Hugging Face's logo

mlx-community
/
snowflake-arctic-embed-l-v2.0-4bit

Sentence Similarity
sentence-transformers
Safetensors
Transformers.js
MLX
xlm-roberta
feature-extraction
mteb
arctic
snowflake-arctic-embed
Eval Results
text-embeddings-inference
Model card Files
xet
Community
prince-canuma commited on
Commit
430b52b
·
verified ·
1 Parent(s): 8fd86ac

Upload folder using huggingface_hub

Browse files
Files changed (10) hide show
  1. .gitattributes +1 -0
  2. README.md +0 -0
  3. config.json +31 -0
  4. config_sentence_transformers.json +11 -0
  5. model.safetensors +3 -0
  6. model.safetensors.index.json +694 -0
  7. modules.json +20 -0
  8. special_tokens_map.json +51 -0
  9. tokenizer.json +3 -0
  10. tokenizer_config.json +62 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "XLMRobertaModel"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "classifier_dropout": null,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 1024,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 4096,
14
+ "layer_norm_eps": 1e-05,
15
+ "max_position_embeddings": 8194,
16
+ "model_type": "xlm-roberta",
17
+ "num_attention_heads": 16,
18
+ "num_hidden_layers": 24,
19
+ "output_past": true,
20
+ "pad_token_id": 1,
21
+ "position_embedding_type": "absolute",
22
+ "quantization": {
23
+ "group_size": 64,
24
+ "bits": 4
25
+ },
26
+ "torch_dtype": "float32",
27
+ "transformers_version": "4.39.3",
28
+ "type_vocab_size": 1,
29
+ "use_cache": true,
30
+ "vocab_size": 250002
31
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "2.7.0.dev0",
4
+ "transformers": "4.39.3",
5
+ "pytorch": "2.1.0+cu121"
6
+ },
7
+ "prompts": {
8
+ "query": "query: "
9
+ },
10
+ "default_prompt_name": null
11
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9eec67b8c87625e204d4bd6392693932a0fdc7ccf3f2e8d83b07d5e856839fb6
3
+ size 319903754
model.safetensors.index.json ADDED
@@ -0,0 +1,694 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 319825728
4
+ },
5
+ "weight_map": {
6
+ "embeddings.LayerNorm.bias": "model.safetensors",
7
+ "embeddings.LayerNorm.weight": "model.safetensors",
8
+ "embeddings.position_embeddings.biases": "model.safetensors",
9
+ "embeddings.position_embeddings.scales": "model.safetensors",
10
+ "embeddings.position_embeddings.weight": "model.safetensors",
11
+ "embeddings.token_type_embeddings.biases": "model.safetensors",
12
+ "embeddings.token_type_embeddings.scales": "model.safetensors",
13
+ "embeddings.token_type_embeddings.weight": "model.safetensors",
14
+ "embeddings.word_embeddings.biases": "model.safetensors",
15
+ "embeddings.word_embeddings.scales": "model.safetensors",
16
+ "embeddings.word_embeddings.weight": "model.safetensors",
17
+ "encoder.layer.0.attention.output.LayerNorm.bias": "model.safetensors",
18
+ "encoder.layer.0.attention.output.LayerNorm.weight": "model.safetensors",
19
+ "encoder.layer.0.attention.output.dense.bias": "model.safetensors",
20
+ "encoder.layer.0.attention.output.dense.biases": "model.safetensors",
21
+ "encoder.layer.0.attention.output.dense.scales": "model.safetensors",
22
+ "encoder.layer.0.attention.output.dense.weight": "model.safetensors",
23
+ "encoder.layer.0.attention.self.key.bias": "model.safetensors",
24
+ "encoder.layer.0.attention.self.key.biases": "model.safetensors",
25
+ "encoder.layer.0.attention.self.key.scales": "model.safetensors",
26
+ "encoder.layer.0.attention.self.key.weight": "model.safetensors",
27
+ "encoder.layer.0.attention.self.query.bias": "model.safetensors",
28
+ "encoder.layer.0.attention.self.query.biases": "model.safetensors",
29
+ "encoder.layer.0.attention.self.query.scales": "model.safetensors",
30
+ "encoder.layer.0.attention.self.query.weight": "model.safetensors",
31
+ "encoder.layer.0.attention.self.value.bias": "model.safetensors",
32
+ "encoder.layer.0.attention.self.value.biases": "model.safetensors",
33
+ "encoder.layer.0.attention.self.value.scales": "model.safetensors",
34
+ "encoder.layer.0.attention.self.value.weight": "model.safetensors",
35
+ "encoder.layer.0.intermediate.dense.bias": "model.safetensors",
36
+ "encoder.layer.0.intermediate.dense.biases": "model.safetensors",
37
+ "encoder.layer.0.intermediate.dense.scales": "model.safetensors",
38
+ "encoder.layer.0.intermediate.dense.weight": "model.safetensors",
39
+ "encoder.layer.0.output.LayerNorm.bias": "model.safetensors",
40
+ "encoder.layer.0.output.LayerNorm.weight": "model.safetensors",
41
+ "encoder.layer.0.output.dense.bias": "model.safetensors",
42
+ "encoder.layer.0.output.dense.biases": "model.safetensors",
43
+ "encoder.layer.0.output.dense.scales": "model.safetensors",
44
+ "encoder.layer.0.output.dense.weight": "model.safetensors",
45
+ "encoder.layer.1.attention.output.LayerNorm.bias": "model.safetensors",
46
+ "encoder.layer.1.attention.output.LayerNorm.weight": "model.safetensors",
47
+ "encoder.layer.1.attention.output.dense.bias": "model.safetensors",
48
+ "encoder.layer.1.attention.output.dense.biases": "model.safetensors",
49
+ "encoder.layer.1.attention.output.dense.scales": "model.safetensors",
50
+ "encoder.layer.1.attention.output.dense.weight": "model.safetensors",
51
+ "encoder.layer.1.attention.self.key.bias": "model.safetensors",
52
+ "encoder.layer.1.attention.self.key.biases": "model.safetensors",
53
+ "encoder.layer.1.attention.self.key.scales": "model.safetensors",
54
+ "encoder.layer.1.attention.self.key.weight": "model.safetensors",
55
+ "encoder.layer.1.attention.self.query.bias": "model.safetensors",
56
+ "encoder.layer.1.attention.self.query.biases": "model.safetensors",
57
+ "encoder.layer.1.attention.self.query.scales": "model.safetensors",
58
+ "encoder.layer.1.attention.self.query.weight": "model.safetensors",
59
+ "encoder.layer.1.attention.self.value.bias": "model.safetensors",
60
+ "encoder.layer.1.attention.self.value.biases": "model.safetensors",
61
+ "encoder.layer.1.attention.self.value.scales": "model.safetensors",
62
+ "encoder.layer.1.attention.self.value.weight": "model.safetensors",
63
+ "encoder.layer.1.intermediate.dense.bias": "model.safetensors",
64
+ "encoder.layer.1.intermediate.dense.biases": "model.safetensors",
65
+ "encoder.layer.1.intermediate.dense.scales": "model.safetensors",
66
+ "encoder.layer.1.intermediate.dense.weight": "model.safetensors",
67
+ "encoder.layer.1.output.LayerNorm.bias": "model.safetensors",
68
+ "encoder.layer.1.output.LayerNorm.weight": "model.safetensors",
69
+ "encoder.layer.1.output.dense.bias": "model.safetensors",
70
+ "encoder.layer.1.output.dense.biases": "model.safetensors",
71
+ "encoder.layer.1.output.dense.scales": "model.safetensors",
72
