Hugging Face's logo

mzbac
/
nougat-small-8bit-mlx

Image-to-Text
Transformers
Safetensors
vision-encoder-decoder
image-text-to-text
vision
nougat
Inference Endpoints
Model card Files Community
mzbac commited on
Commit
5c3616b
•
1 Parent(s): 3883ce6

Upload folder using huggingface_hub

Browse files
Files changed (10) hide show
  1. README.md +48 -0
  2. config.json +192 -0
  3. generation_config.json +8 -0
  4. model.safetensors +3 -0
  5. model.safetensors.index.json +823 -0
  6. preprocessor_config.json +27 -0
  7. pytorch_model.bin +3 -0
  8. special_tokens_map.json +6 -0
  9. tokenizer.json +0 -0
  10. tokenizer_config.json +205 -0
README.md ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-4.0
3
+ tags:
4
+ - vision
5
+ - nougat
6
+ pipeline_tag: image-to-text
7
+ ---
8
+
9
+ # Nougat model, small-sized version
10
+
11
+ Nougat model trained on PDF-to-markdown. It was introduced in the paper [Nougat: Neural Optical Understanding for Academic Documents](https://arxiv.org/abs/2308.13418) by Blecher et al. and first released in [this repository](https://github.com/facebookresearch/nougat/tree/main).
12
+
13
+ Disclaimer: The team releasing Nougat did not write a model card for this model so this model card has been written by the Hugging Face team.
14
+
15
+ Note: this model corresponds to the "0.1.0-small" version of the original repository.
16
+
17
+ ## Model description
18
+
19
+ Nougat is a [Donut](https://huggingface.co/docs/transformers/model_doc/donut) model trained to transcribe scientific PDFs into an easy-to-use markdown format. The model consists of a Swin Transformer as vision encoder, and an mBART model as text decoder.
20
+
21
+ The model is trained to autoregressively predict the markdown given only the pixels of the PDF image as input.
22
+
23
+ <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/model_doc/nougat_architecture.jpg"
24
+ alt="drawing" width="600"/>
25
+
26
+ <small> Nougat high-level overview. Taken from the <a href="https://arxiv.org/abs/2308.13418">original paper</a>. </small>
27
+
28
+ ## Intended uses & limitations
29
+
30
+ You can use the raw model for transcribing a PDF into Markdown. See the [model hub](https://huggingface.co/models?search=nougat) to look for other
31
+ fine-tuned versions that may interest you.
32
+
33
+ ### How to use
34
+
35
+ We refer to the [docs](https://huggingface.co/docs/transformers/main/en/model_doc/nougat).
36
+
37
+ ### BibTeX entry and citation info
38
+
39
+ ```bibtex
40
+ @misc{blecher2023nougat,
41
+ title={Nougat: Neural Optical Understanding for Academic Documents},
42
+ author={Lukas Blecher and Guillem Cucurull and Thomas Scialom and Robert Stojnic},
43
+ year={2023},
44
+ eprint={2308.13418},
45
+ archivePrefix={arXiv},
46
+ primaryClass={cs.LG}
47
+ }
48
+ ```
config.json ADDED
@@ -0,0 +1,192 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "VisionEncoderDecoderModel"
4
+ ],
5
+ "decoder": {
6
+ "_name_or_path": "",
7
+ "activation_dropout": 0.0,
8
+ "activation_function": "gelu",
9
+ "add_cross_attention": true,
10
+ "add_final_layer_norm": true,
11
+ "architectures": null,
12
+ "attention_dropout": 0.0,
13
+ "bad_words_ids": null,
14
+ "begin_suppress_tokens": null,
15
+ "bos_token_id": 0,
16
+ "chunk_size_feed_forward": 0,
17
+ "classifier_dropout": 0.0,
18
+ "cross_attention_hidden_size": null,
19
+ "d_model": 1024,
20
+ "decoder_attention_heads": 16,
21
+ "decoder_ffn_dim": 4096,
22
+ "decoder_layerdrop": 0.0,
23
+ "decoder_layers": 4,
24
+ "decoder_start_token_id": null,
25
+ "diversity_penalty": 0.0,
26
+ "do_sample": false,
27
+ "dropout": 0.1,
28
+ "early_stopping": false,
29
+ "encoder_attention_heads": 16,
30
+ "encoder_ffn_dim": 4096,
31
+ "encoder_layerdrop": 0.0,
32
+ "encoder_layers": 12,
33
+ "encoder_no_repeat_ngram_size": 0,
34
+ "eos_token_id": 2,
35
+ "exponential_decay_length_penalty": null,
36
+ "finetuning_task": null,
37
+ "forced_bos_token_id": null,
38
+ "forced_eos_token_id": 2,
39
+ "id2label": {
40
+ "0": "LABEL_0",
41
+ "1": "LABEL_1"
42
+ },
43
+ "init_std": 0.02,
44
+ "is_decoder": true,
45
+ "is_encoder_decoder": false,
46
+ "label2id": {
47
+ "LABEL_0": 0,
48
+ "LABEL_1": 1
49
+ },
50
+ "length_penalty": 1.0,
51
+ "max_length": 20,
52
+ "max_position_embeddings": 3584,
53
+ "min_length": 0,
54
+ "model_type": "mbart",
55
+ "no_repeat_ngram_size": 0,
56
+ "num_beam_groups": 1,
57
+ "num_beams": 1,
58
+ "num_hidden_layers": 12,
59
+ "num_return_sequences": 1,
60
+ "output_attentions": false,
61
+ "output_hidden_states": false,
62
+ "output_scores": false,
63
+ "pad_token_id": 1,
64
+ "prefix": null,
65
+ "problem_type": null,
66
+ "pruned_heads": {},
67
+ "remove_invalid_values": false,
68
+ "repetition_penalty": 1.0,
69
+ "return_dict": true,
70
+ "return_dict_in_generate": false,
71
+ "scale_embedding": true,
72
+ "sep_token_id": null,
73
+ "suppress_tokens": null,
74
+ "task_specific_params": null,
75
+ "temperature": 1.0,
76
+ "tf_legacy_loss": false,
77
+ "tie_encoder_decoder": false,
78
+ "tie_word_embeddings": false,
79
+ "tokenizer_class": null,
80
+ "top_k": 50,
81
+ "top_p": 1.0,
82
+ "torch_dtype": null,
83
+ "torchscript": false,
84
+ "typical_p": 1.0,
85
+ "use_bfloat16": false,
86
+ "use_cache": true,
87
+ "vocab_size": 50000
88
+ },
89
+ "encoder": {
90
+ "_name_or_path": "",
91
+ "add_cross_attention": false,
92
+ "architectures": null,
93
+ "attention_probs_dropout_prob": 0.0,
94
+ "bad_words_ids": null,
95
+ "begin_suppress_tokens": null,
96
+ "bos_token_id": null,
97
+ "chunk_size_feed_forward": 0,
98
+ "cross_attention_hidden_size": null,
99
+ "decoder_start_token_id": null,
100
+ "depths": [
101
+ 2,
102
+ 2,
103
+ 14,
104
+ 2
105
+ ],
106
+ "diversity_penalty": 0.0,
107
+ "do_sample": false,
108
+ "drop_path_rate": 0.1,
109
+ "early_stopping": false,
110
+ "embed_dim": 128,
111
+ "encoder_no_repeat_ngram_size": 0,
112
+ "eos_token_id": null,
113
+ "exponential_decay_length_penalty": null,
114
+ "finetuning_task": null,
115
+ "forced_bos_token_id": null,
116
+ "forced_eos_token_id": null,
117
+ "hidden_act": "gelu",
118
+ "hidden_dropout_prob": 0.0,
119
+ "hidden_size": 1024,
120
+ "id2label": {
121
+ "0": "LABEL_0",
122
+ "1": "LABEL_1"
123
+ },
124
+ "image_size": [
125
+ 896,
126
+ 672
127
+ ],
128
+ "initializer_range": 0.02,
129
+ "is_decoder": false,
130
+ "is_encoder_decoder": false,
131
+ "label2id": {
132
+ "LABEL_0": 0,
133
+ "LABEL_1": 1
134
+ },
135
+ "layer_norm_eps": 1e-05,
136
+ "length_penalty": 1.0,
137
+ "max_length": 20,
138
+ "min_length": 0,
139
+ "mlp_ratio": 4.0,
140
+ "model_type": "donut-swin",
141
+ "no_repeat_ngram_size": 0,
142
+ "num_beam_groups": 1,
143
+ "num_beams": 1,
144
+ "num_channels": 3,
145
+ "num_heads": [
146
+ 4,
147
+ 8,
148
+ 16,
149
+ 32
150
+ ],
151
+ "num_layers": 4,
152
+ "num_return_sequences": 1,
153
+ "output_attentions": false,
154
+ "output_hidden_states": false,
155
+ "output_scores": false,
156
+ "pad_token_id": null,
157
+ "patch_size": 4,
158
+ "prefix": null,
159
+ "problem_type": null,
160
+ "pruned_heads": {},
161
+ "qkv_bias": true,
162
+ "remove_invalid_values": false,
163
+ "repetition_penalty": 1.0,
164
+ "return_dict": true,
165
+ "return_dict_in_generate": false,
166
+ "sep_token_id": null,
167
+ "suppress_tokens": null,
168
+ "task_specific_params": null,
169
+ "temperature": 1.0,
170
+ "tf_legacy_loss": false,
171
+ "tie_encoder_decoder": false,
172
+ "tie_word_embeddings": true,
173
+ "tokenizer_class": null,
174
+ "top_k": 50,
175
+ "top_p": 1.0,
176
+ "torch_dtype": null,
177
+ "torchscript": false,
178
+ "typical_p": 1.0,
179
+ "use_absolute_embeddings": false,
180
+ "use_bfloat16": false,
181
+ "window_size": 7
182
+ },
183
+ "is_encoder_decoder": true,
184
+ "model_type": "vision-encoder-decoder",
185
+ "quantization": {
186
+ "group_size": 32,
187
+ "bits": 8
188
+ },
189
+ "tie_word_embeddings": false,
190
+ "torch_dtype": "float32",
191
