culverscruple
commited on
Commit
β’
5b8ccb6
1
Parent(s):
a4fd614
Training in progress, epoch 0
Browse files- .gitattributes +1 -0
- config.json +33 -0
- model-00001-of-00003.safetensors +3 -0
- model-00002-of-00003.safetensors +3 -0
- model-00003-of-00003.safetensors +3 -0
- model.safetensors.index.json +565 -0
- special_tokens_map.json +23 -0
- spiece.model +3 -0
- tokenizer.json +3 -0
- tokenizer_config.json +839 -0
- training_args.bin +3 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
config.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "culverscruple/mt5-xl-large-clang8-cleaned",
|
3 |
+
"architectures": [
|
4 |
+
"MT5ForConditionalGeneration"
|
5 |
+
],
|
6 |
+
"classifier_dropout": 0.0,
|
7 |
+
"d_ff": 5120,
|
8 |
+
"d_kv": 64,
|
9 |
+
"d_model": 2048,
|
10 |
+
"decoder_start_token_id": 0,
|
11 |
+
"dense_act_fn": "gelu_new",
|
12 |
+
"dropout_rate": 0.1,
|
13 |
+
"eos_token_id": 1,
|
14 |
+
"feed_forward_proj": "gated-gelu",
|
15 |
+
"initializer_factor": 1.0,
|
16 |
+
"is_encoder_decoder": true,
|
17 |
+
"is_gated_act": true,
|
18 |
+
"layer_norm_epsilon": 1e-06,
|
19 |
+
"model_type": "mt5",
|
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 |
+
"tokenizer_class": "T5Tokenizer",
|
29 |
+
"torch_dtype": "float32",
|
30 |
+
"transformers_version": "4.46.3",
|
31 |
+
"use_cache": true,
|
32 |
+
"vocab_size": 250112
|
33 |
+
}
|
model-00001-of-00003.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c2621bdad3ffd4a514ea2d2262abcf2e59628f16d487be3695f2c255fc4003df
|
3 |
+
size 4993585936
|
model-00002-of-00003.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:69962264c090ccc3f9b6ed05983de073c7d0da621d79b55984a34326401065bd
|
3 |
+
size 4983336088
|
model-00003-of-00003.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:649ae035823b06ca96fb1cdaa00c17a9e3474497bed7a45dff7185b908bba478
|
3 |
+
size 4993625240
|
model.safetensors.index.json
ADDED
@@ -0,0 +1,565 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 14970478592
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"decoder.block.0.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
|
7 |
+
"decoder.block.0.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
|
8 |
+
"decoder.block.0.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
|
9 |
+
"decoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00002-of-00003.safetensors",
|
10 |
+
"decoder.block.0.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
|
11 |
+
"decoder.block.0.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
|
12 |
+
"decoder.block.0.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
|
13 |
+
"decoder.block.0.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
|
14 |
+
"decoder.block.0.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
|
15 |
+
"decoder.block.0.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
|
16 |
+
"decoder.block.0.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
|
17 |
+
"decoder.block.0.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
|
18 |
+
"decoder.block.0.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
|
19 |
+
"decoder.block.0.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
|
20 |
+
"decoder.block.0.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
|
21 |
+
"decoder.block.1.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
|
22 |
+
"decoder.block.1.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
|
23 |
+
"decoder.block.1.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
|
24 |
+
"decoder.block.1.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
|
25 |
+
"decoder.block.1.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
|
26 |
+
"decoder.block.1.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
|
27 |
+
"decoder.block.1.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
|
28 |
+
"decoder.block.1.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
|
29 |
+
"decoder.block.1.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
|
30 |
+
"decoder.block.1.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
|
31 |
+
"decoder.block.1.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
|
32 |
+
"decoder.block.1.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
|
33 |
+
"decoder.block.1.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
|
34 |
+
"decoder.block.1.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
|
35 |
+
"decoder.block.10.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
|
36 |
+
"decoder.block.10.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
|
37 |
+
"decoder.block.10.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
|
38 |
+
"decoder.block.10.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
|
39 |
+
"decoder.block.10.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
|
40 |
+
"decoder.block.10.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
|
41 |
+
"decoder.block.10.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
|
42 |
+
"decoder.block.10.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
|
43 |
+
"decoder.block.10.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
|
44 |
+
"decoder.block.10.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
|
45 |
+
"decoder.block.10.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
|
46 |
+
"decoder.block.10.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
|
47 |
+
"decoder.block.10.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
|
48 |
+
"decoder.block.10.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
|
49 |
+
"decoder.block.11.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
|
50 |
+
"decoder.block.11.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
|
51 |
+
"decoder.block.11.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
|
52 |
+
"decoder.block.11.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
|
53 |
+
"decoder.block.11.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
|
54 |
+
"decoder.block.11.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
|
55 |
+
"decoder.block.11.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
|
56 |
+
"decoder.block.11.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
|
57 |
+
"decoder.block.11.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
|
58 |
+
"decoder.block.11.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
|
59 |
+
"decoder.block.11.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
|
60 |
+
"decoder.block.11.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
|
61 |
+
"decoder.block.11.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
|
62 |
+
"decoder.block.11.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
|
63 |
+
"decoder.block.12.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
|
64 |
+
"decoder.block.12.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
|
65 |
+
"decoder.block.12.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
|
66 |
+
"decoder.block.12.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
|
67 |
+
"decoder.block.12.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
|
68 |
+
"decoder.block.12.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
|
69 |
+
"decoder.block.12.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
|
70 |
+
"decoder.block.12.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
|
71 |
+
"decoder.block.12.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
|
72 |
+
"decoder.block.12.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
|
73 |
+
"decoder.block.12.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
|
74 |
+
"decoder.block.12.layer.2.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors",
|
75 |
+
"decoder.block.12.layer.2.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors",
|
76 |
+
"decoder.block.12.layer.2.layer_norm.weight": "model-00003-of-00003.safetensors",
|
77 |
+
"decoder.block.13.layer.0.SelfAttention.k.weight": "model-00003-of-00003.safetensors",
|
78 |
+
"decoder.block.13.layer.0.SelfAttention.o.weight": "model-00003-of-00003.safetensors",
|
79 |
+
"decoder.block.13.layer.0.SelfAttention.q.weight": "model-00003-of-00003.safetensors",
|
80 |
+
"decoder.block.13.layer.0.SelfAttention.v.weight": "model-00003-of-00003.safetensors",
|
81 |
+
"decoder.block.13.layer.0.layer_norm.weight": "model-00003-of-00003.safetensors",
|
82 |
+
"decoder.block.13.layer.1.EncDecAttention.k.weight": "model-00003-of-00003.safetensors",
|
83 |
+
"decoder.block.13.layer.1.EncDecAttention.o.weight": "model-00003-of-00003.safetensors",
|
84 |
+
"decoder.block.13.layer.1.EncDecAttention.q.weight": "model-00003-of-00003.safetensors",
|
85 |
+
"decoder.block.13.layer.1.EncDecAttention.v.weight": "model-00003-of-00003.safetensors",
|
86 |
+
"decoder.block.13.layer.1.layer_norm.weight": "model-00003-of-00003.safetensors",
|
87 |
+
"decoder.block.13.layer.2.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors",
|
88 |
+
"decoder.block.13.layer.2.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors",
|
89 |
+
"decoder.block.13.layer.2.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors",