+ "encoder.layer.1.output.dense.weight": "model.safetensors",
73
+ "encoder.layer.10.attention.output.LayerNorm.bias": "model.safetensors",
74
+ "encoder.layer.10.attention.output.LayerNorm.weight": "model.safetensors",
75
+ "encoder.layer.10.attention.output.dense.bias": "model.safetensors",
76
+ "encoder.layer.10.attention.output.dense.biases": "model.safetensors",
77
+ "encoder.layer.10.attention.output.dense.scales": "model.safetensors",
78
+ "encoder.layer.10.attention.output.dense.weight": "model.safetensors",
79
+ "encoder.layer.10.attention.self.key.bias": "model.safetensors",
80
+ "encoder.layer.10.attention.self.key.biases": "model.safetensors",
81
+ "encoder.layer.10.attention.self.key.scales": "model.safetensors",
82
+ "encoder.layer.10.attention.self.key.weight": "model.safetensors",
83
+ "encoder.layer.10.attention.self.query.bias": "model.safetensors",
84
+ "encoder.layer.10.attention.self.query.biases": "model.safetensors",
85
+ "encoder.layer.10.attention.self.query.scales": "model.safetensors",
86
+ "encoder.layer.10.attention.self.query.weight": "model.safetensors",
87
+ "encoder.layer.10.attention.self.value.bias": "model.safetensors",
88
+ "encoder.layer.10.attention.self.value.biases": "model.safetensors",
89
+ "encoder.layer.10.attention.self.value.scales": "model.safetensors",
90
+ "encoder.layer.10.attention.self.value.weight": "model.safetensors",
91
+ "encoder.layer.10.intermediate.dense.bias": "model.safetensors",
92
+ "encoder.layer.10.intermediate.dense.biases": "model.safetensors",
93
+ "encoder.layer.10.intermediate.dense.scales": "model.safetensors",
94
+ "encoder.layer.10.intermediate.dense.weight": "model.safetensors",
95
+ "encoder.layer.10.output.LayerNorm.bias": "model.safetensors",
96
+ "encoder.layer.10.output.LayerNorm.weight": "model.safetensors",
97
+ "encoder.layer.10.output.dense.bias": "model.safetensors",
98
+ "encoder.layer.10.output.dense.biases": "model.safetensors",
99
+ "encoder.layer.10.output.dense.scales": "model.safetensors",
100
+ "encoder.layer.10.output.dense.weight": "model.safetensors",
101
+ "encoder.layer.11.attention.output.LayerNorm.bias": "model.safetensors",
102
+ "encoder.layer.11.attention.output.LayerNorm.weight": "model.safetensors",
103
+ "encoder.layer.11.attention.output.dense.bias": "model.safetensors",
104
+ "encoder.layer.11.attention.output.dense.biases": "model.safetensors",
105
+ "encoder.layer.11.attention.output.dense.scales": "model.safetensors",
106
+ "encoder.layer.11.attention.output.dense.weight": "model.safetensors",
107
+ "encoder.layer.11.attention.self.key.bias": "model.safetensors",
108
+ "encoder.layer.11.attention.self.key.biases": "model.safetensors",
109
+ "encoder.layer.11.attention.self.key.scales": "model.safetensors",
110
+ "encoder.layer.11.attention.self.key.weight": "model.safetensors",
111
+ "encoder.layer.11.attention.self.query.bias": "model.safetensors",
112
+ "encoder.layer.11.attention.self.query.biases": "model.safetensors",
113
+ "encoder.layer.11.attention.self.query.scales": "model.safetensors",
114
+ "encoder.layer.11.attention.self.query.weight": "model.safetensors",
115
+ "encoder.layer.11.attention.self.value.bias": "model.safetensors",
116
+ "encoder.layer.11.attention.self.value.biases": "model.safetensors",
117
+ "encoder.layer.11.attention.self.value.scales": "model.safetensors",
118
+ "encoder.layer.11.attention.self.value.weight": "model.safetensors",
119
+ "encoder.layer.11.intermediate.dense.bias": "model.safetensors",
120
+ "encoder.layer.11.intermediate.dense.biases": "model.safetensors",
121
+ "encoder.layer.11.intermediate.dense.scales": "model.safetensors",
122
+ "encoder.layer.11.intermediate.dense.weight": "model.safetensors",
123
+ "encoder.layer.11.output.LayerNorm.bias": "model.safetensors",
124
+ "encoder.layer.11.output.LayerNorm.weight": "model.safetensors",
125
+ "encoder.layer.11.output.dense.bias": "model.safetensors",
126
+ "encoder.layer.11.output.dense.biases": "model.safetensors",
127
+ "encoder.layer.11.output.dense.scales": "model.safetensors",
128
+ "encoder.layer.11.output.dense.weight": "model.safetensors",
129
+ "encoder.layer.12.attention.output.LayerNorm.bias": "model.safetensors",
130
+ "encoder.layer.12.attention.output.LayerNorm.weight": "model.safetensors",
131
+ "encoder.layer.12.attention.output.dense.bias": "model.safetensors",
132
+ "encoder.layer.12.attention.output.dense.biases": "model.safetensors",
133
+ "encoder.layer.12.attention.output.dense.scales": "model.safetensors",
134
+ "encoder.layer.12.attention.output.dense.weight": "model.safetensors",
135
+ "encoder.layer.12.attention.self.key.bias": "model.safetensors",
136
+ "encoder.layer.12.attention.self.key.biases": "model.safetensors",
137
+ "encoder.layer.12.attention.self.key.scales": "model.safetensors",
138
+ "encoder.layer.12.attention.self.key.weight": "model.safetensors",
139
+ "encoder.layer.12.attention.self.query.bias": "model.safetensors",
140
+ "encoder.layer.12.attention.self.query.biases": "model.safetensors",
141
+ "encoder.layer.12.attention.self.query.scales": "model.safetensors",
142
+ "encoder.layer.12.attention.self.query.weight": "model.safetensors",
143
+ "encoder.layer.12.attention.self.value.bias": "model.safetensors",
144
+ "encoder.layer.12.attention.self.value.biases": "model.safetensors",
145
+ "encoder.layer.12.attention.self.value.scales": "model.safetensors",
146
+ "encoder.layer.12.attention.self.value.weight": "model.safetensors",
147
+ "encoder.layer.12.intermediate.dense.bias": "model.safetensors",
148
+ "encoder.layer.12.intermediate.dense.biases": "model.safetensors",
149
+ "encoder.layer.12.intermediate.dense.scales": "model.safetensors",
150
+ "encoder.layer.12.intermediate.dense.weight": "model.safetensors",
151
+ "encoder.layer.12.output.LayerNorm.bias": "model.safetensors",
152
+ "encoder.layer.12.output.LayerNorm.weight": "model.safetensors",
153
+ "encoder.layer.12.output.dense.bias": "model.safetensors",
154
+ "encoder.layer.12.output.dense.biases": "model.safetensors",
155
+ "encoder.layer.12.output.dense.scales": "model.safetensors",
156
+ "encoder.layer.12.output.dense.weight": "model.safetensors",
157
+ "encoder.layer.13.attention.output.LayerNorm.bias": "model.safetensors",
158
+ "encoder.layer.13.attention.output.LayerNorm.weight": "model.safetensors",
159
+ "encoder.layer.13.attention.output.dense.bias": "model.safetensors",
160
+ "encoder.layer.13.attention.output.dense.biases": "model.safetensors",
161
+ "encoder.layer.13.attention.output.dense.scales": "model.safetensors",
162
+ "encoder.layer.13.attention.output.dense.weight": "model.safetensors",
