pszemraj commited on
Commit
f4037dc
·
verified ·
0 Parent(s):

Super-squash branch 'main' using huggingface_hub

Browse files
.gitattributes ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz 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
README.md ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ language:
5
+ - en
6
+ ---
7
+
8
+ # test of ModernBERT2Olmo-large_1b
9
+
10
+ experimental seq2seq with EncoderDecoderModel. You will need to patch `modeling_llama.py` with [this code](https://gist.github.com/pszemraj/a15219f33d94dc53a6e270c0c81360ec) for it work
11
+
12
+ > [!WARNING]
13
+ > WIP + output of this model is gibberish bc cross attn needs training
14
+
15
+ ```py
16
+ from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
17
+
18
+ tokenizer = AutoTokenizer.from_pretrained("pszemraj/ModernBERT2Olmo-large_1b-test")
19
+ model = AutoModelForSeq2SeqLM.from_pretrained("pszemraj/ModernBERT2Olmo-large_1b-test")
20
+
21
+ ARTICLE_TO_SUMMARIZE = (
22
+ "PG&E stated it scheduled the blackouts in response to forecasts for high winds "
23
+ "amid dry conditions. The aim is to reduce the risk of wildfires. Nearly 800 thousand customers were "
24
+ "scheduled to be affected by the shutoffs which were expected to last through at least midday tomorrow."
25
+ )
26
+ prompt = f"summarize dis botmon: {ARTICLE_TO_SUMMARIZE}"
27
+ inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
28
+
29
+ # autoregressively generate summary (uses greedy decoding by default)
30
+ generated_ids = model.generate(
31
+ **inputs,
32
+ min_new_tokens=10,
33
+ max_new_tokens=100,
34
+ )
35
+ generated_text = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
36
+ print(generated_text)
37
+ ```
38
+
config.json ADDED
@@ -0,0 +1,195 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "EncoderDecoderModel"
4
+ ],
5
+ "bos_token_id": 50279,
6
+ "decoder": {
7
+ "_attn_implementation_autoset": true,
8
+ "_name_or_path": "allenai/OLMo-1B-hf",
9
+ "add_cross_attention": true,
10
+ "architectures": [
11
+ "OlmoForCausalLM"
12
+ ],
13
+ "attention_bias": false,
14
+ "attention_dropout": 0.0,
15
+ "bad_words_ids": null,
16
+ "begin_suppress_tokens": null,
17
+ "bos_token_id": 50279,
18
+ "chunk_size_feed_forward": 0,
19
+ "clip_qkv": null,
20
+ "cross_attention_hidden_size": null,
21
+ "decoder_start_token_id": 50279,
22
+ "diversity_penalty": 0.0,
23
+ "do_sample": false,
24
+ "early_stopping": false,
25
+ "encoder_no_repeat_ngram_size": 0,
26
+ "eos_token_id": 50279,
27
+ "exponential_decay_length_penalty": null,
28
+ "finetuning_task": null,
29
+ "forced_bos_token_id": null,
30
+ "forced_eos_token_id": null,
31
+ "hidden_act": "silu",
32
+ "hidden_size": 2048,
33
+ "id2label": {
34
+ "0": "LABEL_0",
35
+ "1": "LABEL_1"
36
+ },
37
+ "initializer_range": 0.02,
38
+ "intermediate_size": 8192,
39
+ "is_decoder": true,
40
+ "is_encoder_decoder": false,
41
+ "label2id": {
42
+ "LABEL_0": 0,
43
+ "LABEL_1": 1
44
+ },
45
+ "length_penalty": 1.0,
46
+ "max_length": 20,
47
+ "max_position_embeddings": 2048,
48
+ "min_length": 0,
49
+ "model_type": "olmo",
50
+ "no_repeat_ngram_size": 0,
51
+ "num_attention_heads": 16,
52
+ "num_beam_groups": 1,
53
+ "num_beams": 1,
54
+ "num_hidden_layers": 16,
55
+ "num_key_value_heads": 16,
56
+ "num_return_sequences": 1,
57
+ "output_attentions": false,
58
+ "output_hidden_states": false,
59
+ "output_scores": false,
60
+ "pad_token_id": 1,
61
+ "prefix": null,
62
+ "pretraining_tp": 1,
63
+ "problem_type": null,
64
+ "pruned_heads": {},
65
+ "remove_invalid_values": false,
66
+ "repetition_penalty": 1.0,
67
+ "return_dict": true,
68
+ "return_dict_in_generate": false,
69
+ "rope_scaling": null,
70
+ "rope_theta": 10000.0,
71
+ "sep_token_id": null,
72
+ "suppress_tokens": null,
73
+ "task_specific_params": null,
74
+ "temperature": 1.0,
75
+ "tf_legacy_loss": false,
76
+ "tie_encoder_decoder": false,
77
+ "tie_word_embeddings": true,
78
+ "tokenizer_class": null,
79
+ "top_k": 50,
80
+ "top_p": 1.0,
81
+ "torch_dtype": "float32",
82
+ "torchscript": false,
83
+ "typical_p": 1.0,
84
+ "use_bfloat16": false,
85
+ "use_cache": true,
86
+ "vocab_size": 50304
87
+ },
88
+ "decoder_start_token_id": 50279,
89
+ "encoder": {
90
+ "_attn_implementation_autoset": true,
91
+ "_name_or_path": "answerdotai/ModernBERT-large",
92
+ "add_cross_attention": false,
93
+ "architectures": [
94
+ "ModernBertForMaskedLM"
95
+ ],
96
+ "attention_bias": false,
97
+ "attention_dropout": 0.0,
98
+ "bad_words_ids": null,
99
+ "begin_suppress_tokens": null,
100
+ "bos_token_id": 50281,
101
+ "chunk_size_feed_forward": 0,
102
+ "classifier_activation": "gelu",
103
+ "classifier_bias": false,
104
+ "classifier_dropout": 0.0,
105
+ "classifier_pooling": "mean",
106
+ "cls_token_id": 50281,
107
+ "cross_attention_hidden_size": null,
108
+ "decoder_bias": true,
109
+ "decoder_start_token_id": null,
110
+ "deterministic_flash_attn": false,
111
+ "diversity_penalty": 0.0,
112
+ "do_sample": false,
113
+ "early_stopping": false,
114
+ "embedding_dropout": 0.0,
115
+ "encoder_no_repeat_ngram_size": 0,
116
+ "eos_token_id": 50282,
117
+ "exponential_decay_length_penalty": null,
118
+ "finetuning_task": null,
119
+ "forced_bos_token_id": null,
120
+ "forced_eos_token_id": null,
121
+ "global_attn_every_n_layers": 3,
122
+ "global_rope_theta": 160000.0,
123
+ "gradient_checkpointing": false,
124
+ "hidden_activation": "gelu",
125
+ "hidden_size": 1024,
126
+ "id2label": {
127
+ "0": "LABEL_0",
128
+ "1": "LABEL_1"
129
+ },
130
+ "initializer_cutoff_factor": 2.0,
131
+ "initializer_range": 0.02,
132
+ "intermediate_size": 2624,
133
+ "is_decoder": false,
134
+ "is_encoder_decoder": false,
135
+ "label2id": {
136
+ "LABEL_0": 0,
137
+ "LABEL_1": 1
138
+ },
139
+ "layer_norm_eps": 1e-05,
140
+ "length_penalty": 1.0,
141
+ "local_attention": 128,
142
+ "local_rope_theta": 10000.0,
143
+ "max_length": 20,
144
+ "max_position_embeddings": 8192,
145
+ "min_length": 0,
146
+ "mlp_bias": false,
147
+ "mlp_dropout": 0.0,
148
+ "model_type": "modernbert",
149
+ "no_repeat_ngram_size": 0,
150
+ "norm_bias": false,
151
+ "norm_eps": 1e-05,
152
+ "num_attention_heads": 16,
153
+ "num_beam_groups": 1,
154
+ "num_beams": 1,
155
+ "num_hidden_layers": 28,
156
+ "num_return_sequences": 1,
157
+ "output_attentions": false,
158
+ "output_hidden_states": false,
159
+ "output_scores": false,
160
+ "pad_token_id": 50283,
161
+ "position_embedding_type": "absolute",
162
+ "prefix": null,
163
+ "problem_type": null,
164
+ "pruned_heads": {},
165
+ "reference_compile": false,
166
+ "remove_invalid_values": false,
167
+ "repad_logits_with_grad": false,
168
+ "repetition_penalty": 1.0,
169
+ "return_dict": true,
170
+ "return_dict_in_generate": false,
171
+ "sep_token_id": 50282,
172
+ "sparse_pred_ignore_index": -100,
173
+ "sparse_prediction": false,
174
+ "suppress_tokens": null,
175
+ "task_specific_params": null,
176
+ "temperature": 1.0,
177
+ "tf_legacy_loss": false,
178
+ "tie_encoder_decoder": false,
179
+ "tie_word_embeddings": true,
180
+ "tokenizer_class": null,
181
+ "top_k": 50,
182
+ "top_p": 1.0,
183
+ "torch_dtype": "float32",
