Upload model
Browse files- config.json +161 -0
- generation_config.json +4 -0
- pytorch_model-00001-of-00006.bin +3 -0
- pytorch_model-00002-of-00006.bin +3 -0
- pytorch_model-00003-of-00006.bin +3 -0
- pytorch_model-00004-of-00006.bin +3 -0
- pytorch_model-00005-of-00006.bin +3 -0
- pytorch_model-00006-of-00006.bin +3 -0
- pytorch_model.bin.index.json +281 -0
config.json
ADDED
|
@@ -0,0 +1,161 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_frozen": true,
|
| 3 |
+
"_n_gpu": 1,
|
| 4 |
+
"adafactor": false,
|
| 5 |
+
"adam_beta1": 0.9,
|
| 6 |
+
"adam_beta2": 0.999,
|
| 7 |
+
"adam_epsilon": 1e-06,
|
| 8 |
+
"architectures": [
|
| 9 |
+
"CorrectorEncoderModel"
|
| 10 |
+
],
|
| 11 |
+
"auto_find_batch_size": false,
|
| 12 |
+
"bf16": true,
|
| 13 |
+
"bf16_full_eval": false,
|
| 14 |
+
"cache_dir": null,
|
| 15 |
+
"cheat_on_train_hypotheses": false,
|
| 16 |
+
"config_name": null,
|
| 17 |
+
"config_overrides": null,
|
| 18 |
+
"corrector_ignore_hypothesis_embedding": false,
|
| 19 |
+
"corrector_model_alias": null,
|
| 20 |
+
"corrector_model_from_pretrained": "jxm/gtr__nq__32",
|
| 21 |
+
"data_seed": null,
|
| 22 |
+
"dataloader_drop_last": false,
|
| 23 |
+
"dataloader_num_workers": 0,
|
| 24 |
+
"dataloader_pin_memory": true,
|
| 25 |
+
"dataset_name": "nq",
|
| 26 |
+
"ddp_backend": null,
|
| 27 |
+
"ddp_broadcast_buffers": null,
|
| 28 |
+
"ddp_bucket_cap_mb": null,
|
| 29 |
+
"ddp_find_unused_parameters": null,
|
| 30 |
+
"ddp_timeout": 1800,
|
| 31 |
+
"debug": [],
|
| 32 |
+
"decoder_dropout_disabled": false,
|
| 33 |
+
"deepspeed": null,
|
| 34 |
+
"deepspeed_plugin": null,
|
| 35 |
+
"disable_tqdm": true,
|
| 36 |
+
"dispatch_batches": null,
|
| 37 |
+
"do_eval": false,
|
| 38 |
+
"do_predict": false,
|
| 39 |
+
"do_train": false,
|
| 40 |
+
"embedder_fake_with_zeros": false,
|
| 41 |
+
"embedder_model_api": null,
|
| 42 |
+
"embedder_model_name": "gtr_base",
|
| 43 |
+
"embedder_no_grad": true,
|
| 44 |
+
"embedder_torch_dtype": "float32",
|
| 45 |
+
"embedding_transform_strategy": "repeat",
|
| 46 |
+
"embedding_zero_except_topk": null,
|
| 47 |
+
"embeddings_from_layer_n": null,
|
| 48 |
+
"encoder_dropout_disabled": false,
|
| 49 |
+
"eval_accumulation_steps": null,
|
| 50 |
+
"eval_delay": 0,
|
| 51 |
+
"eval_steps": 6250,
|
| 52 |
+
"evaluation_strategy": "steps",
|
| 53 |
+
"exp_group_name": "gtr_corrector",
|
| 54 |
+
"exp_name": "",
|
| 55 |
+
"experiment": "corrector",
|
| 56 |
+
"fp16": false,
|
| 57 |
+
"fp16_backend": "auto",
|
| 58 |
+
"fp16_full_eval": false,
|
| 59 |
+
"fp16_opt_level": "O1",
|
| 60 |
+
"freeze_strategy": "none",
|
| 61 |
+
"fsdp": [],
|
| 62 |
+
"fsdp_config": {
|
| 63 |
+
"min_num_params": 0,
|
| 64 |
+
"xla": false,
|
| 65 |
+
"xla_fsdp_grad_ckpt": false
|
| 66 |
+
},
|
| 67 |
+
"fsdp_min_num_params": 0,
|
| 68 |
+
"fsdp_transformer_layer_cls_to_wrap": null,
|
| 69 |
+
"full_determinism": false,
|
| 70 |
+
"gradient_accumulation_steps": 1,
|
| 71 |
+
"gradient_checkpointing": false,
|
| 72 |
+
"greater_is_better": false,
|
| 73 |
+
"group_by_length": true,
|
| 74 |
+
"half_precision_backend": "auto",
|
| 75 |
+
"hub_always_push": false,
|
| 76 |
+
"hub_model_id": null,
|
| 77 |
+
"hub_private_repo": false,
|
| 78 |
+
"hub_strategy": "every_save",
|
| 79 |
+
"hub_token": null,
|
| 80 |
+
"ignore_data_skip": false,
|
| 81 |
+
"include_inputs_for_metrics": true,
|
| 82 |
+
"include_tokens_per_second": false,
|
| 83 |
+
"jit_mode_eval": false,
|
| 84 |
+
"label_names": null,
|
| 85 |
+
"label_smoothing_factor": 0.0,
|
| 86 |
+
"learning_rate": 0.00282842712,
|
| 87 |
+
"length_column_name": "length",
|
| 88 |
+
"load_best_model_at_end": true,
|
| 89 |
+
"local_rank": 0,
|
| 90 |
+
"log_level": "passive",
|
| 91 |
+
"log_level_replica": "warning",
|
| 92 |
+
"log_on_each_node": true,
|
| 93 |
+
"logging_dir": "/home/wentingz/vec2text/saves/gtr-nq-msl32-correct/runs/Nov05_04-29-22_mosaic-cirrascale-03.reviz.ai2.in",
|
| 94 |
+
"logging_first_step": false,
|
| 95 |
+
"logging_nan_inf_filter": true,
|
| 96 |
+
"logging_steps": 50,
|
| 97 |
+
"logging_strategy": "steps",
|
| 98 |
+
"lr_scheduler_type": "linear",
|
| 99 |
+
"max_eval_samples": 500,
|
| 100 |
+
"max_grad_norm": 1.0,
|
| 101 |
+
"max_seq_length": 32,
|
| 102 |
+
"max_steps": -1,
|
| 103 |
+
"metric_for_best_model": "nq_loss",
|
| 104 |
+
"mock_embedder": false,
|
| 105 |
+
"model_name_or_path": "t5-base",
|
| 106 |
+
"model_revision": "main",
|
| 107 |
+
"mp_parameters": "",
|
| 108 |
+
"no_cuda": true,
|
| 109 |
+
"num_repeat_tokens": 16,
|
| 110 |
+
"num_train_epochs": 200.0,
|
| 111 |
+
"optim": "adamw_torch",
|
| 112 |
+
"optim_args": null,
|
| 113 |
+
"output_dir": "/home/wentingz/vec2text/saves/gtr-nq-msl32-correct",
