Peter Szemraj commited on
Commit
412d094
1 Parent(s): 9b124bf

add sharded chkpt @ 2 epochs, sess 2

Browse files
.gitattributes CHANGED
@@ -32,3 +32,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
35
+ pytorch_model-00002-of-00003.bin filter=lfs diff=lfs merge=lfs -text
36
+ pytorch_model-00003-of-00003.bin filter=lfs diff=lfs merge=lfs -text
37
+ pytorch_model-00001-of-00003.bin filter=lfs diff=lfs merge=lfs -text
README.md CHANGED
@@ -1,3 +1,39 @@
1
  ---
2
  license: apache-2.0
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
  ---
6
+
7
+
8
+ # flan-t5-large-grammar-synthesis
9
+
10
+ This model is a fine-tuned version of [google/flan-t5-xl](https://huggingface.co/google/flan-t5-xl) on an expanded version of the `JFLEG` dataset.
11
+
12
+ ## Model description
13
+
14
+ More information needed
15
+
16
+ ## Intended uses & limitations
17
+
18
+ More information needed
19
+
20
+ ## Training and evaluation data
21
+
22
+ More information needed
23
+
24
+ ## Training procedure
25
+
26
+ ### Training hyperparameters
27
+
28
+ The following hyperparameters were used during training:
29
+ - learning_rate: 4e-05
30
+ - train_batch_size: 4
31
+ - eval_batch_size: 1
32
+ - seed: 42
33
+ - distributed_type: multi-GPU
34
+ - gradient_accumulation_steps: 16
35
+ - total_train_batch_size: 64
36
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
37
+ - lr_scheduler_type: cosine
38
+ - lr_scheduler_warmup_ratio: 0.02
39
+ - num_epochs: 2.0
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "runtime-grammar-synthesis",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "d_ff": 5120,
7
+ "d_kv": 64,
8
+ "d_model": 2048,
9
+ "decoder_start_token_id": 0,
10
+ "dense_act_fn": "gelu_new",
11
+ "dropout_rate": 0.1,
12
+ "eos_token_id": 1,
13
+ "feed_forward_proj": "gated-gelu",
14
+ "initializer_factor": 1.0,
15
+ "is_encoder_decoder": true,
16
+ "is_gated_act": true,
17
+ "layer_norm_epsilon": 1e-06,
18
+ "model_type": "t5",
19
+ "n_positions": 512,
20
+ "num_decoder_layers": 24,
21
+ "num_heads": 32,
22
+ "num_layers": 24,
23
+ "output_past": true,
24
+ "pad_token_id": 0,
25
+ "relative_attention_max_distance": 128,
26
+ "relative_attention_num_buckets": 32,
27
+ "tie_word_embeddings": false,
28
+ "torch_dtype": "float32",
29
+ "transformers_version": "4.27.0.dev0",
30
+ "use_cache": true,
31
+ "vocab_size": 32128
32
+ }
generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "decoder_start_token_id": 0,
3
+ "eos_token_id": 1,
4
+ "pad_token_id": 0,
5
+ "penalty_alpha": 0.6,
6
+ "top_k": 4,
7
+ "transformers_version": "4.27.0.dev0"
8
+ }
pytorch_model-00001-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2eb4a780c1903df544786ad6c7571d47de2a8383ec5916a2098ce090bb2c3b17
3
+ size 3736432087
pytorch_model-00002-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98ea9265b0e56edf4b09555250a4a12e5c21d0629f2f4c3218af48cb75fc067b
3
+ size 3979761508
pytorch_model-00003-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:240a14a0dc268d8a67b4bb04994805f70e915c94ffc50fe9100d8767b0836dcd
3
+ size 3946221251
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,567 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 11925413888
4
+ },
5
+ "weight_map": {
6
+ "decoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
7
+ "decoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
8
+ "decoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
9
+ "decoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model-00002-of-00003.bin",
10
+ "decoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
11
+ "decoder.block.0.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
12
+ "decoder.block.0.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
13
+ "decoder.block.0.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
14
+ "decoder.block.0.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
15
+ "decoder.block.0.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
16
+ "decoder.block.0.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
17
+ "decoder.block.0.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
18
+ "decoder.block.0.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
19
+ "decoder.block.0.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
20
+ "decoder.block.0.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
21
+ "decoder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
22
+ "decoder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
23
+ "decoder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
24
+ "decoder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
25
+ "decoder.block.1.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
26
+ "decoder.block.1.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
27
+ "decoder.block.1.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
28
+ "decoder.block.1.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
29
+ "decoder.block.1.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
30
+ "decoder.block.1.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
31
+ "decoder.block.1.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
32
+ "decoder.block.1.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
33
+ "decoder.block.1.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
34
+ "decoder.block.1.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
35
+ "decoder.block.10.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00003.bin",
36
+ "decoder.block.10.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00003.bin",
37
+ "decoder.block.10.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00003.bin",
38
+ "decoder.block.10.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00003.bin",
39
+ "decoder.block.10.layer.0.layer_norm.weight": "pytorch_model-00003-of-00003.bin",
40
+ "decoder.block.10.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00003.bin",
41
+ "decoder.block.10.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00003.bin",
42
+ "decoder.block.10.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00003.bin",
43
+ "decoder.block.10.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00003.bin",
44
+ "decoder.block.10.layer.1.layer_norm.weight": "pytorch_model-00003-of-00003.bin",
45
+ "decoder.block.10.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00003.bin",
46
+ "decoder.block.10.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00003.bin",
47
+ "decoder.block.10.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00003.bin",
48
+ "decoder.block.10.layer.2.layer_norm.weight": "pytorch_model-00003-of-00003.bin",
49
+ "decoder.block.11.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00003.bin",
50