184
+ "torchscript": false,
185
+ "typical_p": 1.0,
186
+ "use_bfloat16": false,
187
+ "vocab_size": 50368
188
+ },
189
+ "eos_token_id": 50279,
190
+ "is_encoder_decoder": true,
191
+ "model_type": "encoder-decoder",
192
+ "pad_token_id": 1,
193
+ "torch_dtype": "float32",
194
+ "transformers_version": "4.49.0.dev0"
195
+ }
generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50279,
4
+ "decoder_start_token_id": 50279,
5
+ "eos_token_id": 50279,
6
+ "pad_token_id": 1,
7
+ "transformers_version": "4.49.0.dev0"
8
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f09f92efe40177c6d1cbb473bdaafc99f31974c5d214dc1f883bd9eb90f297d2
3
+ size 4944112864
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6ef1ebfc8319bb7b0a269ae8378b73111eaa2c963115923de3e3c319d4be893
3
+ size 2424384120
model.safetensors.index.json ADDED
@@ -0,0 +1,372 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 7368454144
4
+ },
5
+ "weight_map": {
6
+ "decoder.model.embed_tokens.weight": "model-00001-of-00002.safetensors",
7
+ "decoder.model.layers.0.cross_attention.k_proj.weight": "model-00001-of-00002.safetensors",
8
+ "decoder.model.layers.0.cross_attention.o_proj.weight": "model-00001-of-00002.safetensors",
9
+ "decoder.model.layers.0.cross_attention.q_proj.weight": "model-00001-of-00002.safetensors",
10
+ "decoder.model.layers.0.cross_attention.v_proj.weight": "model-00001-of-00002.safetensors",
11
+ "decoder.model.layers.0.cross_attention_layernorm.weight": "model-00001-of-00002.safetensors",
12
+ "decoder.model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
13
+ "decoder.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
14
+ "decoder.model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
15
+ "decoder.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
16
+ "decoder.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
17
+ "decoder.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
18
+ "decoder.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
19
+ "decoder.model.layers.1.cross_attention.k_proj.weight": "model-00001-of-00002.safetensors",
20
+ "decoder.model.layers.1.cross_attention.o_proj.weight": "model-00001-of-00002.safetensors",
21
+ "decoder.model.layers.1.cross_attention.q_proj.weight": "model-00001-of-00002.safetensors",
22
+ "decoder.model.layers.1.cross_attention.v_proj.weight": "model-00001-of-00002.safetensors",
23
+ "decoder.model.layers.1.cross_attention_layernorm.weight": "model-00001-of-00002.safetensors",
24
+ "decoder.model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
25
+ "decoder.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
26
+ "decoder.model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
27
+ "decoder.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
28
+ "decoder.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
29
+ "decoder.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
30
+ "decoder.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
31
+ "decoder.model.layers.10.cross_attention.k_proj.weight": "model-00002-of-00002.safetensors",
32
+ "decoder.model.layers.10.cross_attention.o_proj.weight": "model-00002-of-00002.safetensors",
33
+ "decoder.model.layers.10.cross_attention.q_proj.weight": "model-00002-of-00002.safetensors",
34
+ "decoder.model.layers.10.cross_attention.v_proj.weight": "model-00002-of-00002.safetensors",
35
+ "decoder.model.layers.10.cross_attention_layernorm.weight": "model-00002-of-00002.safetensors",
36
+ "decoder.model.layers.10.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
37
+ "decoder.model.layers.10.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
38
+ "decoder.model.layers.10.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
39
+ "decoder.model.layers.10.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
40
+ "decoder.model.layers.10.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
41
+ "decoder.model.layers.10.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
42
+ "decoder.model.layers.10.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
43
+ "decoder.model.layers.11.cross_attention.k_proj.weight": "model-00002-of-00002.safetensors",
44
+ "decoder.model.layers.11.cross_attention.o_proj.weight": "model-00002-of-00002.safetensors",
45
+ "decoder.model.layers.11.cross_attention.q_proj.weight": "model-00002-of-00002.safetensors",
46
+ "decoder.model.layers.11.cross_attention.v_proj.weight": "model-00002-of-00002.safetensors",
47
+ "decoder.model.layers.11.cross_attention_layernorm.weight": "model-00002-of-00002.safetensors",
48
+ "decoder.model.layers.11.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
49
+ "decoder.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
50
+ "decoder.model.layers.11.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
51
+ "decoder.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
52
+ "decoder.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
53
+ "decoder.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
54
+ "decoder.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
55
+ "decoder.model.layers.12.cross_attention.k_proj.weight": "model-00002-of-00002.safetensors",
56
+ "decoder.model.layers.12.cross_attention.o_proj.weight": "model-00002-of-00002.safetensors",
57
+ "decoder.model.layers.12.cross_attention.q_proj.weight": "model-00002-of-00002.safetensors",
58
+ "decoder.model.layers.12.cross_attention.v_proj.weight": "model-00002-of-00002.safetensors",
59
+ "decoder.model.layers.12.cross_attention_layernorm.weight": "model-00002-of-00002.safetensors",
60
+ "decoder.model.layers.12.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
61
+ "decoder.model.layers.12.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
62
+ "decoder.model.layers.12.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
63
+ "decoder.model.layers.12.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
64
+ "decoder.model.layers.12.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
65
+ "decoder.model.layers.12.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
66
+ "decoder.model.layers.12.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
67
+ "decoder.model.layers.13.cross_attention.k_proj.weight": "model-00002-of-00002.safetensors",
68
+ "decoder.model.layers.13.cross_attention.o_proj.weight": "model-00002-of-00002.safetensors",
69
+ "decoder.model.layers.13.cross_attention.q_proj.weight": "model-00002-of-00002.safetensors",
70
+ "decoder.model.layers.13.cross_attention.v_proj.weight": "model-00002-of-00002.safetensors",
71
+ "decoder.model.layers.13.cross_attention_layernorm.weight": "model-00002-of-00002.safetensors",
72
+ "decoder.model.layers.13.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
73
+ "decoder.model.layers.13.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
74
+ "decoder.model.layers.13.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
75
+ "decoder.model.layers.13.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
76
+ "decoder.model.layers.13.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
77
+ "decoder.model.layers.13.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
