Hugging Face's logo

pszemraj
/
flan-ul2-text-encoder

Feature Extraction
Transformers
PyTorch
t5
embedding
text embedding
text-generation-inference
Inference Endpoints
Model card Files Community
1
pszemraj commited on
Commit
b605f10
•
1 Parent(s): 0f4e814

Upload model

Browse files
Files changed (12) hide show
  1. config.json +31 -0
  2. pytorch_model-00001-of-00010.bin +3 -0
  3. pytorch_model-00002-of-00010.bin +3 -0
  4. pytorch_model-00003-of-00010.bin +3 -0
  5. pytorch_model-00004-of-00010.bin +3 -0
  6. pytorch_model-00005-of-00010.bin +3 -0
  7. pytorch_model-00006-of-00010.bin +3 -0
  8. pytorch_model-00007-of-00010.bin +3 -0
  9. pytorch_model-00008-of-00010.bin +3 -0
  10. pytorch_model-00009-of-00010.bin +3 -0
  11. pytorch_model-00010-of-00010.bin +3 -0
  12. pytorch_model.bin.index.json +299 -0
config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/flan-ul2",
3
+ "architectures": [
4
+ "T5EncoderModel"
5
+ ],
6
+ "d_ff": 16384,
7
+ "d_kv": 256,
8
+ "d_model": 4096,
9
+ "decoder_start_token_id": 0,
10
+ "dense_act_fn": "silu",
11
+ "dropout_rate": 0.1,
12
+ "eos_token_id": 1,
13
+ "feed_forward_proj": "gated-silu",
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": 32,
21
+ "num_heads": 16,
22
+ "num_layers": 32,
23
+ "output_past": true,
24
+ "pad_token_id": 0,
25
+ "relative_attention_max_distance": 128,
26
+ "relative_attention_num_buckets": 32,
27
+ "torch_dtype": "bfloat16",
28
+ "transformers_version": "4.31.0",
29
+ "use_cache": true,
30
+ "vocab_size": 32128
31
+ }
pytorch_model-00001-of-00010.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f172bae9a224d6088892087976355ca1bd8e8c83adf02d5e52ab6407dacca3bc
3
+ size 1974529807
pytorch_model-00002-of-00010.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b6857d854de04d0127317ee6a286b86d73de9445d49e3c6857fbaed5a5f8ddc
3
+ size 1912670525
pytorch_model-00003-of-00010.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe27d259c3b74ade192fc0fc667a42caed7b39aa247a9bd5d0ec68a9d748c1ac
3
+ size 1879125299
pytorch_model-00004-of-00010.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:263ea6b85878589bc2d04662d1d25d9a9de4fc624fd334eb7371e9e39cf9e85c
3
+ size 1879107289
pytorch_model-00005-of-00010.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d8ec32802a84fc0d513f0e51159835fd04d95f8a7da21540181220f2d917648
3
+ size 1879125363
pytorch_model-00006-of-00010.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10c2aaf66e967f3a76b14aaeafdafc01e41ebf045b9da33fa7363c2b98d9f648
3
+ size 1879107289
pytorch_model-00007-of-00010.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b9f4ee4639aab4a71dff21571372367ccd76afcae740b4a1ec13fefcb1b457e
3
+ size 1879125363
pytorch_model-00008-of-00010.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79093ab34054f166e35ea4b413fe3442cf3398980a6725844dd2f16dc0d72846
3
+ size 1879107289
pytorch_model-00009-of-00010.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:240d24a2b26622b72c1b147fd398745945e0e0aae52bc91f472279b3bc4786e9
3
+ size 1879125363
pytorch_model-00010-of-00010.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e0785821e6b0a4e8cf731ddd3bb218ec1e300490a9051510b00d1bc56badc32
3
+ size 402671790
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,299 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 17443595264
4
+ },
5
+ "weight_map": {
6
+ "encoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00010.bin",
7
+ "encoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00010.bin",
8
+ "encoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00010.bin",
9
+ "encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model-00001-of-00010.bin",
10
+ "encoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00010.bin",
11
+ "encoder.block.0.layer.0.layer_norm.weight": "pytorch_model-00001-of-00010.bin",
12
+ "encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00010.bin",
13
+ "encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00010.bin",
14
+ "encoder.block.0.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00010.bin",
15
+ "encoder.block.0.layer.1.layer_norm.weight": "pytorch_model-00001-of-00010.bin",
16
