Upload folder using huggingface_hub

README.md

@@ -1,3 +1,44 @@
----
-license: apache-2.0
----
+---
+license: apache-2.0
+language:
+- en
+library_name: gliner
+pipeline_tag: token-classification
+---
+
+# GLiNER-Large (Reproduce) Model
+
+This model is a reproduce version of GLiNER-large, the training hyperparameters are different from the original model.
+
+# Hyperparameters
+
+The detail of training hyperparameters can see in `deberta.yaml`.
+
+Except for config in `deberta.yaml`, i manually set the `lr_scheduler_type` to `cosine_with_min_lr` and `lr_scheduler_kwargs` to `{"min_lr_rate": 0.01}` in `train.py`:
+
+```
+    training_args = TrainingArguments(
+        ...
+        lr_scheduler_type="cosine_with_min_lr",
+        lr_scheduler_kwargs={"min_lr_rate": 0.01},
+        ...
+    )
+```
+
+NOTE: The result is not stable, i guess the random shuffle of the dataset is the reason.
+
+# Weights
+
+Here are two weights, one is the final model after 4k iterations, which has the best performance on the zero-shot evaluation, and the other is the model after full training.
+
+
+|   Model    | link  |  AI   | literature | music | politics | science | movie | restaurant | Average |
+| :--------: | :---: | :---: | :--------: | :---: | :------: | :-----: | :---: | :--------: | :-----: |
+| iter_4000  |   *   | 56.7  |    65.1    | 69.6  |   74.2   |  60.9   | 60.6  |    39.7    |  61.0   |
+| iter_10000 |   *   | 55.1  |    62.9    | 68.3  |   71.6   |  57.3   | 58.4  |    40.5    |  59.2   |
+| ---------- | ----- | ----- | ---------- | ----- | -------- | ------- | ----- | ---------- | ------- |
+|   Paper    |   *   | 57.2  |    64.4    | 69.6  |   72.6   |  62.6   | 57.2  |    42.9    |  60.9   |
+
+
+# Using repo
+See https://github.com/urchade/GLiNER

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<<ENT>>": 128001,
+  "<<SEP>>": 128002,
+  "[MASK]": 128000
+}

deberta.yaml

@@ -0,0 +1,52 @@
+# Model Configuration
+model_name: /large-storage/model/deberta-v3-large # Hugging Face model
+labels_encoder: null
+name: "span level gliner"
+max_width: 12
+hidden_size: 512
+dropout: 0.4
+fine_tune: true
+subtoken_pooling: first
+span_mode: markerV0
+
+# Training Parameters
+num_steps: 10000
+train_batch_size: 8
+eval_every: 1000
+warmup_ratio: 0.1
+scheduler_type: "cosine"
+
+# loss function
+loss_alpha: -1 # focal loss alpha, if -1, no focal loss
+loss_gamma: 0 # focal loss gamma, if 0, no focal loss
+label_smoothing: 0
+loss_reduction: "sum"
+
+# Learning Rate and weight decay Configuration
+lr_encoder: 1e-5
+lr_others: 5e-5
+weight_decay_encoder: 0.01
+weight_decay_other: 0.01
+
+max_grad_norm: 1.0
+
+# Directory Paths
+root_dir: span_gliner_logs
+train_data: "data/pilener_train.json" # see https://github.com/urchade/GLiNER/tree/main/data
+val_data_dir: "/workspace/GNER/regen_data/data/IE_INSTRUCTIONS/NER copy"
+# "NER_datasets": val data from the paper can be obtained from "https://drive.google.com/file/d/1T-5IbocGka35I7X3CE6yKe5N_Xg2lVKT/view"
+
+# Pretrained Model Path
+# Use "none" if no pretrained model is being used
+prev_path: null
+
+save_total_limit: 10 #maximum amount of checkpoints to save
+
+# Advanced Training Settings
+size_sup: -1
+max_types: 25
+shuffle_types: true
+random_drop: true
+max_neg_type_ratio: 1
+max_len: 512
+freeze_token_rep: false

gliner_config.json

@@ -0,0 +1,139 @@
+{
+  "class_token_index": 128001,
+  "dropout": 0.4,
+  "embed_ent_token": true,
+  "encoder_config": {
+    "_name_or_path": "/large-storage/model/deberta-v3-large",
+    "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,
+    "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": 1024,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-07,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 512,
+    "max_relative_positions": -1,
+    "min_length": 0,
+    "model_type": "deberta-v2",
+    "no_repeat_ngram_size": 0,
+    "norm_rel_ebd": "layer_norm",
+    "num_attention_heads": 16,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 24,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 0,
+    "pooler_dropout": 0,
+    "pooler_hidden_act": "gelu",
+    "pooler_hidden_size": 1024,
+    "pos_att_type": [
+      "p2c",
+      "c2p"
+    ],
+    "position_biased_input": false,
+    "position_buckets": 256,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "relative_attention": true,
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "share_att_key": true,
+    "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": 0,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "vocab_size": 128003
+  },
+  "ent_token": "<<ENT>>",
+  "eval_every": 1000,
+  "fine_tune": true,
+  "freeze_token_rep": false,
+  "fuse_layers": false,
+  "has_rnn": true,
+  "hidden_size": 512,
+  "label_smoothing": 0,
+  "labels_encoder": null,
+  "labels_encoder_config": null,
+  "log_dir": "./logs_deberta_span_6",
+  "loss_alpha": -1,
+  "loss_gamma": 0,
+  "loss_reduction": "sum",
+  "lr_encoder": "1e-5",
+  "lr_others": "5e-5",
+  "max_grad_norm": 1.0,
+  "max_len": 512,
+  "max_neg_type_ratio": 1,
+  "max_types": 25,
+  "max_width": 12,
+  "model_name": "/large-storage/model/deberta-v3-large",
+  "model_type": "gliner",
+  "name": "span level gliner",
+  "num_post_fusion_layers": 1,
+  "num_steps": 10000,
+  "post_fusion_schema": "",
+  "prev_path": null,
+  "random_drop": true,
+  "root_dir": "span_gliner_logs",
+  "save_total_limit": 10,
+  "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/pilener_train.json",
+  "transformers_version": "4.45.2",
+  "val_data_dir": "/workspace/GNER/regen_data/data/IE_INSTRUCTIONS/NER copy",
+  "vocab_size": 128003,
+  "warmup_ratio": 0.1,
+  "weight_decay_encoder": 0.01,
+  "weight_decay_other": 0.01,
+  "words_splitter_type": "whitespace"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6dba9dfd9f8e12de24549f4b5c75312c9c16d8620a4d6b101dd9e14567723d47
+size 1781996490

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "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,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
+size 2464616

tokenizer_config.json

@@ -0,0 +1,74 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128000": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<<ENT>>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<<SEP>>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}