+ "transformers_version": "4.34.0.dev0"
192
+ }
generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 2,
5
+ "forced_eos_token_id": 2,
6
+ "pad_token_id": 1,
7
+ "transformers_version": "4.34.0.dev0"
8
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4dc450183a0929f98d5359dfb3bda9d2234ffa87378d36febb1cfdb9fdcd82f
3
+ size 310482872
model.safetensors.index.json ADDED
@@ -0,0 +1,823 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 310378624
4
+ },
5
+ "weight_map": {
6
+ "decoder.lm_head.biases": "model.safetensors",
7
+ "decoder.lm_head.scales": "model.safetensors",
8
+ "decoder.lm_head.weight": "model.safetensors",
9
+ "decoder.model.embed_positions.biases": "model.safetensors",
10
+ "decoder.model.embed_positions.scales": "model.safetensors",
11
+ "decoder.model.embed_positions.weight": "model.safetensors",
12
+ "decoder.model.embed_tokens.biases": "model.safetensors",
13
+ "decoder.model.embed_tokens.scales": "model.safetensors",
14
+ "decoder.model.embed_tokens.weight": "model.safetensors",
15
+ "decoder.model.layer_norm.bias": "model.safetensors",
16
+ "decoder.model.layer_norm.weight": "model.safetensors",
17
+ "decoder.model.layernorm_embedding.bias": "model.safetensors",
18
+ "decoder.model.layernorm_embedding.weight": "model.safetensors",
19
+ "decoder.model.layers.0.encoder_attn.k_proj.bias": "model.safetensors",
20
+ "decoder.model.layers.0.encoder_attn.k_proj.biases": "model.safetensors",
21
+ "decoder.model.layers.0.encoder_attn.k_proj.scales": "model.safetensors",
22
+ "decoder.model.layers.0.encoder_attn.k_proj.weight": "model.safetensors",
23
+ "decoder.model.layers.0.encoder_attn.out_proj.bias": "model.safetensors",
24
+ "decoder.model.layers.0.encoder_attn.out_proj.biases": "model.safetensors",
25
+ "decoder.model.layers.0.encoder_attn.out_proj.scales": "model.safetensors",
26
+ "decoder.model.layers.0.encoder_attn.out_proj.weight": "model.safetensors",
27
+ "decoder.model.layers.0.encoder_attn.q_proj.bias": "model.safetensors",
28
+ "decoder.model.layers.0.encoder_attn.q_proj.biases": "model.safetensors",
29
+ "decoder.model.layers.0.encoder_attn.q_proj.scales": "model.safetensors",
30
+ "decoder.model.layers.0.encoder_attn.q_proj.weight": "model.safetensors",
31
+ "decoder.model.layers.0.encoder_attn.v_proj.bias": "model.safetensors",
32
+ "decoder.model.layers.0.encoder_attn.v_proj.biases": "model.safetensors",
33
+ "decoder.model.layers.0.encoder_attn.v_proj.scales": "model.safetensors",
34
+ "decoder.model.layers.0.encoder_attn.v_proj.weight": "model.safetensors",
35
+ "decoder.model.layers.0.encoder_attn_layer_norm.bias": "model.safetensors",
36
+ "decoder.model.layers.0.encoder_attn_layer_norm.weight": "model.safetensors",
37
+ "decoder.model.layers.0.fc1.bias": "model.safetensors",
38
+ "decoder.model.layers.0.fc1.biases": "model.safetensors",
39
+ "decoder.model.layers.0.fc1.scales": "model.safetensors",
40
+ "decoder.model.layers.0.fc1.weight": "model.safetensors",
41
+ "decoder.model.layers.0.fc2.bias": "model.safetensors",
42
+ "decoder.model.layers.0.fc2.biases": "model.safetensors",
43
+ "decoder.model.layers.0.fc2.scales": "model.safetensors",
44
+ "decoder.model.layers.0.fc2.weight": "model.safetensors",
45
+ "decoder.model.layers.0.final_layer_norm.bias": "model.safetensors",
46
+ "decoder.model.layers.0.final_layer_norm.weight": "model.safetensors",
47
+ "decoder.model.layers.0.self_attn.k_proj.bias": "model.safetensors",
48
+ "decoder.model.layers.0.self_attn.k_proj.biases": "model.safetensors",
49
+ "decoder.model.layers.0.self_attn.k_proj.scales": "model.safetensors",
50
+ "decoder.model.layers.0.self_attn.k_proj.weight": "model.safetensors",
51
+ "decoder.model.layers.0.self_attn.out_proj.bias": "model.safetensors",
52
+ "decoder.model.layers.0.self_attn.out_proj.biases": "model.safetensors",
53
+ "decoder.model.layers.0.self_attn.out_proj.scales": "model.safetensors",
54
+ "decoder.model.layers.0.self_attn.out_proj.weight": "model.safetensors",
55
+ "decoder.model.layers.0.self_attn.q_proj.bias": "model.safetensors",
56
+ "decoder.model.layers.0.self_attn.q_proj.biases": "model.safetensors",
57
+ "decoder.model.layers.0.self_attn.q_proj.scales": "model.safetensors",
58
+ "decoder.model.layers.0.self_attn.q_proj.weight": "model.safetensors",
59
+ "decoder.model.layers.0.self_attn.v_proj.bias": "model.safetensors",
60
+ "decoder.model.layers.0.self_attn.v_proj.biases": "model.safetensors",
61
+ "decoder.model.layers.0.self_attn.v_proj.scales": "model.safetensors",
62
+ "decoder.model.layers.0.self_attn.v_proj.weight": "model.safetensors",
63
+ "decoder.model.layers.0.self_attn_layer_norm.bias": "model.safetensors",
64
+ "decoder.model.layers.0.self_attn_layer_norm.weight": "model.safetensors",
65
+ "decoder.model.layers.1.encoder_attn.k_proj.bias": "model.safetensors",
66
+ "decoder.model.layers.1.encoder_attn.k_proj.biases": "model.safetensors",
67
+ "decoder.model.layers.1.encoder_attn.k_proj.scales": "model.safetensors",
68
+ "decoder.model.layers.1.encoder_attn.k_proj.weight": "model.safetensors",
69
+ "decoder.model.layers.1.encoder_attn.out_proj.bias": "model.safetensors",
70
+ "decoder.model.layers.1.encoder_attn.out_proj.biases": "model.safetensors",
71
+ "decoder.model.layers.1.encoder_attn.out_proj.scales": "model.safetensors",
72
+ "decoder.model.layers.1.encoder_attn.out_proj.weight": "model.safetensors",
73
+ "decoder.model.layers.1.encoder_attn.q_proj.bias": "model.safetensors",
74
+ "decoder.model.layers.1.encoder_attn.q_proj.biases": "model.safetensors",
75
+ "decoder.model.layers.1.encoder_attn.q_proj.scales": "model.safetensors",
76
+ "decoder.model.layers.1.encoder_attn.q_proj.weight": "model.safetensors",
77
+ "decoder.model.layers.1.encoder_attn.v_proj.bias": "model.safetensors",
78
+ "decoder.model.layers.1.encoder_attn.v_proj.biases": "model.safetensors",
79
+ "decoder.model.layers.1.encoder_attn.v_proj.scales": "model.safetensors",
80
+ "decoder.model.layers.1.encoder_attn.v_proj.weight": "model.safetensors",
81
+ "decoder.model.layers.1.encoder_attn_layer_norm.bias": "model.safetensors",
82
+ "decoder.model.layers.1.encoder_attn_layer_norm.weight": "model.safetensors",
83
+ "decoder.model.layers.1.fc1.bias": "model.safetensors",
84
+ "decoder.model.layers.1.fc1.biases": "model.safetensors",
85
+ "decoder.model.layers.1.fc1.scales": "model.safetensors",
86
+ "decoder.model.layers.1.fc1.weight": "model.safetensors",
87
+ "decoder.model.layers.1.fc2.bias": "model.safetensors",
88
+ "decoder.model.layers.1.fc2.biases": "model.safetensors",
89
+ "decoder.model.layers.1.fc2.scales": "model.safetensors",
90
+ "decoder.model.layers.1.fc2.weight": "model.safetensors",
91
+ "decoder.model.layers.1.final_layer_norm.bias": "model.safetensors",
92
+ "decoder.model.layers.1.final_layer_norm.weight": "model.safetensors",
93
+ "decoder.model.layers.1.self_attn.k_proj.bias": "model.safetensors",
94
+ "decoder.model.layers.1.self_attn.k_proj.biases": "model.safetensors",
95
+ "decoder.model.layers.1.self_attn.k_proj.scales": "model.safetensors",
96
+ "decoder.model.layers.1.self_attn.k_proj.weight": "model.safetensors",
97
+ "decoder.model.layers.1.self_attn.out_proj.bias": "model.safetensors",
98
+ "decoder.model.layers.1.self_attn.out_proj.biases": "model.safetensors",
99
+ "decoder.model.layers.1.self_attn.out_proj.scales": "model.safetensors",
100
+ "decoder.model.layers.1.self_attn.out_proj.weight": "model.safetensors",
101
+ "decoder.model.layers.1.self_attn.q_proj.bias": "model.safetensors",
102
+ "decoder.model.layers.1.self_attn.q_proj.biases": "model.safetensors",
103
+ "decoder.model.layers.1.self_attn.q_proj.scales": "model.safetensors",
104
+ "decoder.model.layers.1.self_attn.q_proj.weight": "model.safetensors",
105
+ "decoder.model.layers.1.self_attn.v_proj.bias": "model.safetensors",
106
+ "decoder.model.layers.1.self_attn.v_proj.biases": "model.safetensors",
107