78
+ "decoder.model.layers.13.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
79
+ "decoder.model.layers.14.cross_attention.k_proj.weight": "model-00002-of-00002.safetensors",
80
+ "decoder.model.layers.14.cross_attention.o_proj.weight": "model-00002-of-00002.safetensors",
81
+ "decoder.model.layers.14.cross_attention.q_proj.weight": "model-00002-of-00002.safetensors",
82
+ "decoder.model.layers.14.cross_attention.v_proj.weight": "model-00002-of-00002.safetensors",
83
+ "decoder.model.layers.14.cross_attention_layernorm.weight": "model-00002-of-00002.safetensors",
84
+ "decoder.model.layers.14.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
85
+ "decoder.model.layers.14.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
86
+ "decoder.model.layers.14.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
87
+ "decoder.model.layers.14.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
88
+ "decoder.model.layers.14.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
89
+ "decoder.model.layers.14.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
90
+ "decoder.model.layers.14.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
91
+ "decoder.model.layers.15.cross_attention.k_proj.weight": "model-00002-of-00002.safetensors",
92
+ "decoder.model.layers.15.cross_attention.o_proj.weight": "model-00002-of-00002.safetensors",
93
+ "decoder.model.layers.15.cross_attention.q_proj.weight": "model-00002-of-00002.safetensors",
94
+ "decoder.model.layers.15.cross_attention.v_proj.weight": "model-00002-of-00002.safetensors",
95
+ "decoder.model.layers.15.cross_attention_layernorm.weight": "model-00002-of-00002.safetensors",
96
+ "decoder.model.layers.15.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
97
+ "decoder.model.layers.15.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
98
+ "decoder.model.layers.15.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
99
+ "decoder.model.layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
100
+ "decoder.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
101
+ "decoder.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
102
+ "decoder.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
103
+ "decoder.model.layers.2.cross_attention.k_proj.weight": "model-00001-of-00002.safetensors",
104
+ "decoder.model.layers.2.cross_attention.o_proj.weight": "model-00001-of-00002.safetensors",
105
+ "decoder.model.layers.2.cross_attention.q_proj.weight": "model-00001-of-00002.safetensors",
106
+ "decoder.model.layers.2.cross_attention.v_proj.weight": "model-00001-of-00002.safetensors",
107
+ "decoder.model.layers.2.cross_attention_layernorm.weight": "model-00001-of-00002.safetensors",
108
+ "decoder.model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
109
+ "decoder.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
110
+ "decoder.model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
111
+ "decoder.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
112
+ "decoder.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
113
+ "decoder.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
114
+ "decoder.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
115
+ "decoder.model.layers.3.cross_attention.k_proj.weight": "model-00001-of-00002.safetensors",
116
+ "decoder.model.layers.3.cross_attention.o_proj.weight": "model-00001-of-00002.safetensors",
117
+ "decoder.model.layers.3.cross_attention.q_proj.weight": "model-00001-of-00002.safetensors",
118
+ "decoder.model.layers.3.cross_attention.v_proj.weight": "model-00001-of-00002.safetensors",
119
+ "decoder.model.layers.3.cross_attention_layernorm.weight": "model-00001-of-00002.safetensors",
120
+ "decoder.model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
121
+ "decoder.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
122
+ "decoder.model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
123
+ "decoder.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
124
+ "decoder.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
125
+ "decoder.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
126
+ "decoder.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
127
+ "decoder.model.layers.4.cross_attention.k_proj.weight": "model-00001-of-00002.safetensors",
128
+ "decoder.model.layers.4.cross_attention.o_proj.weight": "model-00001-of-00002.safetensors",
129
+ "decoder.model.layers.4.cross_attention.q_proj.weight": "model-00001-of-00002.safetensors",
130
+ "decoder.model.layers.4.cross_attention.v_proj.weight": "model-00001-of-00002.safetensors",
131
+ "decoder.model.layers.4.cross_attention_layernorm.weight": "model-00001-of-00002.safetensors",
132
+ "decoder.model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
133
+ "decoder.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
134
+ "decoder.model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
135
+ "decoder.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
136
+ "decoder.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
137
+ "decoder.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
138
+ "decoder.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
139
+ "decoder.model.layers.5.cross_attention.k_proj.weight": "model-00001-of-00002.safetensors",
140
+ "decoder.model.layers.5.cross_attention.o_proj.weight": "model-00001-of-00002.safetensors",
141
+ "decoder.model.layers.5.cross_attention.q_proj.weight": "model-00001-of-00002.safetensors",
142
+ "decoder.model.layers.5.cross_attention.v_proj.weight": "model-00001-of-00002.safetensors",
143
+ "decoder.model.layers.5.cross_attention_layernorm.weight": "model-00001-of-00002.safetensors",
144
+ "decoder.model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
145
+ "decoder.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
146
+ "decoder.model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
147
+ "decoder.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
148
+ "decoder.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
149
+ "decoder.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
150
+ "decoder.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
151
+ "decoder.model.layers.6.cross_attention.k_proj.weight": "model-00001-of-00002.safetensors",
152
+ "decoder.model.layers.6.cross_attention.o_proj.weight": "model-00001-of-00002.safetensors",
153
+ "decoder.model.layers.6.cross_attention.q_proj.weight": "model-00001-of-00002.safetensors",
154
+ "decoder.model.layers.6.cross_attention.v_proj.weight": "model-00001-of-00002.safetensors",
155
+ "decoder.model.layers.6.cross_attention_layernorm.weight": "model-00001-of-00002.safetensors",
156
+ "decoder.model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
157
+ "decoder.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
158
+ "decoder.model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
159
+ "decoder.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
160
+ "decoder.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
161
+ "decoder.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
162
