Upload folder using huggingface_hub

Browse files

Files changed (7) hide show

gliner_config.json +209 -0
pytorch_model.bin +3 -0
special_tokens_map.json +37 -0
tokenizer.json +0 -0
tokenizer.model +3 -0
tokenizer_config.json +48 -0
trainer_state.json +91 -0

gliner_config.json ADDED Viewed

	@@ -0,0 +1,209 @@

+{
+  "class_token_index": -1,
+  "dropout": 0.4,
+  "embed_ent_token": true,
+  "encoder_config": {
+    "_name_or_path": "knowledgator/Sheared-LLaMA-encoder-1.3B",
+    "add_cross_attention": false,
+    "architectures": [
+      "LlamaBiModel"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 1,
+    "chunk_size_feed_forward": 0,
+    "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": 2,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "silu",
+    "hidden_size": 2048,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 5504,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 4096,
+    "min_length": 0,
+    "model_type": "llama",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 16,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 24,
+    "num_key_value_heads": 16,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 0,
+    "prefix": null,
+    "pretraining_tp": 1,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "rms_norm_eps": 1e-05,
+    "rope_scaling": null,
+    "rope_theta": 10000.0,
+    "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": false,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": "bfloat16",
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 32000
+  },
+  "ent_token": "<<ENT>>",
+  "eval_every": 3000,
+  "fine_tune": true,
+  "freeze_token_rep": false,
+  "fuse_layers": false,
+  "has_rnn": true,
+  "hidden_size": 1024,
+  "label_smoothing": 0,
+  "labels_encoder": "BAAI/bge-small-en-v1.5",
+  "labels_encoder_config": {
+    "_name_or_path": "BAAI/bge-small-en-v1.5",
+    "add_cross_attention": false,
+    "architectures": [
+      "BertModel"
+    ],
+    "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": 384,
+    "id2label": {
+      "0": "LABEL_0"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 1536,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0
+    },
+    "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": 12,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 12,
+    "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": "float32",
+    "torchscript": false,
+    "type_vocab_size": 2,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 30522
+  },
+  "log_dir": "llama/",
+  "loss_alpha": 0.75,
+  "loss_gamma": 0,
+  "loss_reduction": "sum",
+  "lr_encoder": "1e-5",
+  "lr_others": "3e-5",
+  "max_grad_norm": 1.0,
+  "max_len": 512,
+  "max_neg_type_ratio": 1,
+  "max_types": 100,
+  "max_width": 12,
+  "model_name": "knowledgator/Sheared-LLaMA-encoder-1.3B",
+  "model_type": "gliner",
+  "name": "span level gliner",
+  "num_post_fusion_layers": 1,
+  "num_steps": 100000,
+  "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/nuner_train.json",
+  "transformers_version": "4.40.2",
+  "val_data_dir": "none",
+  "vocab_size": -1,
+  "warmup_ratio": 0.0,
+  "weight_decay_encoder": 0.1,
+  "weight_decay_other": 0.1,
+  "words_splitter_type": "whitespace"
+}

pytorch_model.bin ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:ee0b735d26d3c11f5ebd9f69d64019639163f87cd50f04c200d7b8c13d3546e7
+size 5439423806

special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,37 @@

+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "_",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json ADDED Viewed

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

tokenizer.model ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,48 @@

+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "29918": {
+      "content": "_",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "mask_token": "_",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

trainer_state.json ADDED Viewed

	@@ -0,0 +1,91 @@

+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.07663422484481569,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.007663422484481569,
+      "grad_norm": 2411.532470703125,
+      "learning_rate": 5.555555555555555e-07,
+      "loss": 152.2018,
+      "step": 100
+    },
+    {
+      "epoch": 0.015326844968963138,
+      "grad_norm": 1508.88134765625,
+      "learning_rate": 1.111111111111111e-06,
+      "loss": 142.6181,
+      "step": 200
+    },
+    {
+      "epoch": 0.022990267453444707,
+      "grad_norm": 1164.76953125,
+      "learning_rate": 1.6666666666666667e-06,
+      "loss": 123.6666,
+      "step": 300
+    },
+    {
+      "epoch": 0.030653689937926276,
+      "grad_norm": 1428.1673583984375,
+      "learning_rate": 2.222222222222222e-06,
+      "loss": 117.5532,
+      "step": 400
+    },
+    {
+      "epoch": 0.038317112422407845,
+      "grad_norm": 421.33551025390625,
+      "learning_rate": 2.7777777777777783e-06,
+      "loss": 113.8976,
+      "step": 500
+    },
+    {
+      "epoch": 0.045980534906889414,
+      "grad_norm": 302.48614501953125,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 106.6907,
+      "step": 600
+    },
+    {
+      "epoch": 0.05364395739137098,
+      "grad_norm": 221.99728393554688,
+      "learning_rate": 3.88888888888889e-06,
+      "loss": 108.7462,
+      "step": 700
+    },
+    {
+      "epoch": 0.06130737987585255,
+      "grad_norm": 630.5855102539062,
+      "learning_rate": 4.444444444444444e-06,
+      "loss": 88.6301,
+      "step": 800
+    },
+    {
+      "epoch": 0.06897080236033412,
+      "grad_norm": 749.811279296875,
+      "learning_rate": 5e-06,
+      "loss": 91.8458,
+      "step": 900
+    },
+    {
+      "epoch": 0.07663422484481569,
+      "grad_norm": 168.46031188964844,
+      "learning_rate": 4.938271604938272e-06,
+      "loss": 94.57,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 9000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 0.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}