+ "encoder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00010.bin",
17
+ "encoder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00010.bin",
18
+ "encoder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00010.bin",
19
+ "encoder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00010.bin",
20
+ "encoder.block.1.layer.0.layer_norm.weight": "pytorch_model-00001-of-00010.bin",
21
+ "encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00010.bin",
22
+ "encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00010.bin",
23
+ "encoder.block.1.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00010.bin",
24
+ "encoder.block.1.layer.1.layer_norm.weight": "pytorch_model-00001-of-00010.bin",
25
+ "encoder.block.10.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00010.bin",
26
+ "encoder.block.10.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00010.bin",
27
+ "encoder.block.10.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00010.bin",
28
+ "encoder.block.10.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00010.bin",
29
+ "encoder.block.10.layer.0.layer_norm.weight": "pytorch_model-00003-of-00010.bin",
30
+ "encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00010.bin",
31
+ "encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00010.bin",
32
+ "encoder.block.10.layer.1.DenseReluDense.wo.weight": "pytorch_model-00004-of-00010.bin",
33
+ "encoder.block.10.layer.1.layer_norm.weight": "pytorch_model-00004-of-00010.bin",
34
+ "encoder.block.11.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00010.bin",
35
+ "encoder.block.11.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00010.bin",
36
+ "encoder.block.11.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00010.bin",
37
+ "encoder.block.11.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00010.bin",
38
+ "encoder.block.11.layer.0.layer_norm.weight": "pytorch_model-00004-of-00010.bin",
39
+ "encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00010.bin",
40
+ "encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00010.bin",
41
+ "encoder.block.11.layer.1.DenseReluDense.wo.weight": "pytorch_model-00004-of-00010.bin",
42
+ "encoder.block.11.layer.1.layer_norm.weight": "pytorch_model-00004-of-00010.bin",
43
+ "encoder.block.12.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00010.bin",
44
+ "encoder.block.12.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00010.bin",
45
+ "encoder.block.12.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00010.bin",
46
+ "encoder.block.12.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00010.bin",
47
+ "encoder.block.12.layer.0.layer_norm.weight": "pytorch_model-00004-of-00010.bin",
48
+ "encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00010.bin",
49
+ "encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00010.bin",
50
+ "encoder.block.12.layer.1.DenseReluDense.wo.weight": "pytorch_model-00004-of-00010.bin",
51
+ "encoder.block.12.layer.1.layer_norm.weight": "pytorch_model-00004-of-00010.bin",
52
+ "encoder.block.13.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00010.bin",
53
+ "encoder.block.13.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00010.bin",
54
+ "encoder.block.13.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00010.bin",
55
+ "encoder.block.13.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00010.bin",
56
+ "encoder.block.13.layer.0.layer_norm.weight": "pytorch_model-00004-of-00010.bin",
57
+ "encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00010.bin",
58
+ "encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00010.bin",
59
+ "encoder.block.13.layer.1.DenseReluDense.wo.weight": "pytorch_model-00005-of-00010.bin",
60
+ "encoder.block.13.layer.1.layer_norm.weight": "pytorch_model-00005-of-00010.bin",
61
+ "encoder.block.14.layer.0.SelfAttention.k.weight": "pytorch_model-00005-of-00010.bin",
62
+ "encoder.block.14.layer.0.SelfAttention.o.weight": "pytorch_model-00005-of-00010.bin",
63
+ "encoder.block.14.layer.0.SelfAttention.q.weight": "pytorch_model-00005-of-00010.bin",
64
+ "encoder.block.14.layer.0.SelfAttention.v.weight": "pytorch_model-00005-of-00010.bin",
65