|
90 |
+
"decoder.block.13.layer.2.layer_norm.weight": "model-00003-of-00003.safetensors",
|
91 |
+
"decoder.block.14.layer.0.SelfAttention.k.weight": "model-00003-of-00003.safetensors",
|
92 |
+
"decoder.block.14.layer.0.SelfAttention.o.weight": "model-00003-of-00003.safetensors",
|
93 |
+
"decoder.block.14.layer.0.SelfAttention.q.weight": "model-00003-of-00003.safetensors",
|
94 |
+
"decoder.block.14.layer.0.SelfAttention.v.weight": "model-00003-of-00003.safetensors",
|
95 |
+
"decoder.block.14.layer.0.layer_norm.weight": "model-00003-of-00003.safetensors",
|
96 |
+
"decoder.block.14.layer.1.EncDecAttention.k.weight": "model-00003-of-00003.safetensors",
|
97 |
+
"decoder.block.14.layer.1.EncDecAttention.o.weight": "model-00003-of-00003.safetensors",
|
98 |
+
"decoder.block.14.layer.1.EncDecAttention.q.weight": "model-00003-of-00003.safetensors",
|
99 |
+
"decoder.block.14.layer.1.EncDecAttention.v.weight": "model-00003-of-00003.safetensors",
|
100 |
+
"decoder.block.14.layer.1.layer_norm.weight": "model-00003-of-00003.safetensors",
|
101 |
+
"decoder.block.14.layer.2.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors",
|
102 |
+
"decoder.block.14.layer.2.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors",
|
103 |
+
"decoder.block.14.layer.2.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors",
|
104 |
+
"decoder.block.14.layer.2.layer_norm.weight": "model-00003-of-00003.safetensors",
|
105 |
+
"decoder.block.15.layer.0.SelfAttention.k.weight": "model-00003-of-00003.safetensors",
|
106 |
+
"decoder.block.15.layer.0.SelfAttention.o.weight": "model-00003-of-00003.safetensors",
|
107 |
+
"decoder.block.15.layer.0.SelfAttention.q.weight": "model-00003-of-00003.safetensors",
|
108 |
+
"decoder.block.15.layer.0.SelfAttention.v.weight": "model-00003-of-00003.safetensors",
|
109 |
+
"decoder.block.15.layer.0.layer_norm.weight": "model-00003-of-00003.safetensors",
|
110 |
+
"decoder.block.15.layer.1.EncDecAttention.k.weight": "model-00003-of-00003.safetensors",
|
111 |
+
"decoder.block.15.layer.1.EncDecAttention.o.weight": "model-00003-of-00003.safetensors",
|
112 |
+
"decoder.block.15.layer.1.EncDecAttention.q.weight": "model-00003-of-00003.safetensors",
|
113 |
+
"decoder.block.15.layer.1.EncDecAttention.v.weight": "model-00003-of-00003.safetensors",
|
114 |
+
"decoder.block.15.layer.1.layer_norm.weight": "model-00003-of-00003.safetensors",
|
115 |
+
"decoder.block.15.layer.2.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors",
|
116 |
+
"decoder.block.15.layer.2.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors",
|
117 |
+
"decoder.block.15.layer.2.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors",
|
118 |
+
"decoder.block.15.layer.2.layer_norm.weight": "model-00003-of-00003.safetensors",
|
119 |
+
"decoder.block.16.layer.0.SelfAttention.k.weight": "model-00003-of-00003.safetensors",
|
120 |
+
"decoder.block.16.layer.0.SelfAttention.o.weight": "model-00003-of-00003.safetensors",
|
121 |
+
"decoder.block.16.layer.0.SelfAttention.q.weight": "model-00003-of-00003.safetensors",
|
122 |
+
"decoder.block.16.layer.0.SelfAttention.v.weight": "model-00003-of-00003.safetensors",
|
123 |
+
"decoder.block.16.layer.0.layer_norm.weight": "model-00003-of-00003.safetensors",
|
124 |
+
"decoder.block.16.layer.1.EncDecAttention.k.weight": "model-00003-of-00003.safetensors",
|
125 |
+
"decoder.block.16.layer.1.EncDecAttention.o.weight": "model-00003-of-00003.safetensors",
|
126 |
+
"decoder.block.16.layer.1.EncDecAttention.q.weight": "model-00003-of-00003.safetensors",
|
127 |
+
"decoder.block.16.layer.1.EncDecAttention.v.weight": "model-00003-of-00003.safetensors",
|
128 |
+
"decoder.block.16.layer.1.layer_norm.weight": "model-00003-of-00003.safetensors",
|
129 |
+
"decoder.block.16.layer.2.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors",
|
130 |
+
"decoder.block.16.layer.2.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors",
|
131 |
+
"decoder.block.16.layer.2.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors",
|
132 |
+
"decoder.block.16.layer.2.layer_norm.weight": "model-00003-of-00003.safetensors",
|
133 |
+
"decoder.block.17.layer.0.SelfAttention.k.weight": "model-00003-of-00003.safetensors",
|
134 |
+
"decoder.block.17.layer.0.SelfAttention.o.weight": "model-00003-of-00003.safetensors",
|
135 |
+
"decoder.block.17.layer.0.SelfAttention.q.weight": "model-00003-of-00003.safetensors",
|
136 |
+
"decoder.block.17.layer.0.SelfAttention.v.weight": "model-00003-of-00003.safetensors",
|
137 |
+
"decoder.block.17.layer.0.layer_norm.weight": "model-00003-of-00003.safetensors",
|
138 |
+
"decoder.block.17.layer.1.EncDecAttention.k.weight": "model-00003-of-00003.safetensors",
|
139 |
+
"decoder.block.17.layer.1.EncDecAttention.o.weight": "model-00003-of-00003.safetensors",
|
140 |
+
"decoder.block.17.layer.1.EncDecAttention.q.weight": "model-00003-of-00003.safetensors",
|
141 |
+
"decoder.block.17.layer.1.EncDecAttention.v.weight": "model-00003-of-00003.safetensors",
|
142 |
+
"decoder.block.17.layer.1.layer_norm.weight": "model-00003-of-00003.safetensors",
|
143 |
+
"decoder.block.17.layer.2.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors",
|
144 |
+
"decoder.block.17.layer.2.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors",
|
145 |
+
"decoder.block.17.layer.2.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors",
|
146 |
+
"decoder.block.17.layer.2.layer_norm.weight": "model-00003-of-00003.safetensors",
|
147 |
+
"decoder.block.18.layer.0.SelfAttention.k.weight": "model-00003-of-00003.safetensors",
|
148 |
+
"decoder.block.18.layer.0.SelfAttention.o.weight": "model-00003-of-00003.safetensors",
|
149 |
+
"decoder.block.18.layer.0.SelfAttention.q.weight": "model-00003-of-00003.safetensors",
|
150 |
+
"decoder.block.18.layer.0.SelfAttention.v.weight": "model-00003-of-00003.safetensors",
|
151 |
+
"decoder.block.18.layer.0.layer_norm.weight": "model-00003-of-00003.safetensors",
|
152 |
+
"decoder.block.18.layer.1.EncDecAttention.k.weight": "model-00003-of-00003.safetensors",
|
153 |
+
"decoder.block.18.layer.1.EncDecAttention.o.weight": "model-00003-of-00003.safetensors",
|
154 |
+
"decoder.block.18.layer.1.EncDecAttention.q.weight": "model-00003-of-00003.safetensors",
|
155 |
+
"decoder.block.18.layer.1.EncDecAttention.v.weight": "model-00003-of-00003.safetensors",
|
156 |
+
"decoder.block.18.layer.1.layer_norm.weight": "model-00003-of-00003.safetensors",
|
157 |
+
"decoder.block.18.layer.2.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors",
|
158 |
+
"decoder.block.18.layer.2.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors",
|
159 |
+
"decoder.block.18.layer.2.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors",
|
160 |
+
"decoder.block.18.layer.2.layer_norm.weight": "model-00003-of-00003.safetensors",
|
161 |
+
"decoder.block.19.layer.0.SelfAttention.k.weight": "model-00003-of-00003.safetensors",
|
162 |
+
"decoder.block.19.layer.0.SelfAttention.o.weight": "model-00003-of-00003.safetensors",
|
163 |
+
"decoder.block.19.layer.0.SelfAttention.q.weight": "model-00003-of-00003.safetensors",
|
164 |
+
"decoder.block.19.layer.0.SelfAttention.v.weight": "model-00003-of-00003.safetensors",
|
165 |
+
"decoder.block.19.layer.0.layer_norm.weight": "model-00003-of-00003.safetensors",
|
166 |
+
"decoder.block.19.layer.1.EncDecAttention.k.weight": "model-00003-of-00003.safetensors",
|
167 |
+
"decoder.block.19.layer.1.EncDecAttention.o.weight": "model-00003-of-00003.safetensors",
|
168 |
+
"decoder.block.19.layer.1.EncDecAttention.q.weight": "model-00003-of-00003.safetensors",
|
169 |
+
"decoder.block.19.layer.1.EncDecAttention.v.weight": "model-00003-of-00003.safetensors",
|
170 |
+
"decoder.block.19.layer.1.layer_norm.weight": "model-00003-of-00003.safetensors",
|
171 |
+
"decoder.block.19.layer.2.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors",
|
172 |
+
"decoder.block.19.layer.2.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors",
|
173 |
+
"decoder.block.19.layer.2.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors",
|
174 |
+
"decoder.block.19.layer.2.layer_norm.weight": "model-00003-of-00003.safetensors",
|
175 |
+
"decoder.block.2.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
|
176 |
+
"decoder.block.2.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
|
177 |
+
"decoder.block.2.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
|
178 |
+
"decoder.block.2.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
|
179 |
+
"decoder.block.2.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
|
180 |
+
"decoder.block.2.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
|
181 |
+
"decoder.block.2.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
|
182 |
+
"decoder.block.2.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
|
183 |
+
"decoder.block.2.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
|
184 |
+
"decoder.block.2.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
|
185 |
+
"decoder.block.2.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
