Upload model
Browse files- config.json +162 -0
- generation_config.json +4 -0
- pytorch_model-00001-of-00007.bin +3 -0
- pytorch_model-00002-of-00007.bin +3 -0
- pytorch_model-00003-of-00007.bin +3 -0
- pytorch_model-00004-of-00007.bin +3 -0
- pytorch_model-00005-of-00007.bin +3 -0
- pytorch_model-00006-of-00007.bin +3 -0
- pytorch_model-00007-of-00007.bin +3 -0
- pytorch_model.bin.index.json +290 -0
config.json
ADDED
@@ -0,0 +1,162 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"CorrectorEncoderFromLogitsModel"
|
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/t5-base__llama-7b__one-million-paired-instructions",
|
21 |
+
"data_seed": null,
|
22 |
+
"dataloader_drop_last": false,
|
23 |
+
"dataloader_num_workers": 0,
|
24 |
+
"dataloader_pin_memory": true,
|
25 |
+
"dataset_name": "one_million_instructions",
|
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_dim": 768,
|
41 |
+
"embedder_fake_with_zeros": false,
|
42 |
+
"embedder_model_api": null,
|
43 |
+
"embedder_model_name": "gtr_base",
|
44 |
+
"embedder_no_grad": true,
|
45 |
+
"embedder_torch_dtype": "float32",
|
46 |
+
"embedding_transform_strategy": "repeat",
|
47 |
+
"embedding_zero_except_topk": null,
|
48 |
+
"embeddings_from_layer_n": null,
|
49 |
+
"encoder_dropout_disabled": false,
|
50 |
+
"eval_accumulation_steps": null,
|
51 |
+
"eval_delay": 0,
|
52 |
+
"eval_steps": 20000,
|
53 |
+
"evaluation_strategy": "steps",
|
54 |
+
"exp_group_name": "",
|
55 |
+
"exp_name": "",
|
56 |
+
"experiment": "corrector",
|
57 |
+
"fp16": false,
|
58 |
+
"fp16_backend": "auto",
|
59 |
+
"fp16_full_eval": false,
|
60 |
+
"fp16_opt_level": "O1",
|
61 |
+
"freeze_strategy": "none",
|
62 |
+
"fsdp": [],
|
63 |
+
"fsdp_config": {
|
64 |
+
"min_num_params": 0,
|
65 |
+
"xla": false,
|
66 |
+
"xla_fsdp_grad_ckpt": false
|
67 |
+
},
|
68 |
+
"fsdp_min_num_params": 0,
|
69 |
+
"fsdp_transformer_layer_cls_to_wrap": null,
|
70 |
+
"full_determinism": false,
|
71 |
+
"gradient_accumulation_steps": 1,
|
72 |
+
"gradient_checkpointing": false,
|
73 |
+
"greater_is_better": false,
|
74 |
+
"group_by_length": true,
|
75 |
+
"half_precision_backend": "auto",
|
76 |
+
"hub_always_push": false,
|
77 |
+
"hub_model_id": null,
|
78 |
+
"hub_private_repo": false,
|
79 |
+
"hub_strategy": "every_save",
|
80 |
+
"hub_token": null,
|
81 |
+
"ignore_data_skip": false,
|
82 |
+
"include_inputs_for_metrics": true,
|
83 |
+
"include_tokens_per_second": false,
|
84 |
+
"jit_mode_eval": false,
|
85 |
+
"label_names": null,
|
86 |
+
"label_smoothing_factor": 0.0,
|
87 |
+
"learning_rate": 0.0002,
|
88 |
+
"length_column_name": "length",
|
89 |
+
"load_best_model_at_end": true,
|
90 |
+
"local_rank": 0,
|
91 |
+
"log_level": "passive",
|
92 |
+
"log_level_replica": "warning",
|
93 |
+
"log_on_each_node": true,
|
94 |
+
"logging_dir": "saves/corrector-llama-norm100-3/runs/Nov08_07-53-56_mosaic-cirrascale-35.reviz.ai2.in",
|
95 |
+
"logging_first_step": false,
|
96 |
+
"logging_nan_inf_filter": true,
|
97 |
+
"logging_steps": 100,
|
98 |
+
"logging_strategy": "steps",
|
99 |
+
"lr_scheduler_type": "constant_with_warmup",
|
100 |
+
"max_eval_samples": 500,
|
101 |
+
"max_grad_norm": 1.0,
|
102 |
+
"max_seq_length": 128,
|
103 |
+
"max_steps": -1,
|
104 |
+
"metric_for_best_model": "one_million_instructions_loss",
|
105 |
+
"mock_embedder": false,
|
106 |
+
"model_name_or_path": "t5-base",
|
107 |
+
"model_revision": "main",
|
108 |
+
"mp_parameters": "",
|
109 |
+
"no_cuda": true,
|
110 |
+
"num_repeat_tokens": 42,
|
111 |
+
"num_train_epochs": 300.0,
|
112 |
+
"num_zeros_to_add": 512,
|
113 |
+
"optim": "adamw_torch",
|
114 |
+
"optim_args": null,
|
115 |
+
"output_dir": "saves/corrector-llama-norm100-3",
|
116 |
+
"overwrite_output_dir": false,
|
117 |
+
"past_index": -1,
|
118 |
+
"per_device_eval_batch_size": 32,
|
119 |
+
"per_device_train_batch_size": 32,
|
120 |
+
"per_gpu_eval_batch_size": null,
|
121 |
+
"per_gpu_train_batch_size": null,
|
122 |
+
"prediction_loss_only": false,
|
123 |
+
"push_to_hub": false,
|
124 |
+
"push_to_hub_model_id": null,
|
125 |
+
"push_to_hub_organization": null,
|
126 |
+
"push_to_hub_token": null,
|
127 |
+
"ray_scope": "last",
|
128 |
+
"remove_unused_columns": false,
|
129 |
+
"report_to": [],
|
130 |
+
"resume_from_checkpoint": null,
|
131 |
+
"run_name": "saves/corrector-llama-norm100-3",
|
132 |
+
"save_on_each_node": false,
|
133 |
+
"save_safetensors": false,
|
134 |
+
"save_steps": 4000,
|
135 |
+
"save_strategy": "steps",
|
136 |
+
"save_total_limit": 2,
|
137 |
+
"seed": 42,
|
138 |
+
"skip_memory_metrics": true,
|
139 |
+
"steps_per_epoch": 500000,
|
140 |
+