+ "decoder.block.11.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00003.bin",
51
+ "decoder.block.11.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00003.bin",
52
+ "decoder.block.11.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00003.bin",
53
+ "decoder.block.11.layer.0.layer_norm.weight": "pytorch_model-00003-of-00003.bin",
54
+ "decoder.block.11.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00003.bin",
55
+ "decoder.block.11.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00003.bin",
56
+ "decoder.block.11.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00003.bin",
57
+ "decoder.block.11.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00003.bin",
58
+ "decoder.block.11.layer.1.layer_norm.weight": "pytorch_model-00003-of-00003.bin",
59
+ "decoder.block.11.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00003.bin",
60
+ "decoder.block.11.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00003.bin",
61
+ "decoder.block.11.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00003.bin",
62
+ "decoder.block.11.layer.2.layer_norm.weight": "pytorch_model-00003-of-00003.bin",
63
+ "decoder.block.12.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00003.bin",
64
+ "decoder.block.12.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00003.bin",
65
+ "decoder.block.12.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00003.bin",
66
+ "decoder.block.12.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00003.bin",
67
+ "decoder.block.12.layer.0.layer_norm.weight": "pytorch_model-00003-of-00003.bin",
68
+ "decoder.block.12.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00003.bin",
69
+ "decoder.block.12.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00003.bin",
70
+ "decoder.block.12.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00003.bin",
71
+ "decoder.block.12.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00003.bin",
72
+ "decoder.block.12.layer.1.layer_norm.weight": "pytorch_model-00003-of-00003.bin",
73
+ "decoder.block.12.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00003.bin",
74
+ "decoder.block.12.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00003.bin",
75
+ "decoder.block.12.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00003.bin",
76
+ "decoder.block.12.layer.2.layer_norm.weight": "pytorch_model-00003-of-00003.bin",
77
+ "decoder.block.13.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00003.bin",
78
+ "decoder.block.13.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00003.bin",
79
+ "decoder.block.13.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00003.bin",
80
+ "decoder.block.13.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00003.bin",
81
+ "decoder.block.13.layer.0.layer_norm.weight": "pytorch_model-00003-of-00003.bin",
82
+ "decoder.block.13.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00003.bin",
83
+ "decoder.block.13.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00003.bin",
84
+ "decoder.block.13.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00003.bin",
85
+ "decoder.block.13.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00003.bin",
86
+ "decoder.block.13.layer.1.layer_norm.weight": "pytorch_model-00003-of-00003.bin",
87
+ "decoder.block.13.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00003.bin",
88
+ "decoder.block.13.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00003.bin",
89
+ "decoder.block.13.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00003.bin",
90
+ "decoder.block.13.layer.2.layer_norm.weight": "pytorch_model-00003-of-00003.bin",
91
+ "decoder.block.14.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00003.bin",
92
+ "decoder.block.14.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00003.bin",
93
+ "decoder.block.14.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00003.bin",
94
+ "decoder.block.14.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00003.bin",
95
+ "decoder.block.14.layer.0.layer_norm.weight": "pytorch_model-00003-of-00003.bin",
96
+ "decoder.block.14.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00003.bin",
97
+ "decoder.block.14.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00003.bin",
98
+ "decoder.block.14.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00003.bin",
99
+ "decoder.block.14.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00003.bin",
100
+ "decoder.block.14.layer.1.layer_norm.weight": "pytorch_model-00003-of-00003.bin",
101
+ "decoder.block.14.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00003.bin",
102
+ "decoder.block.14.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00003.bin",
103
+ "decoder.block.14.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00003.bin",
104
+ "decoder.block.14.layer.2.layer_norm.weight": "pytorch_model-00003-of-00003.bin",
105
+ "decoder.block.15.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00003.bin",
106
+ "decoder.block.15.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00003.bin",
107
+ "decoder.block.15.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00003.bin",
108
+ "decoder.block.15.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00003.bin",
109
+ "decoder.block.15.layer.0.layer_norm.weight": "pytorch_model-00003-of-00003.bin",
110
+ "decoder.block.15.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00003.bin",
111
+ "decoder.block.15.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00003.bin",
112
+ "decoder.block.15.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00003.bin",
113
+ "decoder.block.15.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00003.bin",
114
+ "decoder.block.15.layer.1.layer_norm.weight": "pytorch_model-00003-of-00003.bin",
115
+ "decoder.block.15.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00003.bin",
116
+ "decoder.block.15.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00003.bin",
117
+ "decoder.block.15.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00003.bin",
118
+ "decoder.block.15.layer.2.layer_norm.weight": "pytorch_model-00003-of-00003.bin",
119
+ "decoder.block.16.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00003.bin",
120
+ "decoder.block.16.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00003.bin",
121
+ "decoder.block.16.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00003.bin",
122
+ "decoder.block.16.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00003.bin",
123
+ "decoder.block.16.layer.0.layer_norm.weight": "pytorch_model-00003-of-00003.bin",
124
+ "decoder.block.16.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00003.bin",
125
+ "decoder.block.16.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00003.bin",
126
