RyanJDick commited on
Commit
d5f0656
1 Parent(s): 25cf1c0

Add bfloat16 version and optimum_quanto_qfloat8 version.

Browse files
README.md CHANGED
@@ -1,3 +1,12 @@
1
  ---
2
  license: apache-2.0
3
  ---
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: apache-2.0
3
  ---
4
+
5
+ # T5-XXL Encoder
6
+
7
+ This repo contains copies of the T5-XXL encoder in various quantization formats. The models in this repo are intended for use in [InvokeAI](https://github.com/invoke-ai/InvokeAI).
8
+
9
+ Contents:
10
+ - `bfloat16/` - T5-XXL encoder cast to bfloat16. Copied from [here](https://huggingface.co/black-forest-labs/FLUX.1-schnell/tree/741f7c3ce8b383c54771c7003378a50191e9efe9/text_encoder_2).
11
+ - `optimum_quanto_qfloat8` - T5-XXL encoder quantized using [optimum-quanto](https://github.com/huggingface/optimum-quanto) qfloat8 quantization.
12
+
bfloat16/text_encoder_2/config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/t5-v1_1-xxl",
3
+ "architectures": [
4
+ "T5EncoderModel"
5
+ ],
6
+ "classifier_dropout": 0.0,
7
+ "d_ff": 10240,
8
+ "d_kv": 64,
9
+ "d_model": 4096,
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": "t5",
20
+ "num_decoder_layers": 24,
21
+ "num_heads": 64,
22
+ "num_layers": 24,
23
+ "output_past": true,
24
+ "pad_token_id": 0,
25
+ "relative_attention_max_distance": 128,
26
+ "relative_attention_num_buckets": 32,
27
+ "tie_word_embeddings": false,
28
+ "torch_dtype": "bfloat16",
29
+ "transformers_version": "4.43.3",
30
+ "use_cache": true,
31
+ "vocab_size": 32128
32
+ }
bfloat16/text_encoder_2/model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec87bffd1923e8b2774a6d240c922a41f6143081d52cf83b8fe39e9d838c893e
3
+ size 4994582224
bfloat16/text_encoder_2/model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5640855b301fcdbceddfa90ae8066cd9414aff020552a201a255ecf2059da00
3
+ size 4530066360
bfloat16/text_encoder_2/model.safetensors.index.json ADDED
@@ -0,0 +1,226 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 9524621312
4
+ },
5
+ "weight_map": {
6
+ "encoder.block.0.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
7
+ "encoder.block.0.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
8
+ "encoder.block.0.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
9
+ "encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00002.safetensors",
10
+ "encoder.block.0.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
11
+ "encoder.block.0.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
12
+ "encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
13
+ "encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
14
+ "encoder.block.0.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
15
+ "encoder.block.0.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
16
+ "encoder.block.1.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
17
+ "encoder.block.1.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
18
+ "encoder.block.1.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
19
+ "encoder.block.1.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
20
+ "encoder.block.1.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
21
+ "encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
22
+ "encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
23
+ "encoder.block.1.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
24
+ "encoder.block.1.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
25
+ "encoder.block.10.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
26
+ "encoder.block.10.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
27
+ "encoder.block.10.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
28
+ "encoder.block.10.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
29
+ "encoder.block.10.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
30
+ "encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
31
+ "encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
32
+ "encoder.block.10.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
33
+ "encoder.block.10.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
34
+ "encoder.block.11.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
35
+ "encoder.block.11.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
36
+ "encoder.block.11.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
37
+ "encoder.block.11.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
38
+ "encoder.block.11.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
39
+ "encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
40
+ "encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
41
+ "encoder.block.11.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
42
+ "encoder.block.11.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
43
+ "encoder.block.12.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
44
+ "encoder.block.12.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
45
+ "encoder.block.12.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
46
+ "encoder.block.12.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
47
+ "encoder.block.12.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
48
+ "encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
49
+ "encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
50
+ "encoder.block.12.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
51
+ "encoder.block.12.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
52
+ "encoder.block.13.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
53
+ "encoder.block.13.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
54
+ "encoder.block.13.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
55
+ "encoder.block.13.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
56
+ "encoder.block.13.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
57
+ "encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
58
+ "encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
59
+ "encoder.block.13.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
60
+ "encoder.block.13.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
61
+ "encoder.block.14.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
62
+ "encoder.block.14.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
63
+ "encoder.block.14.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
64
+ "encoder.block.14.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
65
+ "encoder.block.14.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
66
+ "encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
67
+ "encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
68
+ "encoder.block.14.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
69
+ "encoder.block.14.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
70
+ "encoder.block.15.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
71
+ "encoder.block.15.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
72
+ "encoder.block.15.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
73
+ "encoder.block.15.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
74
+ "encoder.block.15.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
75
+ "encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
76
+ "encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
77
+ "encoder.block.15.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
78
+ "encoder.block.15.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
79
+ "encoder.block.16.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
80
+ "encoder.block.16.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
81
+ "encoder.block.16.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
82
+ "encoder.block.16.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
83
+ "encoder.block.16.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
84
+ "encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
85
+ "encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
86
+ "encoder.block.16.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
87
+ "encoder.block.16.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
88
+ "encoder.block.17.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
89
+ "encoder.block.17.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
90
+ "encoder.block.17.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
91
+ "encoder.block.17.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
92
+ "encoder.block.17.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
93
+ "encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
94
+ "encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
95
+ "encoder.block.17.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
96
+ "encoder.block.17.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
97
+ "encoder.block.18.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
98
+ "encoder.block.18.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
99
+ "encoder.block.18.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
100
+ "encoder.block.18.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
101
+ "encoder.block.18.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
102
+ "encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
103
+ "encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
104
+ "encoder.block.18.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
105
+ "encoder.block.18.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
106
+ "encoder.block.19.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
107
+ "encoder.block.19.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
108
+ "encoder.block.19.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
109
+ "encoder.block.19.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
110
+ "encoder.block.19.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
111
+ "encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
112
+ "encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
113
+ "encoder.block.19.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
114
+ "encoder.block.19.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
115
+ "encoder.block.2.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
116
+ "encoder.block.2.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
117
+ "encoder.block.2.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
118
+ "encoder.block.2.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
119
+ "encoder.block.2.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
120
+ "encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
121
+ "encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
122
+ "encoder.block.2.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
123
+ "encoder.block.2.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
124
+ "encoder.block.20.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
125
+ "encoder.block.20.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
126
+ "encoder.block.20.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
127
+ "encoder.block.20.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
128
+ "encoder.block.20.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
129
+ "encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
130
+ "encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
131
+ "encoder.block.20.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
132
+ "encoder.block.20.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
133
+ "encoder.block.21.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
134
+ "encoder.block.21.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
135
+ "encoder.block.21.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
136
+ "encoder.block.21.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
137
+ "encoder.block.21.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
138
+ "encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
139
+ "encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
140
+ "encoder.block.21.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
141
+ "encoder.block.21.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
142
+ "encoder.block.22.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
143
+ "encoder.block.22.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
144
+ "encoder.block.22.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
145
+ "encoder.block.22.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
146
+ "encoder.block.22.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
147
+ "encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
148
+ "encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
149
+ "encoder.block.22.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
150
+ "encoder.block.22.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
151
+ "encoder.block.23.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
152
+ "encoder.block.23.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
153
+ "encoder.block.23.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
154
+ "encoder.block.23.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
155
+ "encoder.block.23.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
156
+ "encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
157
+ "encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
158
+ "encoder.block.23.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
159
+ "encoder.block.23.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
160
+ "encoder.block.3.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
161
+ "encoder.block.3.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
162
+ "encoder.block.3.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
163
+ "encoder.block.3.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
164
+ "encoder.block.3.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
165
+ "encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
166
+ "encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
167
+ "encoder.block.3.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
168
+ "encoder.block.3.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
169
+ "encoder.block.4.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
170
+ "encoder.block.4.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
171
+ "encoder.block.4.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
172
+ "encoder.block.4.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
173
+ "encoder.block.4.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
174
+ "encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
175
+ "encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
176
+ "encoder.block.4.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
177
+ "encoder.block.4.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
178
+ "encoder.block.5.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
179
+ "encoder.block.5.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
180
+ "encoder.block.5.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
181
+ "encoder.block.5.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
182
+ "encoder.block.5.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
183
+ "encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
184
+ "encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
185
+ "encoder.block.5.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
186
+ "encoder.block.5.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
187
+ "encoder.block.6.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
188
+ "encoder.block.6.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
189
+ "encoder.block.6.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
190
+ "encoder.block.6.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
191
+ "encoder.block.6.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
192
+ "encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
193
+ "encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
194
+ "encoder.block.6.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
195
+ "encoder.block.6.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
196
+ "encoder.block.7.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
197
+ "encoder.block.7.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
198
+ "encoder.block.7.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
199
+ "encoder.block.7.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
200
+ "encoder.block.7.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
201
+ "encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
202
+ "encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
203
+ "encoder.block.7.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
204
+ "encoder.block.7.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
205
+ "encoder.block.8.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
206
+ "encoder.block.8.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
207
+ "encoder.block.8.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
208
+ "encoder.block.8.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
209
+ "encoder.block.8.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
210
+ "encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
211
+ "encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
212
+ "encoder.block.8.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
213
+ "encoder.block.8.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
214
+ "encoder.block.9.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
215
+ "encoder.block.9.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
216
+ "encoder.block.9.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
217
+ "encoder.block.9.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
218
+ "encoder.block.9.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
219
+ "encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
220
+ "encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
221
+ "encoder.block.9.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
222
+ "encoder.block.9.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
223
+ "encoder.final_layer_norm.weight": "model-00002-of-00002.safetensors",
224
+ "shared.weight": "model-00001-of-00002.safetensors"
225
+ }
226
+ }
bfloat16/tokenizer_2/special_tokens_map.json ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<extra_id_0>",
4
+ "<extra_id_1>",
5
+ "<extra_id_2>",
6
+ "<extra_id_3>",
7
+ "<extra_id_4>",
8
+ "<extra_id_5>",
9
+ "<extra_id_6>",
10
+ "<extra_id_7>",
11
+ "<extra_id_8>",
12
+ "<extra_id_9>",
13
+ "<extra_id_10>",
14
+ "<extra_id_11>",
15
+ "<extra_id_12>",
16
+ "<extra_id_13>",
17
+ "<extra_id_14>",
18
+ "<extra_id_15>",
19
+ "<extra_id_16>",
20
+ "<extra_id_17>",
21
+ "<extra_id_18>",
22
+ "<extra_id_19>",
23
+ "<extra_id_20>",
24
+ "<extra_id_21>",
25
+ "<extra_id_22>",
26
+ "<extra_id_23>",
27
+ "<extra_id_24>",
28
+ "<extra_id_25>",
29
+ "<extra_id_26>",
30
+ "<extra_id_27>",
31
+ "<extra_id_28>",
32
+ "<extra_id_29>",
33
+ "<extra_id_30>",
34
+ "<extra_id_31>",
35
+ "<extra_id_32>",
36
+ "<extra_id_33>",
37
+ "<extra_id_34>",
38
+ "<extra_id_35>",
39
+ "<extra_id_36>",
40
+ "<extra_id_37>",
41
+ "<extra_id_38>",
42
+ "<extra_id_39>",
43
+ "<extra_id_40>",
44
+ "<extra_id_41>",
45
+ "<extra_id_42>",
46
+ "<extra_id_43>",
47
+ "<extra_id_44>",
48
+ "<extra_id_45>",
49
+ "<extra_id_46>",
50
+ "<extra_id_47>",
51