"suffix_conditioning": false,
|
141 |
+
"tf32": null,
|
142 |
+
"tokenizer_name": null,
|
143 |
+
"torch_compile": false,
|
144 |
+
"torch_compile_backend": null,
|
145 |
+
"torch_compile_mode": null,
|
146 |
+
"torch_dtype": "float32",
|
147 |
+
"torchdynamo": null,
|
148 |
+
"tpu_metrics_debug": false,
|
149 |
+
"tpu_num_cores": null,
|
150 |
+
"transformers_version": "4.35.0.dev0",
|
151 |
+
"use_cpu": false,
|
152 |
+
"use_frozen_embeddings_as_input": false,
|
153 |
+
"use_ipex": false,
|
154 |
+
"use_legacy_prediction_loop": false,
|
155 |
+
"use_less_data": -1,
|
156 |
+
"use_lora": false,
|
157 |
+
"use_mps_device": false,
|
158 |
+
"use_wandb": false,
|
159 |
+
"warmup_ratio": 0.0,
|
160 |
+
"warmup_steps": 20000,
|
161 |
+
"weight_decay": 0.0
|
162 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"transformers_version": "4.35.0.dev0"
|
4 |
+
}
|
pytorch_model-00001-of-00007.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:01d6a861f6b30183413dd86f416db19a5de7aff0dcb70f9add1b4e44496001bd
|
3 |
+
size 198182550
|
pytorch_model-00002-of-00007.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f94260ab67a1a7824ecfe7c2020893560f8619def6be672029bbc49478ee89b8
|
3 |
+
size 197789654
|
pytorch_model-00003-of-00007.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:394214724bf7ddea1e6e3724108757248471ed1ea99ac2ff125f6c4e7a61c375
|
3 |
+
size 198246316
|
pytorch_model-00004-of-00007.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0d8ed27c220b88532fd43feb0114953f1fcd3fa6e3196ce302ebeb698f7943da
|
3 |
+
size 198255356
|
pytorch_model-00005-of-00007.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:77e0b3eeea99a477cc60362231e2451f6d4e68bba3a56549c39ee80e49302b39
|
3 |
+
size 198251086
|
pytorch_model-00006-of-00007.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:70e318c3171031bd02886783126c544e31a84f2b71c86bc05d6840baba439737
|
3 |
+
size 198257970
|
pytorch_model-00007-of-00007.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2e063a392389eca9bc01f2c15a328063076f064eaa0cdaa618d5d6da72d92ba5
|
3 |
+
size 14205842
|
pytorch_model.bin.index.json
ADDED
@@ -0,0 +1,290 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 1203084288
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"embedding_transform_1.0.bias": "pytorch_model-00007-of-00007.bin",
|
7 |
+
"embedding_transform_1.0.weight": "pytorch_model-00007-of-00007.bin",
|
8 |
+
"embedding_transform_1.3.bias": "pytorch_model-00007-of-00007.bin",
|
9 |
+
"embedding_transform_1.3.weight": "pytorch_model-00007-of-00007.bin",
|
10 |
+
"embedding_transform_2.0.bias": "pytorch_model-00007-of-00007.bin",
|
11 |
+
"embedding_transform_2.0.weight": "pytorch_model-00007-of-00007.bin",
|
12 |
+
"embedding_transform_2.3.bias": "pytorch_model-00007-of-00007.bin",
|
13 |
+
"embedding_transform_2.3.weight": "pytorch_model-00007-of-00007.bin",
|
14 |
+
"embedding_transform_3.0.bias": "pytorch_model-00007-of-00007.bin",
|
15 |
+
"embedding_transform_3.0.weight": "pytorch_model-00007-of-00007.bin",
|
16 |
+
"embedding_transform_3.3.bias": "pytorch_model-00007-of-00007.bin",
|
17 |
+
"embedding_transform_3.3.weight": "pytorch_model-00007-of-00007.bin",
|
18 |
+
"encoder_decoder.decoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00007.bin",
|
19 |
+
"encoder_decoder.decoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00007.bin",
|
20 |
+
"encoder_decoder.decoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00007.bin",
|
21 |
+
"encoder_decoder.decoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model-00004-of-00007.bin",
|
22 |
+
"encoder_decoder.decoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00007.bin",
|
23 |
+
"encoder_decoder.decoder.block.0.layer.0.layer_norm.weight": "pytorch_model-00004-of-00007.bin",
|
24 |
+
"encoder_decoder.decoder.block.0.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00007.bin",
|
25 |
+
"encoder_decoder.decoder.block.0.layer.1.EncDecAttention.o.weight": "pytorch_model-00004-of-00007.bin",
|
26 |
+
"encoder_decoder.decoder.block.0.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00007.bin",
|
27 |
+
"encoder_decoder.decoder.block.0.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00007.bin",
|
28 |
+
"encoder_decoder.decoder.block.0.layer.1.layer_norm.weight": "pytorch_model-00004-of-00007.bin",
|
29 |
+
"encoder_decoder.decoder.block.0.layer.2.DenseReluDense.wi.weight": "pytorch_model-00004-of-00007.bin",
|
30 |
+
"encoder_decoder.decoder.block.0.layer.2.DenseReluDense.wo.weight": "pytorch_model-00004-of-00007.bin",
|
31 |
+
"encoder_decoder.decoder.block.0.layer.2.layer_norm.weight": "pytorch_model-00004-of-00007.bin",