|
186 |
+
"decoder.block.2.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
|
187 |
+
"decoder.block.2.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
|
188 |
+
"decoder.block.2.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
|
189 |
+
"decoder.block.20.layer.0.SelfAttention.k.weight": "model-00003-of-00003.safetensors",
|
190 |
+
"decoder.block.20.layer.0.SelfAttention.o.weight": "model-00003-of-00003.safetensors",
|
191 |
+
"decoder.block.20.layer.0.SelfAttention.q.weight": "model-00003-of-00003.safetensors",
|
192 |
+
"decoder.block.20.layer.0.SelfAttention.v.weight": "model-00003-of-00003.safetensors",
|
193 |
+
"decoder.block.20.layer.0.layer_norm.weight": "model-00003-of-00003.safetensors",
|
194 |
+
"decoder.block.20.layer.1.EncDecAttention.k.weight": "model-00003-of-00003.safetensors",
|
195 |
+
"decoder.block.20.layer.1.EncDecAttention.o.weight": "model-00003-of-00003.safetensors",
|
196 |
+
"decoder.block.20.layer.1.EncDecAttention.q.weight": "model-00003-of-00003.safetensors",
|
197 |
+
"decoder.block.20.layer.1.EncDecAttention.v.weight": "model-00003-of-00003.safetensors",
|
198 |
+
"decoder.block.20.layer.1.layer_norm.weight": "model-00003-of-00003.safetensors",
|
199 |
+
"decoder.block.20.layer.2.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors",
|
200 |
+
"decoder.block.20.layer.2.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors",
|
201 |
+
"decoder.block.20.layer.2.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors",
|
202 |
+
"decoder.block.20.layer.2.layer_norm.weight": "model-00003-of-00003.safetensors",
|
203 |
+
"decoder.block.21.layer.0.SelfAttention.k.weight": "model-00003-of-00003.safetensors",
|
204 |
+
"decoder.block.21.layer.0.SelfAttention.o.weight": "model-00003-of-00003.safetensors",
|
205 |
+
"decoder.block.21.layer.0.SelfAttention.q.weight": "model-00003-of-00003.safetensors",
|
206 |
+
"decoder.block.21.layer.0.SelfAttention.v.weight": "model-00003-of-00003.safetensors",
|
207 |
+
"decoder.block.21.layer.0.layer_norm.weight": "model-00003-of-00003.safetensors",
|
208 |
+
"decoder.block.21.layer.1.EncDecAttention.k.weight": "model-00003-of-00003.safetensors",
|
209 |
+
"decoder.block.21.layer.1.EncDecAttention.o.weight": "model-00003-of-00003.safetensors",
|
210 |
+
"decoder.block.21.layer.1.EncDecAttention.q.weight": "model-00003-of-00003.safetensors",
|
211 |
+
"decoder.block.21.layer.1.EncDecAttention.v.weight": "model-00003-of-00003.safetensors",
|
212 |
+
"decoder.block.21.layer.1.layer_norm.weight": "model-00003-of-00003.safetensors",
|
213 |
+
"decoder.block.21.layer.2.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors",
|
214 |
+
"decoder.block.21.layer.2.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors",
|
215 |
+
"decoder.block.21.layer.2.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors",
|
216 |
+
"decoder.block.21.layer.2.layer_norm.weight": "model-00003-of-00003.safetensors",
|
217 |
+
"decoder.block.22.layer.0.SelfAttention.k.weight": "model-00003-of-00003.safetensors",
|
218 |
+
"decoder.block.22.layer.0.SelfAttention.o.weight": "model-00003-of-00003.safetensors",
|
219 |
+
"decoder.block.22.layer.0.SelfAttention.q.weight": "model-00003-of-00003.safetensors",
|
220 |
+
"decoder.block.22.layer.0.SelfAttention.v.weight": "model-00003-of-00003.safetensors",
|
221 |
+
"decoder.block.22.layer.0.layer_norm.weight": "model-00003-of-00003.safetensors",
|
222 |
+
"decoder.block.22.layer.1.EncDecAttention.k.weight": "model-00003-of-00003.safetensors",
|
223 |
+
"decoder.block.22.layer.1.EncDecAttention.o.weight": "model-00003-of-00003.safetensors",
|
224 |
+
"decoder.block.22.layer.1.EncDecAttention.q.weight": "model-00003-of-00003.safetensors",
|
225 |
+
"decoder.block.22.layer.1.EncDecAttention.v.weight": "model-00003-of-00003.safetensors",
|
226 |
+
"decoder.block.22.layer.1.layer_norm.weight": "model-00003-of-00003.safetensors",
|
227 |
+
"decoder.block.22.layer.2.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors",
|
228 |
+
"decoder.block.22.layer.2.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors",
|
229 |
+
"decoder.block.22.layer.2.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors",
|
230 |
+
"decoder.block.22.layer.2.layer_norm.weight": "model-00003-of-00003.safetensors",
|
231 |
+
"decoder.block.23.layer.0.SelfAttention.k.weight": "model-00003-of-00003.safetensors",
|
232 |
+
"decoder.block.23.layer.0.SelfAttention.o.weight": "model-00003-of-00003.safetensors",
|
233 |
+
"decoder.block.23.layer.0.SelfAttention.q.weight": "model-00003-of-00003.safetensors",
|
234 |
+
"decoder.block.23.layer.0.SelfAttention.v.weight": "model-00003-of-00003.safetensors",
|
235 |
+
"decoder.block.23.layer.0.layer_norm.weight": "model-00003-of-00003.safetensors",
|
236 |
+
"decoder.block.23.layer.1.EncDecAttention.k.weight": "model-00003-of-00003.safetensors",
|
237 |
+
"decoder.block.23.layer.1.EncDecAttention.o.weight": "model-00003-of-00003.safetensors",
|
238 |
+
"decoder.block.23.layer.1.EncDecAttention.q.weight": "model-00003-of-00003.safetensors",
|
239 |
+
"decoder.block.23.layer.1.EncDecAttention.v.weight": "model-00003-of-00003.safetensors",
|
240 |
+
"decoder.block.23.layer.1.layer_norm.weight": "model-00003-of-00003.safetensors",
|
241 |
+
"decoder.block.23.layer.2.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors",
|
242 |
+
"decoder.block.23.layer.2.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors",
|
243 |
+
"decoder.block.23.layer.2.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors",
|
244 |
+
"decoder.block.23.layer.2.layer_norm.weight": "model-00003-of-00003.safetensors",
|
245 |
+
"decoder.block.3.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
|
246 |
+
"decoder.block.3.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
|
247 |
+
"decoder.block.3.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
|
248 |
+
"decoder.block.3.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
|
249 |
+
"decoder.block.3.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
|
250 |
+
"decoder.block.3.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
|
251 |
+
"decoder.block.3.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
|
252 |
+
"decoder.block.3.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
|
253 |
+
"decoder.block.3.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
|
254 |
+
"decoder.block.3.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
|
255 |
+
"decoder.block.3.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
|
256 |
+
"decoder.block.3.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
|
257 |
+
"decoder.block.3.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
|
258 |
+
"decoder.block.3.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
|
259 |
+
"decoder.block.4.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
|
260 |
+
"decoder.block.4.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
|
261 |
+
"decoder.block.4.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
|
262 |
+
"decoder.block.4.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
|
263 |
+
"decoder.block.4.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
|
264 |
+
"decoder.block.4.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
|
265 |
+
"decoder.block.4.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
|
266 |
+
"decoder.block.4.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
|
267 |
+
"decoder.block.4.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
|
268 |
+
"decoder.block.4.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
|
269 |
+
"decoder.block.4.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
|
270 |
+
"decoder.block.4.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
|
271 |
+
"decoder.block.4.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
|
272 |
+
"decoder.block.4.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
|
273 |
+
"decoder.block.5.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
|
274 |
+
"decoder.block.5.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
|
275 |
+
"decoder.block.5.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
|
276 |
+
"decoder.block.5.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
|
277 |
+
"decoder.block.5.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
|
278 |
+
"decoder.block.5.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
|
279 |
+
"decoder.block.5.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
|
280 |
+
"decoder.block.5.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
|
281 |
+
"decoder.block.5.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
|
282 |
+
"decoder.block.5.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
|
283 |
+
"decoder.block.5.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
|
284 |
+
"decoder.block.5.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
|
285 |
+
"decoder.block.5.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
|
286 |
+
"decoder.block.5.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
|