+ "<extra_id_48>",
52
+ "<extra_id_49>",
53
+ "<extra_id_50>",
54
+ "<extra_id_51>",
55
+ "<extra_id_52>",
56
+ "<extra_id_53>",
57
+ "<extra_id_54>",
58
+ "<extra_id_55>",
59
+ "<extra_id_56>",
60
+ "<extra_id_57>",
61
+ "<extra_id_58>",
62
+ "<extra_id_59>",
63
+ "<extra_id_60>",
64
+ "<extra_id_61>",
65
+ "<extra_id_62>",
66
+ "<extra_id_63>",
67
+ "<extra_id_64>",
68
+ "<extra_id_65>",
69
+ "<extra_id_66>",
70
+ "<extra_id_67>",
71
+ "<extra_id_68>",
72
+ "<extra_id_69>",
73
+ "<extra_id_70>",
74
+ "<extra_id_71>",
75
+ "<extra_id_72>",
76
+ "<extra_id_73>",
77
+ "<extra_id_74>",
78
+ "<extra_id_75>",
79
+ "<extra_id_76>",
80
+ "<extra_id_77>",
81
+ "<extra_id_78>",
82
+ "<extra_id_79>",
83
+ "<extra_id_80>",
84
+ "<extra_id_81>",
85
+ "<extra_id_82>",
86
+ "<extra_id_83>",
87
+ "<extra_id_84>",
88
+ "<extra_id_85>",
89
+ "<extra_id_86>",
90
+ "<extra_id_87>",
91
+ "<extra_id_88>",
92
+ "<extra_id_89>",
93
+ "<extra_id_90>",
94
+ "<extra_id_91>",
95
+ "<extra_id_92>",
96
+ "<extra_id_93>",
97
+ "<extra_id_94>",
98
+ "<extra_id_95>",
99
+ "<extra_id_96>",
100
+ "<extra_id_97>",
101
+ "<extra_id_98>",
102
+ "<extra_id_99>"
103
+ ],
104
+ "eos_token": {
105
+ "content": "</s>",
106
+ "lstrip": false,
107
+ "normalized": false,
108
+ "rstrip": false,
109
+ "single_word": false
110
+ },
111
+ "pad_token": {
112
+ "content": "<pad>",
113
+ "lstrip": false,
114
+ "normalized": false,
115
+ "rstrip": false,
116
+ "single_word": false
117
+ },
118
+ "unk_token": {
119
+ "content": "<unk>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false
124
+ }
125
+ }
bfloat16/tokenizer_2/spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
3
+ size 791656
bfloat16/tokenizer_2/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
bfloat16/tokenizer_2/tokenizer_config.json ADDED
@@ -0,0 +1,940 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "32000": {
29
+ "content": "<extra_id_99>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "32001": {
37
+ "content": "<extra_id_98>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "32002": {
45
+ "content": "<extra_id_97>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "32003": {
53
+ "content": "<extra_id_96>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "32004": {
61
+ "content": "<extra_id_95>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "32005": {
69
+ "content": "<extra_id_94>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "32006": {
77
+ "content": "<extra_id_93>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "32007": {
85
+ "content": "<extra_id_92>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "32008": {
93
+ "content": "<extra_id_91>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "32009": {
101
+ "content": "<extra_id_90>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "32010": {
109
+ "content": "<extra_id_89>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "32011": {
117
+ "content": "<extra_id_88>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "32012": {
125
+ "content": "<extra_id_87>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "32013": {
133
+ "content": "<extra_id_86>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "32014": {
141
+ "content": "<extra_id_85>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "32015": {
149
+ "content": "<extra_id_84>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "32016": {
157
+ "content": "<extra_id_83>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "32017": {
165
+ "content": "<extra_id_82>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "32018": {
173
+ "content": "<extra_id_81>",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "32019": {
181
+ "content": "<extra_id_80>",
182
+ "lstrip": false,
183
+ "normalized": false,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": true
187
+ },
188
+ "32020": {
189
+ "content": "<extra_id_79>",
190
+ "lstrip": false,
191
+ "normalized": false,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": true
195
+ },
196
+ "32021": {
197
+ "content": "<extra_id_78>",
198
+ "lstrip": false,
199
+ "normalized": false,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": true
203
+ },
204
+ "32022": {
205
+ "content": "<extra_id_77>",
206
+ "lstrip": false,
207
+ "normalized": false,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "32023": {
213
+ "content": "<extra_id_76>",
214
+ "lstrip": false,
215
+ "normalized": false,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "32024": {
221
+ "content": "<extra_id_75>",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "32025": {
229
+ "content": "<extra_id_74>",
230
+ "lstrip": false,
231
+ "normalized": false,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "32026": {
237
+ "content": "<extra_id_73>",
238
+ "lstrip": false,
239
+ "normalized": false,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "32027": {
245
+ "content": "<extra_id_72>",
246
+ "lstrip": false,
247
+ "normalized": false,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "32028": {
253
+ "content": "<extra_id_71>",
254
+ "lstrip": false,
255
+ "normalized": false,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "32029": {
261
+ "content": "<extra_id_70>",
262
+ "lstrip": false,
263
+ "normalized": false,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": true
267
+ },
268
+ "32030": {
269
+ "content": "<extra_id_69>",
270
+ "lstrip": false,
271
+ "normalized": false,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": true
275
+ },
276
+ "32031": {
277
+ "content": "<extra_id_68>",
278
+ "lstrip": false,
279
+ "normalized": false,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": true
283
+ },
284
+ "32032": {
285
+ "content": "<extra_id_67>",
286
+ "lstrip": false,
287
+ "normalized": false,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": true
291
+ },
292
+ "32033": {
293
+ "content": "<extra_id_66>",
294
+ "lstrip": false,
295
+ "normalized": false,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": true
299
+ },
300
+ "32034": {
301
+ "content": "<extra_id_65>",
302
+ "lstrip": false,
303
+ "normalized": false,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": true
307
+ },
308
+ "32035": {
309
+ "content": "<extra_id_64>",
310
+ "lstrip": false,
311
+ "normalized": false,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": true
315
+ },
316
+ "32036": {
317
+ "content": "<extra_id_63>",
318
+ "lstrip": false,
319
+ "normalized": false,
320
+ "rstrip": false,
321
+ "single_word": false,
322
+ "special": true
323
+ },
324
+ "32037": {
325
+ "content": "<extra_id_62>",
326
+ "lstrip": false,
327
+ "normalized": false,
328
+ "rstrip": false,
329
+ "single_word": false,
330
+ "special": true
331
+ },
332
+ "32038": {
333
+ "content": "<extra_id_61>",
334
+ "lstrip": false,
335
+ "normalized": false,
336
+ "rstrip": false,
337
+ "single_word": false,
338
+ "special": true
339
+ },
340
+ "32039": {
341
+ "content": "<extra_id_60>",
342
+ "lstrip": false,
343
+ "normalized": false,
344
+ "rstrip": false,
345
+ "single_word": false,
346
+ "special": true
347
+ },
348
+ "32040": {
349
+ "content": "<extra_id_59>",
350
+ "lstrip": false,
351
+ "normalized": false,
352
+ "rstrip": false,
353
+ "single_word": false,
354
+ "special": true
355
+ },
356
+ "32041": {
357
+ "content": "<extra_id_58>",
358
+ "lstrip": false,
359
+ "normalized": false,
360
+ "rstrip": false,
361
+ "single_word": false,
362
+ "special": true
363
+ },
364
+ "32042": {
365
+ "content": "<extra_id_57>",
366
+ "lstrip": false,
367
+ "normalized": false,
368
+ "rstrip": false,
369
+ "single_word": false,
370
+ "special": true
371
+ },
372
+ "32043": {
373
+ "content": "<extra_id_56>",
374
+ "lstrip": false,
375
+ "normalized": false,
376
+ "rstrip": false,
377
+ "single_word": false,
378
+ "special": true
379
+ },
380
+ "32044": {
381
+ "content": "<extra_id_55>",
382
+ "lstrip": false,
383
+ "normalized": false,
384
+ "rstrip": false,
385
+ "single_word": false,
386
+ "special": true
387
+ },
388
+ "32045": {
389
+ "content": "<extra_id_54>",
390
+ "lstrip": false,
391
+ "normalized": false,
392
+ "rstrip": false,
393
+ "single_word": false,
394
+ "special": true
395
+ },
396
+ "32046": {
397
+ "content": "<extra_id_53>",
398
+ "lstrip": false,
399
+ "normalized": false,
400
+ "rstrip": false,
401
+ "single_word": false,
402
+ "special": true
403
+ },
404
+ "32047": {
405
+ "content": "<extra_id_52>",
406
+ "lstrip": false,
407
+ "normalized": false,
408
+ "rstrip": false,
409
+ "single_word": false,
410
+ "special": true
411
+ },
412
+ "32048": {
413
+ "content": "<extra_id_51>",
414
+ "lstrip": false,
415
+ "normalized": false,
416
+ "rstrip": false,
417
+ "single_word": false,
418
+ "special": true
419
+ },
420
+ "32049": {
421
+ "content": "<extra_id_50>",
422
+ "lstrip": false,
423
+ "normalized": false,
424
+ "rstrip": false,
425
+ "single_word": false,
426
+ "special": true
427
+ },
428
+ "32050": {
429
+ "content": "<extra_id_49>",
430
+ "lstrip": false,
431
+ "normalized": false,
432
+ "rstrip": false,
433
+ "single_word": false,
434
+ "special": true
435
+ },
436
+ "32051": {
437
+ "content": "<extra_id_48>",
438
+ "lstrip": false,
439
+ "normalized": false,
440
+ "rstrip": false,
441
+ "single_word": false,
442
+ "special": true
443
+ },
444
+ "32052": {
445
+ "content": "<extra_id_47>",
446
+ "lstrip": false,
447
+ "normalized": false,
448
+ "rstrip": false,
449
+ "single_word": false,
450
+ "special": true
451
+ },
452
+ "32053": {
453
+ "content": "<extra_id_46>",
454
+ "lstrip": false,
455
+ "normalized": false,
456
+ "rstrip": false,
457
+ "single_word": false,
458
+ "special": true
459
+ },
460
+ "32054": {
461
+ "content": "<extra_id_45>",
462
+ "lstrip": false,
463
+ "normalized": false,
464
+ "rstrip": false,
465
+ "single_word": false,
466
+ "special": true
467
+ },
468
+ "32055": {
469
+ "content": "<extra_id_44>",
470
+ "lstrip": false,
471
+ "normalized": false,
472
+ "rstrip": false,
473
+ "single_word": false,
474
+ "special": true
475
+ },
476
+ "32056": {
477
+ "content": "<extra_id_43>",
478
+ "lstrip": false,
479
+ "normalized": false,
480
+ "rstrip": false,
481
+ "single_word": false,
482
+ "special": true
483
+ },
484
+ "32057": {
485
+ "content": "<extra_id_42>",
486
+ "lstrip": false,
487
+ "normalized": false,
488
+ "rstrip": false,
489
+ "single_word": false,
490
+ "special": true
491
+ },
492
+ "32058": {
493
+ "content": "<extra_id_41>",
494
+ "lstrip": false,
495
+ "normalized": false,
496
+ "rstrip": false,
497
+ "single_word": false,
498
+ "special": true
499
+ },
500
+ "32059": {
501
+ "content": "<extra_id_40>",
502
+ "lstrip": false,
503
+ "normalized": false,
504
+ "rstrip": false,
505
+ "single_word": false,
506
+ "special": true
507
+ },
508
+ "32060": {
509
+ "content": "<extra_id_39>",
510
+ "lstrip": false,
511
+ "normalized": false,
512
+ "rstrip": false,
513
+ "single_word": false,
514
+ "special": true
515
+ },
516
+ "32061": {
517
+ "content": "<extra_id_38>",
518
+ "lstrip": false,
519
+ "normalized": false,
520
+ "rstrip": false,
521
+ "single_word": false,
522
+ "special": true
523
+ },
524
+ "32062": {
525
+ "content": "<extra_id_37>",
526
+ "lstrip": false,
527
+ "normalized": false,
528
+ "rstrip": false,
529
+ "single_word": false,
530
+ "special": true
531
+ },
532
+ "32063": {
533
+ "content": "<extra_id_36>",
534
+ "lstrip": false,
535
+ "normalized": false,
536
+ "rstrip": false,
537
+ "single_word": false,
538
+ "special": true
539
+ },
540
+ "32064": {
541
+ "content": "<extra_id_35>",
542
+ "lstrip": false,
543
+ "normalized": false,
544
+ "rstrip": false,
545
+ "single_word": false,
546
+ "special": true
547
+ },
548
+ "32065": {
549
+ "content": "<extra_id_34>",
550
+ "lstrip": false,
551
+ "normalized": false,
552
+ "rstrip": false,
553
+ "single_word": false,
554
+ "special": true
555
+ },
556
+ "32066": {
557
+ "content": "<extra_id_33>",
558
+ "lstrip": false,
559
+ "normalized": false,
560
+ "rstrip": false,
561
+ "single_word": false,
562
+ "special": true
563
+ },
564
+ "32067": {
565
+ "content": "<extra_id_32>",
566
+ "lstrip": false,
567
+ "normalized": false,
568
+ "rstrip": false,
569
+ "single_word": false,
570
+ "special": true
571
+ },
572
+ "32068": {
573
+ "content": "<extra_id_31>",
574
+ "lstrip": false,
575
+ "normalized": false,
576
+ "rstrip": false,
577
+ "single_word": false,
578
+ "special": true
579
+ },
580
+ "32069": {
581
+ "content": "<extra_id_30>",
582
+ "lstrip": false,
583
+ "normalized": false,
584
+ "rstrip": false,
585
+ "single_word": false,
586
+ "special": true
587
+ },
588
+ "32070": {
589
+ "content": "<extra_id_29>",
590
+ "lstrip": false,
591
+ "normalized": false,
592
+ "rstrip": false,
593
+ "single_word": false,
594
+ "special": true
595
+ },
596
+ "32071": {
597
+ "content": "<extra_id_28>",
598
+ "lstrip": false,
599
+ "normalized": false,
600
+ "rstrip": false,
601
+ "single_word": false,
602
+ "special": true
603
+ },
604
+ "32072": {
605
+ "content": "<extra_id_27>",
606
+ "lstrip": false,
607
+ "normalized": false,
608
+ "rstrip": false,
609
+ "single_word": false,
610
+ "special": true
611
+ },
612
+ "32073": {
613
+ "content": "<extra_id_26>",
614
+ "lstrip": false,
615
+ "normalized": false,
616
+ "rstrip": false,
617
+ "single_word": false,
618
+ "special": true
619
+ },
620
+ "32074": {
621
+ "content": "<extra_id_25>",
622
+ "lstrip": false,
623
+ "normalized": false,
624
+ "rstrip": false,
625
+ "single_word": false,
626
+ "special": true
627
+ },
628
+ "32075": {
629
+ "content": "<extra_id_24>",
630
+ "lstrip": false,
631
+ "normalized": false,
632
+ "rstrip": false,
633
+ "single_word": false,
634
+ "special": true
635
+ },
636
+ "32076": {
637
+ "content": "<extra_id_23>",
638
+ "lstrip": false,
639
+ "normalized": false,
640
+ "rstrip": false,
641
+ "single_word": false,
642
+ "special": true
643
+ },
644
+ "32077": {
645
+ "content": "<extra_id_22>",
646
+ "lstrip": false,
647
+ "normalized": false,
648
+ "rstrip": false,
649
+ "single_word": false,
650
+ "special": true
651
+ },
652
+ "32078": {
653
+ "content": "<extra_id_21>",
654
+ "lstrip": false,
655
+ "normalized": false,
656
+ "rstrip": false,
657
+ "single_word": false,
658
+ "special": true
659
+ },
660
+ "32079": {
661
+ "content": "<extra_id_20>",
662
+ "lstrip": false,
663
+ "normalized": false,
664
+ "rstrip": false,
665
+ "single_word": false,
666
+ "special": true
667
+ },
668
+ "32080": {
669
+ "content": "<extra_id_19>",
670
+ "lstrip": false,
671
+ "normalized": false,
672
+ "rstrip": false,
673
+ "single_word": false,
674
+ "special": true
675
+ },
676
+ "32081": {
677
+ "content": "<extra_id_18>",
678
+ "lstrip": false,
679
+ "normalized": false,
680
+ "rstrip": false,
681
+ "single_word": false,
682
+ "special": true
683
+ },
684
+ "32082": {
685
+ "content": "<extra_id_17>",
686
+ "lstrip": false,
687
+ "normalized": false,
688
+ "rstrip": false,
689
+ "single_word": false,
690
+ "special": true
691
+ },
692
+ "32083": {
693
+ "content": "<extra_id_16>",
694
+ "lstrip": false,
695
+ "normalized": false,
696
+ "rstrip": false,
697
+ "single_word": false,
698
+ "special": true
699
+ },
700
+ "32084": {
701
+ "content": "<extra_id_15>",
702
+ "lstrip": false,
703
+ "normalized": false,
704
+ "rstrip": false,
705
+ "single_word": false,
706
+ "special": true
707
+ },
708
+ "32085": {
709
+ "content": "<extra_id_14>",
710
+ "lstrip": false,
711
+ "normalized": false,
712
+ "rstrip": false,
713
+ "single_word": false,
714
+ "special": true
715
+ },
716
+ "32086": {
717
+ "content": "<extra_id_13>",
718
+ "lstrip": false,
719
+ "normalized": false,
720
+ "rstrip": false,
721
+ "single_word": false,
722
+ "special": true
723
+ },
724
+ "32087": {
725
+ "content": "<extra_id_12>",
726
+ "lstrip": false,
727
+ "normalized": false,
728
+ "rstrip": false,
729
+ "single_word": false,
730
+ "special": true
731
+ },
732
+ "32088": {
733
+ "content": "<extra_id_11>",
734
+ "lstrip": false,
735
+ "normalized": false,
736
+ "rstrip": false,
737
+ "single_word": false,
738
+ "special": true
739
+ },
740
+ "32089": {
741
+ "content": "<extra_id_10>",
742
+ "lstrip": false,
743
+ "normalized": false,
744
+ "rstrip": false,
745
+ "single_word": false,
746
+ "special": true
747
+ },
748
+ "32090": {
749
+ "content": "<extra_id_9>",
750
+ "lstrip": false,
751
+ "normalized": false,
752
+ "rstrip": false,
753
+ "single_word": false,
754
+ "special": true
755
+ },
756
+ "32091": {
757
+ "content": "<extra_id_8>",
758
+ "lstrip": false,
759
+ "normalized": false,
760
+ "rstrip": false,
761
+ "single_word": false,
762
+ "special": true
763
+ },
764
+ "32092": {
765
+ "content": "<extra_id_7>",
766
+ "lstrip": false,
767
+ "normalized": false,
768
+ "rstrip": false,
769
+ "single_word": false,
770
+ "special": true
771
+ },
772
+ "32093": {
773
+ "content": "<extra_id_6>",
774
+ "lstrip": false,
775
+ "normalized": false,
776
+ "rstrip": false,
777
+ "single_word": false,
778
+ "special": true
779
+ },
780
+ "32094": {
781
+ "content": "<extra_id_5>",
782
+ "lstrip": false,
783
+ "normalized": false,
784
+ "rstrip": false,
785
+ "single_word": false,
786
+ "special": true
787
+ },
788
+ "32095": {
789
+ "content": "<extra_id_4>",
790
+ "lstrip": false,
791
+ "normalized": false,
792
+ "rstrip": false,
793
+ "single_word": false,
794
+ "special": true
795
+ },
796
+ "32096": {
797
+ "content": "<extra_id_3>",
798
+ "lstrip": false,
799
+ "normalized": false,
800
+ "rstrip": false,
801
+ "single_word": false,
802
+ "special": true
803
+ },
804
+ "32097": {
805
+ "content": "<extra_id_2>",
806
+ "lstrip": false,
807
+ "normalized": false,
808
+ "rstrip": false,
809
+ "single_word": false,
810
+ "special": true
811
+ },
812
+ "32098": {
813
+ "content": "<extra_id_1>",
814
+ "lstrip": false,
815
+ "normalized": false,
816
+ "rstrip": false,
817
+ "single_word": false,
818
+ "special": true
819
+ },
820
+ "32099": {
821
+ "content": "<extra_id_0>",
822
+ "lstrip": false,
823
+ "normalized": false,
824
+ "rstrip": false,
825
+ "single_word": false,
826
+ "special": true
827
+ }
828
+ },
829
+ "additional_special_tokens": [
830
+ "<extra_id_0>",
831
+ "<extra_id_1>",
832
+ "<extra_id_2>",
833
+ "<extra_id_3>",
834
+ "<extra_id_4>",
835
+ "<extra_id_5>",
836
+ "<extra_id_6>",
837
+ "<extra_id_7>",
838
+ "<extra_id_8>",
839
+ "<extra_id_9>",
840
+ "<extra_id_10>",
841
+ "<extra_id_11>",
842
+ "<extra_id_12>",
843
+ "<extra_id_13>",
844
+ "<extra_id_14>",
845
+ "<extra_id_15>",
846
+ "<extra_id_16>",
847
+ "<extra_id_17>",
848
+ "<extra_id_18>",
849
+ "<extra_id_19>",
850
+ "<extra_id_20>",
851
+ "<extra_id_21>",
852
+ "<extra_id_22>",
853
+ "<extra_id_23>",
854
+ "<extra_id_24>",
855
+ "<extra_id_25>",
856
+ "<extra_id_26>",
857
+ "<extra_id_27>",
858
+ "<extra_id_28>",
859
+ "<extra_id_29>",
860
+ "<extra_id_30>",
861
+ "<extra_id_31>",
862
+ "<extra_id_32>",
863
+ "<extra_id_33>",
864
+ "<extra_id_34>",
865
+ "<extra_id_35>",
866
+ "<extra_id_36>",
867
+ "<extra_id_37>",
868
+ "<extra_id_38>",
869
+ "<extra_id_39>",
870
+ "<extra_id_40>",
871
+ "<extra_id_41>",
872
+ "<extra_id_42>",
873
+ "<extra_id_43>",
874
+ "<extra_id_44>",
875
+ "<extra_id_45>",
876
+ "<extra_id_46>",
877
+ "<extra_id_47>",
878
+ "<extra_id_48>",
879
+ "<extra_id_49>",
880
+ "<extra_id_50>",
881
+ "<extra_id_51>",
882
+ "<extra_id_52>",
883
+ "<extra_id_53>",
884
+ "<extra_id_54>",
885
+ "<extra_id_55>",
886
+ "<extra_id_56>",
887
+ "<extra_id_57>",
888
+ "<extra_id_58>",