|
32 |
+
"encoder_decoder.decoder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00007.bin",
|
33 |
+
"encoder_decoder.decoder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00007.bin",
|
34 |
+
"encoder_decoder.decoder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00007.bin",
|
35 |
+
"encoder_decoder.decoder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00007.bin",
|
36 |
+
"encoder_decoder.decoder.block.1.layer.0.layer_norm.weight": "pytorch_model-00004-of-00007.bin",
|
37 |
+
"encoder_decoder.decoder.block.1.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00007.bin",
|
38 |
+
"encoder_decoder.decoder.block.1.layer.1.EncDecAttention.o.weight": "pytorch_model-00004-of-00007.bin",
|
39 |
+
"encoder_decoder.decoder.block.1.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00007.bin",
|
40 |
+
"encoder_decoder.decoder.block.1.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00007.bin",
|
41 |
+
"encoder_decoder.decoder.block.1.layer.1.layer_norm.weight": "pytorch_model-00004-of-00007.bin",
|
42 |
+
"encoder_decoder.decoder.block.1.layer.2.DenseReluDense.wi.weight": "pytorch_model-00005-of-00007.bin",
|
43 |
+
"encoder_decoder.decoder.block.1.layer.2.DenseReluDense.wo.weight": "pytorch_model-00005-of-00007.bin",
|
44 |
+
"encoder_decoder.decoder.block.1.layer.2.layer_norm.weight": "pytorch_model-00005-of-00007.bin",
|
45 |
+
"encoder_decoder.decoder.block.10.layer.0.SelfAttention.k.weight": "pytorch_model-00006-of-00007.bin",
|
46 |
+
"encoder_decoder.decoder.block.10.layer.0.SelfAttention.o.weight": "pytorch_model-00006-of-00007.bin",
|
47 |
+
"encoder_decoder.decoder.block.10.layer.0.SelfAttention.q.weight": "pytorch_model-00006-of-00007.bin",
|
48 |
+
"encoder_decoder.decoder.block.10.layer.0.SelfAttention.v.weight": "pytorch_model-00006-of-00007.bin",
|
49 |
+
"encoder_decoder.decoder.block.10.layer.0.layer_norm.weight": "pytorch_model-00006-of-00007.bin",
|
50 |
+
"encoder_decoder.decoder.block.10.layer.1.EncDecAttention.k.weight": "pytorch_model-00006-of-00007.bin",
|
51 |
+
"encoder_decoder.decoder.block.10.layer.1.EncDecAttention.o.weight": "pytorch_model-00006-of-00007.bin",
|
52 |
+
"encoder_decoder.decoder.block.10.layer.1.EncDecAttention.q.weight": "pytorch_model-00006-of-00007.bin",
|
53 |
+
"encoder_decoder.decoder.block.10.layer.1.EncDecAttention.v.weight": "pytorch_model-00006-of-00007.bin",
|
54 |
+
"encoder_decoder.decoder.block.10.layer.1.layer_norm.weight": "pytorch_model-00006-of-00007.bin",
|
55 |
+
"encoder_decoder.decoder.block.10.layer.2.DenseReluDense.wi.weight": "pytorch_model-00006-of-00007.bin",
|
56 |
+
"encoder_decoder.decoder.block.10.layer.2.DenseReluDense.wo.weight": "pytorch_model-00006-of-00007.bin",
|
57 |
+
"encoder_decoder.decoder.block.10.layer.2.layer_norm.weight": "pytorch_model-00006-of-00007.bin",
|
58 |
+
"encoder_decoder.decoder.block.11.layer.0.SelfAttention.k.weight": "pytorch_model-00006-of-00007.bin",
|
59 |
+
"encoder_decoder.decoder.block.11.layer.0.SelfAttention.o.weight": "pytorch_model-00006-of-00007.bin",
|
60 |
+
"encoder_decoder.decoder.block.11.layer.0.SelfAttention.q.weight": "pytorch_model-00006-of-00007.bin",
|
61 |
+
"encoder_decoder.decoder.block.11.layer.0.SelfAttention.v.weight": "pytorch_model-00006-of-00007.bin",
|
62 |
+
"encoder_decoder.decoder.block.11.layer.0.layer_norm.weight": "pytorch_model-00006-of-00007.bin",
|
63 |
+
"encoder_decoder.decoder.block.11.layer.1.EncDecAttention.k.weight": "pytorch_model-00006-of-00007.bin",
|
64 |
+
"encoder_decoder.decoder.block.11.layer.1.EncDecAttention.o.weight": "pytorch_model-00006-of-00007.bin",
|
65 |
+
"encoder_decoder.decoder.block.11.layer.1.EncDecAttention.q.weight": "pytorch_model-00006-of-00007.bin",
|
66 |
+
"encoder_decoder.decoder.block.11.layer.1.EncDecAttention.v.weight": "pytorch_model-00006-of-00007.bin",
|
67 |
+
"encoder_decoder.decoder.block.11.layer.1.layer_norm.weight": "pytorch_model-00006-of-00007.bin",
|
68 |
+
"encoder_decoder.decoder.block.11.layer.2.DenseReluDense.wi.weight": "pytorch_model-00006-of-00007.bin",
|
69 |
+
"encoder_decoder.decoder.block.11.layer.2.DenseReluDense.wo.weight": "pytorch_model-00006-of-00007.bin",
|
70 |
+
"encoder_decoder.decoder.block.11.layer.2.layer_norm.weight": "pytorch_model-00006-of-00007.bin",
|
71 |
+
"encoder_decoder.decoder.block.2.layer.0.SelfAttention.k.weight": "pytorch_model-00005-of-00007.bin",
|
72 |
+
"encoder_decoder.decoder.block.2.layer.0.SelfAttention.o.weight": "pytorch_model-00005-of-00007.bin",
|
73 |
+
"encoder_decoder.decoder.block.2.layer.0.SelfAttention.q.weight": "pytorch_model-00005-of-00007.bin",
|
74 |
