follows:
+
+1. sort the neighborhood by semantic similarity of relations from its triplets to the relation from the input triplet in order to prioritize more important information in the context; 
+2. limit the sorted neighborhood to 512 triplets, since this will always be at least as big as the size of the allowed context, and, after verbalization, specify the maximum length of 512 for the model tokenizer to fit the resulting verbalized neighborhood representation into the language model context. 
+
+
+Neighborhood sorting by semantic proximity was performed using a pre-calculated matrix of cosine similarity of relations in KG, for similarity calculation the relations were embedded by the fasttext model.
+
+We trained the model on the Wikidata5M dataset for approximately 5M iterations on 8xA100 GPUs using a batch size of 320.
+
+To evaluate the model, we sample 50 times from the decoder for each input and then rank the predictions by their log probabilities. We achieve 0.319 Hits@1 on the test set. 
+
+One can load this model for their personal use of fine-tuning as follows:
+
+```python
+# Load model directly
+from transformers import AutoModel, AutoTokenizer
+tokenizer = AutoTokenizer.from_pretrained("t5-small")
+tokenizer.add_special_tokens({'sep_token': '[SEP]'})
+model = AutoModel.from_pretrained("DeepPavlov/t5-wikidata5M-with-neighbors")
+```

added_tokens.json

@@ -0,0 +1 @@
+{"[SEP]": 32100}

config.json

@@ -0,0 +1,56 @@
+{
+    "_name_or_path": "kgt5-neighbors",
+    "architectures": [
+        "T5ForConditionalGeneration"
+    ],
+    "d_ff": 2048,
+    "d_kv": 64,
+    "d_model": 512,
+    "decoder_start_token_id": 0,
+    "dropout_rate": 0.1,
+    "eos_token_id": 1,
+    "feed_forward_proj": "relu",
+    "initializer_factor": 1.0,
+    "is_encoder_decoder": true,
+    "layer_norm_epsilon": 1e-06,
+    "model_type": "t5",
+    "n_positions": 512,
+    "num_decoder_layers": 6,
+    "num_heads": 8,
+    "num_layers": 6,
+    "output_past": true,
+    "pad_token_id": 0,
+    "relative_attention_num_buckets": 32,
+    "task_specific_params": {
+        "summarization": {
+            "early_stopping": true,
+            "length_penalty": 2.0,
+            "max_length": 200,
+            "min_length": 30,
+            "no_repeat_ngram_size": 3,
+            "num_beams": 4,
+            "prefix": "summarize: "
+        },
+        "translation_en_to_de": {
+            "early_stopping": true,
+            "max_length": 300,
+            "num_beams": 4,
+            "prefix": "translate English to German: "
+        },
+        "translation_en_to_fr": {
+            "early_stopping": true,
+            "max_length": 300,
+            "num_beams": 4,
+            "prefix": "translate English to French: "
+        },
+        "translation_en_to_ro": {
+            "early_stopping": true,
+            "max_length": 300,
+            "num_beams": 4,
+            "prefix": "translate English to Romanian: "
+        }
+    },
+    "transformers_version": "4.17.0",
+    "use_cache": true,
+    "vocab_size": 32128
+}

gitattributes.txt

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:310e1b652d84329772b106f64228ce1e77116043729391a410d3ec2ddeff10d4
+size 242083771

special_tokens_map.json

@@ -0,0 +1 @@
+{"eos_token": "</s>", "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"]}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
+size 791656

tokenizer_config.json

@@ -0,0 +1 @@
+{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 100, "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"], "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "tokenizer-t5-wikidata5m", "tokenizer_class": "T5Tokenizer"}