+ "encoder.block.14.layer.0.layer_norm.weight": "pytorch_model-00005-of-00010.bin",
66
+ "encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00005-of-00010.bin",
67
+ "encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00005-of-00010.bin",
68
+ "encoder.block.14.layer.1.DenseReluDense.wo.weight": "pytorch_model-00005-of-00010.bin",
69
+ "encoder.block.14.layer.1.layer_norm.weight": "pytorch_model-00005-of-00010.bin",
70
+ "encoder.block.15.layer.0.SelfAttention.k.weight": "pytorch_model-00005-of-00010.bin",
71
+ "encoder.block.15.layer.0.SelfAttention.o.weight": "pytorch_model-00005-of-00010.bin",
72
+ "encoder.block.15.layer.0.SelfAttention.q.weight": "pytorch_model-00005-of-00010.bin",
73
+ "encoder.block.15.layer.0.SelfAttention.v.weight": "pytorch_model-00005-of-00010.bin",
74
+ "encoder.block.15.layer.0.layer_norm.weight": "pytorch_model-00005-of-00010.bin",
75
+ "encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00005-of-00010.bin",
76
+ "encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00005-of-00010.bin",
77
+ "encoder.block.15.layer.1.DenseReluDense.wo.weight": "pytorch_model-00005-of-00010.bin",
78
+ "encoder.block.15.layer.1.layer_norm.weight": "pytorch_model-00005-of-00010.bin",
79
+ "encoder.block.16.layer.0.SelfAttention.k.weight": "pytorch_model-00005-of-00010.bin",
80
+ "encoder.block.16.layer.0.SelfAttention.o.weight": "pytorch_model-00005-of-00010.bin",
81
+ "encoder.block.16.layer.0.SelfAttention.q.weight": "pytorch_model-00005-of-00010.bin",
82
+ "encoder.block.16.layer.0.SelfAttention.v.weight": "pytorch_model-00005-of-00010.bin",
83
+ "encoder.block.16.layer.0.layer_norm.weight": "pytorch_model-00005-of-00010.bin",
84
+ "encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00005-of-00010.bin",
85
+ "encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00005-of-00010.bin",
86
+ "encoder.block.16.layer.1.DenseReluDense.wo.weight": "pytorch_model-00005-of-00010.bin",
87
+ "encoder.block.16.layer.1.layer_norm.weight": "pytorch_model-00005-of-00010.bin",
88
+ "encoder.block.17.layer.0.SelfAttention.k.weight": "pytorch_model-00005-of-00010.bin",
89
+ "encoder.block.17.layer.0.SelfAttention.o.weight": "pytorch_model-00005-of-00010.bin",
90
+ "encoder.block.17.layer.0.SelfAttention.q.weight": "pytorch_model-00005-of-00010.bin",
91
+ "encoder.block.17.layer.0.SelfAttention.v.weight": "pytorch_model-00005-of-00010.bin",
92
+ "encoder.block.17.layer.0.layer_norm.weight": "pytorch_model-00005-of-00010.bin",
93
+ "encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00006-of-00010.bin",
94
+ "encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00006-of-00010.bin",
95
+ "encoder.block.17.layer.1.DenseReluDense.wo.weight": "pytorch_model-00006-of-00010.bin",
96
+ "encoder.block.17.layer.1.layer_norm.weight": "pytorch_model-00006-of-00010.bin",
97
+ "encoder.block.18.layer.0.SelfAttention.k.weight": "pytorch_model-00006-of-00010.bin",
98
+ "encoder.block.18.layer.0.SelfAttention.o.weight": "pytorch_model-00006-of-00010.bin",
99
+ "encoder.block.18.layer.0.SelfAttention.q.weight": "pytorch_model-00006-of-00010.bin",
100
+ "encoder.block.18.layer.0.SelfAttention.v.weight": "pytorch_model-00006-of-00010.bin",
101
+ "encoder.block.18.layer.0.layer_norm.weight": "pytorch_model-00006-of-00010.bin",
102
+ "encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00006-of-00010.bin",
103
+ "encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00006-of-00010.bin",
104
+ "encoder.block.18.layer.1.DenseReluDense.wo.weight": "pytorch_model-00006-of-00010.bin",
105
+ "encoder.block.18.layer.1.layer_norm.weight": "pytorch_model-00006-of-00010.bin",
106
+ "encoder.block.19.layer.0.SelfAttention.k.weight": "pytorch_model-00006-of-00010.bin",
107
+ "encoder.block.19.layer.0.SelfAttention.o.weight": "pytorch_model-00006-of-00010.bin",
108
+ "encoder.block.19.layer.0.SelfAttention.q.weight": "pytorch_model-00006-of-00010.bin",
109
+ "encoder.block.19.layer.0.SelfAttention.v.weight": "pytorch_model-00006-of-00010.bin",
110
+ "encoder.block.19.layer.0.layer_norm.weight": "pytorch_model-00006-of-00010.bin",
111
+ "encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00006-of-00010.bin",
