Add small PyTorch model

small/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[MASK]": 128000
+}

small/config.json

@@ -64,7 +64,7 @@
   "num_attention_heads": 12,
   "num_hidden_layers": 6,
   "pad_token_id": 0,
-  "pooler_dropout": 0.0,
+  "pooler_dropout": 0,
   "pooler_hidden_act": "gelu",
   "pooler_hidden_size": 768,
   "pos_att_type": [
@@ -77,6 +77,5 @@
   "share_att_key": true,
   "transformers_version": "4.57.6",
   "type_vocab_size": 0,
-  "use_cache": false,
   "vocab_size": 128100
 }

small/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad3f11a0954b4890618a3a5676d0afb5a832171b76654e8f28493499b1018f53
-size 282653514
+oid sha256:882b77efdff1c0ea323d8b4f7fbb5e6378b0a9df141be169585a8cabf9f24cad
+size 565294452

small/special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

small/spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
+size 2464616

small/tokenizer_config.json

@@ -1,24 +1,59 @@
 {
-  "add_prefix_space": true,
-  "backend": "tokenizers",
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128000": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
   "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": false,
   "cls_token": "[CLS]",
   "do_lower_case": false,
   "eos_token": "[SEP]",
-  "extra_special_tokens": [
-    "[PAD]",
-    "[CLS]",
-    "[SEP]"
-  ],
-  "is_local": false,
-  "local_files_only": false,
+  "extra_special_tokens": {},
   "mask_token": "[MASK]",
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
   "split_by_punct": false,
   "tokenizer_class": "DebertaV2Tokenizer",
-  "unk_id": 3,
   "unk_token": "[UNK]",
   "vocab_type": "spm"
 }

small/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5f6e6c7570901aea91b2cc9d1146d12a26287f62362c13625f02669332f4a00
-size 5329
+oid sha256:c202c95a37f172db133c131d011c86fc0b08f3d7905644d3358223437ee1ab46
+size 5905