Initial version

Browse files

Files changed (6) hide show

README.md +20 -0
gliner_config.json +208 -0
pytorch_model.bin +3 -0
special_tokens_map.json +7 -0
tokenizer.json +0 -0
tokenizer_config.json +58 -0

README.md ADDED Viewed

	@@ -0,0 +1,20 @@

+---
+license: apache-2.0
+language:
+- en
+- fr
+- de
+- es
+- pt
+- it
+library_name: gliner
+pipeline_tag: token-classification
+datasets:
+- urchade/synthetic-pii-ner-mistral-v1
+---
+# Model Card for GLiNER BERT Tiny
+[GLiNER](https://github.com/urchade/GLiNER) model using [BERT Tiny](https://huggingface.co/google/bert_uncased_L-2_H-128_A-2) as the base model with [urchade/synthetic-pii-ner-mistral-v1](https://huggingface.co/datasets/urchade/synthetic-pii-ner-mistral-v1) as the training dataset.
+This model is primarily designed for unit tests in limited compute enviornments such as GitHub Actions. But it does work to an extent for basic use cases.

gliner_config.json ADDED Viewed

	@@ -0,0 +1,208 @@

+{
+  "class_token_index": -1,
+  "dropout": 0.4,
+  "embed_ent_token": true,
+  "encoder_config": {
+    "_attn_implementation_autoset": false,
+    "_name_or_path": "google/bert_uncased_L-2_H-128_A-2",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_probs_dropout_prob": 0.1,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "classifier_dropout": null,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.1,
+    "hidden_size": 128,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 512,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-12,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 512,
+    "min_length": 0,
+    "model_type": "bert",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 2,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 2,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 0,
+    "position_embedding_type": "absolute",
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "type_vocab_size": 2,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 30522
+  },
+  "ent_token": "<<ENT>>",
+  "eval_every": 1000,
+  "fine_tune": true,
+  "freeze_token_rep": false,
+  "fuse_layers": false,
+  "has_rnn": true,
+  "hidden_size": 128,
+  "label_smoothing": 0,
+  "labels_encoder": "google/bert_uncased_L-2_H-128_A-2",
+  "labels_encoder_config": {
+    "_attn_implementation_autoset": false,
+    "_name_or_path": "google/bert_uncased_L-2_H-128_A-2",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_probs_dropout_prob": 0.1,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "classifier_dropout": null,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.1,
+    "hidden_size": 128,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 512,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-12,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 512,
+    "min_length": 0,
+    "model_type": "bert",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 2,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 2,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 0,
+    "position_embedding_type": "absolute",
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "type_vocab_size": 2,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 30522
+  },
+  "log_dir": "models/",
+  "loss_alpha": -1,
+  "loss_gamma": 0,
+  "loss_reduction": "sum",
+  "lr_encoder": "1e-5",
+  "lr_others": "5e-5",
+  "max_grad_norm": 10.0,
+  "max_len": 386,
+  "max_neg_type_ratio": 1,
+  "max_types": 25,
+  "max_width": 12,
+  "model_name": "google/bert_uncased_L-2_H-128_A-2",
+  "model_type": "gliner",
+  "name": "span level gliner",
+  "num_post_fusion_layers": 1,
+  "num_steps": 30000,
+  "post_fusion_schema": "",
+  "prev_path": null,
+  "random_drop": true,
+  "root_dir": "gliner_logs",
+  "save_total_limit": 3,
+  "scheduler_type": "cosine",
+  "sep_token": "<<SEP>>",
+  "shuffle_types": true,
+  "size_sup": -1,
+  "span_mode": "markerV0",
+  "subtoken_pooling": "first",
+  "train_batch_size": 8,
+  "train_data": "data.json",
+  "transformers_version": "4.47.1",
+  "val_data_dir": "none",
+  "vocab_size": -1,
+  "warmup_ratio": 0.1,
+  "weight_decay_encoder": 0.01,
+  "weight_decay_other": 0.01,
+  "words_splitter_type": "whitespace"
+}

pytorch_model.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:472e54db2392336cd464e5c2d53396ff9ce473b7384c316159a853ef555dafb0
+size 37889547

special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,7 @@

+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,58 @@

+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}