163
+ "encoder.layer.13.attention.self.key.bias": "model.safetensors",
164
+ "encoder.layer.13.attention.self.key.biases": "model.safetensors",
165
+ "encoder.layer.13.attention.self.key.scales": "model.safetensors",
166
+ "encoder.layer.13.attention.self.key.weight": "model.safetensors",
167
+ "encoder.layer.13.attention.self.query.bias": "model.safetensors",
168
+ "encoder.layer.13.attention.self.query.biases": "model.safetensors",
169
+ "encoder.layer.13.attention.self.query.scales": "model.safetensors",
170
+ "encoder.layer.13.attention.self.query.weight": "model.safetensors",
171
+ "encoder.layer.13.attention.self.value.bias": "model.safetensors",
172
+ "encoder.layer.13.attention.self.value.biases": "model.safetensors",
173
+ "encoder.layer.13.attention.self.value.scales": "model.safetensors",
174
+ "encoder.layer.13.attention.self.value.weight": "model.safetensors",
175
+ "encoder.layer.13.intermediate.dense.bias": "model.safetensors",
176
+ "encoder.layer.13.intermediate.dense.biases": "model.safetensors",
177
+ "encoder.layer.13.intermediate.dense.scales": "model.safetensors",
178
+ "encoder.layer.13.intermediate.dense.weight": "model.safetensors",
179
+ "encoder.layer.13.output.LayerNorm.bias": "model.safetensors",
180
+ "encoder.layer.13.output.LayerNorm.weight": "model.safetensors",
181
+ "encoder.layer.13.output.dense.bias": "model.safetensors",
182
+ "encoder.layer.13.output.dense.biases": "model.safetensors",
183
+ "encoder.layer.13.output.dense.scales": "model.safetensors",
184
+ "encoder.layer.13.output.dense.weight": "model.safetensors",
185
+ "encoder.layer.14.attention.output.LayerNorm.bias": "model.safetensors",
186
+ "encoder.layer.14.attention.output.LayerNorm.weight": "model.safetensors",
187
+ "encoder.layer.14.attention.output.dense.bias": "model.safetensors",
188
+ "encoder.layer.14.attention.output.dense.biases": "model.safetensors",
189
+ "encoder.layer.14.attention.output.dense.scales": "model.safetensors",
190
+ "encoder.layer.14.attention.output.dense.weight": "model.safetensors",
191
+ "encoder.layer.14.attention.self.key.bias": "model.safetensors",
192
+ "encoder.layer.14.attention.self.key.biases": "model.safetensors",
193
+ "encoder.layer.14.attention.self.key.scales": "model.safetensors",
194
+ "encoder.layer.14.attention.self.key.weight": "model.safetensors",
195
+ "encoder.layer.14.attention.self.query.bias": "model.safetensors",
196
+ "encoder.layer.14.attention.self.query.biases": "model.safetensors",
197
+ "encoder.layer.14.attention.self.query.scales": "model.safetensors",
198
+ "encoder.layer.14.attention.self.query.weight": "model.safetensors",
199
+ "encoder.layer.14.attention.self.value.bias": "model.safetensors",
200
+ "encoder.layer.14.attention.self.value.biases": "model.safetensors",
201
+ "encoder.layer.14.attention.self.value.scales": "model.safetensors",
202
+ "encoder.layer.14.attention.self.value.weight": "model.safetensors",
203
+ "encoder.layer.14.intermediate.dense.bias": "model.safetensors",
204
+ "encoder.layer.14.intermediate.dense.biases": "model.safetensors",
205
+ "encoder.layer.14.intermediate.dense.scales": "model.safetensors",
206
+ "encoder.layer.14.intermediate.dense.weight": "model.safetensors",
207
+ "encoder.layer.14.output.LayerNorm.bias": "model.safetensors",
208
+ "encoder.layer.14.output.LayerNorm.weight": "model.safetensors",
209
+ "encoder.layer.14.output.dense.bias": "model.safetensors",
210
+ "encoder.layer.14.output.dense.biases": "model.safetensors",
211
+ "encoder.layer.14.output.dense.scales": "model.safetensors",
212
+ "encoder.layer.14.output.dense.weight": "model.safetensors",
213
+ "encoder.layer.15.attention.output.LayerNorm.bias": "model.safetensors",
214
+ "encoder.layer.15.attention.output.LayerNorm.weight": "model.safetensors",
215
+ "encoder.layer.15.attention.output.dense.bias": "model.safetensors",
216
+ "encoder.layer.15.attention.output.dense.biases": "model.safetensors",
217
+ "encoder.layer.15.attention.output.dense.scales": "model.safetensors",
218
+ "encoder.layer.15.attention.output.dense.weight": "model.safetensors",
219
+ "encoder.layer.15.attention.self.key.bias": "model.safetensors",
220
+ "encoder.layer.15.attention.self.key.biases": "model.safetensors",
221
+ "encoder.layer.15.attention.self.key.scales": "model.safetensors",
222
+ "encoder.layer.15.attention.self.key.weight": "model.safetensors",
223
+ "encoder.layer.15.attention.self.query.bias": "model.safetensors",
224
+ "encoder.layer.15.attention.self.query.biases": "model.safetensors",
225
+ "encoder.layer.15.attention.self.query.scales": "model.safetensors",
226
+ "encoder.layer.15.attention.self.query.weight": "model.safetensors",
227
+ "encoder.layer.15.attention.self.value.bias": "model.safetensors",
228
+ "encoder.layer.15.attention.self.value.biases": "model.safetensors",
229
+ "encoder.layer.15.attention.self.value.scales": "model.safetensors",
230
+ "encoder.layer.15.attention.self.value.weight": "model.safetensors",
231
+ "encoder.layer.15.intermediate.dense.bias": "model.safetensors",
232
+ "encoder.layer.15.intermediate.dense.biases": "model.safetensors",
233
+ "encoder.layer.15.intermediate.dense.scales": "model.safetensors",
234
+ "encoder.layer.15.intermediate.dense.weight": "model.safetensors",
235
+ "encoder.layer.15.output.LayerNorm.bias": "model.safetensors",
236
+ "encoder.layer.15.output.LayerNorm.weight": "model.safetensors",
237
+ "encoder.layer.15.output.dense.bias": "model.safetensors",
238
+ "encoder.layer.15.output.dense.biases": "model.safetensors",
239
+ "encoder.layer.15.output.dense.scales": "model.safetensors",
240
+ "encoder.layer.15.output.dense.weight": "model.safetensors",
241
+ "encoder.layer.16.attention.output.LayerNorm.bias": "model.safetensors",
242
+ "encoder.layer.16.attention.output.LayerNorm.weight": "model.safetensors",
243
+ "encoder.layer.16.attention.output.dense.bias": "model.safetensors",
244
+ "encoder.layer.16.attention.output.dense.biases": "model.safetensors",
245
+ "encoder.layer.16.attention.output.dense.scales": "model.safetensors",
246
+ "encoder.layer.16.attention.output.dense.weight": "model.safetensors",
247
+ "encoder.layer.16.attention.self.key.bias": "model.safetensors",
248
+ "encoder.layer.16.attention.self.key.biases": "model.safetensors",
249
+ "encoder.layer.16.attention.self.key.scales": "model.safetensors",
250
+ "encoder.layer.16.attention.self.key.weight": "model.safetensors",
251
+ "encoder.layer.16.attention.self.query.bias": "model.safetensors",
252
+ "encoder.layer.16.attention.self.query.biases": "model.safetensors",