+ "decoder.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
163
+ "decoder.model.layers.7.cross_attention.k_proj.weight": "model-00001-of-00002.safetensors",
164
+ "decoder.model.layers.7.cross_attention.o_proj.weight": "model-00001-of-00002.safetensors",
165
+ "decoder.model.layers.7.cross_attention.q_proj.weight": "model-00001-of-00002.safetensors",
166
+ "decoder.model.layers.7.cross_attention.v_proj.weight": "model-00001-of-00002.safetensors",
167
+ "decoder.model.layers.7.cross_attention_layernorm.weight": "model-00001-of-00002.safetensors",
168
+ "decoder.model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
169
+ "decoder.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
170
+ "decoder.model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
171
+ "decoder.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
172
+ "decoder.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
173
+ "decoder.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
174
+ "decoder.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
175
+ "decoder.model.layers.8.cross_attention.k_proj.weight": "model-00001-of-00002.safetensors",
176
+ "decoder.model.layers.8.cross_attention.o_proj.weight": "model-00001-of-00002.safetensors",
177
+ "decoder.model.layers.8.cross_attention.q_proj.weight": "model-00001-of-00002.safetensors",
178
+ "decoder.model.layers.8.cross_attention.v_proj.weight": "model-00001-of-00002.safetensors",
179
+ "decoder.model.layers.8.cross_attention_layernorm.weight": "model-00001-of-00002.safetensors",
180
+ "decoder.model.layers.8.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
181
+ "decoder.model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
182
+ "decoder.model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
183
+ "decoder.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
184
+ "decoder.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
185
+ "decoder.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
186
+ "decoder.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
187
+ "decoder.model.layers.9.cross_attention.k_proj.weight": "model-00002-of-00002.safetensors",
188
+ "decoder.model.layers.9.cross_attention.o_proj.weight": "model-00002-of-00002.safetensors",
189
+ "decoder.model.layers.9.cross_attention.q_proj.weight": "model-00002-of-00002.safetensors",
190
+ "decoder.model.layers.9.cross_attention.v_proj.weight": "model-00002-of-00002.safetensors",
191
+ "decoder.model.layers.9.cross_attention_layernorm.weight": "model-00002-of-00002.safetensors",
192
+ "decoder.model.layers.9.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
193
+ "decoder.model.layers.9.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
194
+ "decoder.model.layers.9.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
195
+ "decoder.model.layers.9.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
196
+ "decoder.model.layers.9.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
197
+ "decoder.model.layers.9.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
198
+ "decoder.model.layers.9.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
199
+ "enc_to_dec_proj.bias": "model-00002-of-00002.safetensors",
200
+ "enc_to_dec_proj.weight": "model-00002-of-00002.safetensors",
201
+ "encoder.embeddings.norm.weight": "model-00001-of-00002.safetensors",
202
+ "encoder.embeddings.tok_embeddings.weight": "model-00001-of-00002.safetensors",
203
+ "encoder.final_norm.weight": "model-00001-of-00002.safetensors",
204
+ "encoder.layers.0.attn.Wo.weight": "model-00001-of-00002.safetensors",
205
+ "encoder.layers.0.attn.Wqkv.weight": "model-00001-of-00002.safetensors",
206
+ "encoder.layers.0.mlp.Wi.weight": "model-00001-of-00002.safetensors",
207
+ "encoder.layers.0.mlp.Wo.weight": "model-00001-of-00002.safetensors",
208
+ "encoder.layers.0.mlp_norm.weight": "model-00001-of-00002.safetensors",
209
+ "encoder.layers.1.attn.Wo.weight": "model-00001-of-00002.safetensors",
210
+ "encoder.layers.1.attn.Wqkv.weight": "model-00001-of-00002.safetensors",
211
+ "encoder.layers.1.attn_norm.weight": "model-00001-of-00002.safetensors",
212
+ "encoder.layers.1.mlp.Wi.weight": "model-00001-of-00002.safetensors",
213
+ "encoder.layers.1.mlp.Wo.weight": "model-00001-of-00002.safetensors",
214
+ "encoder.layers.1.mlp_norm.weight": "model-00001-of-00002.safetensors",
215
+ "encoder.layers.10.attn.Wo.weight": "model-00001-of-00002.safetensors",
216
+ "encoder.layers.10.attn.Wqkv.weight": "model-00001-of-00002.safetensors",
217
+ "encoder.layers.10.attn_norm.weight": "model-00001-of-00002.safetensors",
218
+ "encoder.layers.10.mlp.Wi.weight": "model-00001-of-00002.safetensors",
219
+ "encoder.layers.10.mlp.Wo.weight": "model-00001-of-00002.safetensors",
220
+ "encoder.layers.10.mlp_norm.weight": "model-00001-of-00002.safetensors",
221
+ "encoder.layers.11.attn.Wo.weight": "model-00001-of-00002.safetensors",
222
+ "encoder.layers.11.attn.Wqkv.weight": "model-00001-of-00002.safetensors",
223
+ "encoder.layers.11.attn_norm.weight": "model-00001-of-00002.safetensors",
224
+ "encoder.layers.11.mlp.Wi.weight": "model-00001-of-00002.safetensors",
225
+ "encoder.layers.11.mlp.Wo.weight": "model-00001-of-00002.safetensors",
226
+ "encoder.layers.11.mlp_norm.weight": "model-00001-of-00002.safetensors",
227
+ "encoder.layers.12.attn.Wo.weight": "model-00001-of-00002.safetensors",
228
+ "encoder.layers.12.attn.Wqkv.weight": "model-00001-of-00002.safetensors",
229
+ "encoder.layers.12.attn_norm.weight": "model-00001-of-00002.safetensors",
230
+ "encoder.layers.12.mlp.Wi.weight": "model-00001-of-00002.safetensors",
231
+ "encoder.layers.12.mlp.Wo.weight": "model-00001-of-00002.safetensors",
232
+ "encoder.layers.12.mlp_norm.weight": "model-00001-of-00002.safetensors",
233
+ "encoder.layers.13.attn.Wo.weight": "model-00001-of-00002.safetensors",
234
+ "encoder.layers.13.attn.Wqkv.weight": "model-00001-of-00002.safetensors",
235
+ "encoder.layers.13.attn_norm.weight": "model-00001-of-00002.safetensors",
236
+ "encoder.layers.13.mlp.Wi.weight": "model-00001-of-00002.safetensors",
237
+ "encoder.layers.13.mlp.Wo.weight": "model-00001-of-00002.safetensors",
238
+ "encoder.layers.13.mlp_norm.weight": "model-00001-of-00002.safetensors",
239
+ "encoder.layers.14.attn.Wo.weight": "model-00001-of-00002.safetensors",
240
+ "encoder.layers.14.attn.Wqkv.weight": "model-00001-of-00002.safetensors",
241
+ "encoder.layers.14.attn_norm.weight": "model-00001-of-00002.safetensors",
242
+ "encoder.layers.14.mlp.Wi.weight": "model-00001-of-00002.safetensors",
243
+ "encoder.layers.14.mlp.Wo.weight": "model-00001-of-00002.safetensors",
244
+ "encoder.layers.14.mlp_norm.weight": "model-00001-of-00002.safetensors",
245
+ "encoder.layers.15.attn.Wo.weight": "model-00001-of-00002.safetensors",
246
+ "encoder.layers.15.attn.Wqkv.weight": "model-00001-of-00002.safetensors",
247
+ "encoder.layers.15.attn_norm.weight": "model-00001-of-00002.safetensors",
248
+ "encoder.layers.15.mlp.Wi.weight": "model-00001-of-00002.safetensors",
249
+ "encoder.layers.15.mlp.Wo.weight": "model-00001-of-00002.safetensors",
250
+ "encoder.layers.15.mlp_norm.weight": "model-00001-of-00002.safetensors",
