multilingual-e5-large-v2

.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

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 1024,
+  "pooling_mode_cls_token": false,
+  "pooling_mode_mean_tokens": true,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": false,
+  "include_prompt": true
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "intfloat/multilingual-e5-large",
+  "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": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.49.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.4.1",
+    "transformers": "4.49.0",
+    "pytorch": "2.6.0+cu124"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

eval/Information-Retrieval_evaluation_dim_768_results.csv

@@ -0,0 +1,6 @@
+epoch,steps,cosine-Accuracy@1,cosine-Accuracy@3,cosine-Accuracy@5,cosine-Accuracy@10,cosine-Precision@1,cosine-Recall@1,cosine-Precision@3,cosine-Recall@3,cosine-Precision@5,cosine-Recall@5,cosine-Precision@10,cosine-Recall@10,cosine-MRR@10,cosine-NDCG@10,cosine-MAP@100
+1.0,8761,0.7288166544923301,0.8403944485025566,0.8785609934258582,0.927136596055515,0.7288166544923301,0.7288166544923301,0.28013148283418554,0.8403944485025566,0.17571219868517163,0.8785609934258582,0.09271365960555149,0.927136596055515,0.7938823234431351,0.8260335990918937,0.7968871821398484
+2.0,17522,0.745982468955442,0.8597516435354273,0.8984660336011687,0.9362673484295105,0.745982468955442,0.745982468955442,0.2865838811784758,0.8597516435354273,0.17969320672023373,0.8984660336011687,0.09362673484295105,0.9362673484295105,0.8103865206905746,0.8409414226876948,0.8132072873767562
+3.0,26283,0.7509130752373996,0.8617604090577063,0.8995617238860482,0.9373630387143901,0.7509130752373996,0.7509130752373996,0.2872534696859021,0.8617604090577063,0.1799123447772096,0.8995617238860482,0.093736303871439,0.9373630387143901,0.8141362163321619,0.8440550640780259,0.8169598448982975
+4.0,35044,0.7662527392257122,0.8789262235208181,0.9121621621621622,0.9483199415631848,0.7662527392257122,0.7662527392257122,0.2929754078402727,0.8789262235208181,0.1824324324324324,0.9121621621621622,0.09483199415631847,0.9483199415631848,0.829480518162951,0.8584093485481546,0.8318072571072241
+5.0,43805,0.7647918188458729,0.8677867056245434,0.9092403214024836,0.945763330898466,0.7647918188458729,0.7647918188458729,0.2892622352081812,0.8677867056245434,0.18184806428049669,0.9092403214024836,0.0945763330898466,0.945763330898466,0.8258083614502542,0.8548766612753436,0.8284552027798833

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8a6953f716adc978732b6522f367133fdfbd6dfc7759a1589b09733ab10866c
+size 2239607176

modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]

runs/Mar26_11-08-40_sotatek-Z590-GAMING-X/events.out.tfevents.1742962122.sotatek-Z590-GAMING-X.4297.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fda3f7827830bd4df3b0d05132ab821b5180d8786804d1e814205b76bc7bdde4
+size 4589

runs/Mar26_11-16-09_sotatek-Z590-GAMING-X/events.out.tfevents.1742962570.sotatek-Z590-GAMING-X.4584.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9416a60597072f931846adafd571533fe9dafae1a5dc0d749094c7e228e2faa7
+size 4589

runs/Mar26_13-24-39_sotatek-Z590-GAMING-X/events.out.tfevents.1742970280.sotatek-Z590-GAMING-X.4902.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:894b13783e213c721429ee3614aa36ef6afba8a53c05d264461a9df259c2c9aa
+size 4587

runs/Mar26_13-25-59_sotatek-Z590-GAMING-X/events.out.tfevents.1742970360.sotatek-Z590-GAMING-X.5126.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdb4c1050862bca9e13b160e03b3b5d3b147e98f953ba4a0679a4225e26f53bd
+size 4587

runs/Mar26_13-27-20_sotatek-Z590-GAMING-X/events.out.tfevents.1742970441.sotatek-Z590-GAMING-X.5340.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36e3dab649c6ba47e2eebc4156ed2507a65e584c0ea5fa25a71ec275be75d7d1
+size 946357

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 512,
+  "do_lower_case": false
+}

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:883b037111086fd4dfebbbc9b7cee11e1517b5e0c0514879478661440f137085
+size 17082987

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc4c251c5853ea8132256d17a13a3d4f69a862dca0e792308fb5aee47ba19afd
+size 5752