|
| 114 |
+
"overwrite_output_dir": false,
|
| 115 |
+
"past_index": -1,
|
| 116 |
+
"per_device_eval_batch_size": 256,
|
| 117 |
+
"per_device_train_batch_size": 256,
|
| 118 |
+
"per_gpu_eval_batch_size": null,
|
| 119 |
+
"per_gpu_train_batch_size": null,
|
| 120 |
+
"prediction_loss_only": false,
|
| 121 |
+
"push_to_hub": false,
|
| 122 |
+
"push_to_hub_model_id": null,
|
| 123 |
+
"push_to_hub_organization": null,
|
| 124 |
+
"push_to_hub_token": null,
|
| 125 |
+
"ray_scope": "last",
|
| 126 |
+
"remove_unused_columns": false,
|
| 127 |
+
"report_to": [],
|
| 128 |
+
"resume_from_checkpoint": null,
|
| 129 |
+
"run_name": "/home/wentingz/vec2text/saves/gtr-nq-msl32-correct",
|
| 130 |
+
"save_on_each_node": false,
|
| 131 |
+
"save_safetensors": false,
|
| 132 |
+
"save_steps": 500,
|
| 133 |
+
"save_strategy": "steps",
|
| 134 |
+
"save_total_limit": 2,
|
| 135 |
+
"seed": 42,
|
| 136 |
+
"sharded_ddp": [],
|
| 137 |
+
"skip_memory_metrics": true,
|
| 138 |
+
"steps_per_epoch": 500000,
|
| 139 |
+
"suffix_conditioning": false,
|
| 140 |
+
"tf32": null,
|
| 141 |
+
"tokenizer_name": null,
|
| 142 |
+
"torch_compile": false,
|
| 143 |
+
"torch_compile_backend": null,
|
| 144 |
+
"torch_compile_mode": null,
|
| 145 |
+
"torch_dtype": "float32",
|
| 146 |
+
"torchdynamo": null,
|
| 147 |
+
"tpu_metrics_debug": false,
|
| 148 |
+
"tpu_num_cores": null,
|
| 149 |
+
"transformers_version": "4.34.1",
|
| 150 |
+
"use_cpu": false,
|
| 151 |
+
"use_frozen_embeddings_as_input": false,
|
| 152 |
+
"use_ipex": false,
|
| 153 |
+
"use_legacy_prediction_loop": false,
|
| 154 |
+
"use_less_data": -1,
|
| 155 |
+
"use_lora": false,
|
| 156 |
+
"use_mps_device": false,
|
| 157 |
+
"use_wandb": false,
|
| 158 |
+
"warmup_ratio": 0.0,
|
| 159 |
+
"warmup_steps": 25000,
|
| 160 |
+
"weight_decay": 0.0
|
| 161 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"transformers_version": "4.34.1"
|
| 4 |
+
}
|
pytorch_model-00001-of-00006.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9fbfc51d464b945bac9adf9338221856ba323f8672276c19265e03adb9b0c33e
|
| 3 |
+
size 193103485
|
pytorch_model-00002-of-00006.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5b6ff5aa535d77254e0da4f9b694359caaf90fb9598417ff41bce969c246e1dd
|
| 3 |
+
size 198243903
|
pytorch_model-00003-of-00006.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e27d05cc2f7b4090e502a9dc346dfe9a9213e291ce9719af629806763ffb826a
|
| 3 |
+
size 198254881
|
pytorch_model-00004-of-00006.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9d79267338ab1bfed421fb22c8897806673418d9f6d4dc1e7bfde069d251cdad
|
| 3 |
+
size 198255163
|
pytorch_model-00005-of-00006.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7caed532fd5751462738e27df165b6fa58dc3d8b29ece717f09c3e715749a7bb
|
| 3 |
+
size 186535289
|
pytorch_model-00006-of-00006.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9c2eda610550de48e5bf6999abf8e58dd9582a79116826b2e2a1e487842a7c33
|
| 3 |
+
size 37805853
|
pytorch_model.bin.index.json
ADDED
|
@@ -0,0 +1,281 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 1012101120
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"embedding_transform_1.0.bias": "pytorch_model-00005-of-00006.bin",
|
| 7 |
+
"embedding_transform_1.0.weight": "pytorch_model-00005-of-00006.bin",
|
| 8 |
+
"embedding_transform_1.3.bias": "pytorch_model-00005-of-00006.bin",
|
| 9 |
+
"embedding_transform_1.3.weight": "pytorch_model-00005-of-00006.bin",
|
| 10 |
+
"embedding_transform_2.0.bias": "pytorch_model-00005-of-00006.bin",
|
| 11 |
+
"embedding_transform_2.0.weight": "pytorch_model-00005-of-00006.bin",
|
| 12 |
+
"embedding_transform_2.3.bias": "pytorch_model-00005-of-00006.bin",
|
| 13 |
+
"embedding_transform_2.3.weight": "pytorch_model-00005-of-00006.bin",
|
| 14 |
+
"embedding_transform_3.0.bias": "pytorch_model-00005-of-00006.bin",
|
| 15 |
+
"embedding_transform_3.0.weight": "pytorch_model-00005-of-00006.bin",
|
| 16 |
+
"embedding_transform_3.3.bias": "pytorch_model-00006-of-00006.bin",
|
| 17 |
+
"embedding_transform_3.3.weight": "pytorch_model-00006-of-00006.bin",
|
| 18 |
+
"encoder_decoder.decoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00006.bin",
|
| 19 |
+
"encoder_decoder.decoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00006.bin",
|
| 20 |
+
"encoder_decoder.decoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00006.bin",
|
| 21 |
+
"encoder_decoder.decoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model-00003-of-00006.bin",
|
| 22 |
+
"encoder_decoder.decoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00006.bin",
|
| 23 |
+
"encoder_decoder.decoder.block.0.layer.0.layer_norm.weight": "pytorch_model-00003-of-00006.bin",
