feat: converted ONNX model

README.md

@@ -18,21 +18,4 @@ model-index:
         - type: spearmanr
           value: 0.904
 ---
-**INFO**: The model is being continuously updated.
-
-The model is a [multilingual-e5-base](https://huggingface.co/intfloat/multilingual-e5-base) model fine-tuned with the task of semantic textual similarity in mind.
-
-## Model Training
-The model has been fine-tuned on the German subsets of the following datasets:
-- [German paraphrase corpus by Philip May](https://huggingface.co/datasets/deutsche-telekom/ger-backtrans-paraphrase)
-- [paws-x](https://huggingface.co/datasets/paws-x)
-- [stsb_multi_mt](https://huggingface.co/datasets/stsb_multi_mt)
-
-The training procedure can be divided into two stages:
-- training on paraphrase datasets with the Multiple Negatives Ranking Loss
-- training on semantic textual similarity datasets using the Cosine Similarity Loss
-
-# Results
-The model achieves the following results:
-- 0.920 on stsb's validation subset
-- 0.904 on stsb's test subset
+This is a converted version of [danielheinz/e5-base-sts-en-de](https://huggingface.co/danielheinz/e5-base-sts-en-de) for CPU inference on ONNX Runtime.

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/root/.cache/torch/sentence_transformers/intfloat_multilingual-e5-base/",
+  "_name_or_path": "danielheinz/e5-base-sts-en-de",
   "architectures": [
     "XLMRobertaModel"
   ],
@@ -7,6 +7,7 @@
   "bos_token_id": 0,
   "classifier_dropout": null,
   "eos_token_id": 2,
+  "export_model_type": "transformer",
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
@@ -21,7 +22,7 @@
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",
-  "transformers_version": "4.36.0",
+  "transformers_version": "4.42.4",
   "type_vocab_size": 1,
   "use_cache": true,
   "vocab_size": 250002

model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdb170f419dafbeaf87bda33639fc9a626c0f91f933ed96450054b5e3691987b
+size 1110128012

special_tokens_map.json

@@ -1,7 +1,25 @@
 {
-  "bos_token": "<s>",
-  "cls_token": "<s>",
-  "eos_token": "</s>",
+  "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,
@@ -9,7 +27,25 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "unk_token": "<unk>"
+  "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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1cc44ad7faaeec47241864835473fd5403f2da94673f3f764a77ebcb0a803ec
-size 17083009
+oid sha256:883b037111086fd4dfebbbc9b7cee11e1517b5e0c0514879478661440f137085
+size 17082987

tokenizer_config.json

@@ -46,9 +46,16 @@
   "cls_token": "<s>",
   "eos_token": "</s>",
   "mask_token": "<mask>",
+  "max_length": 512,
   "model_max_length": 512,
+  "pad_to_multiple_of": null,
   "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
   "sep_token": "</s>",
+  "stride": 0,
   "tokenizer_class": "XLMRobertaTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
   "unk_token": "<unk>"
 }