+ "decoder.block.16.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00003.bin",
127
+ "decoder.block.16.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00003.bin",
128
+ "decoder.block.16.layer.1.layer_norm.weight": "pytorch_model-00003-of-00003.bin",
129
+ "decoder.block.16.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00003.bin",
130
+ "decoder.block.16.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00003.bin",
131
+ "decoder.block.16.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00003.bin",
132
+ "decoder.block.16.layer.2.layer_norm.weight": "pytorch_model-00003-of-00003.bin",
133
+ "decoder.block.17.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00003.bin",
134
+ "decoder.block.17.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00003.bin",
135
+ "decoder.block.17.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00003.bin",
136
+ "decoder.block.17.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00003.bin",
137
+ "decoder.block.17.layer.0.layer_norm.weight": "pytorch_model-00003-of-00003.bin",
138
+ "decoder.block.17.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00003.bin",
139
+ "decoder.block.17.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00003.bin",
140
+ "decoder.block.17.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00003.bin",
141
+ "decoder.block.17.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00003.bin",
142
+ "decoder.block.17.layer.1.layer_norm.weight": "pytorch_model-00003-of-00003.bin",
143
+ "decoder.block.17.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00003.bin",
144
+ "decoder.block.17.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00003.bin",
145
+ "decoder.block.17.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00003.bin",
146
+ "decoder.block.17.layer.2.layer_norm.weight": "pytorch_model-00003-of-00003.bin",
147
+ "decoder.block.18.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00003.bin",
148
+ "decoder.block.18.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00003.bin",
149
+ "decoder.block.18.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00003.bin",
150
+ "decoder.block.18.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00003.bin",
151
+ "decoder.block.18.layer.0.layer_norm.weight": "pytorch_model-00003-of-00003.bin",
152
+ "decoder.block.18.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00003.bin",
153
+ "decoder.block.18.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00003.bin",
154
+ "decoder.block.18.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00003.bin",
155
+ "decoder.block.18.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00003.bin",
156
+ "decoder.block.18.layer.1.layer_norm.weight": "pytorch_model-00003-of-00003.bin",
157
+ "decoder.block.18.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00003.bin",
158
+ "decoder.block.18.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00003.bin",
159
+ "decoder.block.18.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00003.bin",
160
+ "decoder.block.18.layer.2.layer_norm.weight": "pytorch_model-00003-of-00003.bin",
161
+ "decoder.block.19.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00003.bin",
162
+ "decoder.block.19.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00003.bin",
163
+ "decoder.block.19.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00003.bin",
164
+ "decoder.block.19.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00003.bin",
165
+ "decoder.block.19.layer.0.layer_norm.weight": "pytorch_model-00003-of-00003.bin",
166
+ "decoder.block.19.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00003.bin",
167
+ "decoder.block.19.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00003.bin",
168
+ "decoder.block.19.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00003.bin",
169
+ "decoder.block.19.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00003.bin",
170
+ "decoder.block.19.layer.1.layer_norm.weight": "pytorch_model-00003-of-00003.bin",
171
+ "decoder.block.19.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00003.bin",
172
+ "decoder.block.19.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00003.bin",
173
+ "decoder.block.19.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00003.bin",
174
+ "decoder.block.19.layer.2.layer_norm.weight": "pytorch_model-00003-of-00003.bin",
175
+ "decoder.block.2.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
176
+ "decoder.block.2.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
177
+ "decoder.block.2.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
178
+ "decoder.block.2.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
179
+ "decoder.block.2.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
180
+ "decoder.block.2.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
181
+ "decoder.block.2.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
182
+ "decoder.block.2.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
183
+ "decoder.block.2.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
184
+ "decoder.block.2.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
185
+ "decoder.block.2.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
186
+ "decoder.block.2.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
187
+ "decoder.block.2.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
188
+ "decoder.block.2.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
189
+ "decoder.block.20.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00003.bin",
190
+ "decoder.block.20.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00003.bin",
191
+ "decoder.block.20.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00003.bin",
192
+ "decoder.block.20.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00003.bin",
193
+ "decoder.block.20.layer.0.layer_norm.weight": "pytorch_model-00003-of-00003.bin",
194
+ "decoder.block.20.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00003.bin",
195
+ "decoder.block.20.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00003.bin",
196
+ "decoder.block.20.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00003.bin",
197
+ "decoder.block.20.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00003.bin",
198
+ "decoder.block.20.layer.1.layer_norm.weight": "pytorch_model-00003-of-00003.bin",
199
+ "decoder.block.20.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00003.bin",
200
+ "decoder.block.20.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00003.bin",
201
+ "decoder.block.20.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00003.bin",
202
+ "decoder.block.20.layer.2.layer_norm.weight": "pytorch_model-00003-of-00003.bin",
203
+ "decoder.block.21.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00003.bin",
