Push model using huggingface_hub.

added_tokens.json

@@ -1,6 +1,5 @@
 {
-  "<<ENT>>": 128002,
-  "<<SEP>>": 128003,
-  "[FLERT]": 128001,
+  "<<ENT>>": 128001,
+  "<<SEP>>": 128002,
   "[MASK]": 128000
 }

gliner_config.json

@@ -1,10 +1,10 @@
 {
-  "class_token_index": 128002,
+  "class_token_index": 128001,
   "dropout": 0.4,
   "embed_ent_token": true,
   "encoder_config": {
     "_attn_implementation_autoset": true,
-    "_name_or_path": "microsoft/deberta-v3-small",
+    "_name_or_path": "microsoft/deberta-v3-base",
     "add_cross_attention": false,
     "architectures": null,
     "attention_probs_dropout_prob": 0.1,
@@ -51,7 +51,7 @@
     "num_attention_heads": 12,
     "num_beam_groups": 1,
     "num_beams": 1,
-    "num_hidden_layers": 6,
+    "num_hidden_layers": 12,
     "num_return_sequences": 1,
     "output_attentions": false,
     "output_hidden_states": false,
@@ -90,37 +90,34 @@
     "type_vocab_size": 0,
     "typical_p": 1.0,
     "use_bfloat16": false,
-    "vocab_size": 128004
+    "vocab_size": 128003
   },
   "ent_token": "<<ENT>>",
-  "eval_every": 5000,
   "fine_tune": true,
   "fuse_layers": false,
   "has_rnn": true,
-  "hidden_size": 512,
+  "hidden_size": 768,
+  "label_smoothing": 0.0,
   "labels_encoder": null,
   "labels_encoder_config": null,
-  "lr_encoder": "1e-5",
-  "lr_others": "5e-5",
+  "loss_alpha": 0.8,
+  "loss_gamma": 0,
+  "loss_reduction": "sum",
   "max_len": 384,
   "max_neg_type_ratio": 1,
-  "max_types": 25,
+  "max_types": 30,
   "max_width": 12,
-  "model_name": "microsoft/deberta-v3-small",
+  "model_name": "microsoft/deberta-v3-base",
   "model_type": "gliner",
-  "name": "correct",
+  "name": "span level gliner",
   "num_post_fusion_layers": 1,
-  "num_steps": 30000,
   "post_fusion_schema": "",
   "random_drop": true,
   "sep_token": "<<SEP>>",
   "shuffle_types": true,
-  "size_sup": -1,
   "span_mode": "markerV0",
   "subtoken_pooling": "first",
-  "train_batch_size": 8,
   "transformers_version": "4.51.3",
-  "vocab_size": 128004,
-  "warmup_ratio": 3000,
+  "vocab_size": 128003,
   "words_splitter_type": "whitespace"
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6b69a17f1c18b56945fb09435fd5ad7d0f71425890ad2fef92acb56b6956919
-size 610640046
+oid sha256:f1a15727ef8b13f1fb9c6de253230b3552b45039464ba1144d4b22821903698c
+size 834285094

special_tokens_map.json

@@ -1,10 +1,46 @@
 {
-  "bos_token": "[CLS]",
-  "cls_token": "[CLS]",
-  "eos_token": "[SEP]",
-  "mask_token": "[MASK]",
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
+  "bos_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "unk_token": {
     "content": "[UNK]",
     "lstrip": false,

tokenizer_config.json

@@ -41,14 +41,6 @@
       "special": true
     },
     "128001": {
-      "content": "[FLERT]",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "128002": {
       "content": "<<ENT>>",
       "lstrip": false,
       "normalized": true,
@@ -56,7 +48,7 @@
       "single_word": false,
       "special": false
     },
-    "128003": {
+    "128002": {
       "content": "<<SEP>>",
       "lstrip": false,
       "normalized": true,
@@ -66,7 +58,7 @@
     }
   },
   "bos_token": "[CLS]",
-  "clean_up_tokenization_spaces": false,
+  "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
   "do_lower_case": false,
   "eos_token": "[SEP]",