|
| 24 |
+
"encoder_decoder.decoder.block.0.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00006.bin",
|
| 25 |
+
"encoder_decoder.decoder.block.0.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00006.bin",
|
| 26 |
+
"encoder_decoder.decoder.block.0.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00006.bin",
|
| 27 |
+
"encoder_decoder.decoder.block.0.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00006.bin",
|
| 28 |
+
"encoder_decoder.decoder.block.0.layer.1.layer_norm.weight": "pytorch_model-00003-of-00006.bin",
|
| 29 |
+
"encoder_decoder.decoder.block.0.layer.2.DenseReluDense.wi.weight": "pytorch_model-00003-of-00006.bin",
|
| 30 |
+
"encoder_decoder.decoder.block.0.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00006.bin",
|
| 31 |
+
"encoder_decoder.decoder.block.0.layer.2.layer_norm.weight": "pytorch_model-00003-of-00006.bin",
|
| 32 |
+
"encoder_decoder.decoder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00006.bin",
|
| 33 |
+
"encoder_decoder.decoder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00006.bin",
|
| 34 |
+
"encoder_decoder.decoder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00006.bin",
|
| 35 |
+
"encoder_decoder.decoder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00006.bin",
|
| 36 |
+
"encoder_decoder.decoder.block.1.layer.0.layer_norm.weight": "pytorch_model-00003-of-00006.bin",
|
| 37 |
+
"encoder_decoder.decoder.block.1.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00006.bin",
|
| 38 |
+
"encoder_decoder.decoder.block.1.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00006.bin",
|
| 39 |
+
"encoder_decoder.decoder.block.1.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00006.bin",
|
| 40 |
+
"encoder_decoder.decoder.block.1.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00006.bin",
|
| 41 |
+
"encoder_decoder.decoder.block.1.layer.1.layer_norm.weight": "pytorch_model-00003-of-00006.bin",
|
| 42 |
+
"encoder_decoder.decoder.block.1.layer.2.DenseReluDense.wi.weight": "pytorch_model-00003-of-00006.bin",
|
| 43 |
+
"encoder_decoder.decoder.block.1.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00006.bin",
|
| 44 |
+
"encoder_decoder.decoder.block.1.layer.2.layer_norm.weight": "pytorch_model-00003-of-00006.bin",
|
| 45 |
+
"encoder_decoder.decoder.block.10.layer.0.SelfAttention.k.weight": "pytorch_model-00005-of-00006.bin",
|
| 46 |
+
"encoder_decoder.decoder.block.10.layer.0.SelfAttention.o.weight": "pytorch_model-00005-of-00006.bin",
|
| 47 |
+
"encoder_decoder.decoder.block.10.layer.0.SelfAttention.q.weight": "pytorch_model-00005-of-00006.bin",
|
| 48 |
+
"encoder_decoder.decoder.block.10.layer.0.SelfAttention.v.weight": "pytorch_model-00005-of-00006.bin",
|
| 49 |
+
"encoder_decoder.decoder.block.10.layer.0.layer_norm.weight": "pytorch_model-00005-of-00006.bin",
|
| 50 |
+
"encoder_decoder.decoder.block.10.layer.1.EncDecAttention.k.weight": "pytorch_model-00005-of-00006.bin",
|
| 51 |
+
"encoder_decoder.decoder.block.10.layer.1.EncDecAttention.o.weight": "pytorch_model-00005-of-00006.bin",
|
| 52 |
+
"encoder_decoder.decoder.block.10.layer.1.EncDecAttention.q.weight": "pytorch_model-00005-of-00006.bin",
|
| 53 |
+
"encoder_decoder.decoder.block.10.layer.1.EncDecAttention.v.weight": "pytorch_model-00005-of-00006.bin",
|
| 54 |
+
"encoder_decoder.decoder.block.10.layer.1.layer_norm.weight": "pytorch_model-00005-of-00006.bin",
|
| 55 |
+
"encoder_decoder.decoder.block.10.layer.2.DenseReluDense.wi.weight": "pytorch_model-00005-of-00006.bin",
|
| 56 |
+
"encoder_decoder.decoder.block.10.layer.2.DenseReluDense.wo.weight": "pytorch_model-00005-of-00006.bin",
|
| 57 |
+
"encoder_decoder.decoder.block.10.layer.2.layer_norm.weight": "pytorch_model-00005-of-00006.bin",
|
| 58 |
+
"encoder_decoder.decoder.block.11.layer.0.SelfAttention.k.weight": "pytorch_model-00005-of-00006.bin",
|
| 59 |
+
"encoder_decoder.decoder.block.11.layer.0.SelfAttention.o.weight": "pytorch_model-00005-of-00006.bin",
|
| 60 |
+
"encoder_decoder.decoder.block.11.layer.0.SelfAttention.q.weight": "pytorch_model-00005-of-00006.bin",
|
| 61 |
+
"encoder_decoder.decoder.block.11.layer.0.SelfAttention.v.weight": "pytorch_model-00005-of-00006.bin",
|
| 62 |
+
"encoder_decoder.decoder.block.11.layer.0.layer_norm.weight": "pytorch_model-00005-of-00006.bin",
|
| 63 |
+
"encoder_decoder.decoder.block.11.layer.1.EncDecAttention.k.weight": "pytorch_model-00005-of-00006.bin",
|
| 64 |
+
"encoder_decoder.decoder.block.11.layer.1.EncDecAttention.o.weight": "pytorch_model-00005-of-00006.bin",
|
| 65 |
+
"encoder_decoder.decoder.block.11.layer.1.EncDecAttention.q.weight": "pytorch_model-00005-of-00006.bin",
|