+ "decoder.model.layers.1.self_attn.v_proj.scales": "model.safetensors",
108
+ "decoder.model.layers.1.self_attn.v_proj.weight": "model.safetensors",
109
+ "decoder.model.layers.1.self_attn_layer_norm.bias": "model.safetensors",
110
+ "decoder.model.layers.1.self_attn_layer_norm.weight": "model.safetensors",
111
+ "decoder.model.layers.2.encoder_attn.k_proj.bias": "model.safetensors",
112
+ "decoder.model.layers.2.encoder_attn.k_proj.biases": "model.safetensors",
113
+ "decoder.model.layers.2.encoder_attn.k_proj.scales": "model.safetensors",
114
+ "decoder.model.layers.2.encoder_attn.k_proj.weight": "model.safetensors",
115
+ "decoder.model.layers.2.encoder_attn.out_proj.bias": "model.safetensors",
116
+ "decoder.model.layers.2.encoder_attn.out_proj.biases": "model.safetensors",
117
+ "decoder.model.layers.2.encoder_attn.out_proj.scales": "model.safetensors",
118
+ "decoder.model.layers.2.encoder_attn.out_proj.weight": "model.safetensors",
119
+ "decoder.model.layers.2.encoder_attn.q_proj.bias": "model.safetensors",
120
+ "decoder.model.layers.2.encoder_attn.q_proj.biases": "model.safetensors",
121
+ "decoder.model.layers.2.encoder_attn.q_proj.scales": "model.safetensors",
122
+ "decoder.model.layers.2.encoder_attn.q_proj.weight": "model.safetensors",
123
+ "decoder.model.layers.2.encoder_attn.v_proj.bias": "model.safetensors",
124
+ "decoder.model.layers.2.encoder_attn.v_proj.biases": "model.safetensors",
125
+ "decoder.model.layers.2.encoder_attn.v_proj.scales": "model.safetensors",
126
+ "decoder.model.layers.2.encoder_attn.v_proj.weight": "model.safetensors",
127
+ "decoder.model.layers.2.encoder_attn_layer_norm.bias": "model.safetensors",
128
+ "decoder.model.layers.2.encoder_attn_layer_norm.weight": "model.safetensors",
129
+ "decoder.model.layers.2.fc1.bias": "model.safetensors",
130
+ "decoder.model.layers.2.fc1.biases": "model.safetensors",
131
+ "decoder.model.layers.2.fc1.scales": "model.safetensors",
132
+ "decoder.model.layers.2.fc1.weight": "model.safetensors",
133
+ "decoder.model.layers.2.fc2.bias": "model.safetensors",
134
+ "decoder.model.layers.2.fc2.biases": "model.safetensors",
135
+ "decoder.model.layers.2.fc2.scales": "model.safetensors",
136
+ "decoder.model.layers.2.fc2.weight": "model.safetensors",
137
+ "decoder.model.layers.2.final_layer_norm.bias": "model.safetensors",
138
+ "decoder.model.layers.2.final_layer_norm.weight": "model.safetensors",
139
+ "decoder.model.layers.2.self_attn.k_proj.bias": "model.safetensors",
140
+ "decoder.model.layers.2.self_attn.k_proj.biases": "model.safetensors",
141
+ "decoder.model.layers.2.self_attn.k_proj.scales": "model.safetensors",
142
+ "decoder.model.layers.2.self_attn.k_proj.weight": "model.safetensors",
143
+ "decoder.model.layers.2.self_attn.out_proj.bias": "model.safetensors",
144
+ "decoder.model.layers.2.self_attn.out_proj.biases": "model.safetensors",
145
+ "decoder.model.layers.2.self_attn.out_proj.scales": "model.safetensors",
146
+ "decoder.model.layers.2.self_attn.out_proj.weight": "model.safetensors",
147
+ "decoder.model.layers.2.self_attn.q_proj.bias": "model.safetensors",
148
+ "decoder.model.layers.2.self_attn.q_proj.biases": "model.safetensors",
149
+ "decoder.model.layers.2.self_attn.q_proj.scales": "model.safetensors",
150
+ "decoder.model.layers.2.self_attn.q_proj.weight": "model.safetensors",
151
+ "decoder.model.layers.2.self_attn.v_proj.bias": "model.safetensors",
152
+ "decoder.model.layers.2.self_attn.v_proj.biases": "model.safetensors",
153
+ "decoder.model.layers.2.self_attn.v_proj.scales": "model.safetensors",
154
+ "decoder.model.layers.2.self_attn.v_proj.weight": "model.safetensors",
155
+ "decoder.model.layers.2.self_attn_layer_norm.bias": "model.safetensors",
156
+ "decoder.model.layers.2.self_attn_layer_norm.weight": "model.safetensors",
157
+ "decoder.model.layers.3.encoder_attn.k_proj.bias": "model.safetensors",
158
+ "decoder.model.layers.3.encoder_attn.k_proj.biases": "model.safetensors",
159
+ "decoder.model.layers.3.encoder_attn.k_proj.scales": "model.safetensors",
160
+ "decoder.model.layers.3.encoder_attn.k_proj.weight": "model.safetensors",
161
+ "decoder.model.layers.3.encoder_attn.out_proj.bias": "model.safetensors",
162
+ "decoder.model.layers.3.encoder_attn.out_proj.biases": "model.safetensors",
163
+ "decoder.model.layers.3.encoder_attn.out_proj.scales": "model.safetensors",
164
+ "decoder.model.layers.3.encoder_attn.out_proj.weight": "model.safetensors",
165
+ "decoder.model.layers.3.encoder_attn.q_proj.bias": "model.safetensors",
166
+ "decoder.model.layers.3.encoder_attn.q_proj.biases": "model.safetensors",
167
+ "decoder.model.layers.3.encoder_attn.q_proj.scales": "model.safetensors",
168
+ "decoder.model.layers.3.encoder_attn.q_proj.weight": "model.safetensors",
169
+ "decoder.model.layers.3.encoder_attn.v_proj.bias": "model.safetensors",
170
+ "decoder.model.layers.3.encoder_attn.v_proj.biases": "model.safetensors",
171
+ "decoder.model.layers.3.encoder_attn.v_proj.scales": "model.safetensors",
172
+ "decoder.model.layers.3.encoder_attn.v_proj.weight": "model.safetensors",
173
+ "decoder.model.layers.3.encoder_attn_layer_norm.bias": "model.safetensors",
174
+ "decoder.model.layers.3.encoder_attn_layer_norm.weight": "model.safetensors",
175
+ "decoder.model.layers.3.fc1.bias": "model.safetensors",
176
+ "decoder.model.layers.3.fc1.biases": "model.safetensors",
177
+ "decoder.model.layers.3.fc1.scales": "model.safetensors",
178
+ "decoder.model.layers.3.fc1.weight": "model.safetensors",
179
+ "decoder.model.layers.3.fc2.bias": "model.safetensors",
180
+ "decoder.model.layers.3.fc2.biases": "model.safetensors",
181
+ "decoder.model.layers.3.fc2.scales": "model.safetensors",
182
+ "decoder.model.layers.3.fc2.weight": "model.safetensors",
183
+ "decoder.model.layers.3.final_layer_norm.bias": "model.safetensors",
184
+ "decoder.model.layers.3.final_layer_norm.weight": "model.safetensors",
185
+ "decoder.model.layers.3.self_attn.k_proj.bias": "model.safetensors",
186
+ "decoder.model.layers.3.self_attn.k_proj.biases": "model.safetensors",
187
+ "decoder.model.layers.3.self_attn.k_proj.scales": "model.safetensors",
188
+ "decoder.model.layers.3.self_attn.k_proj.weight": "model.safetensors",
189
+ "decoder.model.layers.3.self_attn.out_proj.bias": "model.safetensors",
190
+ "decoder.model.layers.3.self_attn.out_proj.biases": "model.safetensors",
191
+ "decoder.model.layers.3.self_attn.out_proj.scales": "model.safetensors",
192
+ "decoder.model.layers.3.self_attn.out_proj.weight": "model.safetensors",
193
+ "decoder.model.layers.3.self_attn.q_proj.bias": "model.safetensors",
194
+ "decoder.model.layers.3.self_attn.q_proj.biases": "model.safetensors",
195
+ "decoder.model.layers.3.self_attn.q_proj.scales": "model.safetensors",
196
+ "decoder.model.layers.3.self_attn.q_proj.weight": "model.safetensors",
197
+ "decoder.model.layers.3.self_attn.v_proj.bias": "model.safetensors",
198
+ "decoder.model.layers.3.self_attn.v_proj.biases": "model.safetensors",
199
+ "decoder.model.layers.3.self_attn.v_proj.scales": "model.safetensors",
200
+ "decoder.model.layers.3.self_attn.v_proj.weight": "model.safetensors",
201
+ "decoder.model.layers.3.self_attn_layer_norm.bias": "model.safetensors",
202
+ "decoder.model.layers.3.self_attn_layer_norm.weight": "model.safetensors",
203
+ "encoder.embeddings.norm.bias": "model.safetensors",
204
+ "encoder.embeddings.norm.weight": "model.safetensors",
205
+ "encoder.embeddings.patch_embeddings.projection.bias": "model.safetensors",
206
+ "encoder.embeddings.patch_embeddings.projection.weight": "model.safetensors",
207
+ "encoder.encoder.layers.0.blocks.0.attention.output.dense.bias": "model.safetensors",
208
+ "encoder.encoder.layers.0.blocks.0.attention.output.dense.biases": "model.safetensors",
209
+ "encoder.encoder.layers.0.blocks.0.attention.output.dense.scales": "model.safetensors",
210
+ "encoder.encoder.layers.0.blocks.0.attention.output.dense.weight": "model.safetensors",