253
+ "encoder.layer.16.attention.self.query.scales": "model.safetensors",
254
+ "encoder.layer.16.attention.self.query.weight": "model.safetensors",
255
+ "encoder.layer.16.attention.self.value.bias": "model.safetensors",
256
+ "encoder.layer.16.attention.self.value.biases": "model.safetensors",
257
+ "encoder.layer.16.attention.self.value.scales": "model.safetensors",
258
+ "encoder.layer.16.attention.self.value.weight": "model.safetensors",
259
+ "encoder.layer.16.intermediate.dense.bias": "model.safetensors",
260
+ "encoder.layer.16.intermediate.dense.biases": "model.safetensors",
261
+ "encoder.layer.16.intermediate.dense.scales": "model.safetensors",
262
+ "encoder.layer.16.intermediate.dense.weight": "model.safetensors",
263
+ "encoder.layer.16.output.LayerNorm.bias": "model.safetensors",
264
+ "encoder.layer.16.output.LayerNorm.weight": "model.safetensors",
265
+ "encoder.layer.16.output.dense.bias": "model.safetensors",
266
+ "encoder.layer.16.output.dense.biases": "model.safetensors",
267
+ "encoder.layer.16.output.dense.scales": "model.safetensors",
268
+ "encoder.layer.16.output.dense.weight": "model.safetensors",
269
+ "encoder.layer.17.attention.output.LayerNorm.bias": "model.safetensors",
270
+ "encoder.layer.17.attention.output.LayerNorm.weight": "model.safetensors",
271
+ "encoder.layer.17.attention.output.dense.bias": "model.safetensors",
272
+ "encoder.layer.17.attention.output.dense.biases": "model.safetensors",
273
+ "encoder.layer.17.attention.output.dense.scales": "model.safetensors",
274
+ "encoder.layer.17.attention.output.dense.weight": "model.safetensors",
275
+ "encoder.layer.17.attention.self.key.bias": "model.safetensors",
276
+ "encoder.layer.17.attention.self.key.biases": "model.safetensors",
277
+ "encoder.layer.17.attention.self.key.scales": "model.safetensors",
278
+ "encoder.layer.17.attention.self.key.weight": "model.safetensors",
279
+ "encoder.layer.17.attention.self.query.bias": "model.safetensors",
280
+ "encoder.layer.17.attention.self.query.biases": "model.safetensors",
281
+ "encoder.layer.17.attention.self.query.scales": "model.safetensors",
282
+ "encoder.layer.17.attention.self.query.weight": "model.safetensors",
283
+ "encoder.layer.17.attention.self.value.bias": "model.safetensors",
284
+ "encoder.layer.17.attention.self.value.biases": "model.safetensors",
285
+ "encoder.layer.17.attention.self.value.scales": "model.safetensors",
286
+ "encoder.layer.17.attention.self.value.weight": "model.safetensors",
287
+ "encoder.layer.17.intermediate.dense.bias": "model.safetensors",
288
+ "encoder.layer.17.intermediate.dense.biases": "model.safetensors",
289
+ "encoder.layer.17.intermediate.dense.scales": "model.safetensors",
290
+ "encoder.layer.17.intermediate.dense.weight": "model.safetensors",
291
+ "encoder.layer.17.output.LayerNorm.bias": "model.safetensors",
292
+ "encoder.layer.17.output.LayerNorm.weight": "model.safetensors",
293
+ "encoder.layer.17.output.dense.bias": "model.safetensors",
294
+ "encoder.layer.17.output.dense.biases": "model.safetensors",
295
+ "encoder.layer.17.output.dense.scales": "model.safetensors",
296
+ "encoder.layer.17.output.dense.weight": "model.safetensors",
297
+ "encoder.layer.18.attention.output.LayerNorm.bias": "model.safetensors",
298
+ "encoder.layer.18.attention.output.LayerNorm.weight": "model.safetensors",
299
+ "encoder.layer.18.attention.output.dense.bias": "model.safetensors",
300
+ "encoder.layer.18.attention.output.dense.biases": "model.safetensors",
301
+ "encoder.layer.18.attention.output.dense.scales": "model.safetensors",
302
+ "encoder.layer.18.attention.output.dense.weight": "model.safetensors",
303
+ "encoder.layer.18.attention.self.key.bias": "model.safetensors",
304
+ "encoder.layer.18.attention.self.key.biases": "model.safetensors",
305
+ "encoder.layer.18.attention.self.key.scales": "model.safetensors",
306
+ "encoder.layer.18.attention.self.key.weight": "model.safetensors",
307
+ "encoder.layer.18.attention.self.query.bias": "model.safetensors",
308
+ "encoder.layer.18.attention.self.query.biases": "model.safetensors",
309
+ "encoder.layer.18.attention.self.query.scales": "model.safetensors",
310
+ "encoder.layer.18.attention.self.query.weight": "model.safetensors",
311
+ "encoder.layer.18.attention.self.value.bias": "model.safetensors",
312
+ "encoder.layer.18.attention.self.value.biases": "model.safetensors",
313
+ "encoder.layer.18.attention.self.value.scales": "model.safetensors",
314
+ "encoder.layer.18.attention.self.value.weight": "model.safetensors",
315
+ "encoder.layer.18.intermediate.dense.bias": "model.safetensors",
316
+ "encoder.layer.18.intermediate.dense.biases": "model.safetensors",
317
+ "encoder.layer.18.intermediate.dense.scales": "model.safetensors",
318
+ "encoder.layer.18.intermediate.dense.weight": "model.safetensors",
319
+ "encoder.layer.18.output.LayerNorm.bias": "model.safetensors",
320
+ "encoder.layer.18.output.LayerNorm.weight": "model.safetensors",
321
+ "encoder.layer.18.output.dense.bias": "model.safetensors",
322
+ "encoder.layer.18.output.dense.biases": "model.safetensors",
323
+ "encoder.layer.18.output.dense.scales": "model.safetensors",
324
+ "encoder.layer.18.output.dense.weight": "model.safetensors",
325
+ "encoder.layer.19.attention.output.LayerNorm.bias": "model.safetensors",
326
+ "encoder.layer.19.attention.output.LayerNorm.weight": "model.safetensors",
327
+ "encoder.layer.19.attention.output.dense.bias": "model.safetensors",
328
+ "encoder.layer.19.attention.output.dense.biases": "model.safetensors",
329
+ "encoder.layer.19.attention.output.dense.scales": "model.safetensors",
330
+ "encoder.layer.19.attention.output.dense.weight": "model.safetensors",
331
+ "encoder.layer.19.attention.self.key.bias": "model.safetensors",
332
+ "encoder.layer.19.attention.self.key.biases": "model.safetensors",
333
+ "encoder.layer.19.attention.self.key.scales": "model.safetensors",
334
+ "encoder.layer.19.attention.self.key.weight": "model.safetensors",
335
+ "encoder.layer.19.attention.self.query.bias": "model.safetensors",
336
+ "encoder.layer.19.attention.self.query.biases": "model.safetensors",
337
+ "encoder.layer.19.attention.self.query.scales": "model.safetensors",
338
+ "encoder.layer.19.attention.self.query.weight": "model.safetensors",
339
+ "encoder.layer.19.attention.self.value.bias": "model.safetensors",
340
+ "encoder.layer.19.attention.self.value.biases": "model.safetensors",
341
+ "encoder.layer.19.attention.self.value.scales": "model.safetensors",
342
+ "encoder.layer.19.attention.self.value.weight": "model.safetensors",
343
