Upload LEDForConditionalGeneration

config.json

@@ -0,0 +1,157 @@
+{
+  "_name_or_path": "allenai/led-base-16384",
+  "accelerator": null,
+  "accumulate_grad_batches": 2,
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "add_context": false,
+  "amp_backend": null,
+  "amp_level": null,
+  "architectures": [
+    "LEDForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "attention_window": [
+    1024,
+    1024,
+    1024,
+    1024,
+    1024,
+    1024
+  ],
+  "auto_lr_find": false,
+  "auto_scale_batch_size": false,
+  "auto_select_gpus": null,
+  "batch_size": 8,
+  "benchmark": null,
+  "bos_token_id": 0,
+  "check_val_every_n_epoch": 1,
+  "checkpoint": null,
+  "class_labels": {
+    "delete": 4,
+    "ignore": 0,
+    "merge": 3,
+    "rephrase": 1,
+    "split": 2
+  },
+  "classif_dropout": 0.0,
+  "classifier_dropout": 0.0,
+  "context_dir": null,
+  "context_doc_id": null,
+  "context_window": 13,
+  "d_model": 768,
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 2,
+  "default_root_dir": null,
+  "detect_anomaly": false,
+  "devices": "2",
+  "dropout": 0.1,
+  "enable_checkpointing": true,
+  "enable_model_summary": true,
+  "enable_progress_bar": true,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 2,
+  "eval_beams": null,
+  "eval_max_length": null,
+  "fast_dev_run": false,
+  "gpus": null,
+  "gradient_checkpointing": false,
+  "gradient_clip_algorithm": null,
+  "gradient_clip_val": null,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "inference_mode": true,
+  "init_std": 0.02,
+  "ipus": null,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "limit_predict_batches": null,
+  "limit_test_batches": null,
+  "limit_train_batches": null,
+  "limit_val_batches": null,
+  "log_every_n_steps": 50,
+  "logger": true,
+  "longformer": true,
+  "lr": 2e-05,
+  "lr_scheduler": false,
+  "max_decoder_position_embeddings": 1024,
+  "max_encoder_position_embeddings": 16384,
+  "max_epochs": null,
+  "max_length": 1024,
+  "max_samples": -1,
+  "max_steps": -1,
+  "max_time": null,
+  "min_epochs": null,
+  "min_steps": null,
+  "model_type": "led",
+  "move_metrics_to_cpu": false,
+  "multiple_trainloader_mode": "max_size_cycle",
+  "name": "ledpara",
+  "num_hidden_layers": 6,
+  "num_nodes": 1,
+  "num_processes": null,
+  "num_sanity_val_steps": 2,
+  "op_col": null,
+  "op_tokens": [
+    "<COPY>",
+    "<REPHRASE>",
+    "<SPLIT>",
+    "<MERGE>",
+    "<DELETE>"
+  ],
+  "overfit_batches": 0.0,
+  "pad_token_id": 1,
+  "plan_col": "labels",
+  "plan_loss": null,
+  "plan_prefix": false,
+  "plan_sep": false,
+  "plugins": null,
+  "precision": 32,
+  "prefix_only": false,
+  "profiler": null,
+  "project": "simplification",
+  "reading_lvl": null,
+  "reload_dataloaders_every_n_epochs": 0,
+  "replace_sampler_ddp": true,
+  "resume_from_checkpoint": null,
+  "save_dir": null,
+  "sent_level": false,
+  "simple_context_dir": null,
+  "simple_context_doc_id": null,
+  "skip_val_gen": true,
+  "strategy": null,
+  "sync_batchnorm": false,
+  "torch_dtype": "float32",
+  "tpu_cores": null,
+  "track_grad_norm": -1,
+  "train_check_interval": 0.2,
+  "train_data_dir": null,
+  "train_file": "merge/cochrane_para_train.csv",
+  "train_split": 0.9,
+  "train_workers": 8,
+  "transformers_version": "4.29.1",
+  "use_cache": true,
+  "val_check_interval": null,
+  "val_file": "merge/cochrane_para_val.csv",
+  "val_metric": "bleu",
+  "val_split": 0.05,
+  "val_workers": 8,
+  "valid_data_dir": null,
+  "vocab_size": 50275,
+  "wandb_id": null,
+  "x_col": "complex",
+  "y_col": "simple"
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "decoder_start_token_id": 2,
+  "eos_token_id": 2,
+  "pad_token_id": 1,
+  "transformers_version": "4.29.1"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:388dd94ced9ff0c7cf54b4fdaa34b9dc64b15ed26ad27409e3b553556e792b03
+size 647711597