feat: Add CrossEncoder Model

CECorrelationEvaluator_sts-dev_results.csv

@@ -0,0 +1,15 @@
+epoch,steps,Pearson_Correlation,Spearman_Correlation
+0,1000,0.883374524387813,0.8878141758572982
+0,-1,0.8778756238245011,0.8868591218174223
+1,1000,0.8940448549924146,0.8968016856183934
+1,-1,0.9029116169622556,0.9012072331426946
+2,1000,0.9009231458755066,0.9003885599798547
+2,-1,0.9033158313584775,0.9019981749696708
+3,1000,0.8998464276084307,0.9020773671951405
+3,-1,0.8976356278255467,0.8986613274711471
+4,1000,0.8994414640077576,0.9028956951620126
+4,-1,0.9034409652005353,0.9014066994725192
+5,1000,0.9007225884212331,0.8999936913799494
+5,-1,0.8999793261506176,0.8999581415333522
+6,1000,0.9021117594963682,0.9008238147286273
+6,-1,0.9047506140805446,0.904083037618421

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "camembert/camembert-large",
+  "architectures": [
+    "CamembertForSequenceClassification"
+  ],
+  "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,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "camembert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.17.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 32005
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6c9a98b5fa4f6e29b887c9a8288c2e9159a8210ba52a1d4a3fb9cf1b313b732
+size 1346816173

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f98f266fdc548c94216aaadc13ffaaafacf0c8793303e2195322d954549ea261
+size 808767

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}, "additional_special_tokens": ["<s>NOTUSED", "</s>NOTUSED"]}

tokenizer_config.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "additional_special_tokens": ["<s>NOTUSED", "</s>NOTUSED"], "special_tokens_map_file": null, "name_or_path": "camembert/camembert-large", "sp_model_kwargs": {}, "tokenizer_class": "CamembertTokenizer"}