251
+ "encoder.layers.16.attn.Wo.weight": "model-00001-of-00002.safetensors",
252
+ "encoder.layers.16.attn.Wqkv.weight": "model-00001-of-00002.safetensors",
253
+ "encoder.layers.16.attn_norm.weight": "model-00001-of-00002.safetensors",
254
+ "encoder.layers.16.mlp.Wi.weight": "model-00001-of-00002.safetensors",
255
+ "encoder.layers.16.mlp.Wo.weight": "model-00001-of-00002.safetensors",
256
+ "encoder.layers.16.mlp_norm.weight": "model-00001-of-00002.safetensors",
257
+ "encoder.layers.17.attn.Wo.weight": "model-00001-of-00002.safetensors",
258
+ "encoder.layers.17.attn.Wqkv.weight": "model-00001-of-00002.safetensors",
259
+ "encoder.layers.17.attn_norm.weight": "model-00001-of-00002.safetensors",
260
+ "encoder.layers.17.mlp.Wi.weight": "model-00001-of-00002.safetensors",
261
+ "encoder.layers.17.mlp.Wo.weight": "model-00001-of-00002.safetensors",
262
+ "encoder.layers.17.mlp_norm.weight": "model-00001-of-00002.safetensors",
263
+ "encoder.layers.18.attn.Wo.weight": "model-00001-of-00002.safetensors",
264
+ "encoder.layers.18.attn.Wqkv.weight": "model-00001-of-00002.safetensors",
265
+ "encoder.layers.18.attn_norm.weight": "model-00001-of-00002.safetensors",
266
+ "encoder.layers.18.mlp.Wi.weight": "model-00001-of-00002.safetensors",
267
+ "encoder.layers.18.mlp.Wo.weight": "model-00001-of-00002.safetensors",
268
+ "encoder.layers.18.mlp_norm.weight": "model-00001-of-00002.safetensors",
269
+ "encoder.layers.19.attn.Wo.weight": "model-00001-of-00002.safetensors",
270
+ "encoder.layers.19.attn.Wqkv.weight": "model-00001-of-00002.safetensors",
271
+ "encoder.layers.19.attn_norm.weight": "model-00001-of-00002.safetensors",
272
+ "encoder.layers.19.mlp.Wi.weight": "model-00001-of-00002.safetensors",
273
+ "encoder.layers.19.mlp.Wo.weight": "model-00001-of-00002.safetensors",
274
+ "encoder.layers.19.mlp_norm.weight": "model-00001-of-00002.safetensors",
275
+ "encoder.layers.2.attn.Wo.weight": "model-00001-of-00002.safetensors",
276
+ "encoder.layers.2.attn.Wqkv.weight": "model-00001-of-00002.safetensors",
277
+ "encoder.layers.2.attn_norm.weight": "model-00001-of-00002.safetensors",
278
+ "encoder.layers.2.mlp.Wi.weight": "model-00001-of-00002.safetensors",
279
+ "encoder.layers.2.mlp.Wo.weight": "model-00001-of-00002.safetensors",
280
+ "encoder.layers.2.mlp_norm.weight": "model-00001-of-00002.safetensors",
281
+ "encoder.layers.20.attn.Wo.weight": "model-00001-of-00002.safetensors",
282
+ "encoder.layers.20.attn.Wqkv.weight": "model-00001-of-00002.safetensors",
283
+ "encoder.layers.20.attn_norm.weight": "model-00001-of-00002.safetensors",
284
+ "encoder.layers.20.mlp.Wi.weight": "model-00001-of-00002.safetensors",
285
+ "encoder.layers.20.mlp.Wo.weight": "model-00001-of-00002.safetensors",
286
+ "encoder.layers.20.mlp_norm.weight": "model-00001-of-00002.safetensors",
287
+ "encoder.layers.21.attn.Wo.weight": "model-00001-of-00002.safetensors",
288
+ "encoder.layers.21.attn.Wqkv.weight": "model-00001-of-00002.safetensors",
289
+ "encoder.layers.21.attn_norm.weight": "model-00001-of-00002.safetensors",
290
+ "encoder.layers.21.mlp.Wi.weight": "model-00001-of-00002.safetensors",
291
+ "encoder.layers.21.mlp.Wo.weight": "model-00001-of-00002.safetensors",
292
+ "encoder.layers.21.mlp_norm.weight": "model-00001-of-00002.safetensors",
293
+ "encoder.layers.22.attn.Wo.weight": "model-00001-of-00002.safetensors",
294
+ "encoder.layers.22.attn.Wqkv.weight": "model-00001-of-00002.safetensors",
295
+ "encoder.layers.22.attn_norm.weight": "model-00001-of-00002.safetensors",
296
+ "encoder.layers.22.mlp.Wi.weight": "model-00001-of-00002.safetensors",
297
+ "encoder.layers.22.mlp.Wo.weight": "model-00001-of-00002.safetensors",
298
+ "encoder.layers.22.mlp_norm.weight": "model-00001-of-00002.safetensors",
299
+ "encoder.layers.23.attn.Wo.weight": "model-00001-of-00002.safetensors",
300
+ "encoder.layers.23.attn.Wqkv.weight": "model-00001-of-00002.safetensors",
301
+ "encoder.layers.23.attn_norm.weight": "model-00001-of-00002.safetensors",
302
+ "encoder.layers.23.mlp.Wi.weight": "model-00001-of-00002.safetensors",
303
+ "encoder.layers.23.mlp.Wo.weight": "model-00001-of-00002.safetensors",
304
+ "encoder.layers.23.mlp_norm.weight": "model-00001-of-00002.safetensors",
305
+ "encoder.layers.24.attn.Wo.weight": "model-00001-of-00002.safetensors",
306
+ "encoder.layers.24.attn.Wqkv.weight": "model-00001-of-00002.safetensors",
307
+ "encoder.layers.24.attn_norm.weight": "model-00001-of-00002.safetensors",
308
+ "encoder.layers.24.mlp.Wi.weight": "model-00001-of-00002.safetensors",
309
+ "encoder.layers.24.mlp.Wo.weight": "model-00001-of-00002.safetensors",
310
+ "encoder.layers.24.mlp_norm.weight": "model-00001-of-00002.safetensors",
311
+ "encoder.layers.25.attn.Wo.weight": "model-00001-of-00002.safetensors",
312
+ "encoder.layers.25.attn.Wqkv.weight": "model-00001-of-00002.safetensors",
313
+ "encoder.layers.25.attn_norm.weight": "model-00001-of-00002.safetensors",
314
+ "encoder.layers.25.mlp.Wi.weight": "model-00001-of-00002.safetensors",
315
+ "encoder.layers.25.mlp.Wo.weight": "model-00001-of-00002.safetensors",
316
+ "encoder.layers.25.mlp_norm.weight": "model-00001-of-00002.safetensors",
317
+ "encoder.layers.26.attn.Wo.weight": "model-00001-of-00002.safetensors",
318
+ "encoder.layers.26.attn.Wqkv.weight": "model-00001-of-00002.safetensors",
319
+ "encoder.layers.26.attn_norm.weight": "model-00001-of-00002.safetensors",
320
+ "encoder.layers.26.mlp.Wi.weight": "model-00001-of-00002.safetensors",
321
+ "encoder.layers.26.mlp.Wo.weight": "model-00001-of-00002.safetensors",
322
+ "encoder.layers.26.mlp_norm.weight": "model-00001-of-00002.safetensors",
323
+ "encoder.layers.27.attn.Wo.weight": "model-00001-of-00002.safetensors",
324
+ "encoder.layers.27.attn.Wqkv.weight": "model-00001-of-00002.safetensors",
325
+ "encoder.layers.27.attn_norm.weight": "model-00001-of-00002.safetensors",
326
+ "encoder.layers.27.mlp.Wi.weight": "model-00001-of-00002.safetensors",
327
+ "encoder.layers.27.mlp.Wo.weight": "model-00001-of-00002.safetensors",
328
+ "encoder.layers.27.mlp_norm.weight": "model-00001-of-00002.safetensors",
329
+ "encoder.layers.3.attn.Wo.weight": "model-00001-of-00002.safetensors",
330
+ "encoder.layers.3.attn.Wqkv.weight": "model-00001-of-00002.safetensors",
331
+ "encoder.layers.3.attn_norm.weight": "model-00001-of-00002.safetensors",
332
+ "encoder.layers.3.mlp.Wi.weight": "model-00001-of-00002.safetensors",
333
+ "encoder.layers.3.mlp.Wo.weight": "model-00001-of-00002.safetensors",
334
+ "encoder.layers.3.mlp_norm.weight": "model-00001-of-00002.safetensors",
335
+ "encoder.layers.4.attn.Wo.weight": "model-00001-of-00002.safetensors",
336
+ "encoder.layers.4.attn.Wqkv.weight": "model-00001-of-00002.safetensors",
337
+ "encoder.layers.4.attn_norm.weight": "model-00001-of-00002.safetensors",
338
+ "encoder.layers.4.mlp.Wi.weight": "model-00001-of-00002.safetensors",
339
+ "encoder.layers.4.mlp.Wo.weight": "model-00001-of-00002.safetensors",
340
+ "encoder.layers.4.mlp_norm.weight": "model-00001-of-00002.safetensors",
341