889
+ "<extra_id_59>",
890
+ "<extra_id_60>",
891
+ "<extra_id_61>",
892
+ "<extra_id_62>",
893
+ "<extra_id_63>",
894
+ "<extra_id_64>",
895
+ "<extra_id_65>",
896
+ "<extra_id_66>",
897
+ "<extra_id_67>",
898
+ "<extra_id_68>",
899
+ "<extra_id_69>",
900
+ "<extra_id_70>",
901
+ "<extra_id_71>",
902
+ "<extra_id_72>",
903
+ "<extra_id_73>",
904
+ "<extra_id_74>",
905
+ "<extra_id_75>",
906
+ "<extra_id_76>",
907
+ "<extra_id_77>",
908
+ "<extra_id_78>",
909
+ "<extra_id_79>",
910
+ "<extra_id_80>",
911
+ "<extra_id_81>",
912
+ "<extra_id_82>",
913
+ "<extra_id_83>",
914
+ "<extra_id_84>",
915
+ "<extra_id_85>",
916
+ "<extra_id_86>",
917
+ "<extra_id_87>",
918
+ "<extra_id_88>",
919
+ "<extra_id_89>",
920
+ "<extra_id_90>",
921
+ "<extra_id_91>",
922
+ "<extra_id_92>",
923
+ "<extra_id_93>",
924
+ "<extra_id_94>",
925
+ "<extra_id_95>",
926
+ "<extra_id_96>",
927
+ "<extra_id_97>",
928
+ "<extra_id_98>",
929
+ "<extra_id_99>"
930
+ ],
931
+ "clean_up_tokenization_spaces": true,
932
+ "eos_token": "</s>",
933
+ "extra_ids": 100,
934
+ "legacy": true,
935
+ "model_max_length": 512,
936
+ "pad_token": "<pad>",
937
+ "sp_model_kwargs": {},
938
+ "tokenizer_class": "T5Tokenizer",
939
+ "unk_token": "<unk>"
940
+ }
optimum_quanto_qfloat8/text_encoder_2/config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/data/invokeai/models/.download_cache/black-forest-labs_flux.1-schnell/FLUX.1-schnell/text_encoder_2",
3
+ "architectures": [
4
+ "T5EncoderModel"
5
+ ],
6
+ "classifier_dropout": 0.0,
7
+ "d_ff": 10240,
8
+ "d_kv": 64,
9
+ "d_model": 4096,
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": "t5",
20
+ "num_decoder_layers": 24,
21
+ "num_heads": 64,
22
+ "num_layers": 24,
23
+ "output_past": true,
24
+ "pad_token_id": 0,
25
+ "relative_attention_max_distance": 128,
26
+ "relative_attention_num_buckets": 32,
27
+ "tie_word_embeddings": false,
28
+ "torch_dtype": "float32",
29
+ "transformers_version": "4.41.1",
30
+ "use_cache": true,
31
+ "vocab_size": 32128
32
+ }
optimum_quanto_qfloat8/text_encoder_2/model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05c4989e6df2d117d598cd5627e59c0ae99222059a9be6b53e116022a80b2bbb
3
+ size 4985368760
optimum_quanto_qfloat8/text_encoder_2/model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b70862008db43ad5b114b6e404f02bfc9b39abad0ab3b13f40d996f8090f53db
3
+ size 176360656
optimum_quanto_qfloat8/text_encoder_2/model.safetensors.index.json ADDED
@@ -0,0 +1,730 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 5161641280
4
+ },
5
+ "weight_map": {
6
+ "encoder.block.0.layer.0.SelfAttention.k.input_scale": "model-00001-of-00002.safetensors",
7
+ "encoder.block.0.layer.0.SelfAttention.k.output_scale": "model-00001-of-00002.safetensors",
8
+ "encoder.block.0.layer.0.SelfAttention.k.weight._data": "model-00001-of-00002.safetensors",
9
+ "encoder.block.0.layer.0.SelfAttention.k.weight._scale": "model-00001-of-00002.safetensors",
10
+ "encoder.block.0.layer.0.SelfAttention.o.input_scale": "model-00001-of-00002.safetensors",
11
+ "encoder.block.0.layer.0.SelfAttention.o.output_scale": "model-00001-of-00002.safetensors",
12
+ "encoder.block.0.layer.0.SelfAttention.o.weight._data": "model-00001-of-00002.safetensors",
13
+ "encoder.block.0.layer.0.SelfAttention.o.weight._scale": "model-00001-of-00002.safetensors",
14
+ "encoder.block.0.layer.0.SelfAttention.q.input_scale": "model-00001-of-00002.safetensors",
15
+ "encoder.block.0.layer.0.SelfAttention.q.output_scale": "model-00001-of-00002.safetensors",
16
+ "encoder.block.0.layer.0.SelfAttention.q.weight._data": "model-00001-of-00002.safetensors",
17
+ "encoder.block.0.layer.0.SelfAttention.q.weight._scale": "model-00001-of-00002.safetensors",
18
+ "encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00002.safetensors",
19
+ "encoder.block.0.layer.0.SelfAttention.v.input_scale": "model-00001-of-00002.safetensors",
20
+ "encoder.block.0.layer.0.SelfAttention.v.output_scale": "model-00001-of-00002.safetensors",
21
+ "encoder.block.0.layer.0.SelfAttention.v.weight._data": "model-00001-of-00002.safetensors",
22
+ "encoder.block.0.layer.0.SelfAttention.v.weight._scale": "model-00001-of-00002.safetensors",
23
+ "encoder.block.0.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
24
+ "encoder.block.0.layer.1.DenseReluDense.wi_0.input_scale": "model-00001-of-00002.safetensors",
25
+ "encoder.block.0.layer.1.DenseReluDense.wi_0.output_scale": "model-00001-of-00002.safetensors",
26
+ "encoder.block.0.layer.1.DenseReluDense.wi_0.weight._data": "model-00001-of-00002.safetensors",
27
+ "encoder.block.0.layer.1.DenseReluDense.wi_0.weight._scale": "model-00001-of-00002.safetensors",
28
+ "encoder.block.0.layer.1.DenseReluDense.wi_1.input_scale": "model-00001-of-00002.safetensors",
29
+ "encoder.block.0.layer.1.DenseReluDense.wi_1.output_scale": "model-00001-of-00002.safetensors",
30
+ "encoder.block.0.layer.1.DenseReluDense.wi_1.weight._data": "model-00001-of-00002.safetensors",
31
+ "encoder.block.0.layer.1.DenseReluDense.wi_1.weight._scale": "model-00001-of-00002.safetensors",
32
+ "encoder.block.0.layer.1.DenseReluDense.wo.input_scale": "model-00001-of-00002.safetensors",
33
+ "encoder.block.0.layer.1.DenseReluDense.wo.output_scale": "model-00001-of-00002.safetensors",
34
+ "encoder.block.0.layer.1.DenseReluDense.wo.weight._data": "model-00001-of-00002.safetensors",
35
+ "encoder.block.0.layer.1.DenseReluDense.wo.weight._scale": "model-00001-of-00002.safetensors",
36
+ "encoder.block.0.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
37
+ "encoder.block.1.layer.0.SelfAttention.k.input_scale": "model-00001-of-00002.safetensors",
38
+ "encoder.block.1.layer.0.SelfAttention.k.output_scale": "model-00001-of-00002.safetensors",
39
+ "encoder.block.1.layer.0.SelfAttention.k.weight._data": "model-00001-of-00002.safetensors",
40
+ "encoder.block.1.layer.0.SelfAttention.k.weight._scale": "model-00001-of-00002.safetensors",
41
+ "encoder.block.1.layer.0.SelfAttention.o.input_scale": "model-00001-of-00002.safetensors",
42
+ "encoder.block.1.layer.0.SelfAttention.o.output_scale": "model-00001-of-00002.safetensors",
43
+ "encoder.block.1.layer.0.SelfAttention.o.weight._data": "model-00001-of-00002.safetensors",
44
+ "encoder.block.1.layer.0.SelfAttention.o.weight._scale": "model-00001-of-00002.safetensors",
45
+ "encoder.block.1.layer.0.SelfAttention.q.input_scale": "model-00001-of-00002.safetensors",
46
+ "encoder.block.1.layer.0.SelfAttention.q.output_scale": "model-00001-of-00002.safetensors",
47
+ "encoder.block.1.layer.0.SelfAttention.q.weight._data": "model-00001-of-00002.safetensors",
48
+ "encoder.block.1.layer.0.SelfAttention.q.weight._scale": "model-00001-of-00002.safetensors",
49
+ "encoder.block.1.layer.0.SelfAttention.v.input_scale": "model-00001-of-00002.safetensors",
50
+ "encoder.block.1.layer.0.SelfAttention.v.output_scale": "model-00001-of-00002.safetensors",
51
+ "encoder.block.1.layer.0.SelfAttention.v.weight._data": "model-00001-of-00002.safetensors",
52
+ "encoder.block.1.layer.0.SelfAttention.v.weight._scale": "model-00001-of-00002.safetensors",
53
+ "encoder.block.1.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
54
+ "encoder.block.1.layer.1.DenseReluDense.wi_0.input_scale": "model-00001-of-00002.safetensors",
55
+ "encoder.block.1.layer.1.DenseReluDense.wi_0.output_scale": "model-00001-of-00002.safetensors",
56
+ "encoder.block.1.layer.1.DenseReluDense.wi_0.weight._data": "model-00001-of-00002.safetensors",
57
+ "encoder.block.1.layer.1.DenseReluDense.wi_0.weight._scale": "model-00001-of-00002.safetensors",
58
+ "encoder.block.1.layer.1.DenseReluDense.wi_1.input_scale": "model-00001-of-00002.safetensors",
59
+ "encoder.block.1.layer.1.DenseReluDense.wi_1.output_scale": "model-00001-of-00002.safetensors",
60
+ "encoder.block.1.layer.1.DenseReluDense.wi_1.weight._data": "model-00001-of-00002.safetensors",
61
+ "encoder.block.1.layer.1.DenseReluDense.wi_1.weight._scale": "model-00001-of-00002.safetensors",
62
+ "encoder.block.1.layer.1.DenseReluDense.wo.input_scale": "model-00001-of-00002.safetensors",
63
+ "encoder.block.1.layer.1.DenseReluDense.wo.output_scale": "model-00001-of-00002.safetensors",
64
+ "encoder.block.1.layer.1.DenseReluDense.wo.weight._data": "model-00001-of-00002.safetensors",
65
+ "encoder.block.1.layer.1.DenseReluDense.wo.weight._scale": "model-00001-of-00002.safetensors",
66
+ "encoder.block.1.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
67
+ "encoder.block.10.layer.0.SelfAttention.k.input_scale": "model-00001-of-00002.safetensors",
68
+ "encoder.block.10.layer.0.SelfAttention.k.output_scale": "model-00001-of-00002.safetensors",
69
+ "encoder.block.10.layer.0.SelfAttention.k.weight._data": "model-00001-of-00002.safetensors",
70
+ "encoder.block.10.layer.0.SelfAttention.k.weight._scale": "model-00001-of-00002.safetensors",
71
+ "encoder.block.10.layer.0.SelfAttention.o.input_scale": "model-00001-of-00002.safetensors",
72
+ "encoder.block.10.layer.0.SelfAttention.o.output_scale": "model-00001-of-00002.safetensors",
73
+ "encoder.block.10.layer.0.SelfAttention.o.weight._data": "model-00001-of-00002.safetensors",
74
+ "encoder.block.10.layer.0.SelfAttention.o.weight._scale": "model-00001-of-00002.safetensors",
75
+ "encoder.block.10.layer.0.SelfAttention.q.input_scale": "model-00001-of-00002.safetensors",
76
+ "encoder.block.10.layer.0.SelfAttention.q.output_scale": "model-00001-of-00002.safetensors",
77
+ "encoder.block.10.layer.0.SelfAttention.q.weight._data": "model-00001-of-00002.safetensors",
78
+ "encoder.block.10.layer.0.SelfAttention.q.weight._scale": "model-00001-of-00002.safetensors",
79
+ "encoder.block.10.layer.0.SelfAttention.v.input_scale": "model-00001-of-00002.safetensors",
80
+ "encoder.block.10.layer.0.SelfAttention.v.output_scale": "model-00001-of-00002.safetensors",
81
+ "encoder.block.10.layer.0.SelfAttention.v.weight._data": "model-00001-of-00002.safetensors",
82
+ "encoder.block.10.layer.0.SelfAttention.v.weight._scale": "model-00001-of-00002.safetensors",
83
+ "encoder.block.10.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
84
+ "encoder.block.10.layer.1.DenseReluDense.wi_0.input_scale": "model-00001-of-00002.safetensors",
85
+ "encoder.block.10.layer.1.DenseReluDense.wi_0.output_scale": "model-00001-of-00002.safetensors",
86
+ "encoder.block.10.layer.1.DenseReluDense.wi_0.weight._data": "model-00001-of-00002.safetensors",
87
+ "encoder.block.10.layer.1.DenseReluDense.wi_0.weight._scale": "model-00001-of-00002.safetensors",
88
+ "encoder.block.10.layer.1.DenseReluDense.wi_1.input_scale": "model-00001-of-00002.safetensors",
89
+ "encoder.block.10.layer.1.DenseReluDense.wi_1.output_scale": "model-00001-of-00002.safetensors",
90
+ "encoder.block.10.layer.1.DenseReluDense.wi_1.weight._data": "model-00001-of-00002.safetensors",
91
+ "encoder.block.10.layer.1.DenseReluDense.wi_1.weight._scale": "model-00001-of-00002.safetensors",
92
+ "encoder.block.10.layer.1.DenseReluDense.wo.input_scale": "model-00001-of-00002.safetensors",
93
+ "encoder.block.10.layer.1.DenseReluDense.wo.output_scale": "model-00001-of-00002.safetensors",
94
+ "encoder.block.10.layer.1.DenseReluDense.wo.weight._data": "model-00001-of-00002.safetensors",
95
+ "encoder.block.10.layer.1.DenseReluDense.wo.weight._scale": "model-00001-of-00002.safetensors",
96
+ "encoder.block.10.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
97
+ "encoder.block.11.layer.0.SelfAttention.k.input_scale": "model-00001-of-00002.safetensors",
98
+ "encoder.block.11.layer.0.SelfAttention.k.output_scale": "model-00001-of-00002.safetensors",
99
+ "encoder.block.11.layer.0.SelfAttention.k.weight._data": "model-00001-of-00002.safetensors",
100
+ "encoder.block.11.layer.0.SelfAttention.k.weight._scale": "model-00001-of-00002.safetensors",
101
+ "encoder.block.11.layer.0.SelfAttention.o.input_scale": "model-00001-of-00002.safetensors",
102
+ "encoder.block.11.layer.0.SelfAttention.o.output_scale": "model-00001-of-00002.safetensors",
103
+ "encoder.block.11.layer.0.SelfAttention.o.weight._data": "model-00001-of-00002.safetensors",
104
+ "encoder.block.11.layer.0.SelfAttention.o.weight._scale": "model-00001-of-00002.safetensors",
105
+ "encoder.block.11.layer.0.SelfAttention.q.input_scale": "model-00001-of-00002.safetensors",
106
+ "encoder.block.11.layer.0.SelfAttention.q.output_scale": "model-00001-of-00002.safetensors",
107
+ "encoder.block.11.layer.0.SelfAttention.q.weight._data": "model-00001-of-00002.safetensors",
108
+ "encoder.block.11.layer.0.SelfAttention.q.weight._scale": "model-00001-of-00002.safetensors",
109
+ "encoder.block.11.layer.0.SelfAttention.v.input_scale": "model-00001-of-00002.safetensors",
110
+ "encoder.block.11.layer.0.SelfAttention.v.output_scale": "model-00001-of-00002.safetensors",
111
+ "encoder.block.11.layer.0.SelfAttention.v.weight._data": "model-00001-of-00002.safetensors",
112
+ "encoder.block.11.layer.0.SelfAttention.v.weight._scale": "model-00001-of-00002.safetensors",
113
+ "encoder.block.11.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
114
+ "encoder.block.11.layer.1.DenseReluDense.wi_0.input_scale": "model-00001-of-00002.safetensors",
115
+ "encoder.block.11.layer.1.DenseReluDense.wi_0.output_scale": "model-00001-of-00002.safetensors",
116
+ "encoder.block.11.layer.1.DenseReluDense.wi_0.weight._data": "model-00001-of-00002.safetensors",
117
+ "encoder.block.11.layer.1.DenseReluDense.wi_0.weight._scale": "model-00001-of-00002.safetensors",
118
+ "encoder.block.11.layer.1.DenseReluDense.wi_1.input_scale": "model-00001-of-00002.safetensors",
119
+ "encoder.block.11.layer.1.DenseReluDense.wi_1.output_scale": "model-00001-of-00002.safetensors",
120
+ "encoder.block.11.layer.1.DenseReluDense.wi_1.weight._data": "model-00001-of-00002.safetensors",
121
+ "encoder.block.11.layer.1.DenseReluDense.wi_1.weight._scale": "model-00001-of-00002.safetensors",
122
+ "encoder.block.11.layer.1.DenseReluDense.wo.input_scale": "model-00001-of-00002.safetensors",
123
+ "encoder.block.11.layer.1.DenseReluDense.wo.output_scale": "model-00001-of-00002.safetensors",
124
+ "encoder.block.11.layer.1.DenseReluDense.wo.weight._data": "model-00001-of-00002.safetensors",
125
+ "encoder.block.11.layer.1.DenseReluDense.wo.weight._scale": "model-00001-of-00002.safetensors",
126
+ "encoder.block.11.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
127
+ "encoder.block.12.layer.0.SelfAttention.k.input_scale": "model-00001-of-00002.safetensors",
128
+ "encoder.block.12.layer.0.SelfAttention.k.output_scale": "model-00001-of-00002.safetensors",
129
+ "encoder.block.12.layer.0.SelfAttention.k.weight._data": "model-00001-of-00002.safetensors",
130
+ "encoder.block.12.layer.0.SelfAttention.k.weight._scale": "model-00001-of-00002.safetensors",
131
+ "encoder.block.12.layer.0.SelfAttention.o.input_scale": "model-00001-of-00002.safetensors",
132
+ "encoder.block.12.layer.0.SelfAttention.o.output_scale": "model-00001-of-00002.safetensors",
133
+ "encoder.block.12.layer.0.SelfAttention.o.weight._data": "model-00001-of-00002.safetensors",
134
+ "encoder.block.12.layer.0.SelfAttention.o.weight._scale": "model-00001-of-00002.safetensors",
135
+ "encoder.block.12.layer.0.SelfAttention.q.input_scale": "model-00001-of-00002.safetensors",
136
+ "encoder.block.12.layer.0.SelfAttention.q.output_scale": "model-00001-of-00002.safetensors",
137
+ "encoder.block.12.layer.0.SelfAttention.q.weight._data": "model-00001-of-00002.safetensors",
138
+ "encoder.block.12.layer.0.SelfAttention.q.weight._scale": "model-00001-of-00002.safetensors",
139
+ "encoder.block.12.layer.0.SelfAttention.v.input_scale": "model-00001-of-00002.safetensors",
140
+ "encoder.block.12.layer.0.SelfAttention.v.output_scale": "model-00001-of-00002.safetensors",
141
+ "encoder.block.12.layer.0.SelfAttention.v.weight._data": "model-00001-of-00002.safetensors",
142
+ "encoder.block.12.layer.0.SelfAttention.v.weight._scale": "model-00001-of-00002.safetensors",
143
+ "encoder.block.12.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
144
+ "encoder.block.12.layer.1.DenseReluDense.wi_0.input_scale": "model-00001-of-00002.safetensors",
145
+ "encoder.block.12.layer.1.DenseReluDense.wi_0.output_scale": "model-00001-of-00002.safetensors",
146
+ "encoder.block.12.layer.1.DenseReluDense.wi_0.weight._data": "model-00001-of-00002.safetensors",
147
+ "encoder.block.12.layer.1.DenseReluDense.wi_0.weight._scale": "model-00001-of-00002.safetensors",
148
+ "encoder.block.12.layer.1.DenseReluDense.wi_1.input_scale": "model-00001-of-00002.safetensors",
149
+ "encoder.block.12.layer.1.DenseReluDense.wi_1.output_scale": "model-00001-of-00002.safetensors",
150
+ "encoder.block.12.layer.1.DenseReluDense.wi_1.weight._data": "model-00001-of-00002.safetensors",
151
+ "encoder.block.12.layer.1.DenseReluDense.wi_1.weight._scale": "model-00001-of-00002.safetensors",
152
+ "encoder.block.12.layer.1.DenseReluDense.wo.input_scale": "model-00001-of-00002.safetensors",
153
+ "encoder.block.12.layer.1.DenseReluDense.wo.output_scale": "model-00001-of-00002.safetensors",
154
+ "encoder.block.12.layer.1.DenseReluDense.wo.weight._data": "model-00001-of-00002.safetensors",
155
+ "encoder.block.12.layer.1.DenseReluDense.wo.weight._scale": "model-00001-of-00002.safetensors",
156
+ "encoder.block.12.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
157
+ "encoder.block.13.layer.0.SelfAttention.k.input_scale": "model-00001-of-00002.safetensors",
158
+ "encoder.block.13.layer.0.SelfAttention.k.output_scale": "model-00001-of-00002.safetensors",
159
+ "encoder.block.13.layer.0.SelfAttention.k.weight._data": "model-00001-of-00002.safetensors",
160
+ "encoder.block.13.layer.0.SelfAttention.k.weight._scale": "model-00001-of-00002.safetensors",
161
+ "encoder.block.13.layer.0.SelfAttention.o.input_scale": "model-00001-of-00002.safetensors",
162
+ "encoder.block.13.layer.0.SelfAttention.o.output_scale": "model-00001-of-00002.safetensors",
163
+ "encoder.block.13.layer.0.SelfAttention.o.weight._data": "model-00001-of-00002.safetensors",
164
+ "encoder.block.13.layer.0.SelfAttention.o.weight._scale": "model-00001-of-00002.safetensors",
165
+ "encoder.block.13.layer.0.SelfAttention.q.input_scale": "model-00001-of-00002.safetensors",
166
+ "encoder.block.13.layer.0.SelfAttention.q.output_scale": "model-00001-of-00002.safetensors",
167
+ "encoder.block.13.layer.0.SelfAttention.q.weight._data": "model-00001-of-00002.safetensors",
168
+ "encoder.block.13.layer.0.SelfAttention.q.weight._scale": "model-00001-of-00002.safetensors",
169
+ "encoder.block.13.layer.0.SelfAttention.v.input_scale": "model-00001-of-00002.safetensors",
170
+ "encoder.block.13.layer.0.SelfAttention.v.output_scale": "model-00001-of-00002.safetensors",
171
+ "encoder.block.13.layer.0.SelfAttention.v.weight._data": "model-00001-of-00002.safetensors",
172
+ "encoder.block.13.layer.0.SelfAttention.v.weight._scale": "model-00001-of-00002.safetensors",
173
+ "encoder.block.13.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
174
+ "encoder.block.13.layer.1.DenseReluDense.wi_0.input_scale": "model-00001-of-00002.safetensors",
175
+ "encoder.block.13.layer.1.DenseReluDense.wi_0.output_scale": "model-00001-of-00002.safetensors",
176
+ "encoder.block.13.layer.1.DenseReluDense.wi_0.weight._data": "model-00001-of-00002.safetensors",
177
+ "encoder.block.13.layer.1.DenseReluDense.wi_0.weight._scale": "model-00001-of-00002.safetensors",
178