287 |
+
"decoder.block.6.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
|
288 |
+
"decoder.block.6.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
|
289 |
+
"decoder.block.6.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
|
290 |
+
"decoder.block.6.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
|
291 |
+
"decoder.block.6.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
|
292 |
+
"decoder.block.6.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
|
293 |
+
"decoder.block.6.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
|
294 |
+
"decoder.block.6.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
|
295 |
+
"decoder.block.6.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
|
296 |
+
"decoder.block.6.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
|
297 |
+
"decoder.block.6.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
|
298 |
+
"decoder.block.6.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
|
299 |
+
"decoder.block.6.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
|
300 |
+
"decoder.block.6.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
|
301 |
+
"decoder.block.7.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
|
302 |
+
"decoder.block.7.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
|
303 |
+
"decoder.block.7.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
|
304 |
+
"decoder.block.7.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
|
305 |
+
"decoder.block.7.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
|
306 |
+
"decoder.block.7.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
|
307 |
+
"decoder.block.7.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
|
308 |
+
"decoder.block.7.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
|
309 |
+
"decoder.block.7.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
|
310 |
+
"decoder.block.7.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
|
311 |
+
"decoder.block.7.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
|
312 |
+
"decoder.block.7.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
|
313 |
+
"decoder.block.7.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
|
314 |
+
"decoder.block.7.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
|
315 |
+
"decoder.block.8.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
|
316 |
+
"decoder.block.8.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
|
317 |
+
"decoder.block.8.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
|
318 |
+
"decoder.block.8.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
|
319 |
+
"decoder.block.8.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
|
320 |
+
"decoder.block.8.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
|
321 |
+
"decoder.block.8.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
|
322 |
+
"decoder.block.8.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
|
323 |
+
"decoder.block.8.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
|
324 |
+
"decoder.block.8.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
|
325 |
+
"decoder.block.8.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
|
326 |
+
"decoder.block.8.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
|
327 |
+
"decoder.block.8.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
|
328 |
+
"decoder.block.8.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
|
329 |
+
"decoder.block.9.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
|
330 |
+
"decoder.block.9.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
|
331 |
+
"decoder.block.9.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
|
332 |
+
"decoder.block.9.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
|
333 |
+
"decoder.block.9.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
|
334 |
+
"decoder.block.9.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
|
335 |
+
"decoder.block.9.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
|
336 |
+
"decoder.block.9.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
|
337 |
+
"decoder.block.9.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
|
338 |
+
"decoder.block.9.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
|
339 |
+
"decoder.block.9.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
|
340 |
+
"decoder.block.9.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
|
341 |
+
"decoder.block.9.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
|
342 |
+
"decoder.block.9.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
|
343 |
+
"decoder.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
344 |
+
"encoder.block.0.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
|
345 |
+
"encoder.block.0.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
|
346 |
+
"encoder.block.0.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
|
347 |
+
"encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00003.safetensors",
|
348 |
+
"encoder.block.0.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
|
349 |
+
"encoder.block.0.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
|
350 |
+
"encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
|
351 |
+
"encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
|
352 |
+
"encoder.block.0.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
|
353 |
+
"encoder.block.0.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
|
354 |
+
"encoder.block.1.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
|
355 |
+
"encoder.block.1.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
|
356 |
+
"encoder.block.1.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
|
357 |
+
"encoder.block.1.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
|
358 |
+
"encoder.block.1.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
|
359 |
+
"encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
|
360 |
+
"encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
|
361 |
+
"encoder.block.1.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
|
362 |
+
"encoder.block.1.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
|
363 |
+
"encoder.block.10.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
|
364 |
+
"encoder.block.10.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
|
365 |
+
"encoder.block.10.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
|
366 |
+
"encoder.block.10.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
|
367 |
+
"encoder.block.10.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
|
368 |
+
"encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
|
369 |
+
"encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
|
370 |
+
"encoder.block.10.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
|
371 |
+
"encoder.block.10.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
|
372 |
+
"encoder.block.11.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
|
373 |
+
"encoder.block.11.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
|
374 |
+
"encoder.block.11.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
|
375 |
+
"encoder.block.11.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
|
376 |
+
"encoder.block.11.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
|
377 |
+
"encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
|
378 |
+
"encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
|
379 |
+
"encoder.block.11.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
|
380 |
+
"encoder.block.11.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
|
381 |
+
"encoder.block.12.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
|
382 |
+
"encoder.block.12.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
|
383 |
+
"encoder.block.12.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
|
384 |
+
"encoder.block.12.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
|
385 |
+
"encoder.block.12.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
|
386 |
+
"encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
|
387 |
+
"encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
|
388 |
+
"encoder.block.12.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
|
389 |
+
"encoder.block.12.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
|
390 |
+
"encoder.block.13.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
|
391 |
+
"encoder.block.13.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
|
392 |
+
"encoder.block.13.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
|
393 |
+
"encoder.block.13.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
|
394 |
+
"encoder.block.13.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
|
395 |
+
"encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
|
396 |
+
"encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
|
397 |
+
"encoder.block.13.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
|
398 |
+
"encoder.block.13.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
|
399 |
+
"encoder.block.14.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
|
400 |
+
