Initial commit

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "../ISC/experiments/supervised/st-sts-roberta-base-all_cls-fp16",
+  "alpha_1": 0.7,
+  "alpha_2": 0.0001,
+  "architectures": [
+    "RobertaModel"
+  ],
+  "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_length": 64,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_experts": 2,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "top_routing": 1,
+  "torch_dtype": "float32",
+  "transformers_version": "4.30.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

fc_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1727bbe5d88e3bb4b52bfc85a8ef8eeb7cf1e142c8d0fdc73bd87d5dc45aab0e
+size 7297

mixsp_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:818e25a2d88f896183a52547cdad2ab871a76d3b5660c20f1c17406a3fffa408
+size 94449746

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d663aeb849dc865e9b4e9f2b558b72c6ada53497255f4ec89662ec3d5733e19
+size 498657143

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_config.json

@@ -0,0 +1,15 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}