+ "encoder.block.13.layer.1.DenseReluDense.wi_1.input_scale": "model-00001-of-00002.safetensors",
179
+ "encoder.block.13.layer.1.DenseReluDense.wi_1.output_scale": "model-00001-of-00002.safetensors",
180
+ "encoder.block.13.layer.1.DenseReluDense.wi_1.weight._data": "model-00001-of-00002.safetensors",
181
+ "encoder.block.13.layer.1.DenseReluDense.wi_1.weight._scale": "model-00001-of-00002.safetensors",
182
+ "encoder.block.13.layer.1.DenseReluDense.wo.input_scale": "model-00001-of-00002.safetensors",
183
+ "encoder.block.13.layer.1.DenseReluDense.wo.output_scale": "model-00001-of-00002.safetensors",
184
+ "encoder.block.13.layer.1.DenseReluDense.wo.weight._data": "model-00001-of-00002.safetensors",
185
+ "encoder.block.13.layer.1.DenseReluDense.wo.weight._scale": "model-00001-of-00002.safetensors",
186
+ "encoder.block.13.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
187
+ "encoder.block.14.layer.0.SelfAttention.k.input_scale": "model-00001-of-00002.safetensors",
188
+ "encoder.block.14.layer.0.SelfAttention.k.output_scale": "model-00001-of-00002.safetensors",
189
+ "encoder.block.14.layer.0.SelfAttention.k.weight._data": "model-00001-of-00002.safetensors",
190
+ "encoder.block.14.layer.0.SelfAttention.k.weight._scale": "model-00001-of-00002.safetensors",
191
+ "encoder.block.14.layer.0.SelfAttention.o.input_scale": "model-00001-of-00002.safetensors",
192
+ "encoder.block.14.layer.0.SelfAttention.o.output_scale": "model-00001-of-00002.safetensors",
193
+ "encoder.block.14.layer.0.SelfAttention.o.weight._data": "model-00001-of-00002.safetensors",
194
+ "encoder.block.14.layer.0.SelfAttention.o.weight._scale": "model-00001-of-00002.safetensors",
195
+ "encoder.block.14.layer.0.SelfAttention.q.input_scale": "model-00001-of-00002.safetensors",
196
+ "encoder.block.14.layer.0.SelfAttention.q.output_scale": "model-00001-of-00002.safetensors",
197
+ "encoder.block.14.layer.0.SelfAttention.q.weight._data": "model-00001-of-00002.safetensors",
198
+ "encoder.block.14.layer.0.SelfAttention.q.weight._scale": "model-00001-of-00002.safetensors",
199
+ "encoder.block.14.layer.0.SelfAttention.v.input_scale": "model-00001-of-00002.safetensors",
200
+ "encoder.block.14.layer.0.SelfAttention.v.output_scale": "model-00001-of-00002.safetensors",
201
+ "encoder.block.14.layer.0.SelfAttention.v.weight._data": "model-00001-of-00002.safetensors",
202
+ "encoder.block.14.layer.0.SelfAttention.v.weight._scale": "model-00001-of-00002.safetensors",
203
+ "encoder.block.14.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
204
+ "encoder.block.14.layer.1.DenseReluDense.wi_0.input_scale": "model-00001-of-00002.safetensors",
205
+ "encoder.block.14.layer.1.DenseReluDense.wi_0.output_scale": "model-00001-of-00002.safetensors",
206
+ "encoder.block.14.layer.1.DenseReluDense.wi_0.weight._data": "model-00001-of-00002.safetensors",
207
+ "encoder.block.14.layer.1.DenseReluDense.wi_0.weight._scale": "model-00001-of-00002.safetensors",
208
+ "encoder.block.14.layer.1.DenseReluDense.wi_1.input_scale": "model-00001-of-00002.safetensors",
209
+ "encoder.block.14.layer.1.DenseReluDense.wi_1.output_scale": "model-00001-of-00002.safetensors",
210
+ "encoder.block.14.layer.1.DenseReluDense.wi_1.weight._data": "model-00001-of-00002.safetensors",
211
+ "encoder.block.14.layer.1.DenseReluDense.wi_1.weight._scale": "model-00001-of-00002.safetensors",
212
+ "encoder.block.14.layer.1.DenseReluDense.wo.input_scale": "model-00001-of-00002.safetensors",
213
+ "encoder.block.14.layer.1.DenseReluDense.wo.output_scale": "model-00001-of-00002.safetensors",
214
+ "encoder.block.14.layer.1.DenseReluDense.wo.weight._data": "model-00001-of-00002.safetensors",
215
+ "encoder.block.14.layer.1.DenseReluDense.wo.weight._scale": "model-00001-of-00002.safetensors",
216
+ "encoder.block.14.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
217
+ "encoder.block.15.layer.0.SelfAttention.k.input_scale": "model-00001-of-00002.safetensors",
218
+ "encoder.block.15.layer.0.SelfAttention.k.output_scale": "model-00001-of-00002.safetensors",
219
+ "encoder.block.15.layer.0.SelfAttention.k.weight._data": "model-00001-of-00002.safetensors",
220
+ "encoder.block.15.layer.0.SelfAttention.k.weight._scale": "model-00001-of-00002.safetensors",
221
+ "encoder.block.15.layer.0.SelfAttention.o.input_scale": "model-00001-of-00002.safetensors",
222
+ "encoder.block.15.layer.0.SelfAttention.o.output_scale": "model-00001-of-00002.safetensors",
223
+ "encoder.block.15.layer.0.SelfAttention.o.weight._data": "model-00001-of-00002.safetensors",
224
+ "encoder.block.15.layer.0.SelfAttention.o.weight._scale": "model-00001-of-00002.safetensors",
225
+ "encoder.block.15.layer.0.SelfAttention.q.input_scale": "model-00001-of-00002.safetensors",
226
+ "encoder.block.15.layer.0.SelfAttention.q.output_scale": "model-00001-of-00002.safetensors",
227
+ "encoder.block.15.layer.0.SelfAttention.q.weight._data": "model-00001-of-00002.safetensors",
228
+ "encoder.block.15.layer.0.SelfAttention.q.weight._scale": "model-00001-of-00002.safetensors",
229
+ "encoder.block.15.layer.0.SelfAttention.v.input_scale": "model-00001-of-00002.safetensors",
230
+ "encoder.block.15.layer.0.SelfAttention.v.output_scale": "model-00001-of-00002.safetensors",
231
+ "encoder.block.15.layer.0.SelfAttention.v.weight._data": "model-00001-of-00002.safetensors",
232
+ "encoder.block.15.layer.0.SelfAttention.v.weight._scale": "model-00001-of-00002.safetensors",
233
+ "encoder.block.15.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
234
+ "encoder.block.15.layer.1.DenseReluDense.wi_0.input_scale": "model-00001-of-00002.safetensors",
235
+ "encoder.block.15.layer.1.DenseReluDense.wi_0.output_scale": "model-00001-of-00002.safetensors",
236
+ "encoder.block.15.layer.1.DenseReluDense.wi_0.weight._data": "model-00001-of-00002.safetensors",
237
+ "encoder.block.15.layer.1.DenseReluDense.wi_0.weight._scale": "model-00001-of-00002.safetensors",
238
+ "encoder.block.15.layer.1.DenseReluDense.wi_1.input_scale": "model-00001-of-00002.safetensors",
239
+ "encoder.block.15.layer.1.DenseReluDense.wi_1.output_scale": "model-00001-of-00002.safetensors",
240
+ "encoder.block.15.layer.1.DenseReluDense.wi_1.weight._data": "model-00001-of-00002.safetensors",
241
+ "encoder.block.15.layer.1.DenseReluDense.wi_1.weight._scale": "model-00001-of-00002.safetensors",
242
+ "encoder.block.15.layer.1.DenseReluDense.wo.input_scale": "model-00001-of-00002.safetensors",
243
+ "encoder.block.15.layer.1.DenseReluDense.wo.output_scale": "model-00001-of-00002.safetensors",
244
+ "encoder.block.15.layer.1.DenseReluDense.wo.weight._data": "model-00001-of-00002.safetensors",
245
+ "encoder.block.15.layer.1.DenseReluDense.wo.weight._scale": "model-00001-of-00002.safetensors",
246
+ "encoder.block.15.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
247
+ "encoder.block.16.layer.0.SelfAttention.k.input_scale": "model-00001-of-00002.safetensors",
248
+ "encoder.block.16.layer.0.SelfAttention.k.output_scale": "model-00001-of-00002.safetensors",
249
+ "encoder.block.16.layer.0.SelfAttention.k.weight._data": "model-00001-of-00002.safetensors",
250
+ "encoder.block.16.layer.0.SelfAttention.k.weight._scale": "model-00001-of-00002.safetensors",
251
+ "encoder.block.16.layer.0.SelfAttention.o.input_scale": "model-00001-of-00002.safetensors",
252
+ "encoder.block.16.layer.0.SelfAttention.o.output_scale": "model-00001-of-00002.safetensors",
253
+ "encoder.block.16.layer.0.SelfAttention.o.weight._data": "model-00001-of-00002.safetensors",
254
+ "encoder.block.16.layer.0.SelfAttention.o.weight._scale": "model-00001-of-00002.safetensors",
255
+ "encoder.block.16.layer.0.SelfAttention.q.input_scale": "model-00001-of-00002.safetensors",
256
+ "encoder.block.16.layer.0.SelfAttention.q.output_scale": "model-00001-of-00002.safetensors",
257
+ "encoder.block.16.layer.0.SelfAttention.q.weight._data": "model-00001-of-00002.safetensors",
258
+ "encoder.block.16.layer.0.SelfAttention.q.weight._scale": "model-00001-of-00002.safetensors",
259
+ "encoder.block.16.layer.0.SelfAttention.v.input_scale": "model-00001-of-00002.safetensors",
260
+ "encoder.block.16.layer.0.SelfAttention.v.output_scale": "model-00001-of-00002.safetensors",
261
+ "encoder.block.16.layer.0.SelfAttention.v.weight._data": "model-00001-of-00002.safetensors",
262
+ "encoder.block.16.layer.0.SelfAttention.v.weight._scale": "model-00001-of-00002.safetensors",
263
+ "encoder.block.16.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
264
+ "encoder.block.16.layer.1.DenseReluDense.wi_0.input_scale": "model-00001-of-00002.safetensors",
265
+ "encoder.block.16.layer.1.DenseReluDense.wi_0.output_scale": "model-00001-of-00002.safetensors",
266
+ "encoder.block.16.layer.1.DenseReluDense.wi_0.weight._data": "model-00001-of-00002.safetensors",
267
+ "encoder.block.16.layer.1.DenseReluDense.wi_0.weight._scale": "model-00001-of-00002.safetensors",
268
+ "encoder.block.16.layer.1.DenseReluDense.wi_1.input_scale": "model-00001-of-00002.safetensors",
269
+ "encoder.block.16.layer.1.DenseReluDense.wi_1.output_scale": "model-00001-of-00002.safetensors",
270
+ "encoder.block.16.layer.1.DenseReluDense.wi_1.weight._data": "model-00001-of-00002.safetensors",
271
+ "encoder.block.16.layer.1.DenseReluDense.wi_1.weight._scale": "model-00001-of-00002.safetensors",
272
+ "encoder.block.16.layer.1.DenseReluDense.wo.input_scale": "model-00001-of-00002.safetensors",
273
+ "encoder.block.16.layer.1.DenseReluDense.wo.output_scale": "model-00001-of-00002.safetensors",
274
+ "encoder.block.16.layer.1.DenseReluDense.wo.weight._data": "model-00001-of-00002.safetensors",
275
+ "encoder.block.16.layer.1.DenseReluDense.wo.weight._scale": "model-00001-of-00002.safetensors",
276
+ "encoder.block.16.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
277
+ "encoder.block.17.layer.0.SelfAttention.k.input_scale": "model-00001-of-00002.safetensors",
278
+ "encoder.block.17.layer.0.SelfAttention.k.output_scale": "model-00001-of-00002.safetensors",
279
+ "encoder.block.17.layer.0.SelfAttention.k.weight._data": "model-00001-of-00002.safetensors",
280
+ "encoder.block.17.layer.0.SelfAttention.k.weight._scale": "model-00001-of-00002.safetensors",
281
+ "encoder.block.17.layer.0.SelfAttention.o.input_scale": "model-00001-of-00002.safetensors",
282
+ "encoder.block.17.layer.0.SelfAttention.o.output_scale": "model-00001-of-00002.safetensors",
283
+ "encoder.block.17.layer.0.SelfAttention.o.weight._data": "model-00001-of-00002.safetensors",
284
+ "encoder.block.17.layer.0.SelfAttention.o.weight._scale": "model-00001-of-00002.safetensors",
285
+ "encoder.block.17.layer.0.SelfAttention.q.input_scale": "model-00001-of-00002.safetensors",
286
+ "encoder.block.17.layer.0.SelfAttention.q.output_scale": "model-00001-of-00002.safetensors",
287
+ "encoder.block.17.layer.0.SelfAttention.q.weight._data": "model-00001-of-00002.safetensors",
288
+ "encoder.block.17.layer.0.SelfAttention.q.weight._scale": "model-00001-of-00002.safetensors",
289
+ "encoder.block.17.layer.0.SelfAttention.v.input_scale": "model-00001-of-00002.safetensors",
290
+ "encoder.block.17.layer.0.SelfAttention.v.output_scale": "model-00001-of-00002.safetensors",
291
+ "encoder.block.17.layer.0.SelfAttention.v.weight._data": "model-00001-of-00002.safetensors",
292
+ "encoder.block.17.layer.0.SelfAttention.v.weight._scale": "model-00001-of-00002.safetensors",
293
+ "encoder.block.17.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
294
+ "encoder.block.17.layer.1.DenseReluDense.wi_0.input_scale": "model-00001-of-00002.safetensors",
295
+ "encoder.block.17.layer.1.DenseReluDense.wi_0.output_scale": "model-00001-of-00002.safetensors",
296
+ "encoder.block.17.layer.1.DenseReluDense.wi_0.weight._data": "model-00001-of-00002.safetensors",
297
+ "encoder.block.17.layer.1.DenseReluDense.wi_0.weight._scale": "model-00001-of-00002.safetensors",
298
+ "encoder.block.17.layer.1.DenseReluDense.wi_1.input_scale": "model-00001-of-00002.safetensors",
299
+ "encoder.block.17.layer.1.DenseReluDense.wi_1.output_scale": "model-00001-of-00002.safetensors",
300
+ "encoder.block.17.layer.1.DenseReluDense.wi_1.weight._data": "model-00001-of-00002.safetensors",
301
+ "encoder.block.17.layer.1.DenseReluDense.wi_1.weight._scale": "model-00001-of-00002.safetensors",
302
+ "encoder.block.17.layer.1.DenseReluDense.wo.input_scale": "model-00001-of-00002.safetensors",
303
+ "encoder.block.17.layer.1.DenseReluDense.wo.output_scale": "model-00001-of-00002.safetensors",
304
+ "encoder.block.17.layer.1.DenseReluDense.wo.weight._data": "model-00001-of-00002.safetensors",
305
+ "encoder.block.17.layer.1.DenseReluDense.wo.weight._scale": "model-00001-of-00002.safetensors",
306
+ "encoder.block.17.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
307
+ "encoder.block.18.layer.0.SelfAttention.k.input_scale": "model-00001-of-00002.safetensors",
308
+ "encoder.block.18.layer.0.SelfAttention.k.output_scale": "model-00001-of-00002.safetensors",
309
+ "encoder.block.18.layer.0.SelfAttention.k.weight._data": "model-00001-of-00002.safetensors",
310
+ "encoder.block.18.layer.0.SelfAttention.k.weight._scale": "model-00001-of-00002.safetensors",
311
+ "encoder.block.18.layer.0.SelfAttention.o.input_scale": "model-00001-of-00002.safetensors",
312
+ "encoder.block.18.layer.0.SelfAttention.o.output_scale": "model-00001-of-00002.safetensors",
313
+ "encoder.block.18.layer.0.SelfAttention.o.weight._data": "model-00001-of-00002.safetensors",
314
+ "encoder.block.18.layer.0.SelfAttention.o.weight._scale": "model-00001-of-00002.safetensors",
315
+ "encoder.block.18.layer.0.SelfAttention.q.input_scale": "model-00001-of-00002.safetensors",
316
+ "encoder.block.18.layer.0.SelfAttention.q.output_scale": "model-00001-of-00002.safetensors",
317
+ "encoder.block.18.layer.0.SelfAttention.q.weight._data": "model-00001-of-00002.safetensors",
318
+ "encoder.block.18.layer.0.SelfAttention.q.weight._scale": "model-00001-of-00002.safetensors",
319
+ "encoder.block.18.layer.0.SelfAttention.v.input_scale": "model-00001-of-00002.safetensors",
320
+ "encoder.block.18.layer.0.SelfAttention.v.output_scale": "model-00001-of-00002.safetensors",
321
+ "encoder.block.18.layer.0.SelfAttention.v.weight._data": "model-00001-of-00002.safetensors",
322
+ "encoder.block.18.layer.0.SelfAttention.v.weight._scale": "model-00001-of-00002.safetensors",
323
+ "encoder.block.18.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
324
+ "encoder.block.18.layer.1.DenseReluDense.wi_0.input_scale": "model-00001-of-00002.safetensors",
325
+ "encoder.block.18.layer.1.DenseReluDense.wi_0.output_scale": "model-00001-of-00002.safetensors",
326
+ "encoder.block.18.layer.1.DenseReluDense.wi_0.weight._data": "model-00001-of-00002.safetensors",
327
+ "encoder.block.18.layer.1.DenseReluDense.wi_0.weight._scale": "model-00001-of-00002.safetensors",
328
+ "encoder.block.18.layer.1.DenseReluDense.wi_1.input_scale": "model-00001-of-00002.safetensors",
329
+ "encoder.block.18.layer.1.DenseReluDense.wi_1.output_scale": "model-00001-of-00002.safetensors",
330
+ "encoder.block.18.layer.1.DenseReluDense.wi_1.weight._data": "model-00001-of-00002.safetensors",
331
+ "encoder.block.18.layer.1.DenseReluDense.wi_1.weight._scale": "model-00001-of-00002.safetensors",
332
+ "encoder.block.18.layer.1.DenseReluDense.wo.input_scale": "model-00001-of-00002.safetensors",
333
+ "encoder.block.18.layer.1.DenseReluDense.wo.output_scale": "model-00001-of-00002.safetensors",
334
+ "encoder.block.18.layer.1.DenseReluDense.wo.weight._data": "model-00001-of-00002.safetensors",
335
+ "encoder.block.18.layer.1.DenseReluDense.wo.weight._scale": "model-00001-of-00002.safetensors",
336
+ "encoder.block.18.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
337
+ "encoder.block.19.layer.0.SelfAttention.k.input_scale": "model-00001-of-00002.safetensors",
338
+ "encoder.block.19.layer.0.SelfAttention.k.output_scale": "model-00001-of-00002.safetensors",
339
+ "encoder.block.19.layer.0.SelfAttention.k.weight._data": "model-00001-of-00002.safetensors",
340
+ "encoder.block.19.layer.0.SelfAttention.k.weight._scale": "model-00001-of-00002.safetensors",
341
+ "encoder.block.19.layer.0.SelfAttention.o.input_scale": "model-00001-of-00002.safetensors",
342
+ "encoder.block.19.layer.0.SelfAttention.o.output_scale": "model-00001-of-00002.safetensors",
343
+ "encoder.block.19.layer.0.SelfAttention.o.weight._data": "model-00001-of-00002.safetensors",
344
+ "encoder.block.19.layer.0.SelfAttention.o.weight._scale": "model-00001-of-00002.safetensors",
345
+ "encoder.block.19.layer.0.SelfAttention.q.input_scale": "model-00001-of-00002.safetensors",
346
+ "encoder.block.19.layer.0.SelfAttention.q.output_scale": "model-00001-of-00002.safetensors",
347
+ "encoder.block.19.layer.0.SelfAttention.q.weight._data": "model-00001-of-00002.safetensors",
348
+ "encoder.block.19.layer.0.SelfAttention.q.weight._scale": "model-00001-of-00002.safetensors",
349
+ "encoder.block.19.layer.0.SelfAttention.v.input_scale": "model-00001-of-00002.safetensors",
350
+ "encoder.block.19.layer.0.SelfAttention.v.output_scale": "model-00001-of-00002.safetensors",
351
+ "encoder.block.19.layer.0.SelfAttention.v.weight._data": "model-00001-of-00002.safetensors",
352
+ "encoder.block.19.layer.0.SelfAttention.v.weight._scale": "model-00001-of-00002.safetensors",
353
+ "encoder.block.19.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
354
+ "encoder.block.19.layer.1.DenseReluDense.wi_0.input_scale": "model-00001-of-00002.safetensors",
355
+ "encoder.block.19.layer.1.DenseReluDense.wi_0.output_scale": "model-00001-of-00002.safetensors",
356
+ "encoder.block.19.layer.1.DenseReluDense.wi_0.weight._data": "model-00001-of-00002.safetensors",
357
+ "encoder.block.19.layer.1.DenseReluDense.wi_0.weight._scale": "model-00001-of-00002.safetensors",
358
+ "encoder.block.19.layer.1.DenseReluDense.wi_1.input_scale": "model-00001-of-00002.safetensors",
359
+ "encoder.block.19.layer.1.DenseReluDense.wi_1.output_scale": "model-00001-of-00002.safetensors",
360
+ "encoder.block.19.layer.1.DenseReluDense.wi_1.weight._data": "model-00001-of-00002.safetensors",
361
+ "encoder.block.19.layer.1.DenseReluDense.wi_1.weight._scale": "model-00001-of-00002.safetensors",
362
+ "encoder.block.19.layer.1.DenseReluDense.wo.input_scale": "model-00001-of-00002.safetensors",
363
+ "encoder.block.19.layer.1.DenseReluDense.wo.output_scale": "model-00001-of-00002.safetensors",
364
+ "encoder.block.19.layer.1.DenseReluDense.wo.weight._data": "model-00001-of-00002.safetensors",
365
+ "encoder.block.19.layer.1.DenseReluDense.wo.weight._scale": "model-00001-of-00002.safetensors",
366
+ "encoder.block.19.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
367
+ "encoder.block.2.layer.0.SelfAttention.k.input_scale": "model-00001-of-00002.safetensors",
368
+ "encoder.block.2.layer.0.SelfAttention.k.output_scale": "model-00001-of-00002.safetensors",
369
+ "encoder.block.2.layer.0.SelfAttention.k.weight._data": "model-00001-of-00002.safetensors",
370
+ "encoder.block.2.layer.0.SelfAttention.k.weight._scale": "model-00001-of-00002.safetensors",
371
+ "encoder.block.2.layer.0.SelfAttention.o.input_scale": "model-00001-of-00002.safetensors",
372
+ "encoder.block.2.layer.0.SelfAttention.o.output_scale": "model-00001-of-00002.safetensors",
373
+ "encoder.block.2.layer.0.SelfAttention.o.weight._data": "model-00001-of-00002.safetensors",
374
+ "encoder.block.2.layer.0.SelfAttention.o.weight._scale": "model-00001-of-00002.safetensors",