"encoder.block.14.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
|
401 |
+
"encoder.block.14.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
|
402 |
+
"encoder.block.14.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
|
403 |
+
"encoder.block.14.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
|
404 |
+
"encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
|
405 |
+
"encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
|
406 |
+
"encoder.block.14.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
|
407 |
+
"encoder.block.14.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
|
408 |
+
"encoder.block.15.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
|
409 |
+
"encoder.block.15.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
|
410 |
+
"encoder.block.15.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
|
411 |
+
"encoder.block.15.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
|
412 |
+
"encoder.block.15.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
|
413 |
+
"encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
|
414 |
+
"encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
|
415 |
+
"encoder.block.15.layer.1.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
|
416 |
+
"encoder.block.15.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
|
417 |
+
"encoder.block.16.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
|
418 |
+
"encoder.block.16.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
|
419 |
+
"encoder.block.16.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
|
420 |
+
"encoder.block.16.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
|
421 |
+
"encoder.block.16.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
|
422 |
+
"encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
|
423 |
+
"encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
|
424 |
+
"encoder.block.16.layer.1.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
|
425 |
+
"encoder.block.16.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
|
426 |
+
"encoder.block.17.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
|
427 |
+
"encoder.block.17.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
|
428 |
+
"encoder.block.17.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
|
429 |
+
"encoder.block.17.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
|
430 |
+
"encoder.block.17.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
|
431 |
+
"encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
|
432 |
+
"encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
|
433 |
+
"encoder.block.17.layer.1.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
|
434 |
+
"encoder.block.17.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
|
435 |
+
"encoder.block.18.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
|
436 |
+
"encoder.block.18.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
|
437 |
+
"encoder.block.18.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
|
438 |
+
"encoder.block.18.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
|
439 |
+
"encoder.block.18.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
|
440 |
+
"encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
|
441 |
+
"encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
|
442 |
+
"encoder.block.18.layer.1.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
|
443 |
+
"encoder.block.18.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
|
444 |
+
"encoder.block.19.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
|
445 |
+
"encoder.block.19.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
|
446 |
+
"encoder.block.19.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
|
447 |
+
"encoder.block.19.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
|
448 |
+
"encoder.block.19.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
|
449 |
+
"encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
|
450 |
+
"encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
|
451 |
+
"encoder.block.19.layer.1.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
|
452 |
+
"encoder.block.19.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
|
453 |
+
"encoder.block.2.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
|
454 |
+
"encoder.block.2.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
|
455 |
+
"encoder.block.2.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
|
456 |
+
"encoder.block.2.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
|
457 |
+
"encoder.block.2.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
|
458 |
+
"encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
|
459 |
+
"encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
|
460 |
+
"encoder.block.2.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
|
461 |
+
"encoder.block.2.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
|
462 |
+
"encoder.block.20.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
|
463 |
+
"encoder.block.20.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
|
464 |
+
"encoder.block.20.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
|
465 |
+
"encoder.block.20.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
|
466 |
+
"encoder.block.20.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
|
467 |
+
"encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
|
468 |
+
"encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
|
469 |
+
"encoder.block.20.layer.1.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
|
470 |
+
"encoder.block.20.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
|
471 |
+
"encoder.block.21.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
|
472 |
+
"encoder.block.21.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
|
473 |
+
"encoder.block.21.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
|
474 |
+
"encoder.block.21.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
|
475 |
+
"encoder.block.21.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
|
476 |
+
"encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
|
477 |
+
"encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
|
478 |
+
"encoder.block.21.layer.1.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
|
479 |
+
"encoder.block.21.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
|
480 |
+
"encoder.block.22.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
|
481 |
+
"encoder.block.22.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
|
482 |
+
"encoder.block.22.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
|
483 |
+
"encoder.block.22.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
|
484 |
+
"encoder.block.22.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
|
485 |
+
"encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
|
486 |
+
"encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
|
487 |
+
"encoder.block.22.layer.1.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
|
488 |
+
"encoder.block.22.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
|
489 |
+
"encoder.block.23.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
|
490 |
+
"encoder.block.23.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
|
491 |
+
"encoder.block.23.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
|
492 |
+
"encoder.block.23.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
|
493 |
+
"encoder.block.23.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
|
494 |
+
"encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
|
495 |
+
"encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
|
496 |
+
"encoder.block.23.layer.1.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
|
497 |
+
"encoder.block.23.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
|
498 |
+
"encoder.block.3.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
|
499 |
+
"encoder.block.3.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
|
500 |
+
"encoder.block.3.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
|
501 |
+
"encoder.block.3.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
|
502 |
+
"encoder.block.3.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
|
503 |
+
"encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
|
504 |
+
"encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
|
505 |
+
"encoder.block.3.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
|
506 |
+
"encoder.block.3.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
|
507 |
+
"encoder.block.4.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
|
508 |
+
"encoder.block.4.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
|
509 |
+
"encoder.block.4.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
|
510 |
+
"encoder.block.4.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
|
511 |
+
"encoder.block.4.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
|
512 |
+
"encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
|
513 |
+
"encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
|
514 |
+