211
+ "encoder.encoder.layers.0.blocks.0.attention.self.key.bias": "model.safetensors",
212
+ "encoder.encoder.layers.0.blocks.0.attention.self.key.biases": "model.safetensors",
213
+ "encoder.encoder.layers.0.blocks.0.attention.self.key.scales": "model.safetensors",
214
+ "encoder.encoder.layers.0.blocks.0.attention.self.key.weight": "model.safetensors",
215
+ "encoder.encoder.layers.0.blocks.0.attention.self.query.bias": "model.safetensors",
216
+ "encoder.encoder.layers.0.blocks.0.attention.self.query.biases": "model.safetensors",
217
+ "encoder.encoder.layers.0.blocks.0.attention.self.query.scales": "model.safetensors",
218
+ "encoder.encoder.layers.0.blocks.0.attention.self.query.weight": "model.safetensors",
219
+ "encoder.encoder.layers.0.blocks.0.attention.self.relative_position_bias_table": "model.safetensors",
220
+ "encoder.encoder.layers.0.blocks.0.attention.self.relative_position_index": "model.safetensors",
221
+ "encoder.encoder.layers.0.blocks.0.attention.self.value.bias": "model.safetensors",
222
+ "encoder.encoder.layers.0.blocks.0.attention.self.value.biases": "model.safetensors",
223
+ "encoder.encoder.layers.0.blocks.0.attention.self.value.scales": "model.safetensors",
224
+ "encoder.encoder.layers.0.blocks.0.attention.self.value.weight": "model.safetensors",
225
+ "encoder.encoder.layers.0.blocks.0.intermediate.dense.bias": "model.safetensors",
226
+ "encoder.encoder.layers.0.blocks.0.intermediate.dense.biases": "model.safetensors",
227
+ "encoder.encoder.layers.0.blocks.0.intermediate.dense.scales": "model.safetensors",
228
+ "encoder.encoder.layers.0.blocks.0.intermediate.dense.weight": "model.safetensors",
229
+ "encoder.encoder.layers.0.blocks.0.layernorm_after.bias": "model.safetensors",
230
+ "encoder.encoder.layers.0.blocks.0.layernorm_after.weight": "model.safetensors",
231
+ "encoder.encoder.layers.0.blocks.0.layernorm_before.bias": "model.safetensors",
232
+ "encoder.encoder.layers.0.blocks.0.layernorm_before.weight": "model.safetensors",
233
+ "encoder.encoder.layers.0.blocks.0.output.dense.bias": "model.safetensors",
234
+ "encoder.encoder.layers.0.blocks.0.output.dense.biases": "model.safetensors",
235
+ "encoder.encoder.layers.0.blocks.0.output.dense.scales": "model.safetensors",
236
+ "encoder.encoder.layers.0.blocks.0.output.dense.weight": "model.safetensors",
237
+ "encoder.encoder.layers.0.blocks.1.attention.output.dense.bias": "model.safetensors",
238
+ "encoder.encoder.layers.0.blocks.1.attention.output.dense.biases": "model.safetensors",
239
+ "encoder.encoder.layers.0.blocks.1.attention.output.dense.scales": "model.safetensors",
240
+ "encoder.encoder.layers.0.blocks.1.attention.output.dense.weight": "model.safetensors",
241
+ "encoder.encoder.layers.0.blocks.1.attention.self.key.bias": "model.safetensors",
242
+ "encoder.encoder.layers.0.blocks.1.attention.self.key.biases": "model.safetensors",
243
+ "encoder.encoder.layers.0.blocks.1.attention.self.key.scales": "model.safetensors",
244
+ "encoder.encoder.layers.0.blocks.1.attention.self.key.weight": "model.safetensors",
245
+ "encoder.encoder.layers.0.blocks.1.attention.self.query.bias": "model.safetensors",
246
+ "encoder.encoder.layers.0.blocks.1.attention.self.query.biases": "model.safetensors",
247
+ "encoder.encoder.layers.0.blocks.1.attention.self.query.scales": "model.safetensors",
248
+ "encoder.encoder.layers.0.blocks.1.attention.self.query.weight": "model.safetensors",
249
+ "encoder.encoder.layers.0.blocks.1.attention.self.relative_position_bias_table": "model.safetensors",
250
+ "encoder.encoder.layers.0.blocks.1.attention.self.relative_position_index": "model.safetensors",
251
+ "encoder.encoder.layers.0.blocks.1.attention.self.value.bias": "model.safetensors",
252
+ "encoder.encoder.layers.0.blocks.1.attention.self.value.biases": "model.safetensors",
253
+ "encoder.encoder.layers.0.blocks.1.attention.self.value.scales": "model.safetensors",
254
+ "encoder.encoder.layers.0.blocks.1.attention.self.value.weight": "model.safetensors",
255
+ "encoder.encoder.layers.0.blocks.1.intermediate.dense.bias": "model.safetensors",
256
+ "encoder.encoder.layers.0.blocks.1.intermediate.dense.biases": "model.safetensors",
257
+ "encoder.encoder.layers.0.blocks.1.intermediate.dense.scales": "model.safetensors",
258
+ "encoder.encoder.layers.0.blocks.1.intermediate.dense.weight": "model.safetensors",
259
+ "encoder.encoder.layers.0.blocks.1.layernorm_after.bias": "model.safetensors",
260
+ "encoder.encoder.layers.0.blocks.1.layernorm_after.weight": "model.safetensors",
261
+ "encoder.encoder.layers.0.blocks.1.layernorm_before.bias": "model.safetensors",
262
+ "encoder.encoder.layers.0.blocks.1.layernorm_before.weight": "model.safetensors",
263
+ "encoder.encoder.layers.0.blocks.1.output.dense.bias": "model.safetensors",
264
+ "encoder.encoder.layers.0.blocks.1.output.dense.biases": "model.safetensors",
265
+ "encoder.encoder.layers.0.blocks.1.output.dense.scales": "model.safetensors",
266
+ "encoder.encoder.layers.0.blocks.1.output.dense.weight": "model.safetensors",
267
+ "encoder.encoder.layers.0.downsample.norm.bias": "model.safetensors",
268
+ "encoder.encoder.layers.0.downsample.norm.weight": "model.safetensors",
269
+ "encoder.encoder.layers.0.downsample.reduction.biases": "model.safetensors",
270
+ "encoder.encoder.layers.0.downsample.reduction.scales": "model.safetensors",
271
+ "encoder.encoder.layers.0.downsample.reduction.weight": "model.safetensors",
272
+ "encoder.encoder.layers.1.blocks.0.attention.output.dense.bias": "model.safetensors",
273
+ "encoder.encoder.layers.1.blocks.0.attention.output.dense.biases": "model.safetensors",
274
+ "encoder.encoder.layers.1.blocks.0.attention.output.dense.scales": "model.safetensors",
275
+ "encoder.encoder.layers.1.blocks.0.attention.output.dense.weight": "model.safetensors",
276
+ "encoder.encoder.layers.1.blocks.0.attention.self.key.bias": "model.safetensors",
277
+ "encoder.encoder.layers.1.blocks.0.attention.self.key.biases": "model.safetensors",
278
+ "encoder.encoder.layers.1.blocks.0.attention.self.key.scales": "model.safetensors",
279
+ "encoder.encoder.layers.1.blocks.0.attention.self.key.weight": "model.safetensors",
280
+ "encoder.encoder.layers.1.blocks.0.attention.self.query.bias": "model.safetensors",
281
+ "encoder.encoder.layers.1.blocks.0.attention.self.query.biases": "model.safetensors",
282
+ "encoder.encoder.layers.1.blocks.0.attention.self.query.scales": "model.safetensors",
283
+ "encoder.encoder.layers.1.blocks.0.attention.self.query.weight": "model.safetensors",
284
+ "encoder.encoder.layers.1.blocks.0.attention.self.relative_position_bias_table": "model.safetensors",
285
+ "encoder.encoder.layers.1.blocks.0.attention.self.relative_position_index": "model.safetensors",
286
+ "encoder.encoder.layers.1.blocks.0.attention.self.value.bias": "model.safetensors",
287
+ "encoder.encoder.layers.1.blocks.0.attention.self.value.biases": "model.safetensors",
288
+ "encoder.encoder.layers.1.blocks.0.attention.self.value.scales": "model.safetensors",
289
+ "encoder.encoder.layers.1.blocks.0.attention.self.value.weight": "model.safetensors",
290
+ "encoder.encoder.layers.1.blocks.0.intermediate.dense.bias": "model.safetensors",
291
+ "encoder.encoder.layers.1.blocks.0.intermediate.dense.biases": "model.safetensors",
292
+ "encoder.encoder.layers.1.blocks.0.intermediate.dense.scales": "model.safetensors",
293
+ "encoder.encoder.layers.1.blocks.0.intermediate.dense.weight": "model.safetensors",
294
+ "encoder.encoder.layers.1.blocks.0.layernorm_after.bias": "model.safetensors",
295
+ "encoder.encoder.layers.1.blocks.0.layernorm_after.weight": "model.safetensors",
296
+ "encoder.encoder.layers.1.blocks.0.layernorm_before.bias": "model.safetensors",
297
+ "encoder.encoder.layers.1.blocks.0.layernorm_before.weight": "model.safetensors",
298