375
+ "encoder.block.2.layer.0.SelfAttention.q.input_scale": "model-00001-of-00002.safetensors",
376
+ "encoder.block.2.layer.0.SelfAttention.q.output_scale": "model-00001-of-00002.safetensors",
377
+ "encoder.block.2.layer.0.SelfAttention.q.weight._data": "model-00001-of-00002.safetensors",
378
+ "encoder.block.2.layer.0.SelfAttention.q.weight._scale": "model-00001-of-00002.safetensors",
379
+ "encoder.block.2.layer.0.SelfAttention.v.input_scale": "model-00001-of-00002.safetensors",
380
+ "encoder.block.2.layer.0.SelfAttention.v.output_scale": "model-00001-of-00002.safetensors",
381
+ "encoder.block.2.layer.0.SelfAttention.v.weight._data": "model-00001-of-00002.safetensors",
382
+ "encoder.block.2.layer.0.SelfAttention.v.weight._scale": "model-00001-of-00002.safetensors",
383
+ "encoder.block.2.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
384
+ "encoder.block.2.layer.1.DenseReluDense.wi_0.input_scale": "model-00001-of-00002.safetensors",
385
+ "encoder.block.2.layer.1.DenseReluDense.wi_0.output_scale": "model-00001-of-00002.safetensors",
386
+ "encoder.block.2.layer.1.DenseReluDense.wi_0.weight._data": "model-00001-of-00002.safetensors",
387
+ "encoder.block.2.layer.1.DenseReluDense.wi_0.weight._scale": "model-00001-of-00002.safetensors",
388
+ "encoder.block.2.layer.1.DenseReluDense.wi_1.input_scale": "model-00001-of-00002.safetensors",
389
+ "encoder.block.2.layer.1.DenseReluDense.wi_1.output_scale": "model-00001-of-00002.safetensors",
390
+ "encoder.block.2.layer.1.DenseReluDense.wi_1.weight._data": "model-00001-of-00002.safetensors",
391
+ "encoder.block.2.layer.1.DenseReluDense.wi_1.weight._scale": "model-00001-of-00002.safetensors",
392
+ "encoder.block.2.layer.1.DenseReluDense.wo.input_scale": "model-00001-of-00002.safetensors",
393
+ "encoder.block.2.layer.1.DenseReluDense.wo.output_scale": "model-00001-of-00002.safetensors",
394
+ "encoder.block.2.layer.1.DenseReluDense.wo.weight._data": "model-00001-of-00002.safetensors",
395
+ "encoder.block.2.layer.1.DenseReluDense.wo.weight._scale": "model-00001-of-00002.safetensors",
396
+ "encoder.block.2.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
397
+ "encoder.block.20.layer.0.SelfAttention.k.input_scale": "model-00001-of-00002.safetensors",
398
+ "encoder.block.20.layer.0.SelfAttention.k.output_scale": "model-00001-of-00002.safetensors",
399
+ "encoder.block.20.layer.0.SelfAttention.k.weight._data": "model-00001-of-00002.safetensors",
400
+ "encoder.block.20.layer.0.SelfAttention.k.weight._scale": "model-00001-of-00002.safetensors",
401
+ "encoder.block.20.layer.0.SelfAttention.o.input_scale": "model-00001-of-00002.safetensors",
402
+ "encoder.block.20.layer.0.SelfAttention.o.output_scale": "model-00001-of-00002.safetensors",
403
+ "encoder.block.20.layer.0.SelfAttention.o.weight._data": "model-00001-of-00002.safetensors",
404
+ "encoder.block.20.layer.0.SelfAttention.o.weight._scale": "model-00001-of-00002.safetensors",
405
+ "encoder.block.20.layer.0.SelfAttention.q.input_scale": "model-00001-of-00002.safetensors",
406
+ "encoder.block.20.layer.0.SelfAttention.q.output_scale": "model-00001-of-00002.safetensors",
407
+ "encoder.block.20.layer.0.SelfAttention.q.weight._data": "model-00001-of-00002.safetensors",
408
+ "encoder.block.20.layer.0.SelfAttention.q.weight._scale": "model-00001-of-00002.safetensors",
409
+ "encoder.block.20.layer.0.SelfAttention.v.input_scale": "model-00001-of-00002.safetensors",
410
+ "encoder.block.20.layer.0.SelfAttention.v.output_scale": "model-00001-of-00002.safetensors",
411
+ "encoder.block.20.layer.0.SelfAttention.v.weight._data": "model-00001-of-00002.safetensors",
412
+ "encoder.block.20.layer.0.SelfAttention.v.weight._scale": "model-00001-of-00002.safetensors",
413
+ "encoder.block.20.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
414
+ "encoder.block.20.layer.1.DenseReluDense.wi_0.input_scale": "model-00001-of-00002.safetensors",
415
+ "encoder.block.20.layer.1.DenseReluDense.wi_0.output_scale": "model-00001-of-00002.safetensors",
416
+ "encoder.block.20.layer.1.DenseReluDense.wi_0.weight._data": "model-00001-of-00002.safetensors",
417
+ "encoder.block.20.layer.1.DenseReluDense.wi_0.weight._scale": "model-00001-of-00002.safetensors",
418
+ "encoder.block.20.layer.1.DenseReluDense.wi_1.input_scale": "model-00001-of-00002.safetensors",
419
+ "encoder.block.20.layer.1.DenseReluDense.wi_1.output_scale": "model-00001-of-00002.safetensors",
420
+ "encoder.block.20.layer.1.DenseReluDense.wi_1.weight._data": "model-00001-of-00002.safetensors",
421
+ "encoder.block.20.layer.1.DenseReluDense.wi_1.weight._scale": "model-00001-of-00002.safetensors",
422
+ "encoder.block.20.layer.1.DenseReluDense.wo.input_scale": "model-00001-of-00002.safetensors",
423
+ "encoder.block.20.layer.1.DenseReluDense.wo.output_scale": "model-00001-of-00002.safetensors",
424
+ "encoder.block.20.layer.1.DenseReluDense.wo.weight._data": "model-00001-of-00002.safetensors",
425
+ "encoder.block.20.layer.1.DenseReluDense.wo.weight._scale": "model-00001-of-00002.safetensors",
426
+ "encoder.block.20.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
427
+ "encoder.block.21.layer.0.SelfAttention.k.input_scale": "model-00001-of-00002.safetensors",
428
+ "encoder.block.21.layer.0.SelfAttention.k.output_scale": "model-00001-of-00002.safetensors",
429
+ "encoder.block.21.layer.0.SelfAttention.k.weight._data": "model-00001-of-00002.safetensors",
430
+ "encoder.block.21.layer.0.SelfAttention.k.weight._scale": "model-00001-of-00002.safetensors",
431
+ "encoder.block.21.layer.0.SelfAttention.o.input_scale": "model-00001-of-00002.safetensors",
432
+ "encoder.block.21.layer.0.SelfAttention.o.output_scale": "model-00001-of-00002.safetensors",
433
+ "encoder.block.21.layer.0.SelfAttention.o.weight._data": "model-00001-of-00002.safetensors",
434
+ "encoder.block.21.layer.0.SelfAttention.o.weight._scale": "model-00001-of-00002.safetensors",
435
+ "encoder.block.21.layer.0.SelfAttention.q.input_scale": "model-00001-of-00002.safetensors",
436
+ "encoder.block.21.layer.0.SelfAttention.q.output_scale": "model-00001-of-00002.safetensors",
437
+ "encoder.block.21.layer.0.SelfAttention.q.weight._data": "model-00001-of-00002.safetensors",
438
+ "encoder.block.21.layer.0.SelfAttention.q.weight._scale": "model-00001-of-00002.safetensors",
439
+ "encoder.block.21.layer.0.SelfAttention.v.input_scale": "model-00001-of-00002.safetensors",
440
+ "encoder.block.21.layer.0.SelfAttention.v.output_scale": "model-00001-of-00002.safetensors",
441
+ "encoder.block.21.layer.0.SelfAttention.v.weight._data": "model-00001-of-00002.safetensors",
442
+ "encoder.block.21.layer.0.SelfAttention.v.weight._scale": "model-00001-of-00002.safetensors",
443
+ "encoder.block.21.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
444
+ "encoder.block.21.layer.1.DenseReluDense.wi_0.input_scale": "model-00001-of-00002.safetensors",
445
+ "encoder.block.21.layer.1.DenseReluDense.wi_0.output_scale": "model-00001-of-00002.safetensors",
446
+ "encoder.block.21.layer.1.DenseReluDense.wi_0.weight._data": "model-00001-of-00002.safetensors",
447
+ "encoder.block.21.layer.1.DenseReluDense.wi_0.weight._scale": "model-00001-of-00002.safetensors",
448
+ "encoder.block.21.layer.1.DenseReluDense.wi_1.input_scale": "model-00001-of-00002.safetensors",
449
+ "encoder.block.21.layer.1.DenseReluDense.wi_1.output_scale": "model-00001-of-00002.safetensors",
450
+ "encoder.block.21.layer.1.DenseReluDense.wi_1.weight._data": "model-00001-of-00002.safetensors",
451
+ "encoder.block.21.layer.1.DenseReluDense.wi_1.weight._scale": "model-00001-of-00002.safetensors",
452
+ "encoder.block.21.layer.1.DenseReluDense.wo.input_scale": "model-00001-of-00002.safetensors",
453
+ "encoder.block.21.layer.1.DenseReluDense.wo.output_scale": "model-00001-of-00002.safetensors",
454
+ "encoder.block.21.layer.1.DenseReluDense.wo.weight._data": "model-00001-of-00002.safetensors",
455
+ "encoder.block.21.layer.1.DenseReluDense.wo.weight._scale": "model-00001-of-00002.safetensors",
456
+ "encoder.block.21.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
457
+ "encoder.block.22.layer.0.SelfAttention.k.input_scale": "model-00001-of-00002.safetensors",
458
+ "encoder.block.22.layer.0.SelfAttention.k.output_scale": "model-00001-of-00002.safetensors",
459
+ "encoder.block.22.layer.0.SelfAttention.k.weight._data": "model-00001-of-00002.safetensors",
460
+ "encoder.block.22.layer.0.SelfAttention.k.weight._scale": "model-00001-of-00002.safetensors",
461
+ "encoder.block.22.layer.0.SelfAttention.o.input_scale": "model-00001-of-00002.safetensors",
462
+ "encoder.block.22.layer.0.SelfAttention.o.output_scale": "model-00001-of-00002.safetensors",
463
+ "encoder.block.22.layer.0.SelfAttention.o.weight._data": "model-00001-of-00002.safetensors",
464
+ "encoder.block.22.layer.0.SelfAttention.o.weight._scale": "model-00001-of-00002.safetensors",
465
+ "encoder.block.22.layer.0.SelfAttention.q.input_scale": "model-00001-of-00002.safetensors",
466
+ "encoder.block.22.layer.0.SelfAttention.q.output_scale": "model-00001-of-00002.safetensors",
467
+ "encoder.block.22.layer.0.SelfAttention.q.weight._data": "model-00001-of-00002.safetensors",
468
+ "encoder.block.22.layer.0.SelfAttention.q.weight._scale": "model-00001-of-00002.safetensors",
469
+ "encoder.block.22.layer.0.SelfAttention.v.input_scale": "model-00001-of-00002.safetensors",
470
+ "encoder.block.22.layer.0.SelfAttention.v.output_scale": "model-00001-of-00002.safetensors",
471
+ "encoder.block.22.layer.0.SelfAttention.v.weight._data": "model-00001-of-00002.safetensors",
472
+ "encoder.block.22.layer.0.SelfAttention.v.weight._scale": "model-00001-of-00002.safetensors",
473
+ "encoder.block.22.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
474
+ "encoder.block.22.layer.1.DenseReluDense.wi_0.input_scale": "model-00001-of-00002.safetensors",
475
+ "encoder.block.22.layer.1.DenseReluDense.wi_0.output_scale": "model-00001-of-00002.safetensors",
476
+ "encoder.block.22.layer.1.DenseReluDense.wi_0.weight._data": "model-00001-of-00002.safetensors",
477
+ "encoder.block.22.layer.1.DenseReluDense.wi_0.weight._scale": "model-00001-of-00002.safetensors",
478
+ "encoder.block.22.layer.1.DenseReluDense.wi_1.input_scale": "model-00001-of-00002.safetensors",
479
+ "encoder.block.22.layer.1.DenseReluDense.wi_1.output_scale": "model-00001-of-00002.safetensors",
480
+ "encoder.block.22.layer.1.DenseReluDense.wi_1.weight._data": "model-00001-of-00002.safetensors",
481
+ "encoder.block.22.layer.1.DenseReluDense.wi_1.weight._scale": "model-00001-of-00002.safetensors",
482
+ "encoder.block.22.layer.1.DenseReluDense.wo.input_scale": "model-00001-of-00002.safetensors",
483
+ "encoder.block.22.layer.1.DenseReluDense.wo.output_scale": "model-00001-of-00002.safetensors",
484
+ "encoder.block.22.layer.1.DenseReluDense.wo.weight._data": "model-00001-of-00002.safetensors",
485
+ "encoder.block.22.layer.1.DenseReluDense.wo.weight._scale": "model-00001-of-00002.safetensors",
486
+ "encoder.block.22.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
487
+ "encoder.block.23.layer.0.SelfAttention.k.input_scale": "model-00002-of-00002.safetensors",
488
+ "encoder.block.23.layer.0.SelfAttention.k.output_scale": "model-00002-of-00002.safetensors",
489
+ "encoder.block.23.layer.0.SelfAttention.k.weight._data": "model-00002-of-00002.safetensors",
490
+ "encoder.block.23.layer.0.SelfAttention.k.weight._scale": "model-00002-of-00002.safetensors",
491
+ "encoder.block.23.layer.0.SelfAttention.o.input_scale": "model-00002-of-00002.safetensors",
492
+ "encoder.block.23.layer.0.SelfAttention.o.output_scale": "model-00002-of-00002.safetensors",
493
+ "encoder.block.23.layer.0.SelfAttention.o.weight._data": "model-00002-of-00002.safetensors",
494
+ "encoder.block.23.layer.0.SelfAttention.o.weight._scale": "model-00002-of-00002.safetensors",
495
+ "encoder.block.23.layer.0.SelfAttention.q.input_scale": "model-00001-of-00002.safetensors",
496
+ "encoder.block.23.layer.0.SelfAttention.q.output_scale": "model-00001-of-00002.safetensors",
497
+ "encoder.block.23.layer.0.SelfAttention.q.weight._data": "model-00001-of-00002.safetensors",
498
+ "encoder.block.23.layer.0.SelfAttention.q.weight._scale": "model-00001-of-00002.safetensors",
499
+ "encoder.block.23.layer.0.SelfAttention.v.input_scale": "model-00002-of-00002.safetensors",
500
+ "encoder.block.23.layer.0.SelfAttention.v.output_scale": "model-00002-of-00002.safetensors",
501
+ "encoder.block.23.layer.0.SelfAttention.v.weight._data": "model-00002-of-00002.safetensors",
502
+ "encoder.block.23.layer.0.SelfAttention.v.weight._scale": "model-00002-of-00002.safetensors",
503
+ "encoder.block.23.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
504
+ "encoder.block.23.layer.1.DenseReluDense.wi_0.input_scale": "model-00002-of-00002.safetensors",
505
+ "encoder.block.23.layer.1.DenseReluDense.wi_0.output_scale": "model-00002-of-00002.safetensors",
506
+ "encoder.block.23.layer.1.DenseReluDense.wi_0.weight._data": "model-00002-of-00002.safetensors",
507
+ "encoder.block.23.layer.1.DenseReluDense.wi_0.weight._scale": "model-00002-of-00002.safetensors",
508
+ "encoder.block.23.layer.1.DenseReluDense.wi_1.input_scale": "model-00002-of-00002.safetensors",
509
+ "encoder.block.23.layer.1.DenseReluDense.wi_1.output_scale": "model-00002-of-00002.safetensors",
510
+ "encoder.block.23.layer.1.DenseReluDense.wi_1.weight._data": "model-00002-of-00002.safetensors",
511
+ "encoder.block.23.layer.1.DenseReluDense.wi_1.weight._scale": "model-00002-of-00002.safetensors",
512
+ "encoder.block.23.layer.1.DenseReluDense.wo.input_scale": "model-00002-of-00002.safetensors",
513
+ "encoder.block.23.layer.1.DenseReluDense.wo.output_scale": "model-00002-of-00002.safetensors",
514
+ "encoder.block.23.layer.1.DenseReluDense.wo.weight._data": "model-00002-of-00002.safetensors",
515
+ "encoder.block.23.layer.1.DenseReluDense.wo.weight._scale": "model-00002-of-00002.safetensors",
516
+ "encoder.block.23.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
517
+ "encoder.block.3.layer.0.SelfAttention.k.input_scale": "model-00001-of-00002.safetensors",
518
+ "encoder.block.3.layer.0.SelfAttention.k.output_scale": "model-00001-of-00002.safetensors",
519
+ "encoder.block.3.layer.0.SelfAttention.k.weight._data": "model-00001-of-00002.safetensors",
520
+ "encoder.block.3.layer.0.SelfAttention.k.weight._scale": "model-00001-of-00002.safetensors",
521
+ "encoder.block.3.layer.0.SelfAttention.o.input_scale": "model-00001-of-00002.safetensors",
522
+ "encoder.block.3.layer.0.SelfAttention.o.output_scale": "model-00001-of-00002.safetensors",
523
+ "encoder.block.3.layer.0.SelfAttention.o.weight._data": "model-00001-of-00002.safetensors",
524
+ "encoder.block.3.layer.0.SelfAttention.o.weight._scale": "model-00001-of-00002.safetensors",
525
+ "encoder.block.3.layer.0.SelfAttention.q.input_scale": "model-00001-of-00002.safetensors",
526
+ "encoder.block.3.layer.0.SelfAttention.q.output_scale": "model-00001-of-00002.safetensors",
527
+ "encoder.block.3.layer.0.SelfAttention.q.weight._data": "model-00001-of-00002.safetensors",
528
+ "encoder.block.3.layer.0.SelfAttention.q.weight._scale": "model-00001-of-00002.safetensors",
529
+ "encoder.block.3.layer.0.SelfAttention.v.input_scale": "model-00001-of-00002.safetensors",
530
+ "encoder.block.3.layer.0.SelfAttention.v.output_scale": "model-00001-of-00002.safetensors",
531
+ "encoder.block.3.layer.0.SelfAttention.v.weight._data": "model-00001-of-00002.safetensors",
532
+ "encoder.block.3.layer.0.SelfAttention.v.weight._scale": "model-00001-of-00002.safetensors",
533
+ "encoder.block.3.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
534
+ "encoder.block.3.layer.1.DenseReluDense.wi_0.input_scale": "model-00001-of-00002.safetensors",
535
+ "encoder.block.3.layer.1.DenseReluDense.wi_0.output_scale": "model-00001-of-00002.safetensors",
536
+ "encoder.block.3.layer.1.DenseReluDense.wi_0.weight._data": "model-00001-of-00002.safetensors",
537
+ "encoder.block.3.layer.1.DenseReluDense.wi_0.weight._scale": "model-00001-of-00002.safetensors",
538
+ "encoder.block.3.layer.1.DenseReluDense.wi_1.input_scale": "model-00001-of-00002.safetensors",
539
+ "encoder.block.3.layer.1.DenseReluDense.wi_1.output_scale": "model-00001-of-00002.safetensors",
540
+ "encoder.block.3.layer.1.DenseReluDense.wi_1.weight._data": "model-00001-of-00002.safetensors",
541
+ "encoder.block.3.layer.1.DenseReluDense.wi_1.weight._scale": "model-00001-of-00002.safetensors",
542
+ "encoder.block.3.layer.1.DenseReluDense.wo.input_scale": "model-00001-of-00002.safetensors",
543
+ "encoder.block.3.layer.1.DenseReluDense.wo.output_scale": "model-00001-of-00002.safetensors",
544
+ "encoder.block.3.layer.1.DenseReluDense.wo.weight._data": "model-00001-of-00002.safetensors",
545
+ "encoder.block.3.layer.1.DenseReluDense.wo.weight._scale": "model-00001-of-00002.safetensors",
546
+ "encoder.block.3.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
547
+ "encoder.block.4.layer.0.SelfAttention.k.input_scale": "model-00001-of-00002.safetensors",
548
+ "encoder.block.4.layer.0.SelfAttention.k.output_scale": "model-00001-of-00002.safetensors",
549
+ "encoder.block.4.layer.0.SelfAttention.k.weight._data": "model-00001-of-00002.safetensors",
550
+ "encoder.block.4.layer.0.SelfAttention.k.weight._scale": "model-00001-of-00002.safetensors",
551
+ "encoder.block.4.layer.0.SelfAttention.o.input_scale": "model-00001-of-00002.safetensors",
552
+ "encoder.block.4.layer.0.SelfAttention.o.output_scale": "model-00001-of-00002.safetensors",
553
+ "encoder.block.4.layer.0.SelfAttention.o.weight._data": "model-00001-of-00002.safetensors",
554
+ "encoder.block.4.layer.0.SelfAttention.o.weight._scale": "model-00001-of-00002.safetensors",
555
+ "encoder.block.4.layer.0.SelfAttention.q.input_scale": "model-00001-of-00002.safetensors",
556
+ "encoder.block.4.layer.0.SelfAttention.q.output_scale": "model-00001-of-00002.safetensors",
557
+ "encoder.block.4.layer.0.SelfAttention.q.weight._data": "model-00001-of-00002.safetensors",
558
+ "encoder.block.4.layer.0.SelfAttention.q.weight._scale": "model-00001-of-00002.safetensors",
559
+ "encoder.block.4.layer.0.SelfAttention.v.input_scale": "model-00001-of-00002.safetensors",
560
+ "encoder.block.4.layer.0.SelfAttention.v.output_scale": "model-00001-of-00002.safetensors",
561
+ "encoder.block.4.layer.0.SelfAttention.v.weight._data": "model-00001-of-00002.safetensors",
562
+ "encoder.block.4.layer.0.SelfAttention.v.weight._scale": "model-00001-of-00002.safetensors",
563
+ "encoder.block.4.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
564
+ "encoder.block.4.layer.1.DenseReluDense.wi_0.input_scale": "model-00001-of-00002.safetensors",
565
+ "encoder.block.4.layer.1.DenseReluDense.wi_0.output_scale": "model-00001-of-00002.safetensors",
566
+ "encoder.block.4.layer.1.DenseReluDense.wi_0.weight._data": "model-00001-of-00002.safetensors",
567
+ "encoder.block.4.layer.1.DenseReluDense.wi_0.weight._scale": "model-00001-of-00002.safetensors",
568
+ "encoder.block.4.layer.1.DenseReluDense.wi_1.input_scale": "model-00001-of-00002.safetensors",
569
+ "encoder.block.4.layer.1.DenseReluDense.wi_1.output_scale": "model-00001-of-00002.safetensors",
570
+ "encoder.block.4.layer.1.DenseReluDense.wi_1.weight._data": "model-00001-of-00002.safetensors",
571