112
+ "encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00006-of-00010.bin",
113
+ "encoder.block.19.layer.1.DenseReluDense.wo.weight": "pytorch_model-00006-of-00010.bin",
114
+ "encoder.block.19.layer.1.layer_norm.weight": "pytorch_model-00006-of-00010.bin",
115
+ "encoder.block.2.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00010.bin",
116
+ "encoder.block.2.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00010.bin",
117
+ "encoder.block.2.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00010.bin",
118
+ "encoder.block.2.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00010.bin",
119
+ "encoder.block.2.layer.0.layer_norm.weight": "pytorch_model-00001-of-00010.bin",
120
+ "encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00010.bin",
121
+ "encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00010.bin",
122
+ "encoder.block.2.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00010.bin",
123
+ "encoder.block.2.layer.1.layer_norm.weight": "pytorch_model-00001-of-00010.bin",
124
+ "encoder.block.20.layer.0.SelfAttention.k.weight": "pytorch_model-00006-of-00010.bin",
125
+ "encoder.block.20.layer.0.SelfAttention.o.weight": "pytorch_model-00006-of-00010.bin",
126
+ "encoder.block.20.layer.0.SelfAttention.q.weight": "pytorch_model-00006-of-00010.bin",
127
+ "encoder.block.20.layer.0.SelfAttention.v.weight": "pytorch_model-00006-of-00010.bin",
128
+ "encoder.block.20.layer.0.layer_norm.weight": "pytorch_model-00006-of-00010.bin",
129
+ "encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00006-of-00010.bin",
130
+ "encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00006-of-00010.bin",
131
+ "encoder.block.20.layer.1.DenseReluDense.wo.weight": "pytorch_model-00007-of-00010.bin",
132
+ "encoder.block.20.layer.1.layer_norm.weight": "pytorch_model-00007-of-00010.bin",
133
+ "encoder.block.21.layer.0.SelfAttention.k.weight": "pytorch_model-00007-of-00010.bin",
134
+ "encoder.block.21.layer.0.SelfAttention.o.weight": "pytorch_model-00007-of-00010.bin",
135
+ "encoder.block.21.layer.0.SelfAttention.q.weight": "pytorch_model-00007-of-00010.bin",
136
+ "encoder.block.21.layer.0.SelfAttention.v.weight": "pytorch_model-00007-of-00010.bin",
137
+ "encoder.block.21.layer.0.layer_norm.weight": "pytorch_model-00007-of-00010.bin",
138
+ "encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00007-of-00010.bin",
139
+ "encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00007-of-00010.bin",
140
+ "encoder.block.21.layer.1.DenseReluDense.wo.weight": "pytorch_model-00007-of-00010.bin",
141
+ "encoder.block.21.layer.1.layer_norm.weight": "pytorch_model-00007-of-00010.bin",
142
+ "encoder.block.22.layer.0.SelfAttention.k.weight": "pytorch_model-00007-of-00010.bin",
143
+ "encoder.block.22.layer.0.SelfAttention.o.weight": "pytorch_model-00007-of-00010.bin",
144
+ "encoder.block.22.layer.0.SelfAttention.q.weight": "pytorch_model-00007-of-00010.bin",
145
+ "encoder.block.22.layer.0.SelfAttention.v.weight": "pytorch_model-00007-of-00010.bin",
146
+ "encoder.block.22.layer.0.layer_norm.weight": "pytorch_model-00007-of-00010.bin",
147
+ "encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00007-of-00010.bin",
148
+ "encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00007-of-00010.bin",
149
+ "encoder.block.22.layer.1.DenseReluDense.wo.weight": "pytorch_model-00007-of-00010.bin",
150
+ "encoder.block.22.layer.1.layer_norm.weight": "pytorch_model-00007-of-00010.bin",
151
+ "encoder.block.23.layer.0.SelfAttention.k.weight": "pytorch_model-00007-of-00010.bin",
152
+ "encoder.block.23.layer.0.SelfAttention.o.weight": "pytorch_model-00007-of-00010.bin",
153
+ "encoder.block.23.layer.0.SelfAttention.q.weight": "pytorch_model-00007-of-00010.bin",
154
+ "encoder.block.23.layer.0.SelfAttention.v.weight": "pytorch_model-00007-of-00010.bin",
155
+ "encoder.block.23.layer.0.layer_norm.weight": "pytorch_model-00007-of-00010.bin",
156
+ "encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00007-of-00010.bin",
157
+ "encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00007-of-00010.bin",
158