+ "encoder.layer.19.intermediate.dense.bias": "model.safetensors",
344
+ "encoder.layer.19.intermediate.dense.biases": "model.safetensors",
345
+ "encoder.layer.19.intermediate.dense.scales": "model.safetensors",
346
+ "encoder.layer.19.intermediate.dense.weight": "model.safetensors",
347
+ "encoder.layer.19.output.LayerNorm.bias": "model.safetensors",
348
+ "encoder.layer.19.output.LayerNorm.weight": "model.safetensors",
349
+ "encoder.layer.19.output.dense.bias": "model.safetensors",
350
+ "encoder.layer.19.output.dense.biases": "model.safetensors",
351
+ "encoder.layer.19.output.dense.scales": "model.safetensors",
352
+ "encoder.layer.19.output.dense.weight": "model.safetensors",
353
+ "encoder.layer.2.attention.output.LayerNorm.bias": "model.safetensors",
354
+ "encoder.layer.2.attention.output.LayerNorm.weight": "model.safetensors",
355
+ "encoder.layer.2.attention.output.dense.bias": "model.safetensors",
356
+ "encoder.layer.2.attention.output.dense.biases": "model.safetensors",
357
+ "encoder.layer.2.attention.output.dense.scales": "model.safetensors",
358
+ "encoder.layer.2.attention.output.dense.weight": "model.safetensors",
359
+ "encoder.layer.2.attention.self.key.bias": "model.safetensors",
360
+ "encoder.layer.2.attention.self.key.biases": "model.safetensors",
361
+ "encoder.layer.2.attention.self.key.scales": "model.safetensors",
362
+ "encoder.layer.2.attention.self.key.weight": "model.safetensors",
363
+ "encoder.layer.2.attention.self.query.bias": "model.safetensors",
364
+ "encoder.layer.2.attention.self.query.biases": "model.safetensors",
365
+ "encoder.layer.2.attention.self.query.scales": "model.safetensors",
366
+ "encoder.layer.2.attention.self.query.weight": "model.safetensors",
367
+ "encoder.layer.2.attention.self.value.bias": "model.safetensors",
368
+ "encoder.layer.2.attention.self.value.biases": "model.safetensors",
369
+ "encoder.layer.2.attention.self.value.scales": "model.safetensors",
370
+ "encoder.layer.2.attention.self.value.weight": "model.safetensors",
371
+ "encoder.layer.2.intermediate.dense.bias": "model.safetensors",
372
+ "encoder.layer.2.intermediate.dense.biases": "model.safetensors",
373
+ "encoder.layer.2.intermediate.dense.scales": "model.safetensors",
374
+ "encoder.layer.2.intermediate.dense.weight": "model.safetensors",
375
+ "encoder.layer.2.output.LayerNorm.bias": "model.safetensors",
376
+ "encoder.layer.2.output.LayerNorm.weight": "model.safetensors",
377
+ "encoder.layer.2.output.dense.bias": "model.safetensors",
378
+ "encoder.layer.2.output.dense.biases": "model.safetensors",
379
+ "encoder.layer.2.output.dense.scales": "model.safetensors",
380
+ "encoder.layer.2.output.dense.weight": "model.safetensors",
381
+ "encoder.layer.20.attention.output.LayerNorm.bias": "model.safetensors",
382
+ "encoder.layer.20.attention.output.LayerNorm.weight": "model.safetensors",
383
+ "encoder.layer.20.attention.output.dense.bias": "model.safetensors",
384
+ "encoder.layer.20.attention.output.dense.biases": "model.safetensors",
385
+ "encoder.layer.20.attention.output.dense.scales": "model.safetensors",
386
+ "encoder.layer.20.attention.output.dense.weight": "model.safetensors",
387
+ "encoder.layer.20.attention.self.key.bias": "model.safetensors",
388
+ "encoder.layer.20.attention.self.key.biases": "model.safetensors",
389
+ "encoder.layer.20.attention.self.key.scales": "model.safetensors",
390
+ "encoder.layer.20.attention.self.key.weight": "model.safetensors",
391
+ "encoder.layer.20.attention.self.query.bias": "model.safetensors",
392
+ "encoder.layer.20.attention.self.query.biases": "model.safetensors",
393
+ "encoder.layer.20.attention.self.query.scales": "model.safetensors",
394
+ "encoder.layer.20.attention.self.query.weight": "model.safetensors",
395
+ "encoder.layer.20.attention.self.value.bias": "model.safetensors",
396
+ "encoder.layer.20.attention.self.value.biases": "model.safetensors",
397
+ "encoder.layer.20.attention.self.value.scales": "model.safetensors",
398
+ "encoder.layer.20.attention.self.value.weight": "model.safetensors",
399
+ "encoder.layer.20.intermediate.dense.bias": "model.safetensors",
400
+ "encoder.layer.20.intermediate.dense.biases": "model.safetensors",
401
+ "encoder.layer.20.intermediate.dense.scales": "model.safetensors",
402
+ "encoder.layer.20.intermediate.dense.weight": "model.safetensors",
403
+ "encoder.layer.20.output.LayerNorm.bias": "model.safetensors",
404
+ "encoder.layer.20.output.LayerNorm.weight": "model.safetensors",
405
+ "encoder.layer.20.output.dense.bias": "model.safetensors",
406
+ "encoder.layer.20.output.dense.biases": "model.safetensors",
407
+ "encoder.layer.20.output.dense.scales": "model.safetensors",
408
+ "encoder.layer.20.output.dense.weight": "model.safetensors",
409
+ "encoder.layer.21.attention.output.LayerNorm.bias": "model.safetensors",
410
+ "encoder.layer.21.attention.output.LayerNorm.weight": "model.safetensors",
411
+ "encoder.layer.21.attention.output.dense.bias": "model.safetensors",
412
+ "encoder.layer.21.attention.output.dense.biases": "model.safetensors",
413
+ "encoder.layer.21.attention.output.dense.scales": "model.safetensors",
414
+ "encoder.layer.21.attention.output.dense.weight": "model.safetensors",
415
+ "encoder.layer.21.attention.self.key.bias": "model.safetensors",
416
+ "encoder.layer.21.attention.self.key.biases": "model.safetensors",
417
+ "encoder.layer.21.attention.self.key.scales": "model.safetensors",
418
+ "encoder.layer.21.attention.self.key.weight": "model.safetensors",
419
+ "encoder.layer.21.attention.self.query.bias": "model.safetensors",
420
+ "encoder.layer.21.attention.self.query.biases": "model.safetensors",
421
+ "encoder.layer.21.attention.self.query.scales": "model.safetensors",
422
+ "encoder.layer.21.attention.self.query.weight": "model.safetensors",
423
+ "encoder.layer.21.attention.self.value.bias": "model.safetensors",
424
+ "encoder.layer.21.attention.self.value.biases": "model.safetensors",
425
+ "encoder.layer.21.attention.self.value.scales": "model.safetensors",
426
+ "encoder.layer.21.attention.self.value.weight": "model.safetensors",
427
+ "encoder.layer.21.intermediate.dense.bias": "model.safetensors",
428
+ "encoder.layer.21.intermediate.dense.biases": "model.safetensors",
429
+ "encoder.layer.21.intermediate.dense.scales": "model.safetensors",
430
+ "encoder.layer.21.intermediate.dense.weight": "model.safetensors",
431
+ "encoder.layer.21.output.LayerNorm.bias": "model.safetensors",
432
+ "encoder.layer.21.output.LayerNorm.weight": "model.safetensors",
433
+ "encoder.layer.21.output.dense.bias": "model.safetensors",
434