| 66 |
+
"encoder_decoder.decoder.block.11.layer.1.EncDecAttention.v.weight": "pytorch_model-00005-of-00006.bin",
|
| 67 |
+
"encoder_decoder.decoder.block.11.layer.1.layer_norm.weight": "pytorch_model-00005-of-00006.bin",
|
| 68 |
+
"encoder_decoder.decoder.block.11.layer.2.DenseReluDense.wi.weight": "pytorch_model-00005-of-00006.bin",
|
| 69 |
+
"encoder_decoder.decoder.block.11.layer.2.DenseReluDense.wo.weight": "pytorch_model-00005-of-00006.bin",
|
| 70 |
+
"encoder_decoder.decoder.block.11.layer.2.layer_norm.weight": "pytorch_model-00005-of-00006.bin",
|
| 71 |
+
"encoder_decoder.decoder.block.2.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00006.bin",
|
| 72 |
+
"encoder_decoder.decoder.block.2.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00006.bin",
|
| 73 |
+
"encoder_decoder.decoder.block.2.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00006.bin",
|
| 74 |
+
"encoder_decoder.decoder.block.2.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00006.bin",
|
| 75 |
+
"encoder_decoder.decoder.block.2.layer.0.layer_norm.weight": "pytorch_model-00003-of-00006.bin",
|
| 76 |
+
"encoder_decoder.decoder.block.2.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00006.bin",
|
| 77 |
+
"encoder_decoder.decoder.block.2.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00006.bin",
|
| 78 |
+
"encoder_decoder.decoder.block.2.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00006.bin",
|
| 79 |
+
"encoder_decoder.decoder.block.2.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00006.bin",
|
| 80 |
+
"encoder_decoder.decoder.block.2.layer.1.layer_norm.weight": "pytorch_model-00003-of-00006.bin",
|
| 81 |
+
"encoder_decoder.decoder.block.2.layer.2.DenseReluDense.wi.weight": "pytorch_model-00003-of-00006.bin",
|
| 82 |
+
"encoder_decoder.decoder.block.2.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00006.bin",
|
| 83 |
+
"encoder_decoder.decoder.block.2.layer.2.layer_norm.weight": "pytorch_model-00003-of-00006.bin",
|
| 84 |
+
"encoder_decoder.decoder.block.3.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00006.bin",
|
| 85 |
+
"encoder_decoder.decoder.block.3.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00006.bin",
|
| 86 |
+
"encoder_decoder.decoder.block.3.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00006.bin",
|
| 87 |
+
"encoder_decoder.decoder.block.3.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00006.bin",
|
| 88 |
+
"encoder_decoder.decoder.block.3.layer.0.layer_norm.weight": "pytorch_model-00003-of-00006.bin",
|
| 89 |
+
"encoder_decoder.decoder.block.3.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00006.bin",
|
| 90 |
+
"encoder_decoder.decoder.block.3.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00006.bin",
|
| 91 |
+
"encoder_decoder.decoder.block.3.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00006.bin",
|
| 92 |
+
"encoder_decoder.decoder.block.3.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00006.bin",
|
| 93 |
+
"encoder_decoder.decoder.block.3.layer.1.layer_norm.weight": "pytorch_model-00003-of-00006.bin",
|
| 94 |
+
"encoder_decoder.decoder.block.3.layer.2.DenseReluDense.wi.weight": "pytorch_model-00003-of-00006.bin",
|
| 95 |
+
"encoder_decoder.decoder.block.3.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00006.bin",
|
| 96 |
+
"encoder_decoder.decoder.block.3.layer.2.layer_norm.weight": "pytorch_model-00003-of-00006.bin",
|
| 97 |
+
"encoder_decoder.decoder.block.4.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00006.bin",
|
| 98 |
+
"encoder_decoder.decoder.block.4.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00006.bin",
|
| 99 |
+
"encoder_decoder.decoder.block.4.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00006.bin",
|
| 100 |
+
"encoder_decoder.decoder.block.4.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00006.bin",
|
| 101 |
+
"encoder_decoder.decoder.block.4.layer.0.layer_norm.weight": "pytorch_model-00004-of-00006.bin",
|
| 102 |
+
"encoder_decoder.decoder.block.4.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00006.bin",
|
| 103 |
+
"encoder_decoder.decoder.block.4.layer.1.EncDecAttention.o.weight": "pytorch_model-00004-of-00006.bin",
|
| 104 |
+
"encoder_decoder.decoder.block.4.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00006.bin",
|
| 105 |
+
"encoder_decoder.decoder.block.4.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00006.bin",
|
| 106 |
+
"encoder_decoder.decoder.block.4.layer.1.layer_norm.weight": "pytorch_model-00004-of-00006.bin",
|
| 107 |
+
"encoder_decoder.decoder.block.4.layer.2.DenseReluDense.wi.weight": "pytorch_model-00004-of-00006.bin",
|
| 108 |
+
"encoder_decoder.decoder.block.4.layer.2.DenseReluDense.wo.weight": "pytorch_model-00004-of-00006.bin",