+ "encoder.block.23.layer.1.DenseReluDense.wo.weight": "pytorch_model-00007-of-00010.bin",
159
+ "encoder.block.23.layer.1.layer_norm.weight": "pytorch_model-00007-of-00010.bin",
160
+ "encoder.block.24.layer.0.SelfAttention.k.weight": "pytorch_model-00007-of-00010.bin",
161
+ "encoder.block.24.layer.0.SelfAttention.o.weight": "pytorch_model-00007-of-00010.bin",
162
+ "encoder.block.24.layer.0.SelfAttention.q.weight": "pytorch_model-00007-of-00010.bin",
163
+ "encoder.block.24.layer.0.SelfAttention.v.weight": "pytorch_model-00007-of-00010.bin",
164
+ "encoder.block.24.layer.0.layer_norm.weight": "pytorch_model-00007-of-00010.bin",
165
+ "encoder.block.24.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00008-of-00010.bin",
166
+ "encoder.block.24.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00008-of-00010.bin",
167
+ "encoder.block.24.layer.1.DenseReluDense.wo.weight": "pytorch_model-00008-of-00010.bin",
168
+ "encoder.block.24.layer.1.layer_norm.weight": "pytorch_model-00008-of-00010.bin",
169
+ "encoder.block.25.layer.0.SelfAttention.k.weight": "pytorch_model-00008-of-00010.bin",
170
+ "encoder.block.25.layer.0.SelfAttention.o.weight": "pytorch_model-00008-of-00010.bin",
171
+ "encoder.block.25.layer.0.SelfAttention.q.weight": "pytorch_model-00008-of-00010.bin",
172
+ "encoder.block.25.layer.0.SelfAttention.v.weight": "pytorch_model-00008-of-00010.bin",
173
+ "encoder.block.25.layer.0.layer_norm.weight": "pytorch_model-00008-of-00010.bin",
174
+ "encoder.block.25.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00008-of-00010.bin",
175
+ "encoder.block.25.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00008-of-00010.bin",
176
+ "encoder.block.25.layer.1.DenseReluDense.wo.weight": "pytorch_model-00008-of-00010.bin",
177
+ "encoder.block.25.layer.1.layer_norm.weight": "pytorch_model-00008-of-00010.bin",
178
+ "encoder.block.26.layer.0.SelfAttention.k.weight": "pytorch_model-00008-of-00010.bin",
179
+ "encoder.block.26.layer.0.SelfAttention.o.weight": "pytorch_model-00008-of-00010.bin",
180
+ "encoder.block.26.layer.0.SelfAttention.q.weight": "pytorch_model-00008-of-00010.bin",
181
+ "encoder.block.26.layer.0.SelfAttention.v.weight": "pytorch_model-00008-of-00010.bin",
182
+ "encoder.block.26.layer.0.layer_norm.weight": "pytorch_model-00008-of-00010.bin",
183
+ "encoder.block.26.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00008-of-00010.bin",
184
+ "encoder.block.26.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00008-of-00010.bin",
185
+ "encoder.block.26.layer.1.DenseReluDense.wo.weight": "pytorch_model-00008-of-00010.bin",
186
+ "encoder.block.26.layer.1.layer_norm.weight": "pytorch_model-00008-of-00010.bin",
187
+ "encoder.block.27.layer.0.SelfAttention.k.weight": "pytorch_model-00008-of-00010.bin",
188
+ "encoder.block.27.layer.0.SelfAttention.o.weight": "pytorch_model-00008-of-00010.bin",
189
+ "encoder.block.27.layer.0.SelfAttention.q.weight": "pytorch_model-00008-of-00010.bin",
190
+ "encoder.block.27.layer.0.SelfAttention.v.weight": "pytorch_model-00008-of-00010.bin",
191
+ "encoder.block.27.layer.0.layer_norm.weight": "pytorch_model-00008-of-00010.bin",
192
+ "encoder.block.27.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00008-of-00010.bin",
193
+ "encoder.block.27.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00008-of-00010.bin",
194
+ "encoder.block.27.layer.1.DenseReluDense.wo.weight": "pytorch_model-00009-of-00010.bin",
195
+ "encoder.block.27.layer.1.layer_norm.weight": "pytorch_model-00009-of-00010.bin",
196
+ "encoder.block.28.layer.0.SelfAttention.k.weight": "pytorch_model-00009-of-00010.bin",
197
+ "encoder.block.28.layer.0.SelfAttention.o.weight": "pytorch_model-00009-of-00010.bin",
198
+ "encoder.block.28.layer.0.SelfAttention.q.weight": "pytorch_model-00009-of-00010.bin",
199
+ "encoder.block.28.layer.0.SelfAttention.v.weight": "pytorch_model-00009-of-00010.bin",
200
+ "encoder.block.28.layer.0.layer_norm.weight": "pytorch_model-00009-of-00010.bin",
201
+ "encoder.block.28.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00009-of-00010.bin",
202
+ "encoder.block.28.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00009-of-00010.bin",