+ "encoder.encoder.layers.1.blocks.0.output.dense.bias": "model.safetensors",
299
+ "encoder.encoder.layers.1.blocks.0.output.dense.biases": "model.safetensors",
300
+ "encoder.encoder.layers.1.blocks.0.output.dense.scales": "model.safetensors",
301
+ "encoder.encoder.layers.1.blocks.0.output.dense.weight": "model.safetensors",
302
+ "encoder.encoder.layers.1.blocks.1.attention.output.dense.bias": "model.safetensors",
303
+ "encoder.encoder.layers.1.blocks.1.attention.output.dense.biases": "model.safetensors",
304
+ "encoder.encoder.layers.1.blocks.1.attention.output.dense.scales": "model.safetensors",
305
+ "encoder.encoder.layers.1.blocks.1.attention.output.dense.weight": "model.safetensors",
306
+ "encoder.encoder.layers.1.blocks.1.attention.self.key.bias": "model.safetensors",
307
+ "encoder.encoder.layers.1.blocks.1.attention.self.key.biases": "model.safetensors",
308
+ "encoder.encoder.layers.1.blocks.1.attention.self.key.scales": "model.safetensors",
309
+ "encoder.encoder.layers.1.blocks.1.attention.self.key.weight": "model.safetensors",
310
+ "encoder.encoder.layers.1.blocks.1.attention.self.query.bias": "model.safetensors",
311
+ "encoder.encoder.layers.1.blocks.1.attention.self.query.biases": "model.safetensors",
312
+ "encoder.encoder.layers.1.blocks.1.attention.self.query.scales": "model.safetensors",
313
+ "encoder.encoder.layers.1.blocks.1.attention.self.query.weight": "model.safetensors",
314
+ "encoder.encoder.layers.1.blocks.1.attention.self.relative_position_bias_table": "model.safetensors",
315
+ "encoder.encoder.layers.1.blocks.1.attention.self.relative_position_index": "model.safetensors",
316
+ "encoder.encoder.layers.1.blocks.1.attention.self.value.bias": "model.safetensors",
317
+ "encoder.encoder.layers.1.blocks.1.attention.self.value.biases": "model.safetensors",
318
+ "encoder.encoder.layers.1.blocks.1.attention.self.value.scales": "model.safetensors",
319
+ "encoder.encoder.layers.1.blocks.1.attention.self.value.weight": "model.safetensors",
320
+ "encoder.encoder.layers.1.blocks.1.intermediate.dense.bias": "model.safetensors",
321
+ "encoder.encoder.layers.1.blocks.1.intermediate.dense.biases": "model.safetensors",
322
+ "encoder.encoder.layers.1.blocks.1.intermediate.dense.scales": "model.safetensors",
323
+ "encoder.encoder.layers.1.blocks.1.intermediate.dense.weight": "model.safetensors",
324
+ "encoder.encoder.layers.1.blocks.1.layernorm_after.bias": "model.safetensors",
325
+ "encoder.encoder.layers.1.blocks.1.layernorm_after.weight": "model.safetensors",
326
+ "encoder.encoder.layers.1.blocks.1.layernorm_before.bias": "model.safetensors",
327
+ "encoder.encoder.layers.1.blocks.1.layernorm_before.weight": "model.safetensors",
328
+ "encoder.encoder.layers.1.blocks.1.output.dense.bias": "model.safetensors",
329
+ "encoder.encoder.layers.1.blocks.1.output.dense.biases": "model.safetensors",
330
+ "encoder.encoder.layers.1.blocks.1.output.dense.scales": "model.safetensors",
331
+ "encoder.encoder.layers.1.blocks.1.output.dense.weight": "model.safetensors",
332
+ "encoder.encoder.layers.1.downsample.norm.bias": "model.safetensors",
333
+ "encoder.encoder.layers.1.downsample.norm.weight": "model.safetensors",
334
+ "encoder.encoder.layers.1.downsample.reduction.biases": "model.safetensors",
335
+ "encoder.encoder.layers.1.downsample.reduction.scales": "model.safetensors",
336
+ "encoder.encoder.layers.1.downsample.reduction.weight": "model.safetensors",
337
+ "encoder.encoder.layers.2.blocks.0.attention.output.dense.bias": "model.safetensors",
338
+ "encoder.encoder.layers.2.blocks.0.attention.output.dense.biases": "model.safetensors",
339
+ "encoder.encoder.layers.2.blocks.0.attention.output.dense.scales": "model.safetensors",
340
+ "encoder.encoder.layers.2.blocks.0.attention.output.dense.weight": "model.safetensors",
341
+ "encoder.encoder.layers.2.blocks.0.attention.self.key.bias": "model.safetensors",
342
+ "encoder.encoder.layers.2.blocks.0.attention.self.key.biases": "model.safetensors",
343
+ "encoder.encoder.layers.2.blocks.0.attention.self.key.scales": "model.safetensors",
344
+ "encoder.encoder.layers.2.blocks.0.attention.self.key.weight": "model.safetensors",
345
+ "encoder.encoder.layers.2.blocks.0.attention.self.query.bias": "model.safetensors",
346
+ "encoder.encoder.layers.2.blocks.0.attention.self.query.biases": "model.safetensors",
347
+ "encoder.encoder.layers.2.blocks.0.attention.self.query.scales": "model.safetensors",
348
+ "encoder.encoder.layers.2.blocks.0.attention.self.query.weight": "model.safetensors",
349
+ "encoder.encoder.layers.2.blocks.0.attention.self.relative_position_bias_table": "model.safetensors",
350
+ "encoder.encoder.layers.2.blocks.0.attention.self.relative_position_index": "model.safetensors",
351
+ "encoder.encoder.layers.2.blocks.0.attention.self.value.bias": "model.safetensors",
352
+ "encoder.encoder.layers.2.blocks.0.attention.self.value.biases": "model.safetensors",
353
+ "encoder.encoder.layers.2.blocks.0.attention.self.value.scales": "model.safetensors",
354
+ "encoder.encoder.layers.2.blocks.0.attention.self.value.weight": "model.safetensors",
355
+ "encoder.encoder.layers.2.blocks.0.intermediate.dense.bias": "model.safetensors",
356
+ "encoder.encoder.layers.2.blocks.0.intermediate.dense.biases": "model.safetensors",
357
+ "encoder.encoder.layers.2.blocks.0.intermediate.dense.scales": "model.safetensors",
358
+ "encoder.encoder.layers.2.blocks.0.intermediate.dense.weight": "model.safetensors",
359
+ "encoder.encoder.layers.2.blocks.0.layernorm_after.bias": "model.safetensors",
360
+ "encoder.encoder.layers.2.blocks.0.layernorm_after.weight": "model.safetensors",
361
+ "encoder.encoder.layers.2.blocks.0.layernorm_before.bias": "model.safetensors",
362
+ "encoder.encoder.layers.2.blocks.0.layernorm_before.weight": "model.safetensors",
363
+ "encoder.encoder.layers.2.blocks.0.output.dense.bias": "model.safetensors",
364
+ "encoder.encoder.layers.2.blocks.0.output.dense.biases": "model.safetensors",
365
+ "encoder.encoder.layers.2.blocks.0.output.dense.scales": "model.safetensors",
366
+ "encoder.encoder.layers.2.blocks.0.output.dense.weight": "model.safetensors",
367
+ "encoder.encoder.layers.2.blocks.1.attention.output.dense.bias": "model.safetensors",
368
+ "encoder.encoder.layers.2.blocks.1.attention.output.dense.biases": "model.safetensors",
369
+ "encoder.encoder.layers.2.blocks.1.attention.output.dense.scales": "model.safetensors",
370
+ "encoder.encoder.layers.2.blocks.1.attention.output.dense.weight": "model.safetensors",
371
+ "encoder.encoder.layers.2.blocks.1.attention.self.key.bias": "model.safetensors",
372
+ "encoder.encoder.layers.2.blocks.1.attention.self.key.biases": "model.safetensors",
373
+ "encoder.encoder.layers.2.blocks.1.attention.self.key.scales": "model.safetensors",
374
+ "encoder.encoder.layers.2.blocks.1.attention.self.key.weight": "model.safetensors",
375
+ "encoder.encoder.layers.2.blocks.1.attention.self.query.bias": "model.safetensors",
376
+ "encoder.encoder.layers.2.blocks.1.attention.self.query.biases": "model.safetensors",
377
+ "encoder.encoder.layers.2.blocks.1.attention.self.query.scales": "model.safetensors",
378
+ "encoder.encoder.layers.2.blocks.1.attention.self.query.weight": "model.safetensors",
379
+ "encoder.encoder.layers.2.blocks.1.attention.self.relative_position_bias_table": "model.safetensors",
380
+ "encoder.encoder.layers.2.blocks.1.attention.self.relative_position_index": "model.safetensors",
381
+ "encoder.encoder.layers.2.blocks.1.attention.self.value.bias": "model.safetensors",
382
+ "encoder.encoder.layers.2.blocks.1.attention.self.value.biases": "model.safetensors",
383
+ "encoder.encoder.layers.2.blocks.1.attention.self.value.scales": "model.safetensors",
384
+ "encoder.encoder.layers.2.blocks.1.attention.self.value.weight": "model.safetensors",
385
+ "encoder.encoder.layers.2.blocks.1.intermediate.dense.bias": "model.safetensors",
386