|
| 109 |
+
"encoder_decoder.decoder.block.4.layer.2.layer_norm.weight": "pytorch_model-00004-of-00006.bin",
|
| 110 |
+
"encoder_decoder.decoder.block.5.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00006.bin",
|
| 111 |
+
"encoder_decoder.decoder.block.5.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00006.bin",
|
| 112 |
+
"encoder_decoder.decoder.block.5.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00006.bin",
|
| 113 |
+
"encoder_decoder.decoder.block.5.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00006.bin",
|
| 114 |
+
"encoder_decoder.decoder.block.5.layer.0.layer_norm.weight": "pytorch_model-00004-of-00006.bin",
|
| 115 |
+
"encoder_decoder.decoder.block.5.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00006.bin",
|
| 116 |
+
"encoder_decoder.decoder.block.5.layer.1.EncDecAttention.o.weight": "pytorch_model-00004-of-00006.bin",
|
| 117 |
+
"encoder_decoder.decoder.block.5.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00006.bin",
|
| 118 |
+
"encoder_decoder.decoder.block.5.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00006.bin",
|
| 119 |
+
"encoder_decoder.decoder.block.5.layer.1.layer_norm.weight": "pytorch_model-00004-of-00006.bin",
|
| 120 |
+
"encoder_decoder.decoder.block.5.layer.2.DenseReluDense.wi.weight": "pytorch_model-00004-of-00006.bin",
|
| 121 |
+
"encoder_decoder.decoder.block.5.layer.2.DenseReluDense.wo.weight": "pytorch_model-00004-of-00006.bin",
|
| 122 |
+
"encoder_decoder.decoder.block.5.layer.2.layer_norm.weight": "pytorch_model-00004-of-00006.bin",
|
| 123 |
+
"encoder_decoder.decoder.block.6.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00006.bin",
|
| 124 |
+
"encoder_decoder.decoder.block.6.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00006.bin",
|
| 125 |
+
"encoder_decoder.decoder.block.6.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00006.bin",
|
| 126 |
+
"encoder_decoder.decoder.block.6.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00006.bin",
|
| 127 |
+
"encoder_decoder.decoder.block.6.layer.0.layer_norm.weight": "pytorch_model-00004-of-00006.bin",
|
| 128 |
+
"encoder_decoder.decoder.block.6.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00006.bin",
|
| 129 |
+
"encoder_decoder.decoder.block.6.layer.1.EncDecAttention.o.weight": "pytorch_model-00004-of-00006.bin",
|
| 130 |
+
"encoder_decoder.decoder.block.6.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00006.bin",
|
| 131 |
+
"encoder_decoder.decoder.block.6.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00006.bin",
|
| 132 |
+
"encoder_decoder.decoder.block.6.layer.1.layer_norm.weight": "pytorch_model-00004-of-00006.bin",
|
| 133 |
+
"encoder_decoder.decoder.block.6.layer.2.DenseReluDense.wi.weight": "pytorch_model-00004-of-00006.bin",
|
| 134 |
+
"encoder_decoder.decoder.block.6.layer.2.DenseReluDense.wo.weight": "pytorch_model-00004-of-00006.bin",
|
| 135 |
+
"encoder_decoder.decoder.block.6.layer.2.layer_norm.weight": "pytorch_model-00004-of-00006.bin",
|
| 136 |
+
"encoder_decoder.decoder.block.7.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00006.bin",
|
| 137 |
+
"encoder_decoder.decoder.block.7.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00006.bin",
|
| 138 |
+
"encoder_decoder.decoder.block.7.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00006.bin",
|
| 139 |
+
"encoder_decoder.decoder.block.7.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00006.bin",
|
| 140 |
+
"encoder_decoder.decoder.block.7.layer.0.layer_norm.weight": "pytorch_model-00004-of-00006.bin",
|
| 141 |
+
"encoder_decoder.decoder.block.7.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00006.bin",
|
| 142 |
+
"encoder_decoder.decoder.block.7.layer.1.EncDecAttention.o.weight": "pytorch_model-00004-of-00006.bin",
|
| 143 |
+
"encoder_decoder.decoder.block.7.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00006.bin",
|
| 144 |
+
"encoder_decoder.decoder.block.7.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00006.bin",
|
| 145 |
+
"encoder_decoder.decoder.block.7.layer.1.layer_norm.weight": "pytorch_model-00004-of-00006.bin",
|
| 146 |
+
"encoder_decoder.decoder.block.7.layer.2.DenseReluDense.wi.weight": "pytorch_model-00004-of-00006.bin",
|
| 147 |
+
"encoder_decoder.decoder.block.7.layer.2.DenseReluDense.wo.weight": "pytorch_model-00004-of-00006.bin",
|
| 148 |
+
"encoder_decoder.decoder.block.7.layer.2.layer_norm.weight": "pytorch_model-00004-of-00006.bin",
|
| 149 |
+
"encoder_decoder.decoder.block.8.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00006.bin",
|
| 150 |
+
"encoder_decoder.decoder.block.8.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00006.bin",
