Upload folder using huggingface_hub

checkpoint-51750/gliner_config.json

@@ -0,0 +1,112 @@
+{
+  "class_token_index": 50369,
+  "dropout": 0.3,
+  "embed_ent_token": true,
+  "encoder_config": {
+    "_name_or_path": "jhu-clsp/ettin-encoder-32m",
+    "architectures": [
+      "ModernBertForMaskedLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 50281,
+    "causal_mask": false,
+    "chunk_size_feed_forward": 0,
+    "classifier_activation": "gelu",
+    "classifier_bias": false,
+    "classifier_dropout": 0.0,
+    "classifier_pooling": "mean",
+    "cls_token_id": 50281,
+    "decoder_bias": true,
+    "deterministic_flash_attn": false,
+    "dtype": "float32",
+    "embedding_dropout": 0.0,
+    "eos_token_id": 50282,
+    "global_attn_every_n_layers": 3,
+    "gradient_checkpointing": false,
+    "hidden_activation": "gelu",
+    "hidden_size": 384,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_cutoff_factor": 2.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 576,
+    "is_causal": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-05,
+    "layer_types": [
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention"
+    ],
+    "local_attention": 128,
+    "max_position_embeddings": 7999,
+    "mlp_bias": false,
+    "mlp_dropout": 0.0,
+    "model_type": "modernbert",
+    "norm_bias": false,
+    "norm_eps": 1e-05,
+    "num_attention_heads": 6,
+    "num_hidden_layers": 10,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "pad_token_id": 50283,
+    "position_embedding_type": "sans_pos",
+    "problem_type": null,
+    "return_dict": true,
+    "rope_parameters": {
+      "full_attention": {
+        "rope_theta": 160000.0,
+        "rope_type": "default"
+      },
+      "sliding_attention": {
+        "rope_theta": 160000.0,
+        "rope_type": "default"
+      }
+    },
+    "sep_token_id": 50282,
+    "sparse_pred_ignore_index": -100,
+    "sparse_prediction": false,
+    "tie_word_embeddings": true,
+    "vocab_size": 50371
+  },
+  "ent_token": "<<ENT>>",
+  "fine_tune": true,
+  "fuse_layers": false,
+  "hidden_size": 384,
+  "max_len": 1024,
+  "max_neg_type_ratio": 1,
+  "max_types": 100,
+  "max_width": 100,
+  "model_name": "jhu-clsp/ettin-encoder-32m",
+  "model_type": null,
+  "name": "gliner-ettin-32m-ptbr-pii-full-3x",
+  "neg_spans_ratio": 1.0,
+  "num_post_fusion_layers": 1,
+  "num_rnn_layers": 1,
+  "pad_token_id": 50283,
+  "post_fusion_schema": null,
+  "represent_spans": false,
+  "sep_token": "<<SEP>>",
+  "span_loss_coef": 1.0,
+  "span_mode": "token_level",
+  "subtoken_pooling": "first",
+  "token_loss_coef": 1.0,
+  "transformers_version": "5.1.0",
+  "use_cache": false,
+  "vocab_size": 50371,
+  "words_splitter_type": "whitespace"
+}

checkpoint-51750/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0eaa920b7105f942c664ae42918a6a2bdad438f340c25ee864c02525d6e05aa
+size 281179211

checkpoint-51750/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4819df7a02daf1c67d0ec93f274e75ea33c0ce79ed04aae8e70fbc2579f54c96
+size 140583921

checkpoint-51750/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29dbb3b33c3151142209571d86bbf362dc18ec055ff6a7cc45dc72a8747cf9c7
+size 14645

checkpoint-51750/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09be88a2eabcfbef139368cffcd98504dce200b7987a4d90a60f010a582839de
+size 1529

checkpoint-51750/tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "backend": "tokenizers",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "is_local": false,
+  "mask_token": "[MASK]",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 8192,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "[UNK]"
+}