"encoder.block.4.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
|
515 |
+
"encoder.block.4.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
|
516 |
+
"encoder.block.5.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
|
517 |
+
"encoder.block.5.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
|
518 |
+
"encoder.block.5.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
|
519 |
+
"encoder.block.5.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
|
520 |
+
"encoder.block.5.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
|
521 |
+
"encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
|
522 |
+
"encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
|
523 |
+
"encoder.block.5.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
|
524 |
+
"encoder.block.5.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
|
525 |
+
"encoder.block.6.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
|
526 |
+
"encoder.block.6.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
|
527 |
+
"encoder.block.6.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
|
528 |
+
"encoder.block.6.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
|
529 |
+
"encoder.block.6.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
|
530 |
+
"encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
|
531 |
+
"encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
|
532 |
+
"encoder.block.6.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
|
533 |
+
"encoder.block.6.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
|
534 |
+
"encoder.block.7.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
|
535 |
+
"encoder.block.7.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
|
536 |
+
"encoder.block.7.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
|
537 |
+
"encoder.block.7.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
|
538 |
+
"encoder.block.7.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
|
539 |
+
"encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
|
540 |
+
"encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
|
541 |
+
"encoder.block.7.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
|
542 |
+
"encoder.block.7.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
|
543 |
+
"encoder.block.8.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
|
544 |
+
"encoder.block.8.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
|
545 |
+
"encoder.block.8.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
|
546 |
+
"encoder.block.8.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
|
547 |
+
"encoder.block.8.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
|
548 |
+
"encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
|
549 |
+
"encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
|
550 |
+
"encoder.block.8.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
|
551 |
+
"encoder.block.8.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
|
552 |
+
"encoder.block.9.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
|
553 |
+
"encoder.block.9.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
|
554 |
+
"encoder.block.9.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
|
555 |
+
"encoder.block.9.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
|
556 |
+
"encoder.block.9.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
|
557 |
+
"encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
|
558 |
+
"encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
|
559 |
+
"encoder.block.9.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
|
560 |
+
"encoder.block.9.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
|
561 |
+
"encoder.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
562 |
+
"lm_head.weight": "model-00003-of-00003.safetensors",
|
563 |
+
"shared.weight": "model-00001-of-00003.safetensors"
|
564 |
+
}
|
565 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"eos_token": {
|
3 |
+
"content": "</s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"pad_token": {
|
10 |
+
"content": "<pad>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"unk_token": {
|
17 |
+
"content": "<unk>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
}
|
23 |
+
}
|
spiece.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
|
3 |
+
size 4309802
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fd8b8841204ea80c5db9c9c682249877c02e804d124079764bd51a6c22b8ab65
|
3 |
+
size 16350026
|
tokenizer_config.json
ADDED
@@ -0,0 +1,839 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": true,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"0": {
|
5 |
+
"content": "<pad>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"1": {
|
13 |
+
"content": "</s>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"2": {
|
21 |
+
"content": "<unk>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
},
|
28 |
+
"250000": {
|
29 |
+
"content": "β<extra_id_99>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": false,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": false
|
35 |
+
},
|
36 |
+
"250001": {
|
37 |
+
"content": "β<extra_id_98>",
|
38 |
+
"lstrip": false,
|
39 |
+
"normalized": false,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false,
|
42 |
+
"special": false
|
43 |
+
},
|
44 |
+
"250002": {
|
45 |
+
"content": "β<extra_id_97>",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": false,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false,
|
50 |
+
"special": false
|
51 |
+
},
|
52 |
+
"250003": {
|
53 |
+
"content": "β<extra_id_96>",
|
54 |
+
"lstrip": false,
|
55 |
+
"normalized": false,
|
56 |
+
"rstrip": false,
|
57 |
+
"single_word": false,
|
58 |
+
"special": false
|
59 |
+
},
|
60 |
+
"250004": {
|
61 |
+
"content": "β<extra_id_95>",
|
62 |
+
"lstrip": false,
|
63 |
+
"normalized": false,
|
64 |
+
"rstrip": false,
|
65 |
+
"single_word": false,
|
66 |
+
"special": false
|
67 |
+
},
|
68 |
+
"250005": {
|
69 |
+
"content": "β<extra_id_94>",
|
70 |
+
"lstrip": false,
|
71 |
+
"normalized": false,
|
72 |
+
"rstrip": false,
|
73 |
+
"single_word": false,
|
74 |
+
"special": false
|
75 |
+
},
|
76 |
+
"250006": {
|
77 |
+
"content": "β<extra_id_93>",
|
78 |
+
"lstrip": false,
|
79 |
+
"normalized": false,
|
80 |
+
"rstrip": false,
|
81 |
+
"single_word": false,
|
82 |
+
"special": false
|
83 |
+
},
|
84 |
+
"250007": {
|
85 |
+
"content": "β<extra_id_92>",
|
86 |
+
"lstrip": false,
|
87 |
+
"normalized": false,
|
88 |
+
"rstrip": false,
|
89 |
+
"single_word": false,
|
90 |
+
"special": false
|
91 |
+
},
|
92 |
+
"250008": {
|
93 |
+
"content": "β<extra_id_91>",
|
94 |
+
"lstrip": false,
|
95 |
+
"normalized": false,
|
96 |
+
"rstrip": false,
|
97 |
+
"single_word": false,
|
98 |
+
"special": false
|
99 |
+
},
|
100 |
+
"250009": {
|
101 |
+
"content": "β<extra_id_90>",
|
102 |
+
"lstrip": false,
|
103 |
+
"normalized": false,
|
104 |
+
"rstrip": false,
|
105 |
+
"single_word": false,
|
106 |
+
"special": false
|
107 |
+
},
|
108 |
+
"250010": {
|
109 |
+
"content": "β<extra_id_89>",
|
110 |
+
"lstrip": false,
|
111 |
+
"normalized": false,
|
112 |
+
"rstrip": false,
|
113 |
+
"single_word": false,
|
114 |
+
"special": false
|
115 |
+
},
|
116 |
+
"250011": {
|
117 |
+
"content": "β<extra_id_88>",
|
118 |
+
"lstrip": false,
|
119 |
+
"normalized": false,
|
120 |
+
"rstrip": false,
|
121 |
+
"single_word": false,
|
122 |
+
"special": false
|
123 |
+
},
|
124 |
+
"250012": {
|
125 |
+
"content": "β<extra_id_87>",
|
126 |
+
"lstrip": false,
|
127 |
+
"normalized": false,
|
128 |
+
"rstrip": false,
|
129 |
+
"single_word": false,
|
130 |
+
"special": false
|
131 |
+
},
|
132 |
+
"250013": {
|
133 |
+
"content": "β<extra_id_86>",
|
134 |
+
"lstrip": false,
|
135 |
+
"normalized": false,
|
136 |
+
"rstrip": false,
|
137 |
+
"single_word": false,
|
138 |
+
"special": false
|
139 |
+
},
|
140 |
+
"250014": {
|
141 |
+
"content": "β<extra_id_85>",
|
142 |
+
"lstrip": false,
|
143 |
+
"normalized": false,
|
144 |
+
"rstrip": false,
|
145 |
+
"single_word": false,
|
146 |
+
"special": false
|
147 |
+
},
|
148 |
+
"250015": {
|
149 |
+
"content": "β<extra_id_84>",
|
150 |
+
"lstrip": false,
|
151 |
+
"normalized": false,
|
152 |
+
"rstrip": false,
|
153 |
+
"single_word": false,
|
154 |
+
"special": false
|
155 |
+
},
|
156 |
+
"250016": {
|
157 |
+
"content": "β<extra_id_83>",
|
158 |
+
"lstrip": false,
|
159 |
+
"normalized": false,
|
160 |
+
"rstrip": false,
|
161 |
+
"single_word": false,
|
162 |
+
"special": false
|
163 |
+
},
|
164 |
+
"250017": {
|
165 |
+
"content": "β<extra_id_82>",
|
166 |
+
"lstrip": false,
|
167 |
+
"normalized": false,
|
168 |
+
"rstrip": false,
|
169 |
+
"single_word": false,
|
170 |
+
"special": false
|
171 |
+
},
|
172 |
+
"250018": {
|
173 |
+
"content": "β<extra_id_81>",
|
174 |
+
"lstrip": false,
|
175 |
+
"normalized": false,
|
176 |
+
"rstrip": false,
|
177 |
+
"single_word": false,
|
178 |
+
"special": false
|
179 |
+
},
|
180 |
+
"250019": {
|
181 |
+
"content": "β<extra_id_80>",
|
182 |
+
"lstrip": false,
|
183 |
+
"normalized": false,