+
"encoder_decoder.decoder.block.2.layer.0.SelfAttention.v.weight": "pytorch_model-00005-of-00007.bin",
|
75 |
+
"encoder_decoder.decoder.block.2.layer.0.layer_norm.weight": "pytorch_model-00005-of-00007.bin",
|
76 |
+
"encoder_decoder.decoder.block.2.layer.1.EncDecAttention.k.weight": "pytorch_model-00005-of-00007.bin",
|
77 |
+
"encoder_decoder.decoder.block.2.layer.1.EncDecAttention.o.weight": "pytorch_model-00005-of-00007.bin",
|
78 |
+
"encoder_decoder.decoder.block.2.layer.1.EncDecAttention.q.weight": "pytorch_model-00005-of-00007.bin",
|
79 |
+
"encoder_decoder.decoder.block.2.layer.1.EncDecAttention.v.weight": "pytorch_model-00005-of-00007.bin",
|
80 |
+
"encoder_decoder.decoder.block.2.layer.1.layer_norm.weight": "pytorch_model-00005-of-00007.bin",
|
81 |
+
"encoder_decoder.decoder.block.2.layer.2.DenseReluDense.wi.weight": "pytorch_model-00005-of-00007.bin",
|
82 |
+
"encoder_decoder.decoder.block.2.layer.2.DenseReluDense.wo.weight": "pytorch_model-00005-of-00007.bin",
|
83 |
+
"encoder_decoder.decoder.block.2.layer.2.layer_norm.weight": "pytorch_model-00005-of-00007.bin",
|
84 |
+
"encoder_decoder.decoder.block.3.layer.0.SelfAttention.k.weight": "pytorch_model-00005-of-00007.bin",
|
85 |
+
"encoder_decoder.decoder.block.3.layer.0.SelfAttention.o.weight": "pytorch_model-00005-of-00007.bin",
|
86 |
+
"encoder_decoder.decoder.block.3.layer.0.SelfAttention.q.weight": "pytorch_model-00005-of-00007.bin",
|
87 |
+
"encoder_decoder.decoder.block.3.layer.0.SelfAttention.v.weight": "pytorch_model-00005-of-00007.bin",
|
88 |
+
"encoder_decoder.decoder.block.3.layer.0.layer_norm.weight": "pytorch_model-00005-of-00007.bin",
|
89 |
+
"encoder_decoder.decoder.block.3.layer.1.EncDecAttention.k.weight": "pytorch_model-00005-of-00007.bin",
|
90 |
+
"encoder_decoder.decoder.block.3.layer.1.EncDecAttention.o.weight": "pytorch_model-00005-of-00007.bin",
|
91 |
+
"encoder_decoder.decoder.block.3.layer.1.EncDecAttention.q.weight": "pytorch_model-00005-of-00007.bin",
|
92 |
+
"encoder_decoder.decoder.block.3.layer.1.EncDecAttention.v.weight": "pytorch_model-00005-of-00007.bin",
|
93 |
+
"encoder_decoder.decoder.block.3.layer.1.layer_norm.weight": "pytorch_model-00005-of-00007.bin",
|
94 |
+
"encoder_decoder.decoder.block.3.layer.2.DenseReluDense.wi.weight": "pytorch_model-00005-of-00007.bin",
|
95 |
+
"encoder_decoder.decoder.block.3.layer.2.DenseReluDense.wo.weight": "pytorch_model-00005-of-00007.bin",
|
96 |
+
"encoder_decoder.decoder.block.3.layer.2.layer_norm.weight": "pytorch_model-00005-of-00007.bin",
|
97 |
+
"encoder_decoder.decoder.block.4.layer.0.SelfAttention.k.weight": "pytorch_model-00005-of-00007.bin",
|
98 |
+
"encoder_decoder.decoder.block.4.layer.0.SelfAttention.o.weight": "pytorch_model-00005-of-00007.bin",
|
99 |
+
"encoder_decoder.decoder.block.4.layer.0.SelfAttention.q.weight": "pytorch_model-00005-of-00007.bin",
|
100 |
+
"encoder_decoder.decoder.block.4.layer.0.SelfAttention.v.weight": "pytorch_model-00005-of-00007.bin",
|
101 |
+
"encoder_decoder.decoder.block.4.layer.0.layer_norm.weight": "pytorch_model-00005-of-00007.bin",
|
102 |
+
"encoder_decoder.decoder.block.4.layer.1.EncDecAttention.k.weight": "pytorch_model-00005-of-00007.bin",
|
103 |
+
"encoder_decoder.decoder.block.4.layer.1.EncDecAttention.o.weight": "pytorch_model-00005-of-00007.bin",
|
104 |
+
"encoder_decoder.decoder.block.4.layer.1.EncDecAttention.q.weight": "pytorch_model-00005-of-00007.bin",
|
105 |
+
"encoder_decoder.decoder.block.4.layer.1.EncDecAttention.v.weight": "pytorch_model-00005-of-00007.bin",
|
106 |
+
"encoder_decoder.decoder.block.4.layer.1.layer_norm.weight": "pytorch_model-00005-of-00007.bin",
|
107 |
+
"encoder_decoder.decoder.block.4.layer.2.DenseReluDense.wi.weight": "pytorch_model-00005-of-00007.bin",
|
108 |
+
"encoder_decoder.decoder.block.4.layer.2.DenseReluDense.wo.weight": "pytorch_model-00005-of-00007.bin",
|
109 |
+
"encoder_decoder.decoder.block.4.layer.2.layer_norm.weight": "pytorch_model-00005-of-00007.bin",
|
110 |
+
"encoder_decoder.decoder.block.5.layer.0.SelfAttention.k.weight": "pytorch_model-00005-of-00007.bin",
|
111 |
+
"encoder_decoder.decoder.block.5.layer.0.SelfAttention.o.weight": "pytorch_model-00005-of-00007.bin",
|
112 |
+
"encoder_decoder.decoder.block.5.layer.0.SelfAttention.q.weight": "pytorch_model-00005-of-00007.bin",
|
113 |
+
"encoder_decoder.decoder.block.5.layer.0.SelfAttention.v.weight": "pytorch_model-00005-of-00007.bin",
|
114 |
+
"encoder_decoder.decoder.block.5.layer.0.layer_norm.weight": "pytorch_model-00005-of-00007.bin",
|
115 |
+
"encoder_decoder.decoder.block.5.layer.1.EncDecAttention.k.weight": "pytorch_model-00005-of-00007.bin",