+ "encoder.encoder.layers.2.blocks.1.intermediate.dense.biases": "model.safetensors",
387
+ "encoder.encoder.layers.2.blocks.1.intermediate.dense.scales": "model.safetensors",
388
+ "encoder.encoder.layers.2.blocks.1.intermediate.dense.weight": "model.safetensors",
389
+ "encoder.encoder.layers.2.blocks.1.layernorm_after.bias": "model.safetensors",
390
+ "encoder.encoder.layers.2.blocks.1.layernorm_after.weight": "model.safetensors",
391
+ "encoder.encoder.layers.2.blocks.1.layernorm_before.bias": "model.safetensors",
392
+ "encoder.encoder.layers.2.blocks.1.layernorm_before.weight": "model.safetensors",
393
+ "encoder.encoder.layers.2.blocks.1.output.dense.bias": "model.safetensors",
394
+ "encoder.encoder.layers.2.blocks.1.output.dense.biases": "model.safetensors",
395
+ "encoder.encoder.layers.2.blocks.1.output.dense.scales": "model.safetensors",
396
+ "encoder.encoder.layers.2.blocks.1.output.dense.weight": "model.safetensors",
397
+ "encoder.encoder.layers.2.blocks.10.attention.output.dense.bias": "model.safetensors",
398
+ "encoder.encoder.layers.2.blocks.10.attention.output.dense.biases": "model.safetensors",
399
+ "encoder.encoder.layers.2.blocks.10.attention.output.dense.scales": "model.safetensors",
400
+ "encoder.encoder.layers.2.blocks.10.attention.output.dense.weight": "model.safetensors",
401
+ "encoder.encoder.layers.2.blocks.10.attention.self.key.bias": "model.safetensors",
402
+ "encoder.encoder.layers.2.blocks.10.attention.self.key.biases": "model.safetensors",
403
+ "encoder.encoder.layers.2.blocks.10.attention.self.key.scales": "model.safetensors",
404
+ "encoder.encoder.layers.2.blocks.10.attention.self.key.weight": "model.safetensors",
405
+ "encoder.encoder.layers.2.blocks.10.attention.self.query.bias": "model.safetensors",
406
+ "encoder.encoder.layers.2.blocks.10.attention.self.query.biases": "model.safetensors",
407
+ "encoder.encoder.layers.2.blocks.10.attention.self.query.scales": "model.safetensors",
408
+ "encoder.encoder.layers.2.blocks.10.attention.self.query.weight": "model.safetensors",
409
+ "encoder.encoder.layers.2.blocks.10.attention.self.relative_position_bias_table": "model.safetensors",
410
+ "encoder.encoder.layers.2.blocks.10.attention.self.relative_position_index": "model.safetensors",
411
+ "encoder.encoder.layers.2.blocks.10.attention.self.value.bias": "model.safetensors",
412
+ "encoder.encoder.layers.2.blocks.10.attention.self.value.biases": "model.safetensors",
413
+ "encoder.encoder.layers.2.blocks.10.attention.self.value.scales": "model.safetensors",
414
+ "encoder.encoder.layers.2.blocks.10.attention.self.value.weight": "model.safetensors",
415
+ "encoder.encoder.layers.2.blocks.10.intermediate.dense.bias": "model.safetensors",
416
+ "encoder.encoder.layers.2.blocks.10.intermediate.dense.biases": "model.safetensors",
417
+ "encoder.encoder.layers.2.blocks.10.intermediate.dense.scales": "model.safetensors",
418
+ "encoder.encoder.layers.2.blocks.10.intermediate.dense.weight": "model.safetensors",
419
+ "encoder.encoder.layers.2.blocks.10.layernorm_after.bias": "model.safetensors",
420
+ "encoder.encoder.layers.2.blocks.10.layernorm_after.weight": "model.safetensors",
421
+ "encoder.encoder.layers.2.blocks.10.layernorm_before.bias": "model.safetensors",
422
+ "encoder.encoder.layers.2.blocks.10.layernorm_before.weight": "model.safetensors",
423
+ "encoder.encoder.layers.2.blocks.10.output.dense.bias": "model.safetensors",
424
+ "encoder.encoder.layers.2.blocks.10.output.dense.biases": "model.safetensors",
425
+ "encoder.encoder.layers.2.blocks.10.output.dense.scales": "model.safetensors",
426
+ "encoder.encoder.layers.2.blocks.10.output.dense.weight": "model.safetensors",
427
+ "encoder.encoder.layers.2.blocks.11.attention.output.dense.bias": "model.safetensors",
428
+ "encoder.encoder.layers.2.blocks.11.attention.output.dense.biases": "model.safetensors",
429
+ "encoder.encoder.layers.2.blocks.11.attention.output.dense.scales": "model.safetensors",
430
+ "encoder.encoder.layers.2.blocks.11.attention.output.dense.weight": "model.safetensors",
431
+ "encoder.encoder.layers.2.blocks.11.attention.self.key.bias": "model.safetensors",
432
+ "encoder.encoder.layers.2.blocks.11.attention.self.key.biases": "model.safetensors",
433
+ "encoder.encoder.layers.2.blocks.11.attention.self.key.scales": "model.safetensors",
434
+ "encoder.encoder.layers.2.blocks.11.attention.self.key.weight": "model.safetensors",
435
+ "encoder.encoder.layers.2.blocks.11.attention.self.query.bias": "model.safetensors",
436
+ "encoder.encoder.layers.2.blocks.11.attention.self.query.biases": "model.safetensors",
437
+ "encoder.encoder.layers.2.blocks.11.attention.self.query.scales": "model.safetensors",
438
+ "encoder.encoder.layers.2.blocks.11.attention.self.query.weight": "model.safetensors",
439
+ "encoder.encoder.layers.2.blocks.11.attention.self.relative_position_bias_table": "model.safetensors",
440
+ "encoder.encoder.layers.2.blocks.11.attention.self.relative_position_index": "model.safetensors",
441
+ "encoder.encoder.layers.2.blocks.11.attention.self.value.bias": "model.safetensors",
442
+ "encoder.encoder.layers.2.blocks.11.attention.self.value.biases": "model.safetensors",
443
+ "encoder.encoder.layers.2.blocks.11.attention.self.value.scales": "model.safetensors",
444
+ "encoder.encoder.layers.2.blocks.11.attention.self.value.weight": "model.safetensors",
445
+ "encoder.encoder.layers.2.blocks.11.intermediate.dense.bias": "model.safetensors",
446
+ "encoder.encoder.layers.2.blocks.11.intermediate.dense.biases": "model.safetensors",
447
+ "encoder.encoder.layers.2.blocks.11.intermediate.dense.scales": "model.safetensors",
448
+ "encoder.encoder.layers.2.blocks.11.intermediate.dense.weight": "model.safetensors",
449
+ "encoder.encoder.layers.2.blocks.11.layernorm_after.bias": "model.safetensors",
450
+ "encoder.encoder.layers.2.blocks.11.layernorm_after.weight": "model.safetensors",
451
+ "encoder.encoder.layers.2.blocks.11.layernorm_before.bias": "model.safetensors",
452
+ "encoder.encoder.layers.2.blocks.11.layernorm_before.weight": "model.safetensors",
453
+ "encoder.encoder.layers.2.blocks.11.output.dense.bias": "model.safetensors",
454
+ "encoder.encoder.layers.2.blocks.11.output.dense.biases": "model.safetensors",
455
+ "encoder.encoder.layers.2.blocks.11.output.dense.scales": "model.safetensors",
456
+ "encoder.encoder.layers.2.blocks.11.output.dense.weight": "model.safetensors",
457
+ "encoder.encoder.layers.2.blocks.12.attention.output.dense.bias": "model.safetensors",
458
+ "encoder.encoder.layers.2.blocks.12.attention.output.dense.biases": "model.safetensors",
459
+ "encoder.encoder.layers.2.blocks.12.attention.output.dense.scales": "model.safetensors",
460
+ "encoder.encoder.layers.2.blocks.12.attention.output.dense.weight": "model.safetensors",
461
+ "encoder.encoder.layers.2.blocks.12.attention.self.key.bias": "model.safetensors",
462
+ "encoder.encoder.layers.2.blocks.12.attention.self.key.biases": "model.safetensors",
463
+ "encoder.encoder.layers.2.blocks.12.attention.self.key.scales": "model.safetensors",
464
+ "encoder.encoder.layers.2.blocks.12.attention.self.key.weight": "model.safetensors",
465
+ "encoder.encoder.layers.2.blocks.12.attention.self.query.bias": "model.safetensors",
466
+ "encoder.encoder.layers.2.blocks.12.attention.self.query.biases": "model.safetensors",
467
+ "encoder.encoder.layers.2.blocks.12.attention.self.query.scales": "model.safetensors",
468
+ "encoder.encoder.layers.2.blocks.12.attention.self.query.weight": "model.safetensors",
469
+ "encoder.encoder.layers.2.blocks.12.attention.self.relative_position_bias_table": "model.safetensors",
470
+ "encoder.encoder.layers.2.blocks.12.attention.self.relative_position_index": "model.safetensors",
471
+ "encoder.encoder.layers.2.blocks.12.attention.self.value.bias": "model.safetensors",
472
+ "encoder.encoder.layers.2.blocks.12.attention.self.value.biases": "model.safetensors",
