Upload 5 files

Add model for 4 class prediction of spaces between scriptio continua

config.json

@@ -0,0 +1,40 @@
+{
+  "architectures": [
+    "CanineForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 57344,
+  "downsampling_rate": 4,
+  "dtype": "float32",
+  "eos_token_id": 57345,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "inside",
+    "1": "end",
+    "2": "beginning",
+    "3": "single"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "beginning": 2,
+    "end": 1,
+    "inside": 0,
+    "single": 3
+  },
+  "layer_norm_eps": 1e-12,
+  "local_transformer_stride": 128,
+  "max_position_embeddings": 16384,
+  "model_type": "canine",
+  "num_attention_heads": 12,
+  "num_hash_buckets": 16384,
+  "num_hash_functions": 8,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "transformers_version": "4.57.1",
+  "type_vocab_size": 16,
+  "upsampling_kernel_size": 4,
+  "use_cache": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a42868a023b28c149608589325eb4c6a5d0b124e864393df7965d859119bb2a0
+size 528374080

special_tokens_map.json

@@ -0,0 +1,44 @@
+{
+  "bos_token": {
+    "content": "",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "\u0000",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,47 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "\u0000",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "57344": {
+      "content": "",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "57345": {
+      "content": "",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "57347": {
+      "content": "",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "",
+  "eos_token": "",
+  "extra_special_tokens": {},
+  "mask_token": "",
+  "model_max_length": 2048,
+  "pad_token": "\u0000",
+  "sep_token": "",
+  "tokenizer_class": "CanineTokenizer"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:451d0488aeedcbcf9184b90cb40fcf8913fac0a152af7708968166ce03de1eb8
+size 5841