|
116 |
+
"encoder_decoder.decoder.block.5.layer.1.EncDecAttention.o.weight": "pytorch_model-00005-of-00007.bin",
|
117 |
+
"encoder_decoder.decoder.block.5.layer.1.EncDecAttention.q.weight": "pytorch_model-00005-of-00007.bin",
|
118 |
+
"encoder_decoder.decoder.block.5.layer.1.EncDecAttention.v.weight": "pytorch_model-00005-of-00007.bin",
|
119 |
+
"encoder_decoder.decoder.block.5.layer.1.layer_norm.weight": "pytorch_model-00005-of-00007.bin",
|
120 |
+
"encoder_decoder.decoder.block.5.layer.2.DenseReluDense.wi.weight": "pytorch_model-00005-of-00007.bin",
|
121 |
+
"encoder_decoder.decoder.block.5.layer.2.DenseReluDense.wo.weight": "pytorch_model-00005-of-00007.bin",
|
122 |
+
"encoder_decoder.decoder.block.5.layer.2.layer_norm.weight": "pytorch_model-00005-of-00007.bin",
|
123 |
+
"encoder_decoder.decoder.block.6.layer.0.SelfAttention.k.weight": "pytorch_model-00005-of-00007.bin",
|
124 |
+
"encoder_decoder.decoder.block.6.layer.0.SelfAttention.o.weight": "pytorch_model-00005-of-00007.bin",
|
125 |
+
"encoder_decoder.decoder.block.6.layer.0.SelfAttention.q.weight": "pytorch_model-00005-of-00007.bin",
|
126 |
+
"encoder_decoder.decoder.block.6.layer.0.SelfAttention.v.weight": "pytorch_model-00005-of-00007.bin",
|
127 |
+
"encoder_decoder.decoder.block.6.layer.0.layer_norm.weight": "pytorch_model-00005-of-00007.bin",
|
128 |
+
"encoder_decoder.decoder.block.6.layer.1.EncDecAttention.k.weight": "pytorch_model-00005-of-00007.bin",
|
129 |
+
"encoder_decoder.decoder.block.6.layer.1.EncDecAttention.o.weight": "pytorch_model-00005-of-00007.bin",
|
130 |
+
"encoder_decoder.decoder.block.6.layer.1.EncDecAttention.q.weight": "pytorch_model-00005-of-00007.bin",
|
131 |
+
"encoder_decoder.decoder.block.6.layer.1.EncDecAttention.v.weight": "pytorch_model-00005-of-00007.bin",
|
132 |
+
"encoder_decoder.decoder.block.6.layer.1.layer_norm.weight": "pytorch_model-00005-of-00007.bin",
|
133 |
+
"encoder_decoder.decoder.block.6.layer.2.DenseReluDense.wi.weight": "pytorch_model-00005-of-00007.bin",
|
134 |
+
"encoder_decoder.decoder.block.6.layer.2.DenseReluDense.wo.weight": "pytorch_model-00006-of-00007.bin",
|
135 |
+
"encoder_decoder.decoder.block.6.layer.2.layer_norm.weight": "pytorch_model-00006-of-00007.bin",
|
136 |
+
"encoder_decoder.decoder.block.7.layer.0.SelfAttention.k.weight": "pytorch_model-00006-of-00007.bin",
|
137 |
+
"encoder_decoder.decoder.block.7.layer.0.SelfAttention.o.weight": "pytorch_model-00006-of-00007.bin",
|
138 |
+
"encoder_decoder.decoder.block.7.layer.0.SelfAttention.q.weight": "pytorch_model-00006-of-00007.bin",
|
139 |
+
"encoder_decoder.decoder.block.7.layer.0.SelfAttention.v.weight": "pytorch_model-00006-of-00007.bin",
|
140 |
+
"encoder_decoder.decoder.block.7.layer.0.layer_norm.weight": "pytorch_model-00006-of-00007.bin",
|
141 |
+
"encoder_decoder.decoder.block.7.layer.1.EncDecAttention.k.weight": "pytorch_model-00006-of-00007.bin",
|
142 |
+
"encoder_decoder.decoder.block.7.layer.1.EncDecAttention.o.weight": "pytorch_model-00006-of-00007.bin",
|
143 |
+
"encoder_decoder.decoder.block.7.layer.1.EncDecAttention.q.weight": "pytorch_model-00006-of-00007.bin",
|
144 |
+
"encoder_decoder.decoder.block.7.layer.1.EncDecAttention.v.weight": "pytorch_model-00006-of-00007.bin",
|
145 |
+
"encoder_decoder.decoder.block.7.layer.1.layer_norm.weight": "pytorch_model-00006-of-00007.bin",
|
146 |
+
"encoder_decoder.decoder.block.7.layer.2.DenseReluDense.wi.weight": "pytorch_model-00006-of-00007.bin",
|
147 |
+
"encoder_decoder.decoder.block.7.layer.2.DenseReluDense.wo.weight": "pytorch_model-00006-of-00007.bin",
|
148 |
+
"encoder_decoder.decoder.block.7.layer.2.layer_norm.weight": "pytorch_model-00006-of-00007.bin",
|
149 |
+
"encoder_decoder.decoder.block.8.layer.0.SelfAttention.k.weight": "pytorch_model-00006-of-00007.bin",
|
150 |
+
"encoder_decoder.decoder.block.8.layer.0.SelfAttention.o.weight": "pytorch_model-00006-of-00007.bin",
|
151 |
+
"encoder_decoder.decoder.block.8.layer.0.SelfAttention.q.weight": "pytorch_model-00006-of-00007.bin",
|
152 |
+
"encoder_decoder.decoder.block.8.layer.0.SelfAttention.v.weight": "pytorch_model-00006-of-00007.bin",
|
153 |
+
"encoder_decoder.decoder.block.8.layer.0.layer_norm.weight": "pytorch_model-00006-of-00007.bin",
|
154 |
+
"encoder_decoder.decoder.block.8.layer.1.EncDecAttention.k.weight": "pytorch_model-00006-of-00007.bin",
|
155 |
+
"encoder_decoder.decoder.block.8.layer.1.EncDecAttention.o.weight": "pytorch_model-00006-of-00007.bin",
|
156 |
+
"encoder_decoder.decoder.block.8.layer.1.EncDecAttention.q.weight": "pytorch_model-00006-of-00007.bin",
|
157 |
+