204
+ "decoder.block.21.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00003.bin",
205
+ "decoder.block.21.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00003.bin",
206
+ "decoder.block.21.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00003.bin",
207
+ "decoder.block.21.layer.0.layer_norm.weight": "pytorch_model-00003-of-00003.bin",
208
+ "decoder.block.21.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00003.bin",
209
+ "decoder.block.21.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00003.bin",
210
+ "decoder.block.21.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00003.bin",
211
+ "decoder.block.21.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00003.bin",
212
+ "decoder.block.21.layer.1.layer_norm.weight": "pytorch_model-00003-of-00003.bin",
213
+ "decoder.block.21.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00003.bin",
214
+ "decoder.block.21.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00003.bin",
215
+ "decoder.block.21.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00003.bin",
216
+ "decoder.block.21.layer.2.layer_norm.weight": "pytorch_model-00003-of-00003.bin",
217
+ "decoder.block.22.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00003.bin",
218
+ "decoder.block.22.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00003.bin",
219
+ "decoder.block.22.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00003.bin",
220
+ "decoder.block.22.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00003.bin",
221
+ "decoder.block.22.layer.0.layer_norm.weight": "pytorch_model-00003-of-00003.bin",
222
+ "decoder.block.22.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00003.bin",
223
+ "decoder.block.22.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00003.bin",
224
+ "decoder.block.22.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00003.bin",
225
+ "decoder.block.22.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00003.bin",
226
+ "decoder.block.22.layer.1.layer_norm.weight": "pytorch_model-00003-of-00003.bin",
227
+ "decoder.block.22.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00003.bin",
228
+ "decoder.block.22.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00003.bin",
229
+ "decoder.block.22.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00003.bin",
230
+ "decoder.block.22.layer.2.layer_norm.weight": "pytorch_model-00003-of-00003.bin",
231
+ "decoder.block.23.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00003.bin",
232
+ "decoder.block.23.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00003.bin",
233
+ "decoder.block.23.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00003.bin",
234
+ "decoder.block.23.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00003.bin",
235
+ "decoder.block.23.layer.0.layer_norm.weight": "pytorch_model-00003-of-00003.bin",
236
+ "decoder.block.23.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00003.bin",
237
+ "decoder.block.23.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00003.bin",
238
+ "decoder.block.23.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00003.bin",
239
+ "decoder.block.23.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00003.bin",
240
+ "decoder.block.23.layer.1.layer_norm.weight": "pytorch_model-00003-of-00003.bin",
241
+ "decoder.block.23.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00003.bin",
242
+ "decoder.block.23.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00003.bin",
243
+ "decoder.block.23.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00003.bin",
244
+ "decoder.block.23.layer.2.layer_norm.weight": "pytorch_model-00003-of-00003.bin",
245
+ "decoder.block.3.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
246
+ "decoder.block.3.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
247
+ "decoder.block.3.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
248
+ "decoder.block.3.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
249
+ "decoder.block.3.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
250
+ "decoder.block.3.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
251
+ "decoder.block.3.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
252
+ "decoder.block.3.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
253
+ "decoder.block.3.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
254
+ "decoder.block.3.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
255
+ "decoder.block.3.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
256
+ "decoder.block.3.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
257
+ "decoder.block.3.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
258
+ "decoder.block.3.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
259
+ "decoder.block.4.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
260
+ "decoder.block.4.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
261
+ "decoder.block.4.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
262
+ "decoder.block.4.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
263
+ "decoder.block.4.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
264
+ "decoder.block.4.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
265
+ "decoder.block.4.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
266
+ "decoder.block.4.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
267
+ "decoder.block.4.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
268
+ "decoder.block.4.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
269
+ "decoder.block.4.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
270
+ "decoder.block.4.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
271
+ "decoder.block.4.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
272
+ "decoder.block.4.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
273
+ "decoder.block.5.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
274
+ "decoder.block.5.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
275
+ "decoder.block.5.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
276
+ "decoder.block.5.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
277
+ "decoder.block.5.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
278
+ "decoder.block.5.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
279
+ "decoder.block.5.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
280
+ "decoder.block.5.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
281
+ "decoder.block.5.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
282
+ "decoder.block.5.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
283
+ "decoder.block.5.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
284