|
184 |
+
"rstrip": false,
|
185 |
+
"single_word": false,
|
186 |
+
"special": false
|
187 |
+
},
|
188 |
+
"250020": {
|
189 |
+
"content": "β<extra_id_79>",
|
190 |
+
"lstrip": false,
|
191 |
+
"normalized": false,
|
192 |
+
"rstrip": false,
|
193 |
+
"single_word": false,
|
194 |
+
"special": false
|
195 |
+
},
|
196 |
+
"250021": {
|
197 |
+
"content": "β<extra_id_78>",
|
198 |
+
"lstrip": false,
|
199 |
+
"normalized": false,
|
200 |
+
"rstrip": false,
|
201 |
+
"single_word": false,
|
202 |
+
"special": false
|
203 |
+
},
|
204 |
+
"250022": {
|
205 |
+
"content": "β<extra_id_77>",
|
206 |
+
"lstrip": false,
|
207 |
+
"normalized": false,
|
208 |
+
"rstrip": false,
|
209 |
+
"single_word": false,
|
210 |
+
"special": false
|
211 |
+
},
|
212 |
+
"250023": {
|
213 |
+
"content": "β<extra_id_76>",
|
214 |
+
"lstrip": false,
|
215 |
+
"normalized": false,
|
216 |
+
"rstrip": false,
|
217 |
+
"single_word": false,
|
218 |
+
"special": false
|
219 |
+
},
|
220 |
+
"250024": {
|
221 |
+
"content": "β<extra_id_75>",
|
222 |
+
"lstrip": false,
|
223 |
+
"normalized": false,
|
224 |
+
"rstrip": false,
|
225 |
+
"single_word": false,
|
226 |
+
"special": false
|
227 |
+
},
|
228 |
+
"250025": {
|
229 |
+
"content": "β<extra_id_74>",
|
230 |
+
"lstrip": false,
|
231 |
+
"normalized": false,
|
232 |
+
"rstrip": false,
|
233 |
+
"single_word": false,
|
234 |
+
"special": false
|
235 |
+
},
|
236 |
+
"250026": {
|
237 |
+
"content": "β<extra_id_73>",
|
238 |
+
"lstrip": false,
|
239 |
+
"normalized": false,
|
240 |
+
"rstrip": false,
|
241 |
+
"single_word": false,
|
242 |
+
"special": false
|
243 |
+
},
|
244 |
+
"250027": {
|
245 |
+
"content": "β<extra_id_72>",
|
246 |
+
"lstrip": false,
|
247 |
+
"normalized": false,
|
248 |
+
"rstrip": false,
|
249 |
+
"single_word": false,
|
250 |
+
"special": false
|
251 |
+
},
|
252 |
+
"250028": {
|
253 |
+
"content": "β<extra_id_71>",
|
254 |
+
"lstrip": false,
|
255 |
+
"normalized": false,
|
256 |
+
"rstrip": false,
|
257 |
+
"single_word": false,
|
258 |
+
"special": false
|
259 |
+
},
|
260 |
+
"250029": {
|
261 |
+
"content": "β<extra_id_70>",
|
262 |
+
"lstrip": false,
|
263 |
+
"normalized": false,
|
264 |
+
"rstrip": false,
|
265 |
+
"single_word": false,
|
266 |
+
"special": false
|
267 |
+
},
|
268 |
+
"250030": {
|
269 |
+
"content": "β<extra_id_69>",
|
270 |
+
"lstrip": false,
|
271 |
+
"normalized": false,
|
272 |
+
"rstrip": false,
|
273 |
+
"single_word": false,
|
274 |
+
"special": false
|
275 |
+
},
|
276 |
+
"250031": {
|
277 |
+
"content": "β<extra_id_68>",
|
278 |
+
"lstrip": false,
|
279 |
+
"normalized": false,
|
280 |
+
"rstrip": false,
|
281 |
+
"single_word": false,
|
282 |
+
"special": false
|
283 |
+
},
|
284 |
+
"250032": {
|
285 |
+
"content": "β<extra_id_67>",
|
286 |
+
"lstrip": false,
|
287 |
+
"normalized": false,
|
288 |
+
"rstrip": false,
|
289 |
+
"single_word": false,
|
290 |
+
"special": false
|
291 |
+
},
|
292 |
+
"250033": {
|
293 |
+
"content": "β<extra_id_66>",
|
294 |
+
"lstrip": false,
|
295 |
+
"normalized": false,
|
296 |
+
"rstrip": false,
|
297 |
+
"single_word": false,
|
298 |
+
"special": false
|
299 |
+
},
|
300 |
+
"250034": {
|
301 |
+
"content": "β<extra_id_65>",
|
302 |
+
"lstrip": false,
|
303 |
+
"normalized": false,
|
304 |
+
"rstrip": false,
|
305 |
+
"single_word": false,
|
306 |
+
"special": false
|
307 |
+
},
|
308 |
+
"250035": {
|
309 |
+
"content": "β<extra_id_64>",
|
310 |
+
"lstrip": false,
|
311 |
+
"normalized": false,
|
312 |
+
"rstrip": false,
|
313 |
+
"single_word": false,
|
314 |
+
"special": false
|
315 |
+
},
|
316 |
+
"250036": {
|
317 |
+
"content": "β<extra_id_63>",
|
318 |
+
"lstrip": false,
|
319 |
+
"normalized": false,
|
320 |
+
"rstrip": false,
|
321 |
+
"single_word": false,
|
322 |
+
"special": false
|
323 |
+
},
|
324 |
+
"250037": {
|
325 |
+
"content": "β<extra_id_62>",
|
326 |
+
"lstrip": false,
|
327 |
+
"normalized": false,
|
328 |
+
"rstrip": false,
|
329 |
+
"single_word": false,
|
330 |
+
"special": false
|
331 |
+
},
|
332 |
+
"250038": {
|
333 |
+
"content": "β<extra_id_61>",
|
334 |
+
"lstrip": false,
|
335 |
+
"normalized": false,
|
336 |
+
"rstrip": false,
|
337 |
+
"single_word": false,
|
338 |
+
"special": false
|
339 |
+
},
|
340 |
+
"250039": {
|
341 |
+
"content": "β<extra_id_60>",
|
342 |
+
"lstrip": false,
|
343 |
+
"normalized": false,
|
344 |
+
"rstrip": false,
|
345 |
+
"single_word": false,
|
346 |
+
"special": false
|
347 |
+
},
|
348 |
+
"250040": {
|
349 |
+
"content": "β<extra_id_59>",
|
350 |
+
"lstrip": false,
|
351 |
+
"normalized": false,
|
352 |
+
"rstrip": false,
|
353 |
+
"single_word": false,
|
354 |
+
"special": false
|
355 |
+
},
|
356 |
+
"250041": {
|
357 |
+
"content": "β<extra_id_58>",
|
358 |
+
"lstrip": false,
|
359 |
+
"normalized": false,
|
360 |
+
"rstrip": false,
|
361 |
+
"single_word": false,
|
362 |
+
"special": false
|
363 |
+
},
|
364 |
+
"250042": {
|
365 |
+
"content": "β<extra_id_57>",
|
366 |
+
"lstrip": false,
|
367 |
+
"normalized": false,
|
368 |
+
"rstrip": false,
|
369 |
+
"single_word": false,
|
370 |
+
"special": false
|
371 |
+
},
|
372 |
+
"250043": {
|
373 |
+
"content": "β<extra_id_56>",
|
374 |
+
"lstrip": false,
|
375 |
+
"normalized": false,
|
376 |
+
"rstrip": false,
|
377 |
+
"single_word": false,
|
378 |
+
"special": false
|
379 |
+
},
|
380 |
+
"250044": {
|
381 |
+
"content": "β<extra_id_55>",
|
382 |
+
"lstrip": false,
|
383 |
+
"normalized": false,
|
384 |
+
"rstrip": false,
|
385 |
+
"single_word": false,
|
386 |
+
"special": false
|
387 |
+
},
|
388 |
+
"250045": {
|
389 |
+
"content": "β<extra_id_54>",
|
390 |
+
"lstrip": false,
|
391 |
+
"normalized": false,
|
392 |
+
"rstrip": false,
|
393 |
+
"single_word": false,
|
394 |
+
"special": false
|
395 |
+
},
|
396 |
+
"250046": {
|
397 |
+
"content": "β<extra_id_53>",
|
398 |
+
"lstrip": false,
|
399 |
+
"normalized": false,
|
400 |
+
"rstrip": false,
|
401 |
+
"single_word": false,
|
402 |
+
"special": false
|
403 |
+
},
|
404 |
+
"250047": {
|
405 |
+
"content": "β<extra_id_52>",
|
406 |
+
"lstrip": false,
|
407 |
+
"normalized": false,
|
408 |
+
"rstrip": false,
|
409 |
+
"single_word": false,
|
410 |
+
"special": false
|
411 |
+
},
|
412 |
+
"250048": {
|
413 |
+
"content": "β<extra_id_51>",
|
414 |
+
"lstrip": false,
|
415 |
+
"normalized": false,
|
416 |
+
"rstrip": false,
|
417 |
+
"single_word": false,
|
418 |
+
"special": false
|
419 |
+
},
|
420 |
+
"250049": {
|
421 |
+
"content": "β<extra_id_50>",
|
422 |
+
"lstrip": false,
|
423 |
+
"normalized": false,
|
424 |
+
"rstrip": false,
|
425 |
+
"single_word": false,
|
426 |
+
"special": false
|
427 |
+
},
|
428 |
+
"250050": {
|
429 |
+
"content": "οΏ½οΏ½οΏ½<extra_id_49>",
|
430 |
+
"lstrip": false,
|
431 |
+
"normalized": false,
|
432 |
+
"rstrip": false,
|
433 |
+
"single_word": false,
|
434 |
+
"special": false
|
435 |
+
},
|
436 |
+
"250051": {
|
437 |
+
"content": "β<extra_id_48>",
|
438 |
+
"lstrip": false,
|
439 |
+
"normalized": false,
|
440 |
+
"rstrip": false,
|
441 |
+
"single_word": false,
|
442 |
+
"special": false
|
443 |
+
},
|
444 |
+
"250052": {
|
445 |
+
"content": "β<extra_id_47>",
|
446 |
+
"lstrip": false,
|
447 |
+
"normalized": false,
|
448 |
+
"rstrip": false,
|
449 |
+
"single_word": false,
|
450 |
+
"special": false
|
451 |
+
},
|
452 |
+
"250053": {
|
453 |
+
"content": "β<extra_id_46>",
|
454 |
+
"lstrip": false,
|
455 |
+
"normalized": false,
|
456 |
+
"rstrip": false,
|
457 |
+
"single_word": false,
|
458 |
+
"special": false
|
459 |
+
},
|
460 |
+
"250054": {
|
461 |
+
"content": "β<extra_id_45>",
|
462 |
+
"lstrip": false,
|
463 |
+
"normalized": false,
|
464 |
+
"rstrip": false,
|
465 |
+
"single_word": false,
|
466 |
+
"special": false
|
467 |
+
},
|
468 |
+
"250055": {
|
469 |
+
"content": "β<extra_id_44>",
|
470 |
+
"lstrip": false,
|
471 |
+
"normalized": false,
|
472 |
+
"rstrip": false,
|
473 |
+
"single_word": false,
|
474 |
+
"special": false
|
475 |
+
},
|
476 |
+
"250056": {
|
477 |
+
"content": "β<extra_id_43>",
|
478 |
+
"lstrip": false,
|
479 |
+
"normalized": false,
|
480 |
+
"rstrip": false,
|
481 |
+
"single_word": false,
|
482 |
+
"special": false
|
483 |
+
},
|
484 |
+
"250057": {
|
485 |
+
"content": "β<extra_id_42>",
|
486 |
+
"lstrip": false,
|
487 |
+
"normalized": false,
|
488 |
+
"rstrip": false,
|
489 |
+
"single_word": false,
|
490 |
+
"special": false
|
491 |
+
},
|
492 |
+
"250058": {
|
493 |
+
"content": "β<extra_id_41>",
|
494 |
+
"lstrip": false,
|
495 |
+
"normalized": false,
|
496 |
+
"rstrip": false,
|
497 |
+
"single_word": false,
|
498 |
+
"special": false
|
499 |
+
},
|
500 |
+
"250059": {
|
501 |
+
"content": "β<extra_id_40>",
|
502 |
+
"lstrip": false,
|
503 |
+
"normalized": false,
|
504 |
+
"rstrip": false,
|
505 |
+
"single_word": false,
|
506 |
+
"special": false
|
507 |
+
},
|
508 |
+
"250060": {
|
509 |
+
"content": "β<extra_id_39>",
|
510 |
+
"lstrip": false,
|
511 |
+
"normalized": false,
|
512 |
+
"rstrip": false,
|
513 |
+
"single_word": false,
|
514 |
+
"special": false
|