"encoder_decoder.decoder.block.8.layer.1.EncDecAttention.v.weight": "pytorch_model-00006-of-00007.bin",
|
158 |
+
"encoder_decoder.decoder.block.8.layer.1.layer_norm.weight": "pytorch_model-00006-of-00007.bin",
|
159 |
+
"encoder_decoder.decoder.block.8.layer.2.DenseReluDense.wi.weight": "pytorch_model-00006-of-00007.bin",
|
160 |
+
"encoder_decoder.decoder.block.8.layer.2.DenseReluDense.wo.weight": "pytorch_model-00006-of-00007.bin",
|
161 |
+
"encoder_decoder.decoder.block.8.layer.2.layer_norm.weight": "pytorch_model-00006-of-00007.bin",
|
162 |
+
"encoder_decoder.decoder.block.9.layer.0.SelfAttention.k.weight": "pytorch_model-00006-of-00007.bin",
|
163 |
+
"encoder_decoder.decoder.block.9.layer.0.SelfAttention.o.weight": "pytorch_model-00006-of-00007.bin",
|
164 |
+
"encoder_decoder.decoder.block.9.layer.0.SelfAttention.q.weight": "pytorch_model-00006-of-00007.bin",
|
165 |
+
"encoder_decoder.decoder.block.9.layer.0.SelfAttention.v.weight": "pytorch_model-00006-of-00007.bin",
|
166 |
+
"encoder_decoder.decoder.block.9.layer.0.layer_norm.weight": "pytorch_model-00006-of-00007.bin",
|
167 |
+
"encoder_decoder.decoder.block.9.layer.1.EncDecAttention.k.weight": "pytorch_model-00006-of-00007.bin",
|
168 |
+
"encoder_decoder.decoder.block.9.layer.1.EncDecAttention.o.weight": "pytorch_model-00006-of-00007.bin",
|
169 |
+
"encoder_decoder.decoder.block.9.layer.1.EncDecAttention.q.weight": "pytorch_model-00006-of-00007.bin",
|
170 |
+
"encoder_decoder.decoder.block.9.layer.1.EncDecAttention.v.weight": "pytorch_model-00006-of-00007.bin",
|
171 |
+
"encoder_decoder.decoder.block.9.layer.1.layer_norm.weight": "pytorch_model-00006-of-00007.bin",
|
172 |
+
"encoder_decoder.decoder.block.9.layer.2.DenseReluDense.wi.weight": "pytorch_model-00006-of-00007.bin",
|
173 |
+
"encoder_decoder.decoder.block.9.layer.2.DenseReluDense.wo.weight": "pytorch_model-00006-of-00007.bin",
|
174 |
+
"encoder_decoder.decoder.block.9.layer.2.layer_norm.weight": "pytorch_model-00006-of-00007.bin",
|
175 |
+
"encoder_decoder.decoder.embed_tokens.weight": "pytorch_model-00002-of-00007.bin",
|
176 |
+
"encoder_decoder.decoder.final_layer_norm.weight": "pytorch_model-00006-of-00007.bin",
|
177 |
+
"encoder_decoder.encoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00007.bin",
|
178 |
+
"encoder_decoder.encoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00007.bin",
|
179 |
+
"encoder_decoder.encoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00007.bin",
|
180 |
+
"encoder_decoder.encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model-00003-of-00007.bin",
|
181 |
+
"encoder_decoder.encoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00007.bin",
|
182 |
+
"encoder_decoder.encoder.block.0.layer.0.layer_norm.weight": "pytorch_model-00003-of-00007.bin",
|
183 |
+
"encoder_decoder.encoder.block.0.layer.1.DenseReluDense.wi.weight": "pytorch_model-00003-of-00007.bin",
|
184 |
+
"encoder_decoder.encoder.block.0.layer.1.DenseReluDense.wo.weight": "pytorch_model-00003-of-00007.bin",
|
185 |
+
"encoder_decoder.encoder.block.0.layer.1.layer_norm.weight": "pytorch_model-00003-of-00007.bin",
|
186 |
+
"encoder_decoder.encoder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00007.bin",
|
187 |
+
"encoder_decoder.encoder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00007.bin",
|
188 |
+
"encoder_decoder.encoder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00007.bin",
|
189 |
+
"encoder_decoder.encoder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00007.bin",
|
190 |
+
"encoder_decoder.encoder.block.1.layer.0.layer_norm.weight": "pytorch_model-00003-of-00007.bin",
|
191 |
+
"encoder_decoder.encoder.block.1.layer.1.DenseReluDense.wi.weight": "pytorch_model-00003-of-00007.bin",
|
192 |
+
"encoder_decoder.encoder.block.1.layer.1.DenseReluDense.wo.weight": "pytorch_model-00003-of-00007.bin",
|
193 |
+
"encoder_decoder.encoder.block.1.layer.1.layer_norm.weight": "pytorch_model-00003-of-00007.bin",
|
194 |
+
"encoder_decoder.encoder.block.10.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00007.bin",
|
195 |
+
"encoder_decoder.encoder.block.10.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00007.bin",
|
196 |
+
"encoder_decoder.encoder.block.10.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00007.bin",
|
197 |
+
"encoder_decoder.encoder.block.10.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00007.bin",
|
198 |
+
"encoder_decoder.encoder.block.10.layer.0.layer_norm.weight": "pytorch_model-00004-of-00007.bin",
|
199 |
+
"encoder_decoder.encoder.block.10.layer.1.DenseReluDense.wi.weight": "pytorch_model-00004-of-00007.bin",
|