+ "decoder.block.5.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
285
+ "decoder.block.5.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
286
+ "decoder.block.5.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
287
+ "decoder.block.6.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
288
+ "decoder.block.6.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
289
+ "decoder.block.6.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
290
+ "decoder.block.6.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
291
+ "decoder.block.6.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
292
+ "decoder.block.6.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
293
+ "decoder.block.6.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
294
+ "decoder.block.6.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
295
+ "decoder.block.6.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
296
+ "decoder.block.6.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
297
+ "decoder.block.6.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
298
+ "decoder.block.6.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
299
+ "decoder.block.6.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
300
+ "decoder.block.6.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
301
+ "decoder.block.7.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
302
+ "decoder.block.7.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
303
+ "decoder.block.7.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
304
+ "decoder.block.7.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
305
+ "decoder.block.7.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
306
+ "decoder.block.7.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
307
+ "decoder.block.7.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
308
+ "decoder.block.7.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
309
+ "decoder.block.7.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
310
+ "decoder.block.7.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
311
+ "decoder.block.7.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
312
+ "decoder.block.7.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
313
+ "decoder.block.7.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
314
+ "decoder.block.7.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
315
+ "decoder.block.8.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
316
+ "decoder.block.8.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
317
+ "decoder.block.8.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
318
+ "decoder.block.8.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
319
+ "decoder.block.8.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
320
+ "decoder.block.8.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
321
+ "decoder.block.8.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
322
+ "decoder.block.8.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
323
+ "decoder.block.8.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
324
+ "decoder.block.8.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
325
+ "decoder.block.8.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
326
+ "decoder.block.8.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
327
+ "decoder.block.8.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
328
+ "decoder.block.8.layer.2.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
329
+ "decoder.block.9.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
330
+ "decoder.block.9.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
331
+ "decoder.block.9.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
332
+ "decoder.block.9.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
333
+ "decoder.block.9.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
334
+ "decoder.block.9.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00003.bin",
335
+ "decoder.block.9.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00003.bin",
336
+ "decoder.block.9.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00003.bin",
337
+ "decoder.block.9.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00003.bin",
338
+ "decoder.block.9.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
339
+ "decoder.block.9.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
340
+ "decoder.block.9.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
341
+ "decoder.block.9.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00003.bin",
342
+ "decoder.block.9.layer.2.layer_norm.weight": "pytorch_model-00003-of-00003.bin",
343
+ "decoder.embed_tokens.weight": "pytorch_model-00002-of-00003.bin",
344
+ "decoder.final_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
345
+ "encoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
346
+ "encoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
347
+ "encoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
348
+ "encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model-00001-of-00003.bin",
349
+ "encoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
350
+ "encoder.block.0.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
351
+ "encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
352
+ "encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
353
+ "encoder.block.0.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
354
+ "encoder.block.0.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
355
+ "encoder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
356
+ "encoder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
357
+ "encoder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
358
+ "encoder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
359
+ "encoder.block.1.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
360
+ "encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
361
+ "encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
362
+ "encoder.block.1.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
363
+ "encoder.block.1.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
364
+ "encoder.block.10.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
365
+ "encoder.block.10.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
366
+ "encoder.block.10.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
367
+ "encoder.block.10.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
368
+ "encoder.block.10.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
369
+ "encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
370
+ "encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
371
+ "encoder.block.10.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
372