+ "encoder.block.4.layer.1.DenseReluDense.wi_1.weight._scale": "model-00001-of-00002.safetensors",
572
+ "encoder.block.4.layer.1.DenseReluDense.wo.input_scale": "model-00001-of-00002.safetensors",
573
+ "encoder.block.4.layer.1.DenseReluDense.wo.output_scale": "model-00001-of-00002.safetensors",
574
+ "encoder.block.4.layer.1.DenseReluDense.wo.weight._data": "model-00001-of-00002.safetensors",
575
+ "encoder.block.4.layer.1.DenseReluDense.wo.weight._scale": "model-00001-of-00002.safetensors",
576
+ "encoder.block.4.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
577
+ "encoder.block.5.layer.0.SelfAttention.k.input_scale": "model-00001-of-00002.safetensors",
578
+ "encoder.block.5.layer.0.SelfAttention.k.output_scale": "model-00001-of-00002.safetensors",
579
+ "encoder.block.5.layer.0.SelfAttention.k.weight._data": "model-00001-of-00002.safetensors",
580
+ "encoder.block.5.layer.0.SelfAttention.k.weight._scale": "model-00001-of-00002.safetensors",
581
+ "encoder.block.5.layer.0.SelfAttention.o.input_scale": "model-00001-of-00002.safetensors",
582
+ "encoder.block.5.layer.0.SelfAttention.o.output_scale": "model-00001-of-00002.safetensors",
583
+ "encoder.block.5.layer.0.SelfAttention.o.weight._data": "model-00001-of-00002.safetensors",
584
+ "encoder.block.5.layer.0.SelfAttention.o.weight._scale": "model-00001-of-00002.safetensors",
585
+ "encoder.block.5.layer.0.SelfAttention.q.input_scale": "model-00001-of-00002.safetensors",
586
+ "encoder.block.5.layer.0.SelfAttention.q.output_scale": "model-00001-of-00002.safetensors",
587
+ "encoder.block.5.layer.0.SelfAttention.q.weight._data": "model-00001-of-00002.safetensors",
588
+ "encoder.block.5.layer.0.SelfAttention.q.weight._scale": "model-00001-of-00002.safetensors",
589
+ "encoder.block.5.layer.0.SelfAttention.v.input_scale": "model-00001-of-00002.safetensors",
590
+ "encoder.block.5.layer.0.SelfAttention.v.output_scale": "model-00001-of-00002.safetensors",
591
+ "encoder.block.5.layer.0.SelfAttention.v.weight._data": "model-00001-of-00002.safetensors",
592
+ "encoder.block.5.layer.0.SelfAttention.v.weight._scale": "model-00001-of-00002.safetensors",
593
+ "encoder.block.5.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
594
+ "encoder.block.5.layer.1.DenseReluDense.wi_0.input_scale": "model-00001-of-00002.safetensors",
595
+ "encoder.block.5.layer.1.DenseReluDense.wi_0.output_scale": "model-00001-of-00002.safetensors",
596
+ "encoder.block.5.layer.1.DenseReluDense.wi_0.weight._data": "model-00001-of-00002.safetensors",
597
+ "encoder.block.5.layer.1.DenseReluDense.wi_0.weight._scale": "model-00001-of-00002.safetensors",
598
+ "encoder.block.5.layer.1.DenseReluDense.wi_1.input_scale": "model-00001-of-00002.safetensors",
599
+ "encoder.block.5.layer.1.DenseReluDense.wi_1.output_scale": "model-00001-of-00002.safetensors",
600
+ "encoder.block.5.layer.1.DenseReluDense.wi_1.weight._data": "model-00001-of-00002.safetensors",
601
+ "encoder.block.5.layer.1.DenseReluDense.wi_1.weight._scale": "model-00001-of-00002.safetensors",
602
+ "encoder.block.5.layer.1.DenseReluDense.wo.input_scale": "model-00001-of-00002.safetensors",
603
+ "encoder.block.5.layer.1.DenseReluDense.wo.output_scale": "model-00001-of-00002.safetensors",
604
+ "encoder.block.5.layer.1.DenseReluDense.wo.weight._data": "model-00001-of-00002.safetensors",
605
+ "encoder.block.5.layer.1.DenseReluDense.wo.weight._scale": "model-00001-of-00002.safetensors",
606
+ "encoder.block.5.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
607
+ "encoder.block.6.layer.0.SelfAttention.k.input_scale": "model-00001-of-00002.safetensors",
608
+ "encoder.block.6.layer.0.SelfAttention.k.output_scale": "model-00001-of-00002.safetensors",
609
+ "encoder.block.6.layer.0.SelfAttention.k.weight._data": "model-00001-of-00002.safetensors",
610
+ "encoder.block.6.layer.0.SelfAttention.k.weight._scale": "model-00001-of-00002.safetensors",
611
+ "encoder.block.6.layer.0.SelfAttention.o.input_scale": "model-00001-of-00002.safetensors",
612
+ "encoder.block.6.layer.0.SelfAttention.o.output_scale": "model-00001-of-00002.safetensors",
613
+ "encoder.block.6.layer.0.SelfAttention.o.weight._data": "model-00001-of-00002.safetensors",
614
+ "encoder.block.6.layer.0.SelfAttention.o.weight._scale": "model-00001-of-00002.safetensors",
615
+ "encoder.block.6.layer.0.SelfAttention.q.input_scale": "model-00001-of-00002.safetensors",
616
+ "encoder.block.6.layer.0.SelfAttention.q.output_scale": "model-00001-of-00002.safetensors",
617
+ "encoder.block.6.layer.0.SelfAttention.q.weight._data": "model-00001-of-00002.safetensors",
618
+ "encoder.block.6.layer.0.SelfAttention.q.weight._scale": "model-00001-of-00002.safetensors",
619
+ "encoder.block.6.layer.0.SelfAttention.v.input_scale": "model-00001-of-00002.safetensors",
620
+ "encoder.block.6.layer.0.SelfAttention.v.output_scale": "model-00001-of-00002.safetensors",
621
+ "encoder.block.6.layer.0.SelfAttention.v.weight._data": "model-00001-of-00002.safetensors",
622
+ "encoder.block.6.layer.0.SelfAttention.v.weight._scale": "model-00001-of-00002.safetensors",
623
+ "encoder.block.6.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
624
+ "encoder.block.6.layer.1.DenseReluDense.wi_0.input_scale": "model-00001-of-00002.safetensors",
625
+ "encoder.block.6.layer.1.DenseReluDense.wi_0.output_scale": "model-00001-of-00002.safetensors",
626
+ "encoder.block.6.layer.1.DenseReluDense.wi_0.weight._data": "model-00001-of-00002.safetensors",
627
+ "encoder.block.6.layer.1.DenseReluDense.wi_0.weight._scale": "model-00001-of-00002.safetensors",
628
+ "encoder.block.6.layer.1.DenseReluDense.wi_1.input_scale": "model-00001-of-00002.safetensors",
629
+ "encoder.block.6.layer.1.DenseReluDense.wi_1.output_scale": "model-00001-of-00002.safetensors",
630
+ "encoder.block.6.layer.1.DenseReluDense.wi_1.weight._data": "model-00001-of-00002.safetensors",
631
+ "encoder.block.6.layer.1.DenseReluDense.wi_1.weight._scale": "model-00001-of-00002.safetensors",
632
+ "encoder.block.6.layer.1.DenseReluDense.wo.input_scale": "model-00001-of-00002.safetensors",
633
+ "encoder.block.6.layer.1.DenseReluDense.wo.output_scale": "model-00001-of-00002.safetensors",
634
+ "encoder.block.6.layer.1.DenseReluDense.wo.weight._data": "model-00001-of-00002.safetensors",
635
+ "encoder.block.6.layer.1.DenseReluDense.wo.weight._scale": "model-00001-of-00002.safetensors",
636
+ "encoder.block.6.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
637
+ "encoder.block.7.layer.0.SelfAttention.k.input_scale": "model-00001-of-00002.safetensors",
638
+ "encoder.block.7.layer.0.SelfAttention.k.output_scale": "model-00001-of-00002.safetensors",
639
+ "encoder.block.7.layer.0.SelfAttention.k.weight._data": "model-00001-of-00002.safetensors",
640
+ "encoder.block.7.layer.0.SelfAttention.k.weight._scale": "model-00001-of-00002.safetensors",
641
+ "encoder.block.7.layer.0.SelfAttention.o.input_scale": "model-00001-of-00002.safetensors",
642
+ "encoder.block.7.layer.0.SelfAttention.o.output_scale": "model-00001-of-00002.safetensors",
643
+ "encoder.block.7.layer.0.SelfAttention.o.weight._data": "model-00001-of-00002.safetensors",
644
+ "encoder.block.7.layer.0.SelfAttention.o.weight._scale": "model-00001-of-00002.safetensors",
645
+ "encoder.block.7.layer.0.SelfAttention.q.input_scale": "model-00001-of-00002.safetensors",
646
+ "encoder.block.7.layer.0.SelfAttention.q.output_scale": "model-00001-of-00002.safetensors",
647
+ "encoder.block.7.layer.0.SelfAttention.q.weight._data": "model-00001-of-00002.safetensors",
648
+ "encoder.block.7.layer.0.SelfAttention.q.weight._scale": "model-00001-of-00002.safetensors",
649
+ "encoder.block.7.layer.0.SelfAttention.v.input_scale": "model-00001-of-00002.safetensors",
650
+ "encoder.block.7.layer.0.SelfAttention.v.output_scale": "model-00001-of-00002.safetensors",
651
+ "encoder.block.7.layer.0.SelfAttention.v.weight._data": "model-00001-of-00002.safetensors",
652
+ "encoder.block.7.layer.0.SelfAttention.v.weight._scale": "model-00001-of-00002.safetensors",
653
+ "encoder.block.7.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
654
+ "encoder.block.7.layer.1.DenseReluDense.wi_0.input_scale": "model-00001-of-00002.safetensors",
655
+ "encoder.block.7.layer.1.DenseReluDense.wi_0.output_scale": "model-00001-of-00002.safetensors",
656
+ "encoder.block.7.layer.1.DenseReluDense.wi_0.weight._data": "model-00001-of-00002.safetensors",
657
+ "encoder.block.7.layer.1.DenseReluDense.wi_0.weight._scale": "model-00001-of-00002.safetensors",
658
+ "encoder.block.7.layer.1.DenseReluDense.wi_1.input_scale": "model-00001-of-00002.safetensors",
659
+ "encoder.block.7.layer.1.DenseReluDense.wi_1.output_scale": "model-00001-of-00002.safetensors",
660
+ "encoder.block.7.layer.1.DenseReluDense.wi_1.weight._data": "model-00001-of-00002.safetensors",
661
+ "encoder.block.7.layer.1.DenseReluDense.wi_1.weight._scale": "model-00001-of-00002.safetensors",
662
+ "encoder.block.7.layer.1.DenseReluDense.wo.input_scale": "model-00001-of-00002.safetensors",
663
+ "encoder.block.7.layer.1.DenseReluDense.wo.output_scale": "model-00001-of-00002.safetensors",
664
+ "encoder.block.7.layer.1.DenseReluDense.wo.weight._data": "model-00001-of-00002.safetensors",
665
+ "encoder.block.7.layer.1.DenseReluDense.wo.weight._scale": "model-00001-of-00002.safetensors",
666
+ "encoder.block.7.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
667
+ "encoder.block.8.layer.0.SelfAttention.k.input_scale": "model-00001-of-00002.safetensors",
668
+ "encoder.block.8.layer.0.SelfAttention.k.output_scale": "model-00001-of-00002.safetensors",
669
+ "encoder.block.8.layer.0.SelfAttention.k.weight._data": "model-00001-of-00002.safetensors",
670
+ "encoder.block.8.layer.0.SelfAttention.k.weight._scale": "model-00001-of-00002.safetensors",
671
+ "encoder.block.8.layer.0.SelfAttention.o.input_scale": "model-00001-of-00002.safetensors",
672
+ "encoder.block.8.layer.0.SelfAttention.o.output_scale": "model-00001-of-00002.safetensors",
673
+ "encoder.block.8.layer.0.SelfAttention.o.weight._data": "model-00001-of-00002.safetensors",
674
+ "encoder.block.8.layer.0.SelfAttention.o.weight._scale": "model-00001-of-00002.safetensors",
675
+ "encoder.block.8.layer.0.SelfAttention.q.input_scale": "model-00001-of-00002.safetensors",
676
+ "encoder.block.8.layer.0.SelfAttention.q.output_scale": "model-00001-of-00002.safetensors",
677
+ "encoder.block.8.layer.0.SelfAttention.q.weight._data": "model-00001-of-00002.safetensors",
678
+ "encoder.block.8.layer.0.SelfAttention.q.weight._scale": "model-00001-of-00002.safetensors",
679
+ "encoder.block.8.layer.0.SelfAttention.v.input_scale": "model-00001-of-00002.safetensors",
680
+ "encoder.block.8.layer.0.SelfAttention.v.output_scale": "model-00001-of-00002.safetensors",
681
+ "encoder.block.8.layer.0.SelfAttention.v.weight._data": "model-00001-of-00002.safetensors",
682
+ "encoder.block.8.layer.0.SelfAttention.v.weight._scale": "model-00001-of-00002.safetensors",
683
+ "encoder.block.8.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
684
+ "encoder.block.8.layer.1.DenseReluDense.wi_0.input_scale": "model-00001-of-00002.safetensors",
685
+ "encoder.block.8.layer.1.DenseReluDense.wi_0.output_scale": "model-00001-of-00002.safetensors",
686
+ "encoder.block.8.layer.1.DenseReluDense.wi_0.weight._data": "model-00001-of-00002.safetensors",
687
+ "encoder.block.8.layer.1.DenseReluDense.wi_0.weight._scale": "model-00001-of-00002.safetensors",
688
+ "encoder.block.8.layer.1.DenseReluDense.wi_1.input_scale": "model-00001-of-00002.safetensors",
689
+ "encoder.block.8.layer.1.DenseReluDense.wi_1.output_scale": "model-00001-of-00002.safetensors",
690
+ "encoder.block.8.layer.1.DenseReluDense.wi_1.weight._data": "model-00001-of-00002.safetensors",
691
+ "encoder.block.8.layer.1.DenseReluDense.wi_1.weight._scale": "model-00001-of-00002.safetensors",
692
+ "encoder.block.8.layer.1.DenseReluDense.wo.input_scale": "model-00001-of-00002.safetensors",
693
+ "encoder.block.8.layer.1.DenseReluDense.wo.output_scale": "model-00001-of-00002.safetensors",
694
+ "encoder.block.8.layer.1.DenseReluDense.wo.weight._data": "model-00001-of-00002.safetensors",
695
+ "encoder.block.8.layer.1.DenseReluDense.wo.weight._scale": "model-00001-of-00002.safetensors",
696
+ "encoder.block.8.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
697
+ "encoder.block.9.layer.0.SelfAttention.k.input_scale": "model-00001-of-00002.safetensors",
698
+ "encoder.block.9.layer.0.SelfAttention.k.output_scale": "model-00001-of-00002.safetensors",
699
+ "encoder.block.9.layer.0.SelfAttention.k.weight._data": "model-00001-of-00002.safetensors",
700
+ "encoder.block.9.layer.0.SelfAttention.k.weight._scale": "model-00001-of-00002.safetensors",
701
+ "encoder.block.9.layer.0.SelfAttention.o.input_scale": "model-00001-of-00002.safetensors",
702
+ "encoder.block.9.layer.0.SelfAttention.o.output_scale": "model-00001-of-00002.safetensors",
703
+ "encoder.block.9.layer.0.SelfAttention.o.weight._data": "model-00001-of-00002.safetensors",
704
+ "encoder.block.9.layer.0.SelfAttention.o.weight._scale": "model-00001-of-00002.safetensors",
705
+ "encoder.block.9.layer.0.SelfAttention.q.input_scale": "model-00001-of-00002.safetensors",
706
+ "encoder.block.9.layer.0.SelfAttention.q.output_scale": "model-00001-of-00002.safetensors",
707
+ "encoder.block.9.layer.0.SelfAttention.q.weight._data": "model-00001-of-00002.safetensors",
708
+ "encoder.block.9.layer.0.SelfAttention.q.weight._scale": "model-00001-of-00002.safetensors",
709
+ "encoder.block.9.layer.0.SelfAttention.v.input_scale": "model-00001-of-00002.safetensors",
710
+ "encoder.block.9.layer.0.SelfAttention.v.output_scale": "model-00001-of-00002.safetensors",
711
+ "encoder.block.9.layer.0.SelfAttention.v.weight._data": "model-00001-of-00002.safetensors",
712
+ "encoder.block.9.layer.0.SelfAttention.v.weight._scale": "model-00001-of-00002.safetensors",
713
+ "encoder.block.9.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
714
+ "encoder.block.9.layer.1.DenseReluDense.wi_0.input_scale": "model-00001-of-00002.safetensors",
715
+ "encoder.block.9.layer.1.DenseReluDense.wi_0.output_scale": "model-00001-of-00002.safetensors",
716
+ "encoder.block.9.layer.1.DenseReluDense.wi_0.weight._data": "model-00001-of-00002.safetensors",
717
+ "encoder.block.9.layer.1.DenseReluDense.wi_0.weight._scale": "model-00001-of-00002.safetensors",
718
+ "encoder.block.9.layer.1.DenseReluDense.wi_1.input_scale": "model-00001-of-00002.safetensors",
719
+ "encoder.block.9.layer.1.DenseReluDense.wi_1.output_scale": "model-00001-of-00002.safetensors",
720
+ "encoder.block.9.layer.1.DenseReluDense.wi_1.weight._data": "model-00001-of-00002.safetensors",
721
+ "encoder.block.9.layer.1.DenseReluDense.wi_1.weight._scale": "model-00001-of-00002.safetensors",
722
+ "encoder.block.9.layer.1.DenseReluDense.wo.input_scale": "model-00001-of-00002.safetensors",
723
+ "encoder.block.9.layer.1.DenseReluDense.wo.output_scale": "model-00001-of-00002.safetensors",
724
+ "encoder.block.9.layer.1.DenseReluDense.wo.weight._data": "model-00001-of-00002.safetensors",
725
+ "encoder.block.9.layer.1.DenseReluDense.wo.weight._scale": "model-00001-of-00002.safetensors",
726
+ "encoder.block.9.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
727
+ "encoder.final_layer_norm.weight": "model-00002-of-00002.safetensors",
728
+ "shared.weight": "model-00001-of-00002.safetensors"
729
+ }
730
+ }
optimum_quanto_qfloat8/text_encoder_2/quanto_qmap.json ADDED
@@ -0,0 +1,674 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "encoder.block.0.layer.0.SelfAttention.q": {
3
+ "weights": "qfloat8_e4m3fn",
4
+ "activations": "none"
5
+ },
6
+ "encoder.block.0.layer.0.SelfAttention.k": {
7
+ "weights": "qfloat8_e4m3fn",
8
+ "activations": "none"
9
+ },
10
+ "encoder.block.0.layer.0.SelfAttention.v": {
11
+ "weights": "qfloat8_e4m3fn",
12
+ "activations": "none"
13
+ },
14
+ "encoder.block.0.layer.0.SelfAttention.o": {
15
+ "weights": "qfloat8_e4m3fn",
16
+ "activations": "none"
17
+ },
18
+ "encoder.block.0.layer.1.DenseReluDense.wi_0": {
19
+ "weights": "qfloat8_e4m3fn",
20
+ "activations": "none"
21
+ },
22
+ "encoder.block.0.layer.1.DenseReluDense.wi_1": {
23
+ "weights": "qfloat8_e4m3fn",
24
+ "activations": "none"
25
+ },
26
+ "encoder.block.0.layer.1.DenseReluDense.wo": {
27
+ "weights": "qfloat8_e4m3fn",
28
+ "activations": "none"
29
+ },
30
+ "encoder.block.1.layer.0.SelfAttention.q": {
31
+ "weights": "qfloat8_e4m3fn",
32
+ "activations": "none"
33
+ },
34
+ "encoder.block.1.layer.0.SelfAttention.k": {
35
+ "weights": "qfloat8_e4m3fn",
36
+ "activations": "none"
37
+ },
38
+ "encoder.block.1.layer.0.SelfAttention.v": {
39
+ "weights": "qfloat8_e4m3fn",
40
+ "activations": "none"
41
+ },
42
+ "encoder.block.1.layer.0.SelfAttention.o": {
43
+ "weights": "qfloat8_e4m3fn",
44
+ "activations": "none"
45
+ },
46
+ "encoder.block.1.layer.1.DenseReluDense.wi_0": {
47
+ "weights": "qfloat8_e4m3fn",
48
+ "activations": "none"
49
+ },
50
+ "encoder.block.1.layer.1.DenseReluDense.wi_1": {
51
+ "weights": "qfloat8_e4m3fn",
52
+ "activations": "none"
53
+ },
54
+ "encoder.block.1.layer.1.DenseReluDense.wo": {
55
+ "weights": "qfloat8_e4m3fn",
56
+ "activations": "none"
57
+ },
58
+ "encoder.block.2.layer.0.SelfAttention.q": {
59
+ "weights": "qfloat8_e4m3fn",
60
+ "activations": "none"
61
+ },
62
+ "encoder.block.2.layer.0.SelfAttention.k": {
63
+ "weights": "qfloat8_e4m3fn",
64
+ "activations": "none"
65
+ },
66
+ "encoder.block.2.layer.0.SelfAttention.v": {
67
+ "weights": "qfloat8_e4m3fn",
68
+ "activations": "none"
69
+ },
70
+ "encoder.block.2.layer.0.SelfAttention.o": {
71
+ "weights": "qfloat8_e4m3fn",
72
+ "activations": "none"
73
+ },
74
+ "encoder.block.2.layer.1.DenseReluDense.wi_0": {
75
+ "weights": "qfloat8_e4m3fn",
76
+ "activations": "none"
77
+ },
78
+ "encoder.block.2.layer.1.DenseReluDense.wi_1": {
79
+ "weights": "qfloat8_e4m3fn",
80
+ "activations": "none"
81
+ },
82
+ "encoder.block.2.layer.1.DenseReluDense.wo": {
83
+ "weights": "qfloat8_e4m3fn",
84
+ "activations": "none"
85
+ },
86
+ "encoder.block.3.layer.0.SelfAttention.q": {
87
+ "weights": "qfloat8_e4m3fn",
88
+ "activations": "none"
89
+ },
90
+ "encoder.block.3.layer.0.SelfAttention.k": {
91
+ "weights": "qfloat8_e4m3fn",
92
+ "activations": "none"
93
+ },
94
+ "encoder.block.3.layer.0.SelfAttention.v": {
95
+ "weights": "qfloat8_e4m3fn",
96
+ "activations": "none"
97
+ },
98
+ "encoder.block.3.layer.0.SelfAttention.o": {
99
+ "weights": "qfloat8_e4m3fn",
100
+ "activations": "none"
101
+ },
102
+ "encoder.block.3.layer.1.DenseReluDense.wi_0": {
103
+ "weights": "qfloat8_e4m3fn",
104
+ "activations": "none"
105
+ },
106
+ "encoder.block.3.layer.1.DenseReluDense.wi_1": {
107
+ "weights": "qfloat8_e4m3fn",
108
+ "activations": "none"
109
+ },
110
+ "encoder.block.3.layer.1.DenseReluDense.wo": {
111
+ "weights": "qfloat8_e4m3fn",
112
+ "activations": "none"
113
+ },
114
+ "encoder.block.4.layer.0.SelfAttention.q": {
115
+ "weights": "qfloat8_e4m3fn",
116
+ "activations": "none"
117
+ },
118
+ "encoder.block.4.layer.0.SelfAttention.k": {
119
+ "weights": "qfloat8_e4m3fn",
120
+ "activations": "none"
121
+ },
122
+ "encoder.block.4.layer.0.SelfAttention.v": {
123
+ "weights": "qfloat8_e4m3fn",
124
+ "activations": "none"
125
+ },
126
+ "encoder.block.4.layer.0.SelfAttention.o": {
127
+ "weights": "qfloat8_e4m3fn",
128
+ "activations": "none"
129
+ },
130
+ "encoder.block.4.layer.1.DenseReluDense.wi_0": {