473
+ "encoder.encoder.layers.2.blocks.12.attention.self.value.scales": "model.safetensors",
474
+ "encoder.encoder.layers.2.blocks.12.attention.self.value.weight": "model.safetensors",
475
+ "encoder.encoder.layers.2.blocks.12.intermediate.dense.bias": "model.safetensors",
476
+ "encoder.encoder.layers.2.blocks.12.intermediate.dense.biases": "model.safetensors",
477
+ "encoder.encoder.layers.2.blocks.12.intermediate.dense.scales": "model.safetensors",
478
+ "encoder.encoder.layers.2.blocks.12.intermediate.dense.weight": "model.safetensors",
479
+ "encoder.encoder.layers.2.blocks.12.layernorm_after.bias": "model.safetensors",
480
+ "encoder.encoder.layers.2.blocks.12.layernorm_after.weight": "model.safetensors",
481
+ "encoder.encoder.layers.2.blocks.12.layernorm_before.bias": "model.safetensors",
482
+ "encoder.encoder.layers.2.blocks.12.layernorm_before.weight": "model.safetensors",
483
+ "encoder.encoder.layers.2.blocks.12.output.dense.bias": "model.safetensors",
484
+ "encoder.encoder.layers.2.blocks.12.output.dense.biases": "model.safetensors",
485
+ "encoder.encoder.layers.2.blocks.12.output.dense.scales": "model.safetensors",
486
+ "encoder.encoder.layers.2.blocks.12.output.dense.weight": "model.safetensors",
487
+ "encoder.encoder.layers.2.blocks.13.attention.output.dense.bias": "model.safetensors",
488
+ "encoder.encoder.layers.2.blocks.13.attention.output.dense.biases": "model.safetensors",
489
+ "encoder.encoder.layers.2.blocks.13.attention.output.dense.scales": "model.safetensors",
490
+ "encoder.encoder.layers.2.blocks.13.attention.output.dense.weight": "model.safetensors",
491
+ "encoder.encoder.layers.2.blocks.13.attention.self.key.bias": "model.safetensors",
492
+ "encoder.encoder.layers.2.blocks.13.attention.self.key.biases": "model.safetensors",
493
+ "encoder.encoder.layers.2.blocks.13.attention.self.key.scales": "model.safetensors",
494
+ "encoder.encoder.layers.2.blocks.13.attention.self.key.weight": "model.safetensors",
495
+ "encoder.encoder.layers.2.blocks.13.attention.self.query.bias": "model.safetensors",
496
+ "encoder.encoder.layers.2.blocks.13.attention.self.query.biases": "model.safetensors",
497
+ "encoder.encoder.layers.2.blocks.13.attention.self.query.scales": "model.safetensors",
498
+ "encoder.encoder.layers.2.blocks.13.attention.self.query.weight": "model.safetensors",
499
+ "encoder.encoder.layers.2.blocks.13.attention.self.relative_position_bias_table": "model.safetensors",
500
+ "encoder.encoder.layers.2.blocks.13.attention.self.relative_position_index": "model.safetensors",
501
+ "encoder.encoder.layers.2.blocks.13.attention.self.value.bias": "model.safetensors",
502
+ "encoder.encoder.layers.2.blocks.13.attention.self.value.biases": "model.safetensors",
503
+ "encoder.encoder.layers.2.blocks.13.attention.self.value.scales": "model.safetensors",
504
+ "encoder.encoder.layers.2.blocks.13.attention.self.value.weight": "model.safetensors",
505
+ "encoder.encoder.layers.2.blocks.13.intermediate.dense.bias": "model.safetensors",
506
+ "encoder.encoder.layers.2.blocks.13.intermediate.dense.biases": "model.safetensors",
507
+ "encoder.encoder.layers.2.blocks.13.intermediate.dense.scales": "model.safetensors",
508
+ "encoder.encoder.layers.2.blocks.13.intermediate.dense.weight": "model.safetensors",
509
+ "encoder.encoder.layers.2.blocks.13.layernorm_after.bias": "model.safetensors",
510
+ "encoder.encoder.layers.2.blocks.13.layernorm_after.weight": "model.safetensors",
511
+ "encoder.encoder.layers.2.blocks.13.layernorm_before.bias": "model.safetensors",
512
+ "encoder.encoder.layers.2.blocks.13.layernorm_before.weight": "model.safetensors",
513
+ "encoder.encoder.layers.2.blocks.13.output.dense.bias": "model.safetensors",
514
+ "encoder.encoder.layers.2.blocks.13.output.dense.biases": "model.safetensors",
515
+ "encoder.encoder.layers.2.blocks.13.output.dense.scales": "model.safetensors",
516
+ "encoder.encoder.layers.2.blocks.13.output.dense.weight": "model.safetensors",
517
+ "encoder.encoder.layers.2.blocks.2.attention.output.dense.bias": "model.safetensors",
518
+ "encoder.encoder.layers.2.blocks.2.attention.output.dense.biases": "model.safetensors",
519
+ "encoder.encoder.layers.2.blocks.2.attention.output.dense.scales": "model.safetensors",
520
+ "encoder.encoder.layers.2.blocks.2.attention.output.dense.weight": "model.safetensors",
521
+ "encoder.encoder.layers.2.blocks.2.attention.self.key.bias": "model.safetensors",
522
+ "encoder.encoder.layers.2.blocks.2.attention.self.key.biases": "model.safetensors",
523
+ "encoder.encoder.layers.2.blocks.2.attention.self.key.scales": "model.safetensors",
524
+ "encoder.encoder.layers.2.blocks.2.attention.self.key.weight": "model.safetensors",
525
+ "encoder.encoder.layers.2.blocks.2.attention.self.query.bias": "model.safetensors",
526
+ "encoder.encoder.layers.2.blocks.2.attention.self.query.biases": "model.safetensors",
527
+ "encoder.encoder.layers.2.blocks.2.attention.self.query.scales": "model.safetensors",
528
+ "encoder.encoder.layers.2.blocks.2.attention.self.query.weight": "model.safetensors",
529
+ "encoder.encoder.layers.2.blocks.2.attention.self.relative_position_bias_table": "model.safetensors",
530
+ "encoder.encoder.layers.2.blocks.2.attention.self.relative_position_index": "model.safetensors",
531
+ "encoder.encoder.layers.2.blocks.2.attention.self.value.bias": "model.safetensors",
532
+ "encoder.encoder.layers.2.blocks.2.attention.self.value.biases": "model.safetensors",
533
+ "encoder.encoder.layers.2.blocks.2.attention.self.value.scales": "model.safetensors",
534
+ "encoder.encoder.layers.2.blocks.2.attention.self.value.weight": "model.safetensors",
535
+ "encoder.encoder.layers.2.blocks.2.intermediate.dense.bias": "model.safetensors",
536
+ "encoder.encoder.layers.2.blocks.2.intermediate.dense.biases": "model.safetensors",
537
+ "encoder.encoder.layers.2.blocks.2.intermediate.dense.scales": "model.safetensors",
538
+ "encoder.encoder.layers.2.blocks.2.intermediate.dense.weight": "model.safetensors",
539
+ "encoder.encoder.layers.2.blocks.2.layernorm_after.bias": "model.safetensors",
540
+ "encoder.encoder.layers.2.blocks.2.layernorm_after.weight": "model.safetensors",
541
+ "encoder.encoder.layers.2.blocks.2.layernorm_before.bias": "model.safetensors",
542
+ "encoder.encoder.layers.2.blocks.2.layernorm_before.weight": "model.safetensors",
543
+ "encoder.encoder.layers.2.blocks.2.output.dense.bias": "model.safetensors",
544
+ "encoder.encoder.layers.2.blocks.2.output.dense.biases": "model.safetensors",
545
+ "encoder.encoder.layers.2.blocks.2.output.dense.scales": "model.safetensors",
546
+ "encoder.encoder.layers.2.blocks.2.output.dense.weight": "model.safetensors",
547
+ "encoder.encoder.layers.2.blocks.3.attention.output.dense.bias": "model.safetensors",
548
+ "encoder.encoder.layers.2.blocks.3.attention.output.dense.biases": "model.safetensors",
549
+ "encoder.encoder.layers.2.blocks.3.attention.output.dense.scales": "model.safetensors",
550
+ "encoder.encoder.layers.2.blocks.3.attention.output.dense.weight": "model.safetensors",
551
+ "encoder.encoder.layers.2.blocks.3.attention.self.key.bias": "model.safetensors",
552
+ "encoder.encoder.layers.2.blocks.3.attention.self.key.biases": "model.safetensors",
553
+ "encoder.encoder.layers.2.blocks.3.attention.self.key.scales": "model.safetensors",
554
+ "encoder.encoder.layers.2.blocks.3.attention.self.key.weight": "model.safetensors",
555
+ "encoder.encoder.layers.2.blocks.3.attention.self.query.bias": "model.safetensors",
556
+ "encoder.encoder.layers.2.blocks.3.attention.self.query.biases": "model.safetensors",
557
+ "encoder.encoder.layers.2.blocks.3.attention.self.query.scales": "model.safetensors",
558
+ "encoder.encoder.layers.2.blocks.3.attention.self.query.weight": "model.safetensors",
559
+ "encoder.encoder.layers.2.blocks.3.attention.self.relative_position_bias_table": "model.safetensors",