+ "encoder.layers.5.attn.Wo.weight": "model-00001-of-00002.safetensors",
342
+ "encoder.layers.5.attn.Wqkv.weight": "model-00001-of-00002.safetensors",
343
+ "encoder.layers.5.attn_norm.weight": "model-00001-of-00002.safetensors",
344
+ "encoder.layers.5.mlp.Wi.weight": "model-00001-of-00002.safetensors",
345
+ "encoder.layers.5.mlp.Wo.weight": "model-00001-of-00002.safetensors",
346
+ "encoder.layers.5.mlp_norm.weight": "model-00001-of-00002.safetensors",
347
+ "encoder.layers.6.attn.Wo.weight": "model-00001-of-00002.safetensors",
348
+ "encoder.layers.6.attn.Wqkv.weight": "model-00001-of-00002.safetensors",
349
+ "encoder.layers.6.attn_norm.weight": "model-00001-of-00002.safetensors",
350
+ "encoder.layers.6.mlp.Wi.weight": "model-00001-of-00002.safetensors",
351
+ "encoder.layers.6.mlp.Wo.weight": "model-00001-of-00002.safetensors",
352
+ "encoder.layers.6.mlp_norm.weight": "model-00001-of-00002.safetensors",
353
+ "encoder.layers.7.attn.Wo.weight": "model-00001-of-00002.safetensors",
354
+ "encoder.layers.7.attn.Wqkv.weight": "model-00001-of-00002.safetensors",
355
+ "encoder.layers.7.attn_norm.weight": "model-00001-of-00002.safetensors",
356
+ "encoder.layers.7.mlp.Wi.weight": "model-00001-of-00002.safetensors",
357
+ "encoder.layers.7.mlp.Wo.weight": "model-00001-of-00002.safetensors",
358
+ "encoder.layers.7.mlp_norm.weight": "model-00001-of-00002.safetensors",
359
+ "encoder.layers.8.attn.Wo.weight": "model-00001-of-00002.safetensors",
360
+ "encoder.layers.8.attn.Wqkv.weight": "model-00001-of-00002.safetensors",
361
+ "encoder.layers.8.attn_norm.weight": "model-00001-of-00002.safetensors",
362
+ "encoder.layers.8.mlp.Wi.weight": "model-00001-of-00002.safetensors",
363
+ "encoder.layers.8.mlp.Wo.weight": "model-00001-of-00002.safetensors",
364
+ "encoder.layers.8.mlp_norm.weight": "model-00001-of-00002.safetensors",
365
+ "encoder.layers.9.attn.Wo.weight": "model-00001-of-00002.safetensors",
366
+ "encoder.layers.9.attn.Wqkv.weight": "model-00001-of-00002.safetensors",
367
+ "encoder.layers.9.attn_norm.weight": "model-00001-of-00002.safetensors",
368
+ "encoder.layers.9.mlp.Wi.weight": "model-00001-of-00002.safetensors",
369
+ "encoder.layers.9.mlp.Wo.weight": "model-00001-of-00002.safetensors",
370
+ "encoder.layers.9.mlp_norm.weight": "model-00001-of-00002.safetensors"
371
+ }
372
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": true,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,945 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "|||IP_ADDRESS|||",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "1": {
12
+ "content": "<|padding|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "50254": {
20
+ "content": " ",
21
+ "lstrip": false,
22
+ "normalized": true,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": false
26
+ },
27
+ "50255": {
28
+ "content": " ",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": false
34
+ },
35
+ "50256": {
36
+ "content": " ",
37
+ "lstrip": false,
38
+ "normalized": true,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": false
42
+ },
43
+ "50257": {
44
+ "content": " ",
45
+ "lstrip": false,
46
+ "normalized": true,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": false
50
+ },
51
+ "50258": {
52
+ "content": " ",
53
+ "lstrip": false,
54
+ "normalized": true,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": false
58
+ },
59
+ "50259": {
60
+ "content": " ",
61
+ "lstrip": false,
62
+ "normalized": true,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": false
66
+ },
67
+ "50260": {
68
+ "content": " ",
69
+ "lstrip": false,
70
+ "normalized": true,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": false
74
+ },
75
+ "50261": {
76
+ "content": " ",
77
+ "lstrip": false,
78
+ "normalized": true,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": false
82
+ },
83
+ "50262": {
84
+ "content": " ",
85
+ "lstrip": false,
86
+ "normalized": true,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": false
90
+ },
91
+ "50263": {
92
+ "content": " ",
93
+ "lstrip": false,
94
+ "normalized": true,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": false
98
+ },
99
+ "50264": {
100
+ "content": " ",
101
+ "lstrip": false,
102
+ "normalized": true,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": false
106
+ },
107
+ "50265": {
108
+ "content": " ",
109
+ "lstrip": false,
110
+ "normalized": true,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": false
114
+ },
115
+ "50266": {
116
+ "content": " ",
117
+ "lstrip": false,
118
+ "normalized": true,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": false
122
+ },
123
+ "50267": {
124
+ "content": " ",
125
+ "lstrip": false,
126
+ "normalized": true,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": false
130
+ },
131
+ "50268": {
132
+ "content": " ",
133
+ "lstrip": false,
134
+ "normalized": true,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": false
138
+ },
139
+ "50269": {
140
+ "content": " ",
141
+ "lstrip": false,
142
+ "normalized": true,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": false
146
+ },
147
+ "50270": {
148
+ "content": " ",
149
+ "lstrip": false,
150
+ "normalized": true,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": false
154
+ },
155
+ "50271": {
156
+ "content": " ",
157
+ "lstrip": false,
158
+ "normalized": true,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": false
162
+ },
163
+ "50272": {
164
+ "content": " ",
165
+ "lstrip": false,
166
+ "normalized": true,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": false
170
+ },
171
+ "50273": {
172
+ "content": " ",
173
+ "lstrip": false,
174
+ "normalized": true,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": false
178
+ },
179
+ "50274": {
180
+ "content": " ",
181
+ "lstrip": false,
182
+ "normalized": true,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": false
186
+ },
187
+ "50275": {
188
+ "content": " ",
189
+ "lstrip": false,
190
+ "normalized": true,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": false
194
+ },
195
+ "50276": {
196
+ "content": " ",
197
+ "lstrip": false,
198
+ "normalized": true,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": false
202
+ },
203
+ "50277": {
204
+ "content": "|||EMAIL_ADDRESS|||",
205
+ "lstrip": false,
206
+ "normalized": true,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": false
210
+ },
211
+ "50278": {
212
+ "content": "|||PHONE_NUMBER|||",
213
+ "lstrip": false,
214
+ "normalized": true,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": false
218
+ },
219
+ "50279": {
220
+ "content": "<|endoftext|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "50280": {
228
+ "content": "[UNK]",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "50281": {
236
+ "content": "[CLS]",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "50282": {
244
+ "content": "[SEP]",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "50283": {
252
+ "content": "[PAD]",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "50284": {
260
+ "content": "[MASK]",
261
+ "lstrip": true,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "50285": {
268