|
| 151 |
+
"encoder_decoder.decoder.block.8.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00006.bin",
|
| 152 |
+
"encoder_decoder.decoder.block.8.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00006.bin",
|
| 153 |
+
"encoder_decoder.decoder.block.8.layer.0.layer_norm.weight": "pytorch_model-00004-of-00006.bin",
|
| 154 |
+
"encoder_decoder.decoder.block.8.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00006.bin",
|
| 155 |
+
"encoder_decoder.decoder.block.8.layer.1.EncDecAttention.o.weight": "pytorch_model-00004-of-00006.bin",
|
| 156 |
+
"encoder_decoder.decoder.block.8.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00006.bin",
|
| 157 |
+
"encoder_decoder.decoder.block.8.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00006.bin",
|
| 158 |
+
"encoder_decoder.decoder.block.8.layer.1.layer_norm.weight": "pytorch_model-00004-of-00006.bin",
|
| 159 |
+
"encoder_decoder.decoder.block.8.layer.2.DenseReluDense.wi.weight": "pytorch_model-00004-of-00006.bin",
|
| 160 |
+
"encoder_decoder.decoder.block.8.layer.2.DenseReluDense.wo.weight": "pytorch_model-00004-of-00006.bin",
|
| 161 |
+
"encoder_decoder.decoder.block.8.layer.2.layer_norm.weight": "pytorch_model-00004-of-00006.bin",
|
| 162 |
+
"encoder_decoder.decoder.block.9.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00006.bin",
|
| 163 |
+
"encoder_decoder.decoder.block.9.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00006.bin",
|
| 164 |
+
"encoder_decoder.decoder.block.9.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00006.bin",
|
| 165 |
+
"encoder_decoder.decoder.block.9.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00006.bin",
|
| 166 |
+
"encoder_decoder.decoder.block.9.layer.0.layer_norm.weight": "pytorch_model-00004-of-00006.bin",
|
| 167 |
+
"encoder_decoder.decoder.block.9.layer.1.EncDecAttention.k.weight": "pytorch_model-00005-of-00006.bin",
|
| 168 |
+
"encoder_decoder.decoder.block.9.layer.1.EncDecAttention.o.weight": "pytorch_model-00005-of-00006.bin",
|
| 169 |
+
"encoder_decoder.decoder.block.9.layer.1.EncDecAttention.q.weight": "pytorch_model-00005-of-00006.bin",
|
| 170 |
+
"encoder_decoder.decoder.block.9.layer.1.EncDecAttention.v.weight": "pytorch_model-00005-of-00006.bin",
|
| 171 |
+
"encoder_decoder.decoder.block.9.layer.1.layer_norm.weight": "pytorch_model-00005-of-00006.bin",
|
| 172 |
+
"encoder_decoder.decoder.block.9.layer.2.DenseReluDense.wi.weight": "pytorch_model-00005-of-00006.bin",
|
| 173 |
+
"encoder_decoder.decoder.block.9.layer.2.DenseReluDense.wo.weight": "pytorch_model-00005-of-00006.bin",
|
| 174 |
+
"encoder_decoder.decoder.block.9.layer.2.layer_norm.weight": "pytorch_model-00005-of-00006.bin",
|
| 175 |
+
"encoder_decoder.decoder.embed_tokens.weight": "pytorch_model-00001-of-00006.bin",
|
| 176 |
+
"encoder_decoder.decoder.final_layer_norm.weight": "pytorch_model-00005-of-00006.bin",
|
| 177 |
+
"encoder_decoder.encoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00006.bin",
|
| 178 |
+
"encoder_decoder.encoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00006.bin",
|
| 179 |
+
"encoder_decoder.encoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00006.bin",
|
| 180 |
+
"encoder_decoder.encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model-00001-of-00006.bin",
|
| 181 |
+
"encoder_decoder.encoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00006.bin",
|
| 182 |
+
"encoder_decoder.encoder.block.0.layer.0.layer_norm.weight": "pytorch_model-00001-of-00006.bin",
|
| 183 |
+
"encoder_decoder.encoder.block.0.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00006.bin",
|
| 184 |
+
"encoder_decoder.encoder.block.0.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00006.bin",
|
| 185 |
+
"encoder_decoder.encoder.block.0.layer.1.layer_norm.weight": "pytorch_model-00001-of-00006.bin",
|
| 186 |
+
"encoder_decoder.encoder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00006.bin",
|
| 187 |
+
"encoder_decoder.encoder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00006.bin",
|
| 188 |
+
"encoder_decoder.encoder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00006.bin",
|
| 189 |
+
"encoder_decoder.encoder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00006.bin",
|
| 190 |
+
"encoder_decoder.encoder.block.1.layer.0.layer_norm.weight": "pytorch_model-00001-of-00006.bin",
|
| 191 |
+
"encoder_decoder.encoder.block.1.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00006.bin",
|
| 192 |
+
"encoder_decoder.encoder.block.1.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00006.bin",
|
| 193 |
+
"encoder_decoder.encoder.block.1.layer.1.layer_norm.weight": "pytorch_model-00001-of-00006.bin",
|