+ "encoder.block.10.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
373
+ "encoder.block.11.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
374
+ "encoder.block.11.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
375
+ "encoder.block.11.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
376
+ "encoder.block.11.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
377
+ "encoder.block.11.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
378
+ "encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
379
+ "encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
380
+ "encoder.block.11.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
381
+ "encoder.block.11.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
382
+ "encoder.block.12.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
383
+ "encoder.block.12.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
384
+ "encoder.block.12.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
385
+ "encoder.block.12.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
386
+ "encoder.block.12.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
387
+ "encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
388
+ "encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
389
+ "encoder.block.12.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
390
+ "encoder.block.12.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
391
+ "encoder.block.13.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
392
+ "encoder.block.13.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
393
+ "encoder.block.13.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
394
+ "encoder.block.13.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
395
+ "encoder.block.13.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
396
+ "encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
397
+ "encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
398
+ "encoder.block.13.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
399
+ "encoder.block.13.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
400
+ "encoder.block.14.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
401
+ "encoder.block.14.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
402
+ "encoder.block.14.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
403
+ "encoder.block.14.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
404
+ "encoder.block.14.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
405
+ "encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
406
+ "encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
407
+ "encoder.block.14.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
408
+ "encoder.block.14.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
409
+ "encoder.block.15.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
410
+ "encoder.block.15.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
411
+ "encoder.block.15.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
412
+ "encoder.block.15.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
413
+ "encoder.block.15.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
414
+ "encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
415
+ "encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
416
+ "encoder.block.15.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
417
+ "encoder.block.15.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
418
+ "encoder.block.16.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
419
+ "encoder.block.16.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
420
+ "encoder.block.16.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
421
+ "encoder.block.16.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
422
+ "encoder.block.16.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
423
+ "encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
424
+ "encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
425
+ "encoder.block.16.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
426
+ "encoder.block.16.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
427
+ "encoder.block.17.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
428
+ "encoder.block.17.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
429
+ "encoder.block.17.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
430
+ "encoder.block.17.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
431
+ "encoder.block.17.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
432
+ "encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
433
+ "encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
434
+ "encoder.block.17.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
435
+ "encoder.block.17.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
436
+ "encoder.block.18.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
437
+ "encoder.block.18.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
438
+ "encoder.block.18.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
439
+ "encoder.block.18.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
440
+ "encoder.block.18.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
441
+ "encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
442
+ "encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
443
+ "encoder.block.18.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
444
+ "encoder.block.18.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
445
+ "encoder.block.19.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
446
+ "encoder.block.19.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
447
+ "encoder.block.19.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
448
+ "encoder.block.19.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
449
+ "encoder.block.19.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
450
+ "encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
451
+ "encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
452
+ "encoder.block.19.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
453
+ "encoder.block.19.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
454
+ "encoder.block.2.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
455
+ "encoder.block.2.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
456
+ "encoder.block.2.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
457
+ "encoder.block.2.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
458
+ "encoder.block.2.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
459
+ "encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
460
+ "encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
461
+ "encoder.block.2.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