+ "content": "[unused0]",
269
+ "lstrip": false,
270
+ "normalized": true,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": false
274
+ },
275
+ "50286": {
276
+ "content": "[unused1]",
277
+ "lstrip": false,
278
+ "normalized": true,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": false
282
+ },
283
+ "50287": {
284
+ "content": "[unused2]",
285
+ "lstrip": false,
286
+ "normalized": true,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": false
290
+ },
291
+ "50288": {
292
+ "content": "[unused3]",
293
+ "lstrip": false,
294
+ "normalized": true,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": false
298
+ },
299
+ "50289": {
300
+ "content": "[unused4]",
301
+ "lstrip": false,
302
+ "normalized": true,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": false
306
+ },
307
+ "50290": {
308
+ "content": "[unused5]",
309
+ "lstrip": false,
310
+ "normalized": true,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": false
314
+ },
315
+ "50291": {
316
+ "content": "[unused6]",
317
+ "lstrip": false,
318
+ "normalized": true,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": false
322
+ },
323
+ "50292": {
324
+ "content": "[unused7]",
325
+ "lstrip": false,
326
+ "normalized": true,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": false
330
+ },
331
+ "50293": {
332
+ "content": "[unused8]",
333
+ "lstrip": false,
334
+ "normalized": true,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": false
338
+ },
339
+ "50294": {
340
+ "content": "[unused9]",
341
+ "lstrip": false,
342
+ "normalized": true,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": false
346
+ },
347
+ "50295": {
348
+ "content": "[unused10]",
349
+ "lstrip": false,
350
+ "normalized": true,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": false
354
+ },
355
+ "50296": {
356
+ "content": "[unused11]",
357
+ "lstrip": false,
358
+ "normalized": true,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": false
362
+ },
363
+ "50297": {
364
+ "content": "[unused12]",
365
+ "lstrip": false,
366
+ "normalized": true,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": false
370
+ },
371
+ "50298": {
372
+ "content": "[unused13]",
373
+ "lstrip": false,
374
+ "normalized": true,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": false
378
+ },
379
+ "50299": {
380
+ "content": "[unused14]",
381
+ "lstrip": false,
382
+ "normalized": true,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": false
386
+ },
387
+ "50300": {
388
+ "content": "[unused15]",
389
+ "lstrip": false,
390
+ "normalized": true,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": false
394
+ },
395
+ "50301": {
396
+ "content": "[unused16]",
397
+ "lstrip": false,
398
+ "normalized": true,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": false
402
+ },
403
+ "50302": {
404
+ "content": "[unused17]",
405
+ "lstrip": false,
406
+ "normalized": true,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": false
410
+ },
411
+ "50303": {
412
+ "content": "[unused18]",
413
+ "lstrip": false,
414
+ "normalized": true,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": false
418
+ },
419
+ "50304": {
420
+ "content": "[unused19]",
421
+ "lstrip": false,
422
+ "normalized": true,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": false
426
+ },
427
+ "50305": {
428
+ "content": "[unused20]",
429
+ "lstrip": false,
430
+ "normalized": true,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": false
434
+ },
435
+ "50306": {
436
+ "content": "[unused21]",
437
+ "lstrip": false,
438
+ "normalized": true,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": false
442
+ },
443
+ "50307": {
444
+ "content": "[unused22]",
445
+ "lstrip": false,
446
+ "normalized": true,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": false
450
+ },
451
+ "50308": {
452
+ "content": "[unused23]",
453
+ "lstrip": false,
454
+ "normalized": true,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": false
458
+ },
459
+ "50309": {
460
+ "content": "[unused24]",
461
+ "lstrip": false,
462
+ "normalized": true,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": false
466
+ },
467
+ "50310": {
468
+ "content": "[unused25]",
469
+ "lstrip": false,
470
+ "normalized": true,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": false
474
+ },
475
+ "50311": {
476
+ "content": "[unused26]",
477
+ "lstrip": false,
478
+ "normalized": true,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": false
482
+ },
483
+ "50312": {
484
+ "content": "[unused27]",
485
+ "lstrip": false,
486
+ "normalized": true,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": false
490
+ },
491
+ "50313": {
492
+ "content": "[unused28]",
493
+ "lstrip": false,
494
+ "normalized": true,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": false
498
+ },
499
+ "50314": {
500
+ "content": "[unused29]",
501
+ "lstrip": false,
502
+ "normalized": true,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": false
506
+ },
507
+ "50315": {
508
+ "content": "[unused30]",
509
+ "lstrip": false,
510
+ "normalized": true,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": false
514
+ },
515
+ "50316": {
516
+ "content": "[unused31]",
517
+ "lstrip": false,
518
+ "normalized": true,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": false
522
+ },
523
+ "50317": {
524
+ "content": "[unused32]",
525
+ "lstrip": false,
526
+ "normalized": true,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": false
530
+ },
531
+ "50318": {
532
+ "content": "[unused33]",
533
+ "lstrip": false,
534
+ "normalized": true,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": false
538
+ },
539
+ "50319": {
540
+ "content": "[unused34]",
541
+ "lstrip": false,
542
+ "normalized": true,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": false
546
+ },
547
+ "50320": {
548
+ "content": "[unused35]",
549
+ "lstrip": false,
550
+ "normalized": true,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": false
554
+ },
555
+ "50321": {
556
+ "content": "[unused36]",
557
+ "lstrip": false,
558
+ "normalized": true,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": false
562
+ },
563
+ "50322": {
564
+ "content": "[unused37]",
565
+ "lstrip": false,
566
+ "normalized": true,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": false
570
+ },
571
+ "50323": {
572
+ "content": "[unused38]",
573
+ "lstrip": false,
574
+ "normalized": true,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": false
578
+ },
579
+ "50324": {
580
+ "content": "[unused39]",
581
+ "lstrip": false,
582
+ "normalized": true,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": false
586
+ },
587
+ "50325": {
588
+ "content": "[unused40]",
589
+ "lstrip": false,
590
+ "normalized": true,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": false
594
+ },
595
+ "50326": {
596
+ "content": "[unused41]",
597
+ "lstrip": false,
598
+ "normalized": true,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": false
602
+ },
603
+ "50327": {
604
+ "content": "[unused42]",
605
+ "lstrip": false,
606
+ "normalized": true,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": false