| 194 |
+
"encoder_decoder.encoder.block.10.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00006.bin",
|
| 195 |
+
"encoder_decoder.encoder.block.10.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00006.bin",
|
| 196 |
+
"encoder_decoder.encoder.block.10.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00006.bin",
|
| 197 |
+
"encoder_decoder.encoder.block.10.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00006.bin",
|
| 198 |
+
"encoder_decoder.encoder.block.10.layer.0.layer_norm.weight": "pytorch_model-00002-of-00006.bin",
|
| 199 |
+
"encoder_decoder.encoder.block.10.layer.1.DenseReluDense.wi.weight": "pytorch_model-00003-of-00006.bin",
|
| 200 |
+
"encoder_decoder.encoder.block.10.layer.1.DenseReluDense.wo.weight": "pytorch_model-00003-of-00006.bin",
|
| 201 |
+
"encoder_decoder.encoder.block.10.layer.1.layer_norm.weight": "pytorch_model-00003-of-00006.bin",
|
| 202 |
+
"encoder_decoder.encoder.block.11.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00006.bin",
|
| 203 |
+
"encoder_decoder.encoder.block.11.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00006.bin",
|
| 204 |
+
"encoder_decoder.encoder.block.11.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00006.bin",
|
| 205 |
+
"encoder_decoder.encoder.block.11.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00006.bin",
|
| 206 |
+
"encoder_decoder.encoder.block.11.layer.0.layer_norm.weight": "pytorch_model-00003-of-00006.bin",
|
| 207 |
+
"encoder_decoder.encoder.block.11.layer.1.DenseReluDense.wi.weight": "pytorch_model-00003-of-00006.bin",
|
| 208 |
+
"encoder_decoder.encoder.block.11.layer.1.DenseReluDense.wo.weight": "pytorch_model-00003-of-00006.bin",
|
| 209 |
+
"encoder_decoder.encoder.block.11.layer.1.layer_norm.weight": "pytorch_model-00003-of-00006.bin",
|
| 210 |
+
"encoder_decoder.encoder.block.2.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00006.bin",
|
| 211 |
+
"encoder_decoder.encoder.block.2.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00006.bin",
|
| 212 |
+
"encoder_decoder.encoder.block.2.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00006.bin",
|
| 213 |
+
"encoder_decoder.encoder.block.2.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00006.bin",
|
| 214 |
+
"encoder_decoder.encoder.block.2.layer.0.layer_norm.weight": "pytorch_model-00001-of-00006.bin",
|
| 215 |
+
"encoder_decoder.encoder.block.2.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00006.bin",
|
| 216 |
+
"encoder_decoder.encoder.block.2.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00006.bin",
|
| 217 |
+
"encoder_decoder.encoder.block.2.layer.1.layer_norm.weight": "pytorch_model-00001-of-00006.bin",
|
| 218 |
+
"encoder_decoder.encoder.block.3.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00006.bin",
|
| 219 |
+
"encoder_decoder.encoder.block.3.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00006.bin",
|
| 220 |
+
"encoder_decoder.encoder.block.3.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00006.bin",
|
| 221 |
+
"encoder_decoder.encoder.block.3.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00006.bin",
|
| 222 |
+
"encoder_decoder.encoder.block.3.layer.0.layer_norm.weight": "pytorch_model-00001-of-00006.bin",
|
| 223 |
+
"encoder_decoder.encoder.block.3.layer.1.DenseReluDense.wi.weight": "pytorch_model-00002-of-00006.bin",
|
| 224 |
+
"encoder_decoder.encoder.block.3.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00006.bin",
|
| 225 |
+
"encoder_decoder.encoder.block.3.layer.1.layer_norm.weight": "pytorch_model-00002-of-00006.bin",
|
| 226 |
+
"encoder_decoder.encoder.block.4.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00006.bin",
|
| 227 |
+
"encoder_decoder.encoder.block.4.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00006.bin",
|
| 228 |
+
"encoder_decoder.encoder.block.4.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00006.bin",
|
| 229 |
+
"encoder_decoder.encoder.block.4.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00006.bin",
|
| 230 |
+
"encoder_decoder.encoder.block.4.layer.0.layer_norm.weight": "pytorch_model-00002-of-00006.bin",
|
| 231 |
+
"encoder_decoder.encoder.block.4.layer.1.DenseReluDense.wi.weight": "pytorch_model-00002-of-00006.bin",
|
| 232 |
+
"encoder_decoder.encoder.block.4.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00006.bin",
|
| 233 |
+
"encoder_decoder.encoder.block.4.layer.1.layer_norm.weight": "pytorch_model-00002-of-00006.bin",
|
| 234 |
+
"encoder_decoder.encoder.block.5.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00006.bin",
|
| 235 |
+
"encoder_decoder.encoder.block.5.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00006.bin",
|
| 236 |
+