462
+ "encoder.block.2.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
463
+ "encoder.block.20.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
464
+ "encoder.block.20.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
465
+ "encoder.block.20.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
466
+ "encoder.block.20.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
467
+ "encoder.block.20.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
468
+ "encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
469
+ "encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
470
+ "encoder.block.20.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
471
+ "encoder.block.20.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
472
+ "encoder.block.21.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
473
+ "encoder.block.21.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
474
+ "encoder.block.21.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
475
+ "encoder.block.21.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
476
+ "encoder.block.21.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
477
+ "encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
478
+ "encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
479
+ "encoder.block.21.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
480
+ "encoder.block.21.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
481
+ "encoder.block.22.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
482
+ "encoder.block.22.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
483
+ "encoder.block.22.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
484
+ "encoder.block.22.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
485
+ "encoder.block.22.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
486
+ "encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
487
+ "encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
488
+ "encoder.block.22.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
489
+ "encoder.block.22.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
490
+ "encoder.block.23.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00003.bin",
491
+ "encoder.block.23.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00003.bin",
492
+ "encoder.block.23.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00003.bin",
493
+ "encoder.block.23.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00003.bin",
494
+ "encoder.block.23.layer.0.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
495
+ "encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00003.bin",
496
+ "encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00003.bin",
497
+ "encoder.block.23.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00003.bin",
498
+ "encoder.block.23.layer.1.layer_norm.weight": "pytorch_model-00002-of-00003.bin",
499
+ "encoder.block.3.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
500
+ "encoder.block.3.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
501
+ "encoder.block.3.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
502
+ "encoder.block.3.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
503
+ "encoder.block.3.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
504
+ "encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
505
+ "encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
506
+ "encoder.block.3.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
507
+ "encoder.block.3.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
508
+ "encoder.block.4.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
509
+ "encoder.block.4.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
510
+ "encoder.block.4.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
511
+ "encoder.block.4.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
512
+ "encoder.block.4.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
513
+ "encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
514
+ "encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
515
+ "encoder.block.4.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
516
+ "encoder.block.4.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
517
+ "encoder.block.5.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
518
+ "encoder.block.5.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
519
+ "encoder.block.5.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
520
+ "encoder.block.5.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
521
+ "encoder.block.5.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
522
+ "encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
523
+ "encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
524
+ "encoder.block.5.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
525
+ "encoder.block.5.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
526
+ "encoder.block.6.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
527
+ "encoder.block.6.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
528
+ "encoder.block.6.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
529
+ "encoder.block.6.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
530
+ "encoder.block.6.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
531
+ "encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
532
+ "encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
533
+ "encoder.block.6.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
534
+ "encoder.block.6.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
535
+ "encoder.block.7.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
536
+ "encoder.block.7.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
537
+ "encoder.block.7.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
538
+ "encoder.block.7.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
539
+ "encoder.block.7.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
540
+ "encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
541
+ "encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
542
+ "encoder.block.7.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
543
+ "encoder.block.7.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
544
+ "encoder.block.8.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
545
+ "encoder.block.8.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
546
+ "encoder.block.8.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
547
+ "encoder.block.8.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
548
+ "encoder.block.8.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
549
+ "encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
550