+ "encoder.layer.21.output.dense.biases": "model.safetensors",
435
+ "encoder.layer.21.output.dense.scales": "model.safetensors",
436
+ "encoder.layer.21.output.dense.weight": "model.safetensors",
437
+ "encoder.layer.22.attention.output.LayerNorm.bias": "model.safetensors",
438
+ "encoder.layer.22.attention.output.LayerNorm.weight": "model.safetensors",
439
+ "encoder.layer.22.attention.output.dense.bias": "model.safetensors",
440
+ "encoder.layer.22.attention.output.dense.biases": "model.safetensors",
441
+ "encoder.layer.22.attention.output.dense.scales": "model.safetensors",
442
+ "encoder.layer.22.attention.output.dense.weight": "model.safetensors",
443
+ "encoder.layer.22.attention.self.key.bias": "model.safetensors",
444
+ "encoder.layer.22.attention.self.key.biases": "model.safetensors",
445
+ "encoder.layer.22.attention.self.key.scales": "model.safetensors",
446
+ "encoder.layer.22.attention.self.key.weight": "model.safetensors",
447
+ "encoder.layer.22.attention.self.query.bias": "model.safetensors",
448
+ "encoder.layer.22.attention.self.query.biases": "model.safetensors",
449
+ "encoder.layer.22.attention.self.query.scales": "model.safetensors",
450
+ "encoder.layer.22.attention.self.query.weight": "model.safetensors",
451
+ "encoder.layer.22.attention.self.value.bias": "model.safetensors",
452
+ "encoder.layer.22.attention.self.value.biases": "model.safetensors",
453
+ "encoder.layer.22.attention.self.value.scales": "model.safetensors",
454
+ "encoder.layer.22.attention.self.value.weight": "model.safetensors",
455
+ "encoder.layer.22.intermediate.dense.bias": "model.safetensors",
456
+ "encoder.layer.22.intermediate.dense.biases": "model.safetensors",
457
+ "encoder.layer.22.intermediate.dense.scales": "model.safetensors",
458
+ "encoder.layer.22.intermediate.dense.weight": "model.safetensors",
459
+ "encoder.layer.22.output.LayerNorm.bias": "model.safetensors",
460
+ "encoder.layer.22.output.LayerNorm.weight": "model.safetensors",
461
+ "encoder.layer.22.output.dense.bias": "model.safetensors",
462
+ "encoder.layer.22.output.dense.biases": "model.safetensors",
463
+ "encoder.layer.22.output.dense.scales": "model.safetensors",
464
+ "encoder.layer.22.output.dense.weight": "model.safetensors",
465
+ "encoder.layer.23.attention.output.LayerNorm.bias": "model.safetensors",
466
+ "encoder.layer.23.attention.output.LayerNorm.weight": "model.safetensors",
467
+ "encoder.layer.23.attention.output.dense.bias": "model.safetensors",
468
+ "encoder.layer.23.attention.output.dense.biases": "model.safetensors",
469
+ "encoder.layer.23.attention.output.dense.scales": "model.safetensors",
470
+ "encoder.layer.23.attention.output.dense.weight": "model.safetensors",
471
+ "encoder.layer.23.attention.self.key.bias": "model.safetensors",
472
+ "encoder.layer.23.attention.self.key.biases": "model.safetensors",
473
+ "encoder.layer.23.attention.self.key.scales": "model.safetensors",
474
+ "encoder.layer.23.attention.self.key.weight": "model.safetensors",
475
+ "encoder.layer.23.attention.self.query.bias": "model.safetensors",
476
+ "encoder.layer.23.attention.self.query.biases": "model.safetensors",
477
+ "encoder.layer.23.attention.self.query.scales": "model.safetensors",
478
+ "encoder.layer.23.attention.self.query.weight": "model.safetensors",
479
+ "encoder.layer.23.attention.self.value.bias": "model.safetensors",
480
+ "encoder.layer.23.attention.self.value.biases": "model.safetensors",
481
+ "encoder.layer.23.attention.self.value.scales": "model.safetensors",
482
+ "encoder.layer.23.attention.self.value.weight": "model.safetensors",
483
+ "encoder.layer.23.intermediate.dense.bias": "model.safetensors",
484
+ "encoder.layer.23.intermediate.dense.biases": "model.safetensors",
485
+ "encoder.layer.23.intermediate.dense.scales": "model.safetensors",
486
+ "encoder.layer.23.intermediate.dense.weight": "model.safetensors",
487
+ "encoder.layer.23.output.LayerNorm.bias": "model.safetensors",
488
+ "encoder.layer.23.output.LayerNorm.weight": "model.safetensors",
489
+ "encoder.layer.23.output.dense.bias": "model.safetensors",
490
+ "encoder.layer.23.output.dense.biases": "model.safetensors",
491
+ "encoder.layer.23.output.dense.scales": "model.safetensors",
492
+ "encoder.layer.23.output.dense.weight": "model.safetensors",
493
+ "encoder.layer.3.attention.output.LayerNorm.bias": "model.safetensors",
494
+ "encoder.layer.3.attention.output.LayerNorm.weight": "model.safetensors",
495
+ "encoder.layer.3.attention.output.dense.bias": "model.safetensors",
496
+ "encoder.layer.3.attention.output.dense.biases": "model.safetensors",
497
+ "encoder.layer.3.attention.output.dense.scales": "model.safetensors",
498
+ "encoder.layer.3.attention.output.dense.weight": "model.safetensors",
499
+ "encoder.layer.3.attention.self.key.bias": "model.safetensors",
500
+ "encoder.layer.3.attention.self.key.biases": "model.safetensors",
501
+ "encoder.layer.3.attention.self.key.scales": "model.safetensors",
502
+ "encoder.layer.3.attention.self.key.weight": "model.safetensors",
503
+ "encoder.layer.3.attention.self.query.bias": "model.safetensors",
504
+ "encoder.layer.3.attention.self.query.biases": "model.safetensors",
505
+ "encoder.layer.3.attention.self.query.scales": "model.safetensors",
506
+ "encoder.layer.3.attention.self.query.weight": "model.safetensors",
507
+ "encoder.layer.3.attention.self.value.bias": "model.safetensors",
508
+ "encoder.layer.3.attention.self.value.biases": "model.safetensors",
509
+ "encoder.layer.3.attention.self.value.scales": "model.safetensors",
510
+ "encoder.layer.3.attention.self.value.weight": "model.safetensors",
511
+ "encoder.layer.3.intermediate.dense.bias": "model.safetensors",
512
+ "encoder.layer.3.intermediate.dense.biases": "model.safetensors",
513
+ "encoder.layer.3.intermediate.dense.scales": "model.safetensors",
514
+ "encoder.layer.3.intermediate.dense.weight": "model.safetensors",
515
+ "encoder.layer.3.output.LayerNorm.bias": "model.safetensors",
516
+ "encoder.layer.3.output.LayerNorm.weight": "model.safetensors",
517
+ "encoder.layer.3.output.dense.bias": "model.safetensors",
518
+ "encoder.layer.3.output.dense.biases": "model.safetensors",
519
+ "encoder.layer.3.output.dense.scales": "model.safetensors",
520
+ "encoder.layer.3.output.dense.weight": "model.safetensors",
521
+ "encoder.layer.4.attention.output.LayerNorm.bias": "model.safetensors",
522
+ "encoder.layer.4.attention.output.LayerNorm.weight": "model.safetensors",
523
+ "encoder.layer.4.attention.output.dense.bias": "model.safetensors",
524
+ "encoder.layer.4.attention.output.dense.biases": "model.safetensors",
525