610
+ },
611
+ "50328": {
612
+ "content": "[unused43]",
613
+ "lstrip": false,
614
+ "normalized": true,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": false
618
+ },
619
+ "50329": {
620
+ "content": "[unused44]",
621
+ "lstrip": false,
622
+ "normalized": true,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": false
626
+ },
627
+ "50330": {
628
+ "content": "[unused45]",
629
+ "lstrip": false,
630
+ "normalized": true,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": false
634
+ },
635
+ "50331": {
636
+ "content": "[unused46]",
637
+ "lstrip": false,
638
+ "normalized": true,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": false
642
+ },
643
+ "50332": {
644
+ "content": "[unused47]",
645
+ "lstrip": false,
646
+ "normalized": true,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": false
650
+ },
651
+ "50333": {
652
+ "content": "[unused48]",
653
+ "lstrip": false,
654
+ "normalized": true,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": false
658
+ },
659
+ "50334": {
660
+ "content": "[unused49]",
661
+ "lstrip": false,
662
+ "normalized": true,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": false
666
+ },
667
+ "50335": {
668
+ "content": "[unused50]",
669
+ "lstrip": false,
670
+ "normalized": true,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": false
674
+ },
675
+ "50336": {
676
+ "content": "[unused51]",
677
+ "lstrip": false,
678
+ "normalized": true,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": false
682
+ },
683
+ "50337": {
684
+ "content": "[unused52]",
685
+ "lstrip": false,
686
+ "normalized": true,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": false
690
+ },
691
+ "50338": {
692
+ "content": "[unused53]",
693
+ "lstrip": false,
694
+ "normalized": true,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": false
698
+ },
699
+ "50339": {
700
+ "content": "[unused54]",
701
+ "lstrip": false,
702
+ "normalized": true,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": false
706
+ },
707
+ "50340": {
708
+ "content": "[unused55]",
709
+ "lstrip": false,
710
+ "normalized": true,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": false
714
+ },
715
+ "50341": {
716
+ "content": "[unused56]",
717
+ "lstrip": false,
718
+ "normalized": true,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": false
722
+ },
723
+ "50342": {
724
+ "content": "[unused57]",
725
+ "lstrip": false,
726
+ "normalized": true,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": false
730
+ },
731
+ "50343": {
732
+ "content": "[unused58]",
733
+ "lstrip": false,
734
+ "normalized": true,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": false
738
+ },
739
+ "50344": {
740
+ "content": "[unused59]",
741
+ "lstrip": false,
742
+ "normalized": true,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": false
746
+ },
747
+ "50345": {
748
+ "content": "[unused60]",
749
+ "lstrip": false,
750
+ "normalized": true,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": false
754
+ },
755
+ "50346": {
756
+ "content": "[unused61]",
757
+ "lstrip": false,
758
+ "normalized": true,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": false
762
+ },
763
+ "50347": {
764
+ "content": "[unused62]",
765
+ "lstrip": false,
766
+ "normalized": true,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": false
770
+ },
771
+ "50348": {
772
+ "content": "[unused63]",
773
+ "lstrip": false,
774
+ "normalized": true,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": false
778
+ },
779
+ "50349": {
780
+ "content": "[unused64]",
781
+ "lstrip": false,
782
+ "normalized": true,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": false
786
+ },
787
+ "50350": {
788
+ "content": "[unused65]",
789
+ "lstrip": false,
790
+ "normalized": true,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": false
794
+ },
795
+ "50351": {
796
+ "content": "[unused66]",
797
+ "lstrip": false,
798
+ "normalized": true,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": false
802
+ },
803
+ "50352": {
804
+ "content": "[unused67]",
805
+ "lstrip": false,
806
+ "normalized": true,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": false
810
+ },
811
+ "50353": {
812
+ "content": "[unused68]",
813
+ "lstrip": false,
814
+ "normalized": true,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": false
818
+ },
819
+ "50354": {
820
+ "content": "[unused69]",
821
+ "lstrip": false,
822
+ "normalized": true,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": false
826
+ },
827
+ "50355": {
828
+ "content": "[unused70]",
829
+ "lstrip": false,
830
+ "normalized": true,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": false
834
+ },
835
+ "50356": {
836
+ "content": "[unused71]",
837
+ "lstrip": false,
838
+ "normalized": true,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": false
842
+ },
843
+ "50357": {
844
+ "content": "[unused72]",
845
+ "lstrip": false,
846
+ "normalized": true,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": false
850
+ },
851
+ "50358": {
852
+ "content": "[unused73]",
853
+ "lstrip": false,
854
+ "normalized": true,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": false
858
+ },
859
+ "50359": {
860
+ "content": "[unused74]",
861
+ "lstrip": false,
862
+ "normalized": true,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": false
866
+ },
867
+ "50360": {
868
+ "content": "[unused75]",
869
+ "lstrip": false,
870
+ "normalized": true,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": false
874
+ },
875
+ "50361": {
876
+ "content": "[unused76]",
877
+ "lstrip": false,
878
+ "normalized": true,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": false
882
+ },
883
+ "50362": {
884
+ "content": "[unused77]",
885
+ "lstrip": false,
886
+ "normalized": true,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": false
890
+ },
891
+ "50363": {
892
+ "content": "[unused78]",
893
+ "lstrip": false,
894
+ "normalized": true,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": false
898
+ },
899
+ "50364": {
900
+ "content": "[unused79]",
901
+ "lstrip": false,
902
+ "normalized": true,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": false
906
+ },
907
+ "50365": {
908
+ "content": "[unused80]",
909
+ "lstrip": false,
910
+ "normalized": true,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": false
914
+ },
915
+ "50366": {
916
+ "content": "[unused81]",
917
+ "lstrip": false,
918
+ "normalized": true,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": false
922
+ },
923
+ "50367": {
924
+ "content": "[unused82]",
925
+ "lstrip": false,
926
+ "normalized": true,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": false
930
+ }
931
+ },
932
+ "clean_up_tokenization_spaces": true,
933
+ "cls_token": "[CLS]",
934
+ "extra_special_tokens": {},
935
+ "mask_token": "[MASK]",
936
+ "model_input_names": [
937
+ "input_ids",
938
+ "attention_mask"
939
+ ],
940
+ "model_max_length": 8192,
941
+ "pad_token": "[PAD]",
942
+ "sep_token": "[SEP]",
943
+ "tokenizer_class": "PreTrainedTokenizerFast",
944
+ "unk_token": "[UNK]"
945
+ }