203
+ "encoder.block.28.layer.1.DenseReluDense.wo.weight": "pytorch_model-00009-of-00010.bin",
204
+ "encoder.block.28.layer.1.layer_norm.weight": "pytorch_model-00009-of-00010.bin",
205
+ "encoder.block.29.layer.0.SelfAttention.k.weight": "pytorch_model-00009-of-00010.bin",
206
+ "encoder.block.29.layer.0.SelfAttention.o.weight": "pytorch_model-00009-of-00010.bin",
207
+ "encoder.block.29.layer.0.SelfAttention.q.weight": "pytorch_model-00009-of-00010.bin",
208
+ "encoder.block.29.layer.0.SelfAttention.v.weight": "pytorch_model-00009-of-00010.bin",
209
+ "encoder.block.29.layer.0.layer_norm.weight": "pytorch_model-00009-of-00010.bin",
210
+ "encoder.block.29.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00009-of-00010.bin",
211
+ "encoder.block.29.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00009-of-00010.bin",
212
+ "encoder.block.29.layer.1.DenseReluDense.wo.weight": "pytorch_model-00009-of-00010.bin",
213
+ "encoder.block.29.layer.1.layer_norm.weight": "pytorch_model-00009-of-00010.bin",
214
+ "encoder.block.3.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00010.bin",
215
+ "encoder.block.3.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00010.bin",
216
+ "encoder.block.3.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00010.bin",
217
+ "encoder.block.3.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00010.bin",
218
+ "encoder.block.3.layer.0.layer_norm.weight": "pytorch_model-00002-of-00010.bin",
219
+ "encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00010.bin",
220
+ "encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00010.bin",
221
+ "encoder.block.3.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00010.bin",
222
+ "encoder.block.3.layer.1.layer_norm.weight": "pytorch_model-00002-of-00010.bin",
223
+ "encoder.block.30.layer.0.SelfAttention.k.weight": "pytorch_model-00009-of-00010.bin",
224
+ "encoder.block.30.layer.0.SelfAttention.o.weight": "pytorch_model-00009-of-00010.bin",
225
+ "encoder.block.30.layer.0.SelfAttention.q.weight": "pytorch_model-00009-of-00010.bin",
226
+ "encoder.block.30.layer.0.SelfAttention.v.weight": "pytorch_model-00009-of-00010.bin",
227
+ "encoder.block.30.layer.0.layer_norm.weight": "pytorch_model-00009-of-00010.bin",
228
+ "encoder.block.30.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00009-of-00010.bin",
229
+ "encoder.block.30.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00009-of-00010.bin",
230
+ "encoder.block.30.layer.1.DenseReluDense.wo.weight": "pytorch_model-00009-of-00010.bin",
231
+ "encoder.block.30.layer.1.layer_norm.weight": "pytorch_model-00009-of-00010.bin",
232
+ "encoder.block.31.layer.0.SelfAttention.k.weight": "pytorch_model-00009-of-00010.bin",
233
+ "encoder.block.31.layer.0.SelfAttention.o.weight": "pytorch_model-00009-of-00010.bin",
234
+ "encoder.block.31.layer.0.SelfAttention.q.weight": "pytorch_model-00009-of-00010.bin",
235
+ "encoder.block.31.layer.0.SelfAttention.v.weight": "pytorch_model-00009-of-00010.bin",
236
+ "encoder.block.31.layer.0.layer_norm.weight": "pytorch_model-00009-of-00010.bin",
237
+ "encoder.block.31.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00010-of-00010.bin",
238
+ "encoder.block.31.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00010-of-00010.bin",
239
+ "encoder.block.31.layer.1.DenseReluDense.wo.weight": "pytorch_model-00010-of-00010.bin",
240
+ "encoder.block.31.layer.1.layer_norm.weight": "pytorch_model-00010-of-00010.bin",
241
+ "encoder.block.4.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00010.bin",
242
+ "encoder.block.4.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00010.bin",
243
+ "encoder.block.4.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00010.bin",
244
+ "encoder.block.4.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00010.bin",
245
+ "encoder.block.4.layer.0.layer_norm.weight": "pytorch_model-00002-of-00010.bin",
246
+ "encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00010.bin",
247
+ "encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00010.bin",
248
+ "encoder.block.4.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00010.bin",