+ "encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
551
+ "encoder.block.8.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
552
+ "encoder.block.8.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
553
+ "encoder.block.9.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00003.bin",
554
+ "encoder.block.9.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00003.bin",
555
+ "encoder.block.9.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00003.bin",
556
+ "encoder.block.9.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00003.bin",
557
+ "encoder.block.9.layer.0.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
558
+ "encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00003.bin",
559
+ "encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00003.bin",
560
+ "encoder.block.9.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00003.bin",
561
+ "encoder.block.9.layer.1.layer_norm.weight": "pytorch_model-00001-of-00003.bin",
562
+ "encoder.embed_tokens.weight": "pytorch_model-00001-of-00003.bin",
563
+ "encoder.final_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
564
+ "lm_head.weight": "pytorch_model-00003-of-00003.bin",
565
+ "shared.weight": "pytorch_model-00001-of-00003.bin"
566
+ }
567
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,107 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<extra_id_0>",
4
+ "<extra_id_1>",
5
+ "<extra_id_2>",
6
+ "<extra_id_3>",
7
+ "<extra_id_4>",
8
+ "<extra_id_5>",
9
+ "<extra_id_6>",
10
+ "<extra_id_7>",
11
+ "<extra_id_8>",
12
+ "<extra_id_9>",
13
+ "<extra_id_10>",
14
+ "<extra_id_11>",
15
+ "<extra_id_12>",
16
+ "<extra_id_13>",
17
+ "<extra_id_14>",
18
+ "<extra_id_15>",
19
+ "<extra_id_16>",
20
+ "<extra_id_17>",
21
+ "<extra_id_18>",
22
+ "<extra_id_19>",
23
+ "<extra_id_20>",
24
+ "<extra_id_21>",
25
+ "<extra_id_22>",
26
+ "<extra_id_23>",
27
+ "<extra_id_24>",
28
+ "<extra_id_25>",
29
+ "<extra_id_26>",
30
+ "<extra_id_27>",
31
+ "<extra_id_28>",
32
+ "<extra_id_29>",
33
+ "<extra_id_30>",
34
+ "<extra_id_31>",
35
+ "<extra_id_32>",
36
+ "<extra_id_33>",
37
+ "<extra_id_34>",
38
+ "<extra_id_35>",
39
+ "<extra_id_36>",
40
+ "<extra_id_37>",
41
+ "<extra_id_38>",
42
+ "<extra_id_39>",
43
+ "<extra_id_40>",
44
+ "<extra_id_41>",
45
+ "<extra_id_42>",
46
+ "<extra_id_43>",
47
+ "<extra_id_44>",
48
+ "<extra_id_45>",
49
+ "<extra_id_46>",
50
+ "<extra_id_47>",
51
+ "<extra_id_48>",
52
+ "<extra_id_49>",
53
+ "<extra_id_50>",
54
+ "<extra_id_51>",
55
+ "<extra_id_52>",
56
+ "<extra_id_53>",
57
+ "<extra_id_54>",
58
+ "<extra_id_55>",
59
+ "<extra_id_56>",
60
+ "<extra_id_57>",
61
+ "<extra_id_58>",
62
+ "<extra_id_59>",
63
+ "<extra_id_60>",
64
+ "<extra_id_61>",
65
+ "<extra_id_62>",
66
+ "<extra_id_63>",
67
+ "<extra_id_64>",
68
+ "<extra_id_65>",
69
+ "<extra_id_66>",
70
+ "<extra_id_67>",
71
+ "<extra_id_68>",
72
+ "<extra_id_69>",
73
+ "<extra_id_70>",
74
+ "<extra_id_71>",
75
+ "<extra_id_72>",
76
+ "<extra_id_73>",
77
+ "<extra_id_74>",
78
+ "<extra_id_75>",
79
+ "<extra_id_76>",
80
+ "<extra_id_77>",
81
+ "<extra_id_78>",
82
+ "<extra_id_79>",
83
+ "<extra_id_80>",
84
+ "<extra_id_81>",
85
+ "<extra_id_82>",
86
+ "<extra_id_83>",
87
+ "<extra_id_84>",
88
+ "<extra_id_85>",
89
+ "<extra_id_86>",
90
+ "<extra_id_87>",
91
+ "<extra_id_88>",
92
+ "<extra_id_89>",
93
+ "<extra_id_90>",
94
+ "<extra_id_91>",
95
+ "<extra_id_92>",
96
+ "<extra_id_93>",
97
+ "<extra_id_94>",
98
+ "<extra_id_95>",
99
+ "<extra_id_96>",
100
+ "<extra_id_97>",
101
+ "<extra_id_98>",
102
+ "<extra_id_99>"
103
+ ],
104
+ "eos_token": "</s>",
105
+ "pad_token": "<pad>",
106
+ "unk_token": "<unk>"
107
+ }
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
3
+ size 791656
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,113 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<extra_id_0>",
4
+ "<extra_id_1>",
5
+ "<extra_id_2>",
6
+ "<extra_id_3>",
7
+ "<extra_id_4>",
8
+ "<extra_id_5>",
9
+ "<extra_id_6>",
10
+ "<extra_id_7>",
11
+ "<extra_id_8>",
12
+ "<extra_id_9>",
13
+ "<extra_id_10>",
14
+ "<extra_id_11>",
15
+ "<extra_id_12>",
16
+ "<extra_id_13>",
17
+ "<extra_id_14>",
18
+ "<extra_id_15>",
19
+ "<extra_id_16>",
20
+ "<extra_id_17>",
21
+ "<extra_id_18>",
22
+ "<extra_id_19>",
23
+ "<extra_id_20>",
24
+ "<extra_id_21>",
25
+ "<extra_id_22>",
26
+ "<extra_id_23>",
27
+ "<extra_id_24>",
28
+ "<extra_id_25>",
29
+ "<extra_id_26>",
30
+ "<extra_id_27>",
31
+ "<extra_id_28>",
32
+ "<extra_id_29>",
33
+ "<extra_id_30>",
34
+ "<extra_id_31>",
35
+ "<extra_id_32>",
36
+ "<extra_id_33>",
37
+ "<extra_id_34>",
38
+ "<extra_id_35>",
39
+ "<extra_id_36>",
40
+ "<extra_id_37>",
41
+ "<extra_id_38>",
42
+ "<extra_id_39>",
43
+ "<extra_id_40>",
44
+ "<extra_id_41>",
45
+ "<extra_id_42>",
46
+ "<extra_id_43>",
47
+ "<extra_id_44>",
48
+ "<extra_id_45>",
49
+ "<extra_id_46>",
50
+ "<extra_id_47>",
51
+ "<extra_id_48>",
52
+ "<extra_id_49>",
53
+ "<extra_id_50>",
54
+ "<extra_id_51>",
55
+ "<extra_id_52>",
56
+ "<extra_id_53>",
57
+ "<extra_id_54>",
58
+ "<extra_id_55>",
59
+ "<extra_id_56>",
60
+ "<extra_id_57>",
61
+ "<extra_id_58>",
62
+ "<extra_id_59>",
63
+ "<extra_id_60>",
64
+ "<extra_id_61>",
65
+ "<extra_id_62>",
66
+ "<extra_id_63>",
67
+ "<extra_id_64>",
68
+ "<extra_id_65>",
69
+ "<extra_id_66>",
70
+ "<extra_id_67>",
71
+ "<extra_id_68>",
72
+ "<extra_id_69>",
73
+ "<extra_id_70>",
74
+ "<extra_id_71>",
75
+ "<extra_id_72>",
76
+ "<extra_id_73>",
77
+ "<extra_id_74>",
78
+ "<extra_id_75>",
79
+ "<extra_id_76>",
80
+ "<extra_id_77>",
81
+ "<extra_id_78>",
82
+ "<extra_id_79>",
83
+ "<extra_id_80>",
84
+ "<extra_id_81>",
85
+ "<extra_id_82>",
86
+ "<extra_id_83>",
87
+ "<extra_id_84>",
88
+ "<extra_id_85>",
89
+ "<extra_id_86>",
90
+ "<extra_id_87>",
91
+ "<extra_id_88>",
92
+ "<extra_id_89>",
93
+ "<extra_id_90>",
94
+ "<extra_id_91>",
95
+ "<extra_id_92>",
96
+ "<extra_id_93>",
97
+ "<extra_id_94>",
98
+ "<extra_id_95>",
99
+ "<extra_id_96>",
100
+ "<extra_id_97>",
101
+ "<extra_id_98>",
102
+ "<extra_id_99>"
103
+ ],
104
+ "eos_token": "</s>",
105
+ "extra_ids": 100,
106
+ "model_max_length": 512,
107
+ "name_or_path": "runtime-grammar-synthesis",
108
+ "pad_token": "<pad>",
109
+ "sp_model_kwargs": {},
110
+ "special_tokens_map_file": "/home/arthur_huggingface_co/.cache/huggingface/hub/models--google--t5-v1_1-small/snapshots/fb7e6cba609f7bab11c614294bc04f82f613c7b1/special_tokens_map.json",
111
+ "tokenizer_class": "T5Tokenizer",
112
+ "unk_token": "<unk>"
113
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.0,
3
+ "train_loss": 0.054031920192549335,
4
+ "train_runtime": 152294.5114,
5
+ "train_samples": 180080,
6
+ "train_samples_per_second": 2.365,
7
+ "train_steps_per_second": 0.037
8
+ }