515 |
+
},
|
516 |
+
"250061": {
|
517 |
+
"content": "β<extra_id_38>",
|
518 |
+
"lstrip": false,
|
519 |
+
"normalized": false,
|
520 |
+
"rstrip": false,
|
521 |
+
"single_word": false,
|
522 |
+
"special": false
|
523 |
+
},
|
524 |
+
"250062": {
|
525 |
+
"content": "β<extra_id_37>",
|
526 |
+
"lstrip": false,
|
527 |
+
"normalized": false,
|
528 |
+
"rstrip": false,
|
529 |
+
"single_word": false,
|
530 |
+
"special": false
|
531 |
+
},
|
532 |
+
"250063": {
|
533 |
+
"content": "β<extra_id_36>",
|
534 |
+
"lstrip": false,
|
535 |
+
"normalized": false,
|
536 |
+
"rstrip": false,
|
537 |
+
"single_word": false,
|
538 |
+
"special": false
|
539 |
+
},
|
540 |
+
"250064": {
|
541 |
+
"content": "β<extra_id_35>",
|
542 |
+
"lstrip": false,
|
543 |
+
"normalized": false,
|
544 |
+
"rstrip": false,
|
545 |
+
"single_word": false,
|
546 |
+
"special": false
|
547 |
+
},
|
548 |
+
"250065": {
|
549 |
+
"content": "β<extra_id_34>",
|
550 |
+
"lstrip": false,
|
551 |
+
"normalized": false,
|
552 |
+
"rstrip": false,
|
553 |
+
"single_word": false,
|
554 |
+
"special": false
|
555 |
+
},
|
556 |
+
"250066": {
|
557 |
+
"content": "β<extra_id_33>",
|
558 |
+
"lstrip": false,
|
559 |
+
"normalized": false,
|
560 |
+
"rstrip": false,
|
561 |
+
"single_word": false,
|
562 |
+
"special": false
|
563 |
+
},
|
564 |
+
"250067": {
|
565 |
+
"content": "β<extra_id_32>",
|
566 |
+
"lstrip": false,
|
567 |
+
"normalized": false,
|
568 |
+
"rstrip": false,
|
569 |
+
"single_word": false,
|
570 |
+
"special": false
|
571 |
+
},
|
572 |
+
"250068": {
|
573 |
+
"content": "β<extra_id_31>",
|
574 |
+
"lstrip": false,
|
575 |
+
"normalized": false,
|
576 |
+
"rstrip": false,
|
577 |
+
"single_word": false,
|
578 |
+
"special": false
|
579 |
+
},
|
580 |
+
"250069": {
|
581 |
+
"content": "β<extra_id_30>",
|
582 |
+
"lstrip": false,
|
583 |
+
"normalized": false,
|
584 |
+
"rstrip": false,
|
585 |
+
"single_word": false,
|
586 |
+
"special": false
|
587 |
+
},
|
588 |
+
"250070": {
|
589 |
+
"content": "β<extra_id_29>",
|
590 |
+
"lstrip": false,
|
591 |
+
"normalized": false,
|
592 |
+
"rstrip": false,
|
593 |
+
"single_word": false,
|
594 |
+
"special": false
|
595 |
+
},
|
596 |
+
"250071": {
|
597 |
+
"content": "β<extra_id_28>",
|
598 |
+
"lstrip": false,
|
599 |
+
"normalized": false,
|
600 |
+
"rstrip": false,
|
601 |
+
"single_word": false,
|
602 |
+
"special": false
|
603 |
+
},
|
604 |
+
"250072": {
|
605 |
+
"content": "β<extra_id_27>",
|
606 |
+
"lstrip": false,
|
607 |
+
"normalized": false,
|
608 |
+
"rstrip": false,
|
609 |
+
"single_word": false,
|
610 |
+
"special": false
|
611 |
+
},
|
612 |
+
"250073": {
|
613 |
+
"content": "β<extra_id_26>",
|
614 |
+
"lstrip": false,
|
615 |
+
"normalized": false,
|
616 |
+
"rstrip": false,
|
617 |
+
"single_word": false,
|
618 |
+
"special": false
|
619 |
+
},
|
620 |
+
"250074": {
|
621 |
+
"content": "β<extra_id_25>",
|
622 |
+
"lstrip": false,
|
623 |
+
"normalized": false,
|
624 |
+
"rstrip": false,
|
625 |
+
"single_word": false,
|
626 |
+
"special": false
|
627 |
+
},
|
628 |
+
"250075": {
|
629 |
+
"content": "β<extra_id_24>",
|
630 |
+
"lstrip": false,
|
631 |
+
"normalized": false,
|
632 |
+
"rstrip": false,
|
633 |
+
"single_word": false,
|
634 |
+
"special": false
|
635 |
+
},
|
636 |
+
"250076": {
|
637 |
+
"content": "β<extra_id_23>",
|
638 |
+
"lstrip": false,
|
639 |
+
"normalized": false,
|
640 |
+
"rstrip": false,
|
641 |
+
"single_word": false,
|
642 |
+
"special": false
|
643 |
+
},
|
644 |
+
"250077": {
|
645 |
+
"content": "β<extra_id_22>",
|
646 |
+
"lstrip": false,
|
647 |
+
"normalized": false,
|
648 |
+
"rstrip": false,
|
649 |
+
"single_word": false,
|
650 |
+
"special": false
|
651 |
+
},
|
652 |
+
"250078": {
|
653 |
+
"content": "β<extra_id_21>",
|
654 |
+
"lstrip": false,
|
655 |
+
"normalized": false,
|
656 |
+
"rstrip": false,
|
657 |
+
"single_word": false,
|
658 |
+
"special": false
|
659 |
+
},
|
660 |
+
"250079": {
|
661 |
+
"content": "β<extra_id_20>",
|
662 |
+
"lstrip": false,
|
663 |
+
"normalized": false,
|
664 |
+
"rstrip": false,
|
665 |
+
"single_word": false,
|
666 |
+
"special": false
|
667 |
+
},
|
668 |
+
"250080": {
|
669 |
+
"content": "β<extra_id_19>",
|
670 |
+
"lstrip": false,
|
671 |
+
"normalized": false,
|
672 |
+
"rstrip": false,
|
673 |
+
"single_word": false,
|
674 |
+
"special": false
|
675 |
+
},
|
676 |
+
"250081": {
|
677 |
+
"content": "β<extra_id_18>",
|
678 |
+
"lstrip": false,
|
679 |
+
"normalized": false,
|
680 |
+
"rstrip": false,
|
681 |
+
"single_word": false,
|
682 |
+
"special": false
|
683 |
+
},
|
684 |
+
"250082": {
|
685 |
+
"content": "β<extra_id_17>",
|
686 |
+
"lstrip": false,
|
687 |
+
"normalized": false,
|
688 |
+
"rstrip": false,
|
689 |
+
"single_word": false,
|
690 |
+
"special": false
|
691 |
+
},
|
692 |
+
"250083": {
|
693 |
+
"content": "β<extra_id_16>",
|
694 |
+
"lstrip": false,
|
695 |
+
"normalized": false,
|
696 |
+
"rstrip": false,
|
697 |
+
"single_word": false,
|
698 |
+
"special": false
|
699 |
+
},
|
700 |
+
"250084": {
|
701 |
+
"content": "β<extra_id_15>",
|
702 |
+
"lstrip": false,
|
703 |
+
"normalized": false,
|
704 |
+
"rstrip": false,
|
705 |
+
"single_word": false,
|
706 |
+
"special": false
|
707 |
+
},
|
708 |
+
"250085": {
|
709 |
+
"content": "β<extra_id_14>",
|
710 |
+
"lstrip": false,
|
711 |
+
"normalized": false,
|
712 |
+
"rstrip": false,
|
713 |
+
"single_word": false,
|
714 |
+
"special": false
|
715 |
+
},
|
716 |
+
"250086": {
|
717 |
+
"content": "β<extra_id_13>",
|
718 |
+
"lstrip": false,
|
719 |
+
"normalized": false,
|
720 |
+
"rstrip": false,
|
721 |
+
"single_word": false,
|
722 |
+
"special": false
|
723 |
+
},
|
724 |
+
"250087": {
|
725 |
+
"content": "β<extra_id_12>",
|
726 |
+
"lstrip": false,
|
727 |
+
"normalized": false,
|
728 |
+
"rstrip": false,
|
729 |
+
"single_word": false,
|
730 |
+
"special": false
|
731 |
+
},
|
732 |
+
"250088": {
|
733 |
+
"content": "β<extra_id_11>",
|
734 |
+
"lstrip": false,
|
735 |
+
"normalized": false,
|
736 |
+
"rstrip": false,
|
737 |
+
"single_word": false,
|
738 |
+
"special": false
|
739 |
+
},
|
740 |
+
"250089": {
|
741 |
+
"content": "β<extra_id_10>",
|
742 |
+
"lstrip": false,
|
743 |
+
"normalized": false,
|
744 |
+
"rstrip": false,
|
745 |
+
"single_word": false,
|
746 |
+
"special": false
|
747 |
+
},
|
748 |
+
"250090": {
|
749 |
+
"content": "β<extra_id_9>",
|
750 |
+
"lstrip": false,
|
751 |
+
"normalized": false,
|
752 |
+
"rstrip": false,
|
753 |
+
"single_word": false,
|
754 |
+
"special": false
|
755 |
+
},
|
756 |
+
"250091": {
|
757 |
+
"content": "β<extra_id_8>",
|
758 |
+
"lstrip": false,
|
759 |
+
"normalized": false,
|
760 |
+
"rstrip": false,
|
761 |
+
"single_word": false,
|
762 |
+
"special": false
|
763 |
+
},
|
764 |
+
"250092": {
|
765 |
+
"content": "β<extra_id_7>",
|
766 |
+
"lstrip": false,
|
767 |
+
"normalized": false,
|
768 |
+
"rstrip": false,
|
769 |
+
"single_word": false,
|
770 |
+
"special": false
|
771 |
+
},
|
772 |
+
"250093": {
|
773 |
+
"content": "β<extra_id_6>",
|
774 |
+
"lstrip": false,
|
775 |
+
"normalized": false,
|
776 |
+
"rstrip": false,
|
777 |
+
"single_word": false,
|
778 |
+
"special": false
|
779 |
+
},
|
780 |
+
"250094": {
|
781 |
+
"content": "β<extra_id_5>",
|
782 |
+
"lstrip": false,
|
783 |
+
"normalized": false,
|
784 |
+
"rstrip": false,
|
785 |
+
"single_word": false,
|
786 |
+
"special": false
|
787 |
+
},
|
788 |
+
"250095": {
|
789 |
+
"content": "β<extra_id_4>",
|
790 |
+
"lstrip": false,
|
791 |
+
"normalized": false,
|
792 |
+
"rstrip": false,
|
793 |
+
"single_word": false,
|
794 |
+
"special": false
|
795 |
+
},
|
796 |
+
"250096": {
|
797 |
+
"content": "β<extra_id_3>",
|
798 |
+
"lstrip": false,
|
799 |
+
"normalized": false,
|
800 |
+
"rstrip": false,
|
801 |
+
"single_word": false,
|
802 |
+
"special": false
|
803 |
+
},
|
804 |
+
"250097": {
|
805 |
+
"content": "β<extra_id_2>",
|
806 |
+
"lstrip": false,
|
807 |
+
"normalized": false,
|
808 |
+
"rstrip": false,
|
809 |
+
"single_word": false,
|
810 |
+
"special": false
|
811 |
+
},
|
812 |
+
"250098": {
|
813 |
+
"content": "β<extra_id_1>",
|
814 |
+
"lstrip": false,
|
815 |
+
"normalized": false,
|
816 |
+
"rstrip": false,
|
817 |
+
"single_word": false,
|
818 |
+
"special": false
|
819 |
+
},
|
820 |
+
"250099": {
|
821 |
+
"content": "β<extra_id_0>",
|
822 |
+
"lstrip": false,
|
823 |
+
"normalized": false,
|
824 |
+
"rstrip": false,
|
825 |
+
"single_word": false,
|
826 |
+
"special": false
|
827 |
+
}
|
828 |
+
},
|
829 |
+
"additional_special_tokens": [],
|
830 |
+
"clean_up_tokenization_spaces": false,
|
831 |
+
"eos_token": "</s>",
|
832 |
+
"extra_ids": 0,
|
833 |
+
"legacy": false,
|
834 |
+
"model_max_length": 1000000000000000019884624838656,
|
835 |
+
"pad_token": "<pad>",
|
836 |
+
"sp_model_kwargs": {},
|
837 |
+
"tokenizer_class": "T5Tokenizer",
|
838 |
+
"unk_token": "<unk>"
|
839 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:80876f19a01726007c922b06a3348c49179213c54dded08e9444ddfaf8911c51
|
3 |
+
size 5496
|