200 |
+
"encoder_decoder.encoder.block.10.layer.1.DenseReluDense.wo.weight": "pytorch_model-00004-of-00007.bin",
|
201 |
+
"encoder_decoder.encoder.block.10.layer.1.layer_norm.weight": "pytorch_model-00004-of-00007.bin",
|
202 |
+
"encoder_decoder.encoder.block.11.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00007.bin",
|
203 |
+
"encoder_decoder.encoder.block.11.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00007.bin",
|
204 |
+
"encoder_decoder.encoder.block.11.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00007.bin",
|
205 |
+
"encoder_decoder.encoder.block.11.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00007.bin",
|
206 |
+
"encoder_decoder.encoder.block.11.layer.0.layer_norm.weight": "pytorch_model-00004-of-00007.bin",
|
207 |
+
"encoder_decoder.encoder.block.11.layer.1.DenseReluDense.wi.weight": "pytorch_model-00004-of-00007.bin",
|
208 |
+
"encoder_decoder.encoder.block.11.layer.1.DenseReluDense.wo.weight": "pytorch_model-00004-of-00007.bin",
|
209 |
+
"encoder_decoder.encoder.block.11.layer.1.layer_norm.weight": "pytorch_model-00004-of-00007.bin",
|
210 |
+
"encoder_decoder.encoder.block.2.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00007.bin",
|
211 |
+
"encoder_decoder.encoder.block.2.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00007.bin",
|
212 |
+
"encoder_decoder.encoder.block.2.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00007.bin",
|
213 |
+
"encoder_decoder.encoder.block.2.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00007.bin",
|
214 |
+
"encoder_decoder.encoder.block.2.layer.0.layer_norm.weight": "pytorch_model-00003-of-00007.bin",
|
215 |
+
"encoder_decoder.encoder.block.2.layer.1.DenseReluDense.wi.weight": "pytorch_model-00003-of-00007.bin",
|
216 |
+
"encoder_decoder.encoder.block.2.layer.1.DenseReluDense.wo.weight": "pytorch_model-00003-of-00007.bin",
|
217 |
+
"encoder_decoder.encoder.block.2.layer.1.layer_norm.weight": "pytorch_model-00003-of-00007.bin",
|
218 |
+
"encoder_decoder.encoder.block.3.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00007.bin",
|
219 |
+
"encoder_decoder.encoder.block.3.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00007.bin",
|
220 |
+
"encoder_decoder.encoder.block.3.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00007.bin",
|
221 |
+
"encoder_decoder.encoder.block.3.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00007.bin",
|
222 |
+
"encoder_decoder.encoder.block.3.layer.0.layer_norm.weight": "pytorch_model-00003-of-00007.bin",
|
223 |
+
"encoder_decoder.encoder.block.3.layer.1.DenseReluDense.wi.weight": "pytorch_model-00003-of-00007.bin",
|
224 |
+
"encoder_decoder.encoder.block.3.layer.1.DenseReluDense.wo.weight": "pytorch_model-00003-of-00007.bin",
|
225 |
+
"encoder_decoder.encoder.block.3.layer.1.layer_norm.weight": "pytorch_model-00003-of-00007.bin",
|
226 |
+
"encoder_decoder.encoder.block.4.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00007.bin",
|
227 |
+
"encoder_decoder.encoder.block.4.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00007.bin",
|
228 |
+
"encoder_decoder.encoder.block.4.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00007.bin",
|
229 |
+
"encoder_decoder.encoder.block.4.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00007.bin",
|
230 |
+
"encoder_decoder.encoder.block.4.layer.0.layer_norm.weight": "pytorch_model-00003-of-00007.bin",
|
231 |
+
"encoder_decoder.encoder.block.4.layer.1.DenseReluDense.wi.weight": "pytorch_model-00003-of-00007.bin",
|
232 |
+
"encoder_decoder.encoder.block.4.layer.1.DenseReluDense.wo.weight": "pytorch_model-00003-of-00007.bin",
|
233 |
+
"encoder_decoder.encoder.block.4.layer.1.layer_norm.weight": "pytorch_model-00003-of-00007.bin",
|
234 |
+
"encoder_decoder.encoder.block.5.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00007.bin",
|
235 |
+
"encoder_decoder.encoder.block.5.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00007.bin",
|
236 |
+
"encoder_decoder.encoder.block.5.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00007.bin",
|
237 |
+
"encoder_decoder.encoder.block.5.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00007.bin",
|
238 |
+
"encoder_decoder.encoder.block.5.layer.0.layer_norm.weight": "pytorch_model-00003-of-00007.bin",
|
239 |
+
"encoder_decoder.encoder.block.5.layer.1.DenseReluDense.wi.weight": "pytorch_model-00003-of-00007.bin",
|
240 |
+
"encoder_decoder.encoder.block.5.layer.1.DenseReluDense.wo.weight": "pytorch_model-00003-of-00007.bin",
|
241 |
+
"encoder_decoder.encoder.block.5.layer.1.layer_norm.weight": "pytorch_model-00003-of-00007.bin",
|
242 |
+