+ "encoder.layer.4.attention.output.dense.scales": "model.safetensors",
526
+ "encoder.layer.4.attention.output.dense.weight": "model.safetensors",
527
+ "encoder.layer.4.attention.self.key.bias": "model.safetensors",
528
+ "encoder.layer.4.attention.self.key.biases": "model.safetensors",
529
+ "encoder.layer.4.attention.self.key.scales": "model.safetensors",
530
+ "encoder.layer.4.attention.self.key.weight": "model.safetensors",
531
+ "encoder.layer.4.attention.self.query.bias": "model.safetensors",
532
+ "encoder.layer.4.attention.self.query.biases": "model.safetensors",
533
+ "encoder.layer.4.attention.self.query.scales": "model.safetensors",
534
+ "encoder.layer.4.attention.self.query.weight": "model.safetensors",
535
+ "encoder.layer.4.attention.self.value.bias": "model.safetensors",
536
+ "encoder.layer.4.attention.self.value.biases": "model.safetensors",
537
+ "encoder.layer.4.attention.self.value.scales": "model.safetensors",
538
+ "encoder.layer.4.attention.self.value.weight": "model.safetensors",
539
+ "encoder.layer.4.intermediate.dense.bias": "model.safetensors",
540
+ "encoder.layer.4.intermediate.dense.biases": "model.safetensors",
541
+ "encoder.layer.4.intermediate.dense.scales": "model.safetensors",
542
+ "encoder.layer.4.intermediate.dense.weight": "model.safetensors",
543
+ "encoder.layer.4.output.LayerNorm.bias": "model.safetensors",
544
+ "encoder.layer.4.output.LayerNorm.weight": "model.safetensors",
545
+ "encoder.layer.4.output.dense.bias": "model.safetensors",
546
+ "encoder.layer.4.output.dense.biases": "model.safetensors",
547
+ "encoder.layer.4.output.dense.scales": "model.safetensors",
548
+ "encoder.layer.4.output.dense.weight": "model.safetensors",
549
+ "encoder.layer.5.attention.output.LayerNorm.bias": "model.safetensors",
550
+ "encoder.layer.5.attention.output.LayerNorm.weight": "model.safetensors",
551
+ "encoder.layer.5.attention.output.dense.bias": "model.safetensors",
552
+ "encoder.layer.5.attention.output.dense.biases": "model.safetensors",
553
+ "encoder.layer.5.attention.output.dense.scales": "model.safetensors",
554
+ "encoder.layer.5.attention.output.dense.weight": "model.safetensors",
555
+ "encoder.layer.5.attention.self.key.bias": "model.safetensors",
556
+ "encoder.layer.5.attention.self.key.biases": "model.safetensors",
557
+ "encoder.layer.5.attention.self.key.scales": "model.safetensors",
558
+ "encoder.layer.5.attention.self.key.weight": "model.safetensors",
559
+ "encoder.layer.5.attention.self.query.bias": "model.safetensors",
560
+ "encoder.layer.5.attention.self.query.biases": "model.safetensors",
561
+ "encoder.layer.5.attention.self.query.scales": "model.safetensors",
562
+ "encoder.layer.5.attention.self.query.weight": "model.safetensors",
563
+ "encoder.layer.5.attention.self.value.bias": "model.safetensors",
564
+ "encoder.layer.5.attention.self.value.biases": "model.safetensors",
565
+ "encoder.layer.5.attention.self.value.scales": "model.safetensors",
566
+ "encoder.layer.5.attention.self.value.weight": "model.safetensors",
567
+ "encoder.layer.5.intermediate.dense.bias": "model.safetensors",
568
+ "encoder.layer.5.intermediate.dense.biases": "model.safetensors",
569
+ "encoder.layer.5.intermediate.dense.scales": "model.safetensors",
570
+ "encoder.layer.5.intermediate.dense.weight": "model.safetensors",
571
+ "encoder.layer.5.output.LayerNorm.bias": "model.safetensors",
572
+ "encoder.layer.5.output.LayerNorm.weight": "model.safetensors",
573
+ "encoder.layer.5.output.dense.bias": "model.safetensors",
574
+ "encoder.layer.5.output.dense.biases": "model.safetensors",
575
+ "encoder.layer.5.output.dense.scales": "model.safetensors",
576
+ "encoder.layer.5.output.dense.weight": "model.safetensors",
577
+ "encoder.layer.6.attention.output.LayerNorm.bias": "model.safetensors",
578
+ "encoder.layer.6.attention.output.LayerNorm.weight": "model.safetensors",
579
+ "encoder.layer.6.attention.output.dense.bias": "model.safetensors",
580
+ "encoder.layer.6.attention.output.dense.biases": "model.safetensors",
581
+ "encoder.layer.6.attention.output.dense.scales": "model.safetensors",
582
+ "encoder.layer.6.attention.output.dense.weight": "model.safetensors",
583
+ "encoder.layer.6.attention.self.key.bias": "model.safetensors",
584
+ "encoder.layer.6.attention.self.key.biases": "model.safetensors",
585
+ "encoder.layer.6.attention.self.key.scales": "model.safetensors",
586
+ "encoder.layer.6.attention.self.key.weight": "model.safetensors",
587
+ "encoder.layer.6.attention.self.query.bias": "model.safetensors",
588
+ "encoder.layer.6.attention.self.query.biases": "model.safetensors",
589
+ "encoder.layer.6.attention.self.query.scales": "model.safetensors",
590
+ "encoder.layer.6.attention.self.query.weight": "model.safetensors",
591
+ "encoder.layer.6.attention.self.value.bias": "model.safetensors",
592
+ "encoder.layer.6.attention.self.value.biases": "model.safetensors",
593
+ "encoder.layer.6.attention.self.value.scales": "model.safetensors",
594
+ "encoder.layer.6.attention.self.value.weight": "model.safetensors",
595
+ "encoder.layer.6.intermediate.dense.bias": "model.safetensors",
596
+ "encoder.layer.6.intermediate.dense.biases": "model.safetensors",
597
+ "encoder.layer.6.intermediate.dense.scales": "model.safetensors",
598
+ "encoder.layer.6.intermediate.dense.weight": "model.safetensors",
599
+ "encoder.layer.6.output.LayerNorm.bias": "model.safetensors",
600
+ "encoder.layer.6.output.LayerNorm.weight": "model.safetensors",
601
+ "encoder.layer.6.output.dense.bias": "model.safetensors",
602
+ "encoder.layer.6.output.dense.biases": "model.safetensors",
603
+ "encoder.layer.6.output.dense.scales": "model.safetensors",
604
+ "encoder.layer.6.output.dense.weight": "model.safetensors",
605
+ "encoder.layer.7.attention.output.LayerNorm.bias": "model.safetensors",
606
+ "encoder.layer.7.attention.output.LayerNorm.weight": "model.safetensors",
607
+ "encoder.layer.7.attention.output.dense.bias": "model.safetensors",
608
+ "encoder.layer.7.attention.output.dense.biases": "model.safetensors",
609
+ "encoder.layer.7.attention.output.dense.scales": "model.safetensors",
610
+ "encoder.layer.7.attention.output.dense.weight": "model.safetensors",
611
+ "encoder.layer.7.attention.self.key.bias": "model.safetensors",
612
+ "encoder.layer.7.attention.self.key.biases": "model.safetensors",
613
+ "encoder.layer.7.attention.self.key.scales": "model.safetensors",
614
+ "encoder.layer.7.attention.self.key.weight": "model.safetensors",
615
+ "encoder.layer.7.attention.self.query.bias": "model.safetensors",
616
+ "encoder.layer.7.attention.self.query.biases": "model.safetensors",