131
+ "weights": "qfloat8_e4m3fn",
132
+ "activations": "none"
133
+ },
134
+ "encoder.block.4.layer.1.DenseReluDense.wi_1": {
135
+ "weights": "qfloat8_e4m3fn",
136
+ "activations": "none"
137
+ },
138
+ "encoder.block.4.layer.1.DenseReluDense.wo": {
139
+ "weights": "qfloat8_e4m3fn",
140
+ "activations": "none"
141
+ },
142
+ "encoder.block.5.layer.0.SelfAttention.q": {
143
+ "weights": "qfloat8_e4m3fn",
144
+ "activations": "none"
145
+ },
146
+ "encoder.block.5.layer.0.SelfAttention.k": {
147
+ "weights": "qfloat8_e4m3fn",
148
+ "activations": "none"
149
+ },
150
+ "encoder.block.5.layer.0.SelfAttention.v": {
151
+ "weights": "qfloat8_e4m3fn",
152
+ "activations": "none"
153
+ },
154
+ "encoder.block.5.layer.0.SelfAttention.o": {
155
+ "weights": "qfloat8_e4m3fn",
156
+ "activations": "none"
157
+ },
158
+ "encoder.block.5.layer.1.DenseReluDense.wi_0": {
159
+ "weights": "qfloat8_e4m3fn",
160
+ "activations": "none"
161
+ },
162
+ "encoder.block.5.layer.1.DenseReluDense.wi_1": {
163
+ "weights": "qfloat8_e4m3fn",
164
+ "activations": "none"
165
+ },
166
+ "encoder.block.5.layer.1.DenseReluDense.wo": {
167
+ "weights": "qfloat8_e4m3fn",
168
+ "activations": "none"
169
+ },
170
+ "encoder.block.6.layer.0.SelfAttention.q": {
171
+ "weights": "qfloat8_e4m3fn",
172
+ "activations": "none"
173
+ },
174
+ "encoder.block.6.layer.0.SelfAttention.k": {
175
+ "weights": "qfloat8_e4m3fn",
176
+ "activations": "none"
177
+ },
178
+ "encoder.block.6.layer.0.SelfAttention.v": {
179
+ "weights": "qfloat8_e4m3fn",
180
+ "activations": "none"
181
+ },
182
+ "encoder.block.6.layer.0.SelfAttention.o": {
183
+ "weights": "qfloat8_e4m3fn",
184
+ "activations": "none"
185
+ },
186
+ "encoder.block.6.layer.1.DenseReluDense.wi_0": {
187
+ "weights": "qfloat8_e4m3fn",
188
+ "activations": "none"
189
+ },
190
+ "encoder.block.6.layer.1.DenseReluDense.wi_1": {
191
+ "weights": "qfloat8_e4m3fn",
192
+ "activations": "none"
193
+ },
194
+ "encoder.block.6.layer.1.DenseReluDense.wo": {
195
+ "weights": "qfloat8_e4m3fn",
196
+ "activations": "none"
197
+ },
198
+ "encoder.block.7.layer.0.SelfAttention.q": {
199
+ "weights": "qfloat8_e4m3fn",
200
+ "activations": "none"
201
+ },
202
+ "encoder.block.7.layer.0.SelfAttention.k": {
203
+ "weights": "qfloat8_e4m3fn",
204
+ "activations": "none"
205
+ },
206
+ "encoder.block.7.layer.0.SelfAttention.v": {
207
+ "weights": "qfloat8_e4m3fn",
208
+ "activations": "none"
209
+ },
210
+ "encoder.block.7.layer.0.SelfAttention.o": {
211
+ "weights": "qfloat8_e4m3fn",
212
+ "activations": "none"
213
+ },
214
+ "encoder.block.7.layer.1.DenseReluDense.wi_0": {
215
+ "weights": "qfloat8_e4m3fn",
216
+ "activations": "none"
217
+ },
218
+ "encoder.block.7.layer.1.DenseReluDense.wi_1": {
219
+ "weights": "qfloat8_e4m3fn",
220
+ "activations": "none"
221
+ },
222
+ "encoder.block.7.layer.1.DenseReluDense.wo": {
223
+ "weights": "qfloat8_e4m3fn",
224
+ "activations": "none"
225
+ },
226
+ "encoder.block.8.layer.0.SelfAttention.q": {
227
+ "weights": "qfloat8_e4m3fn",
228
+ "activations": "none"
229
+ },
230
+ "encoder.block.8.layer.0.SelfAttention.k": {
231
+ "weights": "qfloat8_e4m3fn",
232
+ "activations": "none"
233
+ },
234
+ "encoder.block.8.layer.0.SelfAttention.v": {
235
+ "weights": "qfloat8_e4m3fn",
236
+ "activations": "none"
237
+ },
238
+ "encoder.block.8.layer.0.SelfAttention.o": {
239
+ "weights": "qfloat8_e4m3fn",
240
+ "activations": "none"
241
+ },
242
+ "encoder.block.8.layer.1.DenseReluDense.wi_0": {
243
+ "weights": "qfloat8_e4m3fn",
244
+ "activations": "none"
245
+ },
246
+ "encoder.block.8.layer.1.DenseReluDense.wi_1": {
247
+ "weights": "qfloat8_e4m3fn",
248
+ "activations": "none"
249
+ },
250
+ "encoder.block.8.layer.1.DenseReluDense.wo": {
251
+ "weights": "qfloat8_e4m3fn",
252
+ "activations": "none"
253
+ },
254
+ "encoder.block.9.layer.0.SelfAttention.q": {
255
+ "weights": "qfloat8_e4m3fn",
256
+ "activations": "none"
257
+ },
258
+ "encoder.block.9.layer.0.SelfAttention.k": {
259
+ "weights": "qfloat8_e4m3fn",
260
+ "activations": "none"
261
+ },
262
+ "encoder.block.9.layer.0.SelfAttention.v": {
263
+ "weights": "qfloat8_e4m3fn",
264
+ "activations": "none"
265
+ },
266
+ "encoder.block.9.layer.0.SelfAttention.o": {
267
+ "weights": "qfloat8_e4m3fn",
268
+ "activations": "none"
269
+ },
270
+ "encoder.block.9.layer.1.DenseReluDense.wi_0": {
271
+ "weights": "qfloat8_e4m3fn",
272
+ "activations": "none"
273
+ },
274
+ "encoder.block.9.layer.1.DenseReluDense.wi_1": {
275
+ "weights": "qfloat8_e4m3fn",
276
+ "activations": "none"
277
+ },
278
+ "encoder.block.9.layer.1.DenseReluDense.wo": {
279
+ "weights": "qfloat8_e4m3fn",
280
+ "activations": "none"
281
+ },
282
+ "encoder.block.10.layer.0.SelfAttention.q": {
283
+ "weights": "qfloat8_e4m3fn",
284
+ "activations": "none"
285
+ },
286
+ "encoder.block.10.layer.0.SelfAttention.k": {
287
+ "weights": "qfloat8_e4m3fn",
288
+ "activations": "none"
289
+ },
290
+ "encoder.block.10.layer.0.SelfAttention.v": {
291
+ "weights": "qfloat8_e4m3fn",
292
+ "activations": "none"
293
+ },
294
+ "encoder.block.10.layer.0.SelfAttention.o": {
295
+ "weights": "qfloat8_e4m3fn",
296
+ "activations": "none"
297
+ },
298
+ "encoder.block.10.layer.1.DenseReluDense.wi_0": {
299
+ "weights": "qfloat8_e4m3fn",
300
+ "activations": "none"
301
+ },
302
+ "encoder.block.10.layer.1.DenseReluDense.wi_1": {
303
+ "weights": "qfloat8_e4m3fn",
304
+ "activations": "none"
305
+ },
306
+ "encoder.block.10.layer.1.DenseReluDense.wo": {
307
+ "weights": "qfloat8_e4m3fn",
308
+ "activations": "none"
309
+ },
310
+ "encoder.block.11.layer.0.SelfAttention.q": {
311
+ "weights": "qfloat8_e4m3fn",
312
+ "activations": "none"
313
+ },
314
+ "encoder.block.11.layer.0.SelfAttention.k": {
315
+ "weights": "qfloat8_e4m3fn",
316
+ "activations": "none"
317
+ },
318
+ "encoder.block.11.layer.0.SelfAttention.v": {
319
+ "weights": "qfloat8_e4m3fn",
320
+ "activations": "none"
321
+ },
322
+ "encoder.block.11.layer.0.SelfAttention.o": {
323
+ "weights": "qfloat8_e4m3fn",
324
+ "activations": "none"
325
+ },
326
+ "encoder.block.11.layer.1.DenseReluDense.wi_0": {
327
+ "weights": "qfloat8_e4m3fn",
328
+ "activations": "none"
329
+ },
330
+ "encoder.block.11.layer.1.DenseReluDense.wi_1": {
331
+ "weights": "qfloat8_e4m3fn",
332
+ "activations": "none"
333
+ },
334
+ "encoder.block.11.layer.1.DenseReluDense.wo": {
335
+ "weights": "qfloat8_e4m3fn",
336
+ "activations": "none"
337
+ },
338
+ "encoder.block.12.layer.0.SelfAttention.q": {
339
+ "weights": "qfloat8_e4m3fn",
340
+ "activations": "none"
341
+ },
342
+ "encoder.block.12.layer.0.SelfAttention.k": {
343
+ "weights": "qfloat8_e4m3fn",
344
+ "activations": "none"
345
+ },
346
+ "encoder.block.12.layer.0.SelfAttention.v": {
347
+ "weights": "qfloat8_e4m3fn",
348
+ "activations": "none"
349
+ },
350
+ "encoder.block.12.layer.0.SelfAttention.o": {
351
+ "weights": "qfloat8_e4m3fn",
352
+ "activations": "none"
353
+ },
354
+ "encoder.block.12.layer.1.DenseReluDense.wi_0": {
355
+ "weights": "qfloat8_e4m3fn",
356
+ "activations": "none"
357
+ },
358
+ "encoder.block.12.layer.1.DenseReluDense.wi_1": {
359
+ "weights": "qfloat8_e4m3fn",
360
+ "activations": "none"
361
+ },
362
+ "encoder.block.12.layer.1.DenseReluDense.wo": {
363
+ "weights": "qfloat8_e4m3fn",
364
+ "activations": "none"
365
+ },
366
+ "encoder.block.13.layer.0.SelfAttention.q": {
367
+ "weights": "qfloat8_e4m3fn",
368
+ "activations": "none"
369
+ },
370
+ "encoder.block.13.layer.0.SelfAttention.k": {
371
+ "weights": "qfloat8_e4m3fn",
372
+ "activations": "none"
373
+ },
374
+ "encoder.block.13.layer.0.SelfAttention.v": {
375
+ "weights": "qfloat8_e4m3fn",
376
+ "activations": "none"
377
+ },
378
+ "encoder.block.13.layer.0.SelfAttention.o": {
379
+ "weights": "qfloat8_e4m3fn",
380
+ "activations": "none"
381
+ },
382
+ "encoder.block.13.layer.1.DenseReluDense.wi_0": {
383
+ "weights": "qfloat8_e4m3fn",
384
+ "activations": "none"
385
+ },
386
+ "encoder.block.13.layer.1.DenseReluDense.wi_1": {
387
+ "weights": "qfloat8_e4m3fn",
388
+ "activations": "none"
389
+ },
390
+ "encoder.block.13.layer.1.DenseReluDense.wo": {
391
+ "weights": "qfloat8_e4m3fn",
392
+ "activations": "none"
393
+ },
394
+ "encoder.block.14.layer.0.SelfAttention.q": {
395
+ "weights": "qfloat8_e4m3fn",
396
+ "activations": "none"
397
+ },
398
+ "encoder.block.14.layer.0.SelfAttention.k": {
399
+ "weights": "qfloat8_e4m3fn",
400
+ "activations": "none"
401
+ },
402
+ "encoder.block.14.layer.0.SelfAttention.v": {
403
+ "weights": "qfloat8_e4m3fn",
404
+ "activations": "none"
405
+ },
406
+ "encoder.block.14.layer.0.SelfAttention.o": {
407
+ "weights": "qfloat8_e4m3fn",
408
+ "activations": "none"
409
+ },
410
+ "encoder.block.14.layer.1.DenseReluDense.wi_0": {
411
+ "weights": "qfloat8_e4m3fn",
412
+ "activations": "none"
413
+ },
414
+ "encoder.block.14.layer.1.DenseReluDense.wi_1": {
415
+ "weights": "qfloat8_e4m3fn",
416
+ "activations": "none"
417
+ },
418
+ "encoder.block.14.layer.1.DenseReluDense.wo": {
419
+ "weights": "qfloat8_e4m3fn",
420
+ "activations": "none"
421
+ },
422
+ "encoder.block.15.layer.0.SelfAttention.q": {
423
+ "weights": "qfloat8_e4m3fn",
424
+ "activations": "none"
425
+ },
426
+ "encoder.block.15.layer.0.SelfAttention.k": {
427
+ "weights": "qfloat8_e4m3fn",
428
+ "activations": "none"
429
+ },
430
+ "encoder.block.15.layer.0.SelfAttention.v": {
431
+ "weights": "qfloat8_e4m3fn",
432
+ "activations": "none"
433
+ },
434
+ "encoder.block.15.layer.0.SelfAttention.o": {
435
+ "weights": "qfloat8_e4m3fn",
436
+ "activations": "none"
437
+ },
438
+ "encoder.block.15.layer.1.DenseReluDense.wi_0": {
439
+ "weights": "qfloat8_e4m3fn",
440
+ "activations": "none"
441
+ },
442
+ "encoder.block.15.layer.1.DenseReluDense.wi_1": {
443
+ "weights": "qfloat8_e4m3fn",
444
+ "activations": "none"
445
+ },
446
+ "encoder.block.15.layer.1.DenseReluDense.wo": {
447
+ "weights": "qfloat8_e4m3fn",
448
+ "activations": "none"
449
+ },
450
+ "encoder.block.16.layer.0.SelfAttention.q": {
451
+ "weights": "qfloat8_e4m3fn",
452
+ "activations": "none"
453
+ },
454
+ "encoder.block.16.layer.0.SelfAttention.k": {
455
+ "weights": "qfloat8_e4m3fn",
456
+ "activations": "none"
457
+ },
458
+ "encoder.block.16.layer.0.SelfAttention.v": {
459
+ "weights": "qfloat8_e4m3fn",
460
+ "activations": "none"
461
+ },
462
+ "encoder.block.16.layer.0.SelfAttention.o": {
463
+ "weights": "qfloat8_e4m3fn",
464
+ "activations": "none"
465
+ },
466
+ "encoder.block.16.layer.1.DenseReluDense.wi_0": {
467
+ "weights": "qfloat8_e4m3fn",
468
+ "activations": "none"
469
+ },
470
+ "encoder.block.16.layer.1.DenseReluDense.wi_1": {
471
+ "weights": "qfloat8_e4m3fn",
472
+ "activations": "none"
473
+ },
474
+ "encoder.block.16.layer.1.DenseReluDense.wo": {
475
+ "weights": "qfloat8_e4m3fn",
476
+ "activations": "none"
477
+ },
478
+ "encoder.block.17.layer.0.SelfAttention.q": {
479
+ "weights": "qfloat8_e4m3fn",
480
+ "activations": "none"
481
+ },
482
+ "encoder.block.17.layer.0.SelfAttention.k": {
483
+ "weights": "qfloat8_e4m3fn",
484
+ "activations": "none"
485
+ },
486
+ "encoder.block.17.layer.0.SelfAttention.v": {
487
+ "weights": "qfloat8_e4m3fn",
488
+ "activations": "none"
489
+ },
490
+ "encoder.block.17.layer.0.SelfAttention.o": {
491
+ "weights": "qfloat8_e4m3fn",
492
+ "activations": "none"
493
+ },
494
+ "encoder.block.17.layer.1.DenseReluDense.wi_0": {
495
+ "weights": "qfloat8_e4m3fn",
496
+ "activations": "none"
497
+ },
498
+ "encoder.block.17.layer.1.DenseReluDense.wi_1": {
499
+ "weights": "qfloat8_e4m3fn",
500
+ "activations": "none"
501
+ },
502
+ "encoder.block.17.layer.1.DenseReluDense.wo": {
503
+ "weights": "qfloat8_e4m3fn",
504
+ "activations": "none"
505
+ },
506
+ "encoder.block.18.layer.0.SelfAttention.q": {
507
+ "weights": "qfloat8_e4m3fn",
508
+ "activations": "none"
509
+ },
510
+ "encoder.block.18.layer.0.SelfAttention.k": {
511
+ "weights": "qfloat8_e4m3fn",
512
+ "activations": "none"
513
+ },
514
+ "encoder.block.18.layer.0.SelfAttention.v": {
515
+ "weights": "qfloat8_e4m3fn",
516
+ "activations": "none"
517
+ },
518
+ "encoder.block.18.layer.0.SelfAttention.o": {
519
+ "weights": "qfloat8_e4m3fn",
520
+ "activations": "none"
521
+ },
522
+ "encoder.block.18.layer.1.DenseReluDense.wi_0": {
523
+ "weights": "qfloat8_e4m3fn",
524
+ "activations": "none"
525
+ },
526
+ "encoder.block.18.layer.1.DenseReluDense.wi_1": {
527
+ "weights": "qfloat8_e4m3fn",
528
+ "activations": "none"
529
+ },
530
+ "encoder.block.18.layer.1.DenseReluDense.wo": {
531
+ "weights": "qfloat8_e4m3fn",
532
+ "activations": "none"
533
+ },
534
+ "encoder.block.19.layer.0.SelfAttention.q": {
535
+ "weights": "qfloat8_e4m3fn",
536
+ "activations": "none"
537
+ },
538
+ "encoder.block.19.layer.0.SelfAttention.k": {
539
+ "weights": "qfloat8_e4m3fn",
540
+ "activations": "none"
541
+ },
542
+ "encoder.block.19.layer.0.SelfAttention.v": {
543
+ "weights": "qfloat8_e4m3fn",
544
+ "activations": "none"
545
+ },
546
+ "encoder.block.19.layer.0.SelfAttention.o": {
547
+ "weights": "qfloat8_e4m3fn",
548
+ "activations": "none"
549
+ },
550
+ "encoder.block.19.layer.1.DenseReluDense.wi_0": {
551
+ "weights": "qfloat8_e4m3fn",
552
+ "activations": "none"
553
+ },
554
+ "encoder.block.19.layer.1.DenseReluDense.wi_1": {
555
+ "weights": "qfloat8_e4m3fn",
556
+ "activations": "none"
557
+ },
558
+ "encoder.block.19.layer.1.DenseReluDense.wo": {
559
+ "weights": "qfloat8_e4m3fn",
560
+ "activations": "none"
561
+ },
562
+ "encoder.block.20.layer.0.SelfAttention.q": {
563
+ "weights": "qfloat8_e4m3fn",
564
+ "activations": "none"
565
+ },
566
+ "encoder.block.20.layer.0.SelfAttention.k": {
567
+ "weights": "qfloat8_e4m3fn",
568
+ "activations": "none"
569
+ },
570
+ "encoder.block.20.layer.0.SelfAttention.v": {
571
+ "weights": "qfloat8_e4m3fn",
572
+ "activations": "none"
573
+ },
574
+ "encoder.block.20.layer.0.SelfAttention.o": {
575
+ "weights": "qfloat8_e4m3fn",
576
+ "activations": "none"
577
+ },
578
+ "encoder.block.20.layer.1.DenseReluDense.wi_0": {
579
+ "weights": "qfloat8_e4m3fn",
580
+ "activations": "none"
581
+ },
582
+ "encoder.block.20.layer.1.DenseReluDense.wi_1": {
583
+ "weights": "qfloat8_e4m3fn",
584
+ "activations": "none"
585
+ },
586
+ "encoder.block.20.layer.1.DenseReluDense.wo": {
587
+ "weights": "qfloat8_e4m3fn",
588
+ "activations": "none"
589
+ },
590
+ "encoder.block.21.layer.0.SelfAttention.q": {
591
+ "weights": "qfloat8_e4m3fn",
592
+ "activations": "none"
593
+ },
594
+ "encoder.block.21.layer.0.SelfAttention.k": {
595
+ "weights": "qfloat8_e4m3fn",
596
+ "activations": "none"
597
+ },
598
+ "encoder.block.21.layer.0.SelfAttention.v": {
599
+ "weights": "qfloat8_e4m3fn",
600
+ "activations": "none"
601
+ },
602
+ "encoder.block.21.layer.0.SelfAttention.o": {
603
+ "weights": "qfloat8_e4m3fn",
604
+ "activations": "none"
605
+ },
606
+ "encoder.block.21.layer.1.DenseReluDense.wi_0": {
607
+ "weights": "qfloat8_e4m3fn",
608
+ "activations": "none"
609
+ },
610
+ "encoder.block.21.layer.1.DenseReluDense.wi_1": {
611
+ "weights": "qfloat8_e4m3fn",
612
+ "activations": "none"
613
+ },
614
+ "encoder.block.21.layer.1.DenseReluDense.wo": {
615
+ "weights": "qfloat8_e4m3fn",
616
+ "activations": "none"
617
+ },
618
+ "encoder.block.22.layer.0.SelfAttention.q": {
619
+ "weights": "qfloat8_e4m3fn",
620
+ "activations": "none"
621
+ },
622
+ "encoder.block.22.layer.0.SelfAttention.k": {
623
+ "weights": "qfloat8_e4m3fn",
624
+ "activations": "none"
625
+ },
626
+ "encoder.block.22.layer.0.SelfAttention.v": {
627
+ "weights": "qfloat8_e4m3fn",
628
+ "activations": "none"
629
+ },
630
+ "encoder.block.22.layer.0.SelfAttention.o": {
631
+ "weights": "qfloat8_e4m3fn",
632
+ "activations": "none"
633
+ },
634
+ "encoder.block.22.layer.1.DenseReluDense.wi_0": {
635
+ "weights": "qfloat8_e4m3fn",
636
+ "activations": "none"
637
+ },
638
+ "encoder.block.22.layer.1.DenseReluDense.wi_1": {
639
+ "weights": "qfloat8_e4m3fn",
640
+ "activations": "none"
641
+ },
642
+ "encoder.block.22.layer.1.DenseReluDense.wo": {
643
+ "weights": "qfloat8_e4m3fn",
644
+ "activations": "none"
645
+ },
646
+ "encoder.block.23.layer.0.SelfAttention.q": {
647
+ "weights": "qfloat8_e4m3fn",
648
+ "activations": "none"
649
+ },
650
+ "encoder.block.23.layer.0.SelfAttention.k": {
651
+ "weights": "qfloat8_e4m3fn",
652
+ "activations": "none"
653
+ },
654
+ "encoder.block.23.layer.0.SelfAttention.v": {
655
+ "weights": "qfloat8_e4m3fn",
656
+ "activations": "none"
657
+ },
658
+ "encoder.block.23.layer.0.SelfAttention.o": {
659
+ "weights": "qfloat8_e4m3fn",
660
+ "activations": "none"
661
+ },
662
+ "encoder.block.23.layer.1.DenseReluDense.wi_0": {
663
+ "weights": "qfloat8_e4m3fn",
664
+ "activations": "none"
665
+ },
666
+ "encoder.block.23.layer.1.DenseReluDense.wi_1": {
667
+ "weights": "qfloat8_e4m3fn",
668
+ "activations": "none"
669
+ },
670
+ "encoder.block.23.layer.1.DenseReluDense.wo": {
671
+ "weights": "qfloat8_e4m3fn",
672
+ "activations": "none"
673
+ }
674
+ }
optimum_quanto_qfloat8/tokenizer_2/special_tokens_map.json ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<extra_id_0>",
4
+ "<extra_id_1>",
5
+ "<extra_id_2>",
6
+ "<extra_id_3>",
7
+ "<extra_id_4>",
8
+ "<extra_id_5>",
9
+ "<extra_id_6>",
10
+ "<extra_id_7>",
11
+ "<extra_id_8>",
12
+ "<extra_id_9>",
13
+ "<extra_id_10>",
14
+ "<extra_id_11>",
15
+ "<extra_id_12>",
16
+ "<extra_id_13>",
17
+ "<extra_id_14>",
18
+ "<extra_id_15>",
19
+ "<extra_id_16>",
20
+ "<extra_id_17>",
21
+ "<extra_id_18>",
22
+ "<extra_id_19>",
23
+ "<extra_id_20>",
24
+ "<extra_id_21>",
25
+ "<extra_id_22>",
26
+ "<extra_id_23>",
27
+ "<extra_id_24>",
28
+ "<extra_id_25>",
29
+ "<extra_id_26>",
30
+ "<extra_id_27>",
31
+ "<extra_id_28>",
32
+ "<extra_id_29>",
33
+ "<extra_id_30>",
34
+ "<extra_id_31>",
35
+ "<extra_id_32>",
36
+ "<extra_id_33>",
37
+ "<extra_id_34>",
38
+ "<extra_id_35>",
39
+ "<extra_id_36>",
40
+ "<extra_id_37>",
41
+ "<extra_id_38>",
42
+ "<extra_id_39>",
43
+ "<extra_id_40>",
44
+ "<extra_id_41>",
45
+ "<extra_id_42>",
46
+ "<extra_id_43>",
47
+ "<extra_id_44>",
48
+ "<extra_id_45>",
49
+ "<extra_id_46>",
50
+ "<extra_id_47>",
51
+ "<extra_id_48>",
52
+ "<extra_id_49>",
53
+ "<extra_id_50>",
54
+ "<extra_id_51>",
55
+ "<extra_id_52>",
56
+ "<extra_id_53>",
57
+ "<extra_id_54>",
58
+ "<extra_id_55>",
59
+ "<extra_id_56>",
60
+ "<extra_id_57>",
61
+ "<extra_id_58>",
62
+ "<extra_id_59>",
63
+ "<extra_id_60>",
64
+ "<extra_id_61>",
65
+ "<extra_id_62>",
66
+ "<extra_id_63>",
67
+ "<extra_id_64>",
68
+ "<extra_id_65>",
69
+ "<extra_id_66>",
70
+ "<extra_id_67>",
71
+ "<extra_id_68>",
72
+ "<extra_id_69>",
73
+ "<extra_id_70>",
74
+ "<extra_id_71>",
75
+ "<extra_id_72>",
76
+ "<extra_id_73>",
77
+ "<extra_id_74>",
78
+ "<extra_id_75>",
79
+ "<extra_id_76>",
80
+ "<extra_id_77>",
81
+ "<extra_id_78>",
82
+ "<extra_id_79>",
83
+ "<extra_id_80>",
84
+ "<extra_id_81>",
85
+ "<extra_id_82>",
86
+ "<extra_id_83>",
87
+ "<extra_id_84>",
88
+ "<extra_id_85>",
89
+ "<extra_id_86>",
90
+ "<extra_id_87>",
91
+ "<extra_id_88>",
92
+ "<extra_id_89>",
93
+ "<extra_id_90>",
94
+ "<extra_id_91>",
95
+ "<extra_id_92>",
96
+ "<extra_id_93>",
97
+ "<extra_id_94>",
98
+ "<extra_id_95>",
99
+ "<extra_id_96>",
100
+ "<extra_id_97>",
101
+ "<extra_id_98>",
102
+ "<extra_id_99>"
103
+ ],
104
+ "eos_token": {
105
+ "content": "</s>",
106
+ "lstrip": false,
107
+ "normalized": false,
108
+ "rstrip": false,
109
+ "single_word": false