"encoder_decoder.encoder.block.6.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00007.bin",
|
243 |
+
"encoder_decoder.encoder.block.6.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00007.bin",
|
244 |
+
"encoder_decoder.encoder.block.6.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00007.bin",
|
245 |
+
"encoder_decoder.encoder.block.6.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00007.bin",
|
246 |
+
"encoder_decoder.encoder.block.6.layer.0.layer_norm.weight": "pytorch_model-00003-of-00007.bin",
|
247 |
+
"encoder_decoder.encoder.block.6.layer.1.DenseReluDense.wi.weight": "pytorch_model-00003-of-00007.bin",
|
248 |
+
"encoder_decoder.encoder.block.6.layer.1.DenseReluDense.wo.weight": "pytorch_model-00003-of-00007.bin",
|
249 |
+
"encoder_decoder.encoder.block.6.layer.1.layer_norm.weight": "pytorch_model-00003-of-00007.bin",
|
250 |
+
"encoder_decoder.encoder.block.7.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00007.bin",
|
251 |
+
"encoder_decoder.encoder.block.7.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00007.bin",
|
252 |
+
"encoder_decoder.encoder.block.7.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00007.bin",
|
253 |
+
"encoder_decoder.encoder.block.7.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00007.bin",
|
254 |
+
"encoder_decoder.encoder.block.7.layer.0.layer_norm.weight": "pytorch_model-00004-of-00007.bin",
|
255 |
+
"encoder_decoder.encoder.block.7.layer.1.DenseReluDense.wi.weight": "pytorch_model-00004-of-00007.bin",
|
256 |
+
"encoder_decoder.encoder.block.7.layer.1.DenseReluDense.wo.weight": "pytorch_model-00004-of-00007.bin",
|
257 |
+
"encoder_decoder.encoder.block.7.layer.1.layer_norm.weight": "pytorch_model-00004-of-00007.bin",
|
258 |
+
"encoder_decoder.encoder.block.8.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00007.bin",
|
259 |
+
"encoder_decoder.encoder.block.8.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00007.bin",
|
260 |
+
"encoder_decoder.encoder.block.8.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00007.bin",
|
261 |
+
"encoder_decoder.encoder.block.8.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00007.bin",
|
262 |
+
"encoder_decoder.encoder.block.8.layer.0.layer_norm.weight": "pytorch_model-00004-of-00007.bin",
|
263 |
+
"encoder_decoder.encoder.block.8.layer.1.DenseReluDense.wi.weight": "pytorch_model-00004-of-00007.bin",
|
264 |
+
"encoder_decoder.encoder.block.8.layer.1.DenseReluDense.wo.weight": "pytorch_model-00004-of-00007.bin",
|
265 |
+
"encoder_decoder.encoder.block.8.layer.1.layer_norm.weight": "pytorch_model-00004-of-00007.bin",
|
266 |
+
"encoder_decoder.encoder.block.9.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00007.bin",
|
267 |
+
"encoder_decoder.encoder.block.9.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00007.bin",
|
268 |
+
"encoder_decoder.encoder.block.9.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00007.bin",
|
269 |
+
"encoder_decoder.encoder.block.9.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00007.bin",
|
270 |
+
"encoder_decoder.encoder.block.9.layer.0.layer_norm.weight": "pytorch_model-00004-of-00007.bin",
|
271 |
+
"encoder_decoder.encoder.block.9.layer.1.DenseReluDense.wi.weight": "pytorch_model-00004-of-00007.bin",
|
272 |
+
"encoder_decoder.encoder.block.9.layer.1.DenseReluDense.wo.weight": "pytorch_model-00004-of-00007.bin",
|
273 |
+
"encoder_decoder.encoder.block.9.layer.1.layer_norm.weight": "pytorch_model-00004-of-00007.bin",
|
274 |
+
"encoder_decoder.encoder.embed_tokens.weight": "pytorch_model-00002-of-00007.bin",
|
275 |
+
"encoder_decoder.encoder.final_layer_norm.weight": "pytorch_model-00004-of-00007.bin",
|
276 |
+
"encoder_decoder.lm_head.weight": "pytorch_model-00002-of-00007.bin",
|
277 |
+
"encoder_decoder.shared.weight": "pytorch_model-00002-of-00007.bin",
|
278 |
+
"layernorm.bias": "pytorch_model-00007-of-00007.bin",
|
279 |
+
"layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
280 |
+
"sequence_layernorm_1.bias": "pytorch_model-00007-of-00007.bin",
|
281 |
+
"sequence_layernorm_1.weight": "pytorch_model-00007-of-00007.bin",
|
282 |
+
"sequence_layernorm_2.bias": "pytorch_model-00007-of-00007.bin",
|
283 |
+
"sequence_layernorm_2.weight": "pytorch_model-00007-of-00007.bin",
|
284 |
+
"sequence_layernorm_3.bias": "pytorch_model-00007-of-00007.bin",
|
285 |
+
"sequence_layernorm_3.weight": "pytorch_model-00007-of-00007.bin",
|
286 |
+
"sequence_weights_1": "pytorch_model-00001-of-00007.bin",
|
287 |
+
"sequence_weights_2": "pytorch_model-00001-of-00007.bin",
|
288 |
+
"sequence_weights_3": "pytorch_model-00002-of-00007.bin"
|
289 |
+
}
|
290 |
+
}
|