617
+ "encoder.layer.7.attention.self.query.scales": "model.safetensors",
618
+ "encoder.layer.7.attention.self.query.weight": "model.safetensors",
619
+ "encoder.layer.7.attention.self.value.bias": "model.safetensors",
620
+ "encoder.layer.7.attention.self.value.biases": "model.safetensors",
621
+ "encoder.layer.7.attention.self.value.scales": "model.safetensors",
622
+ "encoder.layer.7.attention.self.value.weight": "model.safetensors",
623
+ "encoder.layer.7.intermediate.dense.bias": "model.safetensors",
624
+ "encoder.layer.7.intermediate.dense.biases": "model.safetensors",
625
+ "encoder.layer.7.intermediate.dense.scales": "model.safetensors",
626
+ "encoder.layer.7.intermediate.dense.weight": "model.safetensors",
627
+ "encoder.layer.7.output.LayerNorm.bias": "model.safetensors",
628
+ "encoder.layer.7.output.LayerNorm.weight": "model.safetensors",
629
+ "encoder.layer.7.output.dense.bias": "model.safetensors",
630
+ "encoder.layer.7.output.dense.biases": "model.safetensors",
631
+ "encoder.layer.7.output.dense.scales": "model.safetensors",
632
+ "encoder.layer.7.output.dense.weight": "model.safetensors",
633
+ "encoder.layer.8.attention.output.LayerNorm.bias": "model.safetensors",
634
+ "encoder.layer.8.attention.output.LayerNorm.weight": "model.safetensors",
635
+ "encoder.layer.8.attention.output.dense.bias": "model.safetensors",
636
+ "encoder.layer.8.attention.output.dense.biases": "model.safetensors",
637
+ "encoder.layer.8.attention.output.dense.scales": "model.safetensors",
638
+ "encoder.layer.8.attention.output.dense.weight": "model.safetensors",
639
+ "encoder.layer.8.attention.self.key.bias": "model.safetensors",
640
+ "encoder.layer.8.attention.self.key.biases": "model.safetensors",
641
+ "encoder.layer.8.attention.self.key.scales": "model.safetensors",
642
+ "encoder.layer.8.attention.self.key.weight": "model.safetensors",
643
+ "encoder.layer.8.attention.self.query.bias": "model.safetensors",
644
+ "encoder.layer.8.attention.self.query.biases": "model.safetensors",
645
+ "encoder.layer.8.attention.self.query.scales": "model.safetensors",
646
+ "encoder.layer.8.attention.self.query.weight": "model.safetensors",
647
+ "encoder.layer.8.attention.self.value.bias": "model.safetensors",
648
+ "encoder.layer.8.attention.self.value.biases": "model.safetensors",
649
+ "encoder.layer.8.attention.self.value.scales": "model.safetensors",
650
+ "encoder.layer.8.attention.self.value.weight": "model.safetensors",
651
+ "encoder.layer.8.intermediate.dense.bias": "model.safetensors",
652
+ "encoder.layer.8.intermediate.dense.biases": "model.safetensors",
653
+ "encoder.layer.8.intermediate.dense.scales": "model.safetensors",
654
+ "encoder.layer.8.intermediate.dense.weight": "model.safetensors",
655
+ "encoder.layer.8.output.LayerNorm.bias": "model.safetensors",
656
+ "encoder.layer.8.output.LayerNorm.weight": "model.safetensors",
657
+ "encoder.layer.8.output.dense.bias": "model.safetensors",
658
+ "encoder.layer.8.output.dense.biases": "model.safetensors",
659
+ "encoder.layer.8.output.dense.scales": "model.safetensors",
660
+ "encoder.layer.8.output.dense.weight": "model.safetensors",
661
+ "encoder.layer.9.attention.output.LayerNorm.bias": "model.safetensors",
662
+ "encoder.layer.9.attention.output.LayerNorm.weight": "model.safetensors",
663
+ "encoder.layer.9.attention.output.dense.bias": "model.safetensors",
664
+ "encoder.layer.9.attention.output.dense.biases": "model.safetensors",
665
+ "encoder.layer.9.attention.output.dense.scales": "model.safetensors",
666
+ "encoder.layer.9.attention.output.dense.weight": "model.safetensors",
667
+ "encoder.layer.9.attention.self.key.bias": "model.safetensors",
668
+ "encoder.layer.9.attention.self.key.biases": "model.safetensors",
669
+ "encoder.layer.9.attention.self.key.scales": "model.safetensors",
670
+ "encoder.layer.9.attention.self.key.weight": "model.safetensors",
671
+ "encoder.layer.9.attention.self.query.bias": "model.safetensors",
672
+ "encoder.layer.9.attention.self.query.biases": "model.safetensors",
673
+ "encoder.layer.9.attention.self.query.scales": "model.safetensors",
674
+ "encoder.layer.9.attention.self.query.weight": "model.safetensors",
675
+ "encoder.layer.9.attention.self.value.bias": "model.safetensors",
676
+ "encoder.layer.9.attention.self.value.biases": "model.safetensors",
677
+ "encoder.layer.9.attention.self.value.scales": "model.safetensors",
678
+ "encoder.layer.9.attention.self.value.weight": "model.safetensors",
679
+ "encoder.layer.9.intermediate.dense.bias": "model.safetensors",
680
+ "encoder.layer.9.intermediate.dense.biases": "model.safetensors",
681
+ "encoder.layer.9.intermediate.dense.scales": "model.safetensors",
682
+ "encoder.layer.9.intermediate.dense.weight": "model.safetensors",
683
+ "encoder.layer.9.output.LayerNorm.bias": "model.safetensors",
684
+ "encoder.layer.9.output.LayerNorm.weight": "model.safetensors",
685
+ "encoder.layer.9.output.dense.bias": "model.safetensors",
686
+ "encoder.layer.9.output.dense.biases": "model.safetensors",
687
+ "encoder.layer.9.output.dense.scales": "model.safetensors",
688
+ "encoder.layer.9.output.dense.weight": "model.safetensors",
689
+ "pooler.dense.bias": "model.safetensors",
690
+ "pooler.dense.biases": "model.safetensors",
691
+ "pooler.dense.scales": "model.safetensors",
692
+ "pooler.dense.weight": "model.safetensors"
693
+ }
694
+ }
modules.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "idx": 0,
4
+ "name": "0",
5
+ "path": "",
6
+ "type": "sentence_transformers.models.Transformer"
7
+ },
8
+ {
9
+ "idx": 1,
10
+ "name": "1",
11
+ "path": "1_Pooling",
12
+ "type": "sentence_transformers.models.Pooling"
13
+ },
14
+ {
15
+ "idx": 2,
16
+ "name": "2",
17
+ "path": "2_Normalize",
18
+ "type": "sentence_transformers.models.Normalize"
19
+ }
20
+ ]
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9a6af42442a3e3e9f05f618eae0bb2d98ca4f6a6406cb80ef7a4fa865204d61
3
+ size 17083052
tokenizer_config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "250001": {
36
+ "content": "<mask>",
37
+ "lstrip": true,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "<s>",
47
+ "eos_token": "</s>",
48
+ "extra_special_tokens": {},
49
+ "mask_token": "<mask>",
50
+ "max_length": 512,
51
+ "model_max_length": 8192,
52
+ "pad_to_multiple_of": null,
53
+ "pad_token": "<pad>",
54
+ "pad_token_type_id": 0,
55
+ "padding_side": "right",
56
+ "sep_token": "</s>",
57
+ "stride": 0,
58
+ "tokenizer_class": "XLMRobertaTokenizerFast",
59
+ "truncation_side": "right",
60
+ "truncation_strategy": "longest_first",
61
+ "unk_token": "<unk>"
62
+ }