560
+ "encoder.encoder.layers.2.blocks.3.attention.self.relative_position_index": "model.safetensors",
561
+ "encoder.encoder.layers.2.blocks.3.attention.self.value.bias": "model.safetensors",
562
+ "encoder.encoder.layers.2.blocks.3.attention.self.value.biases": "model.safetensors",
563
+ "encoder.encoder.layers.2.blocks.3.attention.self.value.scales": "model.safetensors",
564
+ "encoder.encoder.layers.2.blocks.3.attention.self.value.weight": "model.safetensors",
565
+ "encoder.encoder.layers.2.blocks.3.intermediate.dense.bias": "model.safetensors",
566
+ "encoder.encoder.layers.2.blocks.3.intermediate.dense.biases": "model.safetensors",
567
+ "encoder.encoder.layers.2.blocks.3.intermediate.dense.scales": "model.safetensors",
568
+ "encoder.encoder.layers.2.blocks.3.intermediate.dense.weight": "model.safetensors",
569
+ "encoder.encoder.layers.2.blocks.3.layernorm_after.bias": "model.safetensors",
570
+ "encoder.encoder.layers.2.blocks.3.layernorm_after.weight": "model.safetensors",
571
+ "encoder.encoder.layers.2.blocks.3.layernorm_before.bias": "model.safetensors",
572
+ "encoder.encoder.layers.2.blocks.3.layernorm_before.weight": "model.safetensors",
573
+ "encoder.encoder.layers.2.blocks.3.output.dense.bias": "model.safetensors",
574
+ "encoder.encoder.layers.2.blocks.3.output.dense.biases": "model.safetensors",
575
+ "encoder.encoder.layers.2.blocks.3.output.dense.scales": "model.safetensors",
576
+ "encoder.encoder.layers.2.blocks.3.output.dense.weight": "model.safetensors",
577
+ "encoder.encoder.layers.2.blocks.4.attention.output.dense.bias": "model.safetensors",
578
+ "encoder.encoder.layers.2.blocks.4.attention.output.dense.biases": "model.safetensors",
579
+ "encoder.encoder.layers.2.blocks.4.attention.output.dense.scales": "model.safetensors",
580
+ "encoder.encoder.layers.2.blocks.4.attention.output.dense.weight": "model.safetensors",
581
+ "encoder.encoder.layers.2.blocks.4.attention.self.key.bias": "model.safetensors",
582
+ "encoder.encoder.layers.2.blocks.4.attention.self.key.biases": "model.safetensors",
583
+ "encoder.encoder.layers.2.blocks.4.attention.self.key.scales": "model.safetensors",
584
+ "encoder.encoder.layers.2.blocks.4.attention.self.key.weight": "model.safetensors",
585
+ "encoder.encoder.layers.2.blocks.4.attention.self.query.bias": "model.safetensors",
586
+ "encoder.encoder.layers.2.blocks.4.attention.self.query.biases": "model.safetensors",
587
+ "encoder.encoder.layers.2.blocks.4.attention.self.query.scales": "model.safetensors",
588
+ "encoder.encoder.layers.2.blocks.4.attention.self.query.weight": "model.safetensors",
589
+ "encoder.encoder.layers.2.blocks.4.attention.self.relative_position_bias_table": "model.safetensors",
590
+ "encoder.encoder.layers.2.blocks.4.attention.self.relative_position_index": "model.safetensors",
591
+ "encoder.encoder.layers.2.blocks.4.attention.self.value.bias": "model.safetensors",
592
+ "encoder.encoder.layers.2.blocks.4.attention.self.value.biases": "model.safetensors",
593
+ "encoder.encoder.layers.2.blocks.4.attention.self.value.scales": "model.safetensors",
594
+ "encoder.encoder.layers.2.blocks.4.attention.self.value.weight": "model.safetensors",
595
+ "encoder.encoder.layers.2.blocks.4.intermediate.dense.bias": "model.safetensors",
596
+ "encoder.encoder.layers.2.blocks.4.intermediate.dense.biases": "model.safetensors",
597
+ "encoder.encoder.layers.2.blocks.4.intermediate.dense.scales": "model.safetensors",
598
+ "encoder.encoder.layers.2.blocks.4.intermediate.dense.weight": "model.safetensors",
599
+ "encoder.encoder.layers.2.blocks.4.layernorm_after.bias": "model.safetensors",
600
+ "encoder.encoder.layers.2.blocks.4.layernorm_after.weight": "model.safetensors",
601
+ "encoder.encoder.layers.2.blocks.4.layernorm_before.bias": "model.safetensors",
602
+ "encoder.encoder.layers.2.blocks.4.layernorm_before.weight": "model.safetensors",
603
+ "encoder.encoder.layers.2.blocks.4.output.dense.bias": "model.safetensors",
604
+ "encoder.encoder.layers.2.blocks.4.output.dense.biases": "model.safetensors",
605
+ "encoder.encoder.layers.2.blocks.4.output.dense.scales": "model.safetensors",
606
+ "encoder.encoder.layers.2.blocks.4.output.dense.weight": "model.safetensors",
607
+ "encoder.encoder.layers.2.blocks.5.attention.output.dense.bias": "model.safetensors",
608
+ "encoder.encoder.layers.2.blocks.5.attention.output.dense.biases": "model.safetensors",
609
+ "encoder.encoder.layers.2.blocks.5.attention.output.dense.scales": "model.safetensors",
610
+ "encoder.encoder.layers.2.blocks.5.attention.output.dense.weight": "model.safetensors",
611
+ "encoder.encoder.layers.2.blocks.5.attention.self.key.bias": "model.safetensors",
612
+ "encoder.encoder.layers.2.blocks.5.attention.self.key.biases": "model.safetensors",
613
+ "encoder.encoder.layers.2.blocks.5.attention.self.key.scales": "model.safetensors",
614
+ "encoder.encoder.layers.2.blocks.5.attention.self.key.weight": "model.safetensors",
615
+ "encoder.encoder.layers.2.blocks.5.attention.self.query.bias": "model.safetensors",
616
+ "encoder.encoder.layers.2.blocks.5.attention.self.query.biases": "model.safetensors",
617
+ "encoder.encoder.layers.2.blocks.5.attention.self.query.scales": "model.safetensors",
618
+ "encoder.encoder.layers.2.blocks.5.attention.self.query.weight": "model.safetensors",
619
+ "encoder.encoder.layers.2.blocks.5.attention.self.relative_position_bias_table": "model.safetensors",
620
+ "encoder.encoder.layers.2.blocks.5.attention.self.relative_position_index": "model.safetensors",
621
+ "encoder.encoder.layers.2.blocks.5.attention.self.value.bias": "model.safetensors",
622
+ "encoder.encoder.layers.2.blocks.5.attention.self.value.biases": "model.safetensors",
623
+ "encoder.encoder.layers.2.blocks.5.attention.self.value.scales": "model.safetensors",
624
+ "encoder.encoder.layers.2.blocks.5.attention.self.value.weight": "model.safetensors",
625
+ "encoder.encoder.layers.2.blocks.5.intermediate.dense.bias": "model.safetensors",
626
+ "encoder.encoder.layers.2.blocks.5.intermediate.dense.biases": "model.safetensors",
627
+ "encoder.encoder.layers.2.blocks.5.intermediate.dense.scales": "model.safetensors",
628
+ "encoder.encoder.layers.2.blocks.5.intermediate.dense.weight": "model.safetensors",
629
+ "encoder.encoder.layers.2.blocks.5.layernorm_after.bias": "model.safetensors",
630
+ "encoder.encoder.layers.2.blocks.5.layernorm_after.weight": "model.safetensors",
631
+ "encoder.encoder.layers.2.blocks.5.layernorm_before.bias": "model.safetensors",
632
+ "encoder.encoder.layers.2.blocks.5.layernorm_before.weight": "model.safetensors",
633
+ "encoder.encoder.layers.2.blocks.5.output.dense.bias": "model.safetensors",
634
+ "encoder.encoder.layers.2.blocks.5.output.dense.biases": "model.safetensors",
635
+ "encoder.encoder.layers.2.blocks.5.output.dense.scales": "model.safetensors",
636
+ "encoder.encoder.layers.2.blocks.5.output.dense.weight": "model.safetensors",
637
+ "encoder.encoder.layers.2.blocks.6.attention.output.dense.bias": "model.safetensors",
638
+ "encoder.encoder.layers.2.blocks.6.attention.output.dense.biases": "model.safetensors",
639
+ "encoder.encoder.layers.2.blocks.6.attention.output.dense.scales": "model.safetensors",
640
+ "encoder.encoder.layers.2.blocks.6.attention.output.dense.weight": "model.safetensors",
641
+ "encoder.encoder.layers.2.blocks.6.attention.self.key.bias": "model.safetensors",
642
+ "encoder.encoder.layers.2.blocks.6.attention.self.key.biases": "model.safetensors",
643
+ "encoder.encoder.layers.2.blocks.6.attention.self.key.scales": "model.safetensors",
644
+ "encoder.encoder.layers.2.blocks.6.attention.self.key.weight": "model.safetensors",
645
+ "encoder.encoder.layers.2.blocks.6.attention.self.query.bias": "model.safetensors",
646
+ "encoder.encoder.layers.2.blocks.6.attention.self.query.biases": "model.safetensors",
647
+ "encoder.encoder.layers