249
+ "encoder.block.4.layer.1.layer_norm.weight": "pytorch_model-00002-of-00010.bin",
250
+ "encoder.block.5.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00010.bin",
251
+ "encoder.block.5.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00010.bin",
252
+ "encoder.block.5.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00010.bin",
253
+ "encoder.block.5.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00010.bin",
254
+ "encoder.block.5.layer.0.layer_norm.weight": "pytorch_model-00002-of-00010.bin",
255
+ "encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00010.bin",
256
+ "encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00010.bin",
257
+ "encoder.block.5.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00010.bin",
258
+ "encoder.block.5.layer.1.layer_norm.weight": "pytorch_model-00002-of-00010.bin",
259
+ "encoder.block.6.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00010.bin",
260
+ "encoder.block.6.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00010.bin",
261
+ "encoder.block.6.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00010.bin",
262
+ "encoder.block.6.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00010.bin",
263
+ "encoder.block.6.layer.0.layer_norm.weight": "pytorch_model-00002-of-00010.bin",
264
+ "encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00010.bin",
265
+ "encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00010.bin",
266
+ "encoder.block.6.layer.1.DenseReluDense.wo.weight": "pytorch_model-00003-of-00010.bin",
267
+ "encoder.block.6.layer.1.layer_norm.weight": "pytorch_model-00003-of-00010.bin",
268
+ "encoder.block.7.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00010.bin",
269
+ "encoder.block.7.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00010.bin",
270
+ "encoder.block.7.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00010.bin",
271
+ "encoder.block.7.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00010.bin",
272
+ "encoder.block.7.layer.0.layer_norm.weight": "pytorch_model-00003-of-00010.bin",
273
+ "encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00010.bin",
274
+ "encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00010.bin",
275
+ "encoder.block.7.layer.1.DenseReluDense.wo.weight": "pytorch_model-00003-of-00010.bin",
276
+ "encoder.block.7.layer.1.layer_norm.weight": "pytorch_model-00003-of-00010.bin",
277
+ "encoder.block.8.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00010.bin",
278
+ "encoder.block.8.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00010.bin",
279
+ "encoder.block.8.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00010.bin",
280
+ "encoder.block.8.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00010.bin",
281
+ "encoder.block.8.layer.0.layer_norm.weight": "pytorch_model-00003-of-00010.bin",
282
+ "encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00010.bin",
283
+ "encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00010.bin",
284
+ "encoder.block.8.layer.1.DenseReluDense.wo.weight": "pytorch_model-00003-of-00010.bin",
285
+ "encoder.block.8.layer.1.layer_norm.weight": "pytorch_model-00003-of-00010.bin",
286
+ "encoder.block.9.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00010.bin",
287
+ "encoder.block.9.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00010.bin",
288
+ "encoder.block.9.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00010.bin",
289
+ "encoder.block.9.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00010.bin",
290
+ "encoder.block.9.layer.0.layer_norm.weight": "pytorch_model-00003-of-00010.bin",
291
+ "encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00010.bin",
292
+ "encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00010.bin",
293
+ "encoder.block.9.layer.1.DenseReluDense.wo.weight": "pytorch_model-00003-of-00010.bin",
294
+ "encoder.block.9.layer.1.layer_norm.weight": "pytorch_model-00003-of-00010.bin",
295
+ "encoder.embed_tokens.weight": "pytorch_model-00001-of-00010.bin",
296
+ "encoder.final_layer_norm.weight": "pytorch_model-00010-of-00010.bin",
297
+ "shared.weight": "pytorch_model-00001-of-00010.bin"
298
+ }
299
+ }