110
+ },
111
+ "pad_token": {
112
+ "content": "<pad>",
113
+ "lstrip": false,
114
+ "normalized": false,
115
+ "rstrip": false,
116
+ "single_word": false
117
+ },
118
+ "unk_token": {
119
+ "content": "<unk>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false
124
+ }
125
+ }
optimum_quanto_qfloat8/tokenizer_2/spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
3
+ size 791656
optimum_quanto_qfloat8/tokenizer_2/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
optimum_quanto_qfloat8/tokenizer_2/tokenizer_config.json ADDED
@@ -0,0 +1,940 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "32000": {
29
+ "content": "<extra_id_99>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "32001": {
37
+ "content": "<extra_id_98>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "32002": {
45
+ "content": "<extra_id_97>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "32003": {
53
+ "content": "<extra_id_96>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "32004": {
61
+ "content": "<extra_id_95>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "32005": {
69
+ "content": "<extra_id_94>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "32006": {
77
+ "content": "<extra_id_93>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "32007": {
85
+ "content": "<extra_id_92>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "32008": {
93
+ "content": "<extra_id_91>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "32009": {
101
+ "content": "<extra_id_90>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "32010": {
109
+ "content": "<extra_id_89>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "32011": {
117
+ "content": "<extra_id_88>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "32012": {
125
+ "content": "<extra_id_87>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "32013": {
133
+ "content": "<extra_id_86>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "32014": {
141
+ "content": "<extra_id_85>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "32015": {
149
+ "content": "<extra_id_84>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "32016": {
157
+ "content": "<extra_id_83>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "32017": {
165
+ "content": "<extra_id_82>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "32018": {
173
+ "content": "<extra_id_81>",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "32019": {
181
+ "content": "<extra_id_80>",
182
+ "lstrip": false,
183
+ "normalized": false,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": true
187
+ },
188
+ "32020": {
189
+ "content": "<extra_id_79>",
190
+ "lstrip": false,
191
+ "normalized": false,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": true
195
+ },
196
+ "32021": {
197
+ "content": "<extra_id_78>",
198
+ "lstrip": false,
199
+ "normalized": false,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": true
203
+ },
204
+ "32022": {
205
+ "content": "<extra_id_77>",
206
+ "lstrip": false,
207
+ "normalized": false,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "32023": {
213
+ "content": "<extra_id_76>",
214
+ "lstrip": false,
215
+ "normalized": false,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "32024": {
221
+ "content": "<extra_id_75>",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "32025": {
229
+ "content": "<extra_id_74>",
230
+ "lstrip": false,
231
+ "normalized": false,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "32026": {
237
+ "content": "<extra_id_73>",
238
+ "lstrip": false,
239
+ "normalized": false,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "32027": {
245
+ "content": "<extra_id_72>",
246
+ "lstrip": false,
247
+ "normalized": false,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "32028": {
253
+ "content": "<extra_id_71>",
254
+ "lstrip": false,
255
+ "normalized": false,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "32029": {
261
+ "content": "<extra_id_70>",
262
+ "lstrip": false,
263
+ "normalized": false,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": true
267
+ },
268
+ "32030": {
269
+ "content": "<extra_id_69>",
270
+ "lstrip": false,
271
+ "normalized": false,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": true
275
+ },
276
+ "32031": {
277
+ "content": "<extra_id_68>",
278
+ "lstrip": false,
279
+ "normalized": false,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": true
283
+ },
284
+ "32032": {
285
+ "content": "<extra_id_67>",
286
+ "lstrip": false,
287
+ "normalized": false,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": true
291
+ },
292
+ "32033": {
293
+ "content": "<extra_id_66>",
294
+ "lstrip": false,
295
+ "normalized": false,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": true
299
+ },
300
+ "32034": {
301
+ "content": "<extra_id_65>",
302
+ "lstrip": false,
303
+ "normalized": false,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": true
307
+ },
308
+ "32035": {
309
+ "content": "<extra_id_64>",
310
+ "lstrip": false,
311
+ "normalized": false,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": true
315
+ },
316
+ "32036": {
317
+ "content": "<extra_id_63>",
318
+ "lstrip": false,
319
+ "normalized": false,
320
+ "rstrip": false,
321
+ "single_word": false,
322
+ "special": true
323
+ },
324
+ "32037": {
325
+ "content": "<extra_id_62>",
326
+ "lstrip": false,
327
+ "normalized": false,
328
+ "rstrip": false,
329
+ "single_word": false,
330
+ "special": true
331
+ },
332
+ "32038": {
333
+ "content": "<extra_id_61>",
334
+ "lstrip": false,
335
+ "normalized": false,
336
+ "rstrip": false,
337
+ "single_word": false,
338
+ "special": true
339
+ },
340
+ "32039": {
341
+ "content": "<extra_id_60>",
342
+ "lstrip": false,
343
+ "normalized": false,
344
+ "rstrip": false,
345
+ "single_word": false,
346
+ "special": true
347
+ },
348
+ "32040": {
349
+ "content": "<extra_id_59>",
350
+ "lstrip": false,
351
+ "normalized": false,
352
+ "rstrip": false,
353
+ "single_word": false,
354
+ "special": true
355
+ },
356
+ "32041": {
357
+ "content": "<extra_id_58>",
358
+ "lstrip": false,
359
+ "normalized": false,
360
+ "rstrip": false,
361
+ "single_word": false,
362
+ "special": true
363
+ },
364
+ "32042": {
365
+ "content": "<extra_id_57>",
366
+ "lstrip": false,
367
+ "normalized": false,
368
+ "rstrip": false,
369
+ "single_word": false,
370
+ "special": true
371
+ },
372
+ "32043": {
373
+ "content": "<extra_id_56>",
374
+ "lstrip": false,
375
+ "normalized": false,
376
+ "rstrip": false,
377
+ "single_word": false,
378
+ "special": true
379
+ },
380
+ "32044": {
381
+ "content": "<extra_id_55>",
382
+ "lstrip": false,
383
+ "normalized": false,
384
+ "rstrip": false,
385
+ "single_word": false,
386
+ "special": true
387
+ },
388
+ "32045": {
389
+ "content": "<extra_id_54>",
390
+ "lstrip": false,
391
+ "normalized": false,
392
+ "rstrip": false,
393
+ "single_word": false,
394
+ "special": true
395
+ },
396
+ "32046": {
397
+ "content": "<extra_id_53>",
398
+ "lstrip": false,
399
+ "normalized": false,
400
+ "rstrip": false,
401
+ "single_word": false,
402
+ "special": true
403
+ },
404
+ "32047": {
405
+ "content": "<extra_id_52>",
406
+ "lstrip": false,
407
+ "normalized": false,
408
+ "rstrip": false,
409
+ "single_word": false,
410
+ "special": true
411
+ },
412
+ "32048": {
413
+ "content": "<extra_id_51>",
414
+ "lstrip": false,
415
+ "normalized": false,
416
+ "rstrip": false,
417
+ "single_word": false,
418
+ "special": true
419
+ },
420
+ "32049": {
421
+ "content": "<extra_id_50>",
422
+ "lstrip": false,
423
+ "normalized": false,
424
+ "rstrip": false,
425
+ "single_word": false,
426
+ "special": true
427
+ },
428
+ "32050": {
429
+ "content": "<extra_id_49>",
430
+ "lstrip": false,
431
+ "normalized": false,
432
+ "rstrip": false,
433
+ "single_word": false,
434
+ "special": true
435
+ },
436
+ "32051": {
437
+ "content": "<extra_id_48>",
438
+ "lstrip": false,
439
+ "normalized": false,
440
+ "rstrip": false,
441
+ "single_word": false,
442
+ "special": true
443
+ },
444
+ "32052": {
445
+ "content": "<extra_id_47>",
446
+ "lstrip": false,
447
+ "normalized": false,
448
+ "rstrip": false,
449
+ "single_word": false,
450
+ "special": true
451
+ },
452
+ "32053": {
453
+ "content": "<extra_id_46>",
454
+ "lstrip": false,
455
+ "normalized": false,
456
+ "rstrip": false,
457
+ "single_word": false,
458
+ "special": true
459
+ },
460
+ "32054": {
461
+ "content": "<extra_id_45>",
462
+ "lstrip": false,
463
+ "normalized": false,
464
+ "rstrip": false,
465
+ "single_word": false,
466
+ "special": true
467
+ },
468
+ "32055": {
469
+ "content": "<extra_id_44>",
470
+ "lstrip": false,
471
+ "normalized": false,
472
+ "rstrip": false,
473
+ "single_word": false,
474
+ "special": true
475
+ },
476
+ "32056": {
477
+ "content": "<extra_id_43>",
478
+ "lstrip": false,
479
+ "normalized": false,
480
+ "rstrip": false,
481
+ "single_word": false,
482
+ "special": true
483
+ },
484
+ "32057": {
485
+ "content": "<extra_id_42>",
486
+ "lstrip": false,
487
+ "normalized": false,
488
+ "rstrip": false,
489
+ "single_word": false,
490
+ "special": true
491
+ },
492
+ "32058": {
493
+ "content": "<extra_id_41>",
494
+ "lstrip": false,
495
+ "normalized": false,
496
+ "rstrip": false,
497
+ "single_word": false,
498
+ "special": true
499
+ },
500
+ "32059": {
501
+ "content": "<extra_id_40>",
502
+ "lstrip": false,
503
+ "normalized": false,
504
+ "rstrip": false,
505
+ "single_word": false,
506
+ "special": true
507
+ },
508
+ "32060": {
509
+ "content": "<extra_id_39>",
510
+ "lstrip": false,
511
+ "normalized": false,
512
+ "rstrip": false,
513
+ "single_word": false,
514
+ "special": true
515
+ },
516
+ "32061": {
517
+ "content": "<extra_id_38>",
518
+ "lstrip": false,
519
+ "normalized": false,
520
+ "rstrip": false,
521
+ "single_word": false,
522
+ "special": true
523
+ },
524
+ "32062": {
525
+ "content": "<extra_id_37>",
526
+ "lstrip": false,
527
+ "normalized": false,
528
+ "rstrip": false,
529
+ "single_word": false,
530
+ "special": true
531
+ },
532
+ "32063": {
533
+ "content": "<extra_id_36>",
534
+ "lstrip": false,
535
+ "normalized": false,
536
+ "rstrip": false,
537
+ "single_word": false,
538
+ "special": true
539
+ },
540
+ "32064": {
541
+ "content": "<extra_id_35>",
542
+ "lstrip": false,
543
+ "normalized": false,
544
+ "rstrip": false,
545
+ "single_word": false,
546
+ "special": true
547
+ },
548
+ "32065": {
549
+ "content": "<extra_id_34>",
550
+ "lstrip": false,
551
+ "normalized": false,
552
+ "rstrip": false,
553
+ "single_word": false,
554
+ "special": true
555
+ },
556
+ "32066": {
557
+ "content": "<extra_id_33>",
558
+ "lstrip": false,
559
+ "normalized": false,
560
+ "rstrip": false,
561
+ "single_word": false,
562
+ "special": true
563
+ },
564
+ "32067": {
565
+ "content": "<extra_id_32>",
566
+ "lstrip": false,
567
+ "normalized": false,
568
+ "rstrip": false,
569
+ "single_word": false,
570
+ "special": true
571
+ },
572
+ "32068": {
573
+ "content": "<extra_id_31>",
574
+ "lstrip": false,
575
+ "normalized": false,
576
+ "rstrip": false,
577
+ "single_word": false,
578
+ "special": true
579
+ },
580
+ "32069": {
581
+ "content": "<extra_id_30>",
582
+ "lstrip": false,
583
+ "normalized": false,
584
+ "rstrip": false,
585
+ "single_word": false,
586
+ "special": true
587
+ },
588
+ "32070": {
589
+ "content": "<extra_id_29>",
590
+ "lstrip": false,
591
+ "normalized": false,
592
+ "rstrip": false,
593
+ "single_word": false,
594
+ "special": true
595
+ },
596
+ "32071": {
597
+ "content": "<extra_id_28>",
598
+ "lstrip": false,
599
+ "normalized": false,
600
+ "rstrip": false,
601
+ "single_word": false,
602
+ "special": true
603
+ },
604
+ "32072": {
605
+ "content": "<extra_id_27>",
606
+ "lstrip": false,
607
+ "normalized": false,
608
+ "rstrip": false,
609
+ "single_word": false,
610
+ "special": true
611
+ },
612
+ "32073": {
613
+ "content": "<extra_id_26>",
614
+ "lstrip": false,
615
+ "normalized": false,
616
+ "rstrip": false,
617
+ "single_word": false,
618
+ "special": true
619
+ },
620
+ "32074": {
621
+ "content": "<extra_id_25>",
622
+ "lstrip": false,
623
+ "normalized": false,
624
+ "rstrip": false,
625
+ "single_word": false,
626
+ "special": true
627
+ },
628
+ "32075": {
629
+ "content": "<extra_id_24>",
630
+ "lstrip": false,
631
+ "normalized": false,
632
+ "rstrip": false,
633
+ "single_word": false,
634
+ "special": true
635
+ },
636
+ "32076": {
637
+ "content": "<extra_id_23>",
638
+ "lstrip": false,
639
+ "normalized": false,
640
+ "rstrip": false,
641
+ "single_word": false,
642
+ "special": true
643
+ },
644
+ "32077": {
645
+ "content": "<extra_id_22>",
646
+ "lstrip": false,
647
+ "normalized": false,
648
+ "rstrip": false,
649
+ "single_word": false,
650
+ "special": true
651
+ },
652
+ "32078": {
653
+ "content": "<extra_id_21>",
654
+ "lstrip": false,
655
+ "normalized": false,
656
+ "rstrip": false,
657
+ "single_word": false,
658
+ "special": true
659
+ },
660
+ "32079": {
661
+ "content": "<extra_id_20>",
662
+ "lstrip": false,
663
+ "normalized": false,
664
+ "rstrip": false,
665
+ "single_word": false,
666
+ "special": true
667
+ },
668
+ "32080": {
669
+ "content": "<extra_id_19>",
670
+ "lstrip": false,
671
+ "normalized": false,
672
+ "rstrip": false,
673
+ "single_word": false,
674
+ "special": true
675
+ },
676
+ "32081": {
677
+ "content": "<extra_id_18>",
678
+ "lstrip": false,
679
+ "normalized": false,
680
+ "rstrip": false,
681
+ "single_word": false,
682
+ "special": true
683
+ },
684
+ "32082": {
685
+ "content": "<extra_id_17>",
686
+ "lstrip": false,
687
+ "normalized": false,
688
+ "rstrip": false,
689
+ "single_word": false,
690
+ "special": true
691
+ },
692
+ "32083": {
693
+ "content": "<extra_id_16>",
694
+ "lstrip": false,
695
+ "normalized": false,
696
+ "rstrip": false,
697
+ "single_word": false,
698
+ "special": true
699
+ },
700
+ "32084": {
701
+ "content": "<extra_id_15>",
702
+ "lstrip": false,
703
+ "normalized": false,
704
+ "rstrip": false,
705
+ "single_word": false,
706
+ "special": true
707
+ },
708
+ "32085": {
709
+ "content": "<extra_id_14>",
710
+ "lstrip": false,
711
+ "normalized": false,
712
+ "rstrip": false,
713
+ "single_word": false,
714
+ "special": true
715
+ },
716
+ "32086": {
717
+ "content": "<extra_id_13>",
718
+ "lstrip": false,
719
+ "normalized": false,
720
+ "rstrip": false,
721
+ "single_word": false,
722
+ "special": true
723
+ },
724
+ "32087": {
725
+ "content": "<extra_id_12>",
726
+ "lstrip": false,
727
+ "normalized": false,
728
+ "rstrip": false,
729
+ "single_word": false,
730
+ "special": true
731
+ },
732
+ "32088": {
733
+ "content": "<extra_id_11>",
734
+ "lstrip": false,
735
+ "normalized": false,
736
+ "rstrip": false,
737
+ "single_word": false,
738
+ "special": true
739
+ },
740
+ "32089": {
741
+ "content": "<extra_id_10>",
742
+ "lstrip": false,
743
+ "normalized": false,
744
+ "rstrip": false,
745
+ "single_word": false,
746
+ "special": true
747
+ },
748
+ "32090": {
749
+ "content": "<extra_id_9>",
750
+ "lstrip": false,
751
+ "normalized": false,
752
+ "rstrip": false,
753
+ "single_word": false,
754
+ "special": true
755
+ },
756
+ "32091": {
757
+ "content": "<extra_id_8>",
758
+ "lstrip": false,
759
+ "normalized": false,
760
+ "rstrip": false,
761
+ "single_word": false,
762
+ "special": true
763
+ },
764
+ "32092": {
765
+ "content": "<extra_id_7>",
766
+ "lstrip": false,
767
+ "normalized": false,
768
+ "rstrip": false,
769
+ "single_word": false,
770
+ "special": true
771
+ },
772
+ "32093": {
773
+ "content": "<extra_id_6>",
774
+ "lstrip": false,
775
+ "normalized": false,
776
+ "rstrip": false,
777
+ "single_word": false,
778
+ "special": true
779
+ },
780
+ "32094": {
781
+ "content": "<extra_id_5>",
782
+ "lstrip": false,
783
+ "normalized": false,
784
+ "rstrip": false,
785
+ "single_word": false,
786
+ "special": true
787
+ },
788
+ "32095": {
789
+ "content": "<extra_id_4>",
790
+ "lstrip": false,
791
+ "normalized": false,
792
+ "rstrip": false,
793
+ "single_word": false,
794
+ "special": true
795
+ },
796
+ "32096": {
797
+ "content": "<extra_id_3>",
798
+ "lstrip": false,
799
+ "normalized": false,
800
+ "rstrip": false,
801
+ "single_word": false,
802
+ "special": true
803
+ },
804
+ "32097": {
805
+ "content": "<extra_id_2>",
806
+ "lstrip": false,
807
+ "normalized": false,
808
+ "rstrip": false,
809
+ "single_word": false,
810
+ "special": true
811
+ },
812
+ "32098": {
813
+ "content": "<extra_id_1>",
814
+ "lstrip": false,
815
+ "normalized": false,
816
+ "rstrip": false,
817
+ "single_word": false,
818
+ "special": true
819
+ },
820
+ "32099": {
821
+ "content": "<extra_id_0>",
822
+ "lstrip": false,
823
+ "normalized": false,
824
+ "rstrip": false,
825
+ "single_word": false,
826
+ "special": true
827
+ }
828
+ },
829
+ "additional_special_tokens": [
830
+ "<extra_id_0>",
831
+ "<extra_id_1>",
832
+ "<extra_id_2>",
833
+ "<extra_id_3>",
834
+ "<extra_id_4>",
835
+ "<extra_id_5>",
836
+ "<extra_id_6>",
837
+ "<extra_id_7>",
838
+ "<extra_id_8>",
839
+ "<extra_id_9>",
840
+ "<extra_id_10>",
841
+ "<extra_id_11>",
842
+ "<extra_id_12>",
843
+ "<extra_id_13>",
844
+ "<extra_id_14>",
845
+ "<extra_id_15>",
846
+ "<extra_id_16>",
847
+ "<extra_id_17>",
848
+ "<extra_id_18>",
849
+ "<extra_id_19>",
850
+ "<extra_id_20>",
851
+ "<extra_id_21>",
852
+ "<extra_id_22>",
853
+ "<extra_id_23>",
854
+ "<extra_id_24>",
855
+ "<extra_id_25>",
856
+ "<extra_id_26>",
857
+ "<extra_id_27>",
858
+ "<extra_id_28>",
859
+ "<extra_id_29>",
860
+ "<extra_id_30>",
861
+ "<extra_id_31>",
862
+ "<extra_id_32>",
863
+ "<extra_id_33>",
864
+ "<extra_id_34>",
865
+ "<extra_id_35>",
866
+ "<extra_id_36>",
867
+ "<extra_id_37>",
868
+ "<extra_id_38>",
869
+ "<extra_id_39>",
870
+ "<extra_id_40>",
871
+ "<extra_id_41>",
872
+ "<extra_id_42>",
873
+ "<extra_id_43>",
874
+ "<extra_id_44>",
875
+ "<extra_id_45>",
876
+ "<extra_id_46>",
877
+ "<extra_id_47>",
878
+ "<extra_id_48>",
879
+ "<extra_id_49>",
880
+ "<extra_id_50>",
881
+ "<extra_id_51>",
882
+ "<extra_id_52>",
883
+ "<extra_id_53>",
884
+ "<extra_id_54>",
885
+ "<extra_id_55>",
886
+ "<extra_id_56>",
887
+ "<extra_id_57>",
888
+ "<extra_id_58>",
889
+ "<extra_id_59>",
890
+ "<extra_id_60>",
891
+ "<extra_id_61>",
892
+ "<extra_id_62>",
893
+ "<extra_id_63>",
894
+ "<extra_id_64>",
895
+ "<extra_id_65>",
896
+ "<extra_id_66>",
897
+ "<extra_id_67>",
898
+ "<extra_id_68>",
899
+ "<extra_id_69>",
900
+ "<extra_id_70>",
901
+ "<extra_id_71>",
902
+ "<extra_id_72>",
903
+ "<extra_id_73>",
904
+ "<extra_id_74>",
905
+ "<extra_id_75>",
906
+ "<extra_id_76>",
907
+ "<extra_id_77>",
908
+ "<extra_id_78>",
909
+ "<extra_id_79>",
910
+ "<extra_id_80>",
911
+ "<extra_id_81>",
912
+ "<extra_id_82>",
913
+ "<extra_id_83>",
914
+ "<extra_id_84>",
915
+ "<extra_id_85>",
916
+ "<extra_id_86>",
917
+ "<extra_id_87>",
918
+ "<extra_id_88>",
919
+ "<extra_id_89>",
920
+ "<extra_id_90>",
921
+ "<extra_id_91>",
922
+ "<extra_id_92>",
923
+ "<extra_id_93>",
924
+ "<extra_id_94>",
925
+ "<extra_id_95>",
926
+ "<extra_id_96>",
927
+ "<extra_id_97>",
928
+ "<extra_id_98>",
929
+ "<extra_id_99>"
930
+ ],
931
+ "clean_up_tokenization_spaces": true,
932
+ "eos_token": "</s>",
933
+ "extra_ids": 100,
934
+ "legacy": true,
935
+ "model_max_length": 512,
936
+ "pad_token": "<pad>",
937
+ "sp_model_kwargs": {},
938
+ "tokenizer_class": "T5Tokenizer",
939
+ "unk_token": "<unk>"
940
+ }