"encoder_decoder.encoder.block.5.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00006.bin",
|
| 237 |
+
"encoder_decoder.encoder.block.5.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00006.bin",
|
| 238 |
+
"encoder_decoder.encoder.block.5.layer.0.layer_norm.weight": "pytorch_model-00002-of-00006.bin",
|
| 239 |
+
"encoder_decoder.encoder.block.5.layer.1.DenseReluDense.wi.weight": "pytorch_model-00002-of-00006.bin",
|
| 240 |
+
"encoder_decoder.encoder.block.5.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00006.bin",
|
| 241 |
+
"encoder_decoder.encoder.block.5.layer.1.layer_norm.weight": "pytorch_model-00002-of-00006.bin",
|
| 242 |
+
"encoder_decoder.encoder.block.6.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00006.bin",
|
| 243 |
+
"encoder_decoder.encoder.block.6.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00006.bin",
|
| 244 |
+
"encoder_decoder.encoder.block.6.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00006.bin",
|
| 245 |
+
"encoder_decoder.encoder.block.6.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00006.bin",
|
| 246 |
+
"encoder_decoder.encoder.block.6.layer.0.layer_norm.weight": "pytorch_model-00002-of-00006.bin",
|
| 247 |
+
"encoder_decoder.encoder.block.6.layer.1.DenseReluDense.wi.weight": "pytorch_model-00002-of-00006.bin",
|
| 248 |
+
"encoder_decoder.encoder.block.6.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00006.bin",
|
| 249 |
+
"encoder_decoder.encoder.block.6.layer.1.layer_norm.weight": "pytorch_model-00002-of-00006.bin",
|
| 250 |
+
"encoder_decoder.encoder.block.7.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00006.bin",
|
| 251 |
+
"encoder_decoder.encoder.block.7.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00006.bin",
|
| 252 |
+
"encoder_decoder.encoder.block.7.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00006.bin",
|
| 253 |
+
"encoder_decoder.encoder.block.7.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00006.bin",
|
| 254 |
+
"encoder_decoder.encoder.block.7.layer.0.layer_norm.weight": "pytorch_model-00002-of-00006.bin",
|
| 255 |
+
"encoder_decoder.encoder.block.7.layer.1.DenseReluDense.wi.weight": "pytorch_model-00002-of-00006.bin",
|
| 256 |
+
"encoder_decoder.encoder.block.7.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00006.bin",
|
| 257 |
+
"encoder_decoder.encoder.block.7.layer.1.layer_norm.weight": "pytorch_model-00002-of-00006.bin",
|
| 258 |
+
"encoder_decoder.encoder.block.8.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00006.bin",
|
| 259 |
+
"encoder_decoder.encoder.block.8.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00006.bin",
|
| 260 |
+
"encoder_decoder.encoder.block.8.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00006.bin",
|
| 261 |
+
"encoder_decoder.encoder.block.8.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00006.bin",
|
| 262 |
+
"encoder_decoder.encoder.block.8.layer.0.layer_norm.weight": "pytorch_model-00002-of-00006.bin",
|
| 263 |
+
"encoder_decoder.encoder.block.8.layer.1.DenseReluDense.wi.weight": "pytorch_model-00002-of-00006.bin",
|
| 264 |
+
"encoder_decoder.encoder.block.8.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00006.bin",
|
| 265 |
+
"encoder_decoder.encoder.block.8.layer.1.layer_norm.weight": "pytorch_model-00002-of-00006.bin",
|
| 266 |
+
"encoder_decoder.encoder.block.9.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00006.bin",
|
| 267 |
+
"encoder_decoder.encoder.block.9.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00006.bin",
|
| 268 |
+
"encoder_decoder.encoder.block.9.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00006.bin",
|
| 269 |
+
"encoder_decoder.encoder.block.9.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00006.bin",
|
| 270 |
+
"encoder_decoder.encoder.block.9.layer.0.layer_norm.weight": "pytorch_model-00002-of-00006.bin",
|
| 271 |
+
"encoder_decoder.encoder.block.9.layer.1.DenseReluDense.wi.weight": "pytorch_model-00002-of-00006.bin",
|
| 272 |
+
"encoder_decoder.encoder.block.9.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00006.bin",
|
| 273 |
+
"encoder_decoder.encoder.block.9.layer.1.layer_norm.weight": "pytorch_model-00002-of-00006.bin",
|
| 274 |
+
"encoder_decoder.encoder.embed_tokens.weight": "pytorch_model-00001-of-00006.bin",
|
| 275 |
+
"encoder_decoder.encoder.final_layer_norm.weight": "pytorch_model-00003-of-00006.bin",
|
| 276 |
+
"encoder_decoder.lm_head.weight": "pytorch_model-00001-of-00006.bin",
|
| 277 |
+
"encoder_decoder.shared.weight": "pytorch_model-00001-of-00006.bin",
|
| 278 |
+
"layernorm.bias": "pytorch_model-00006-of-00006.bin",
|
| 279 |
+
"layernorm.weight": "pytorch_model-00006-of-00006.bin"
|
| 280 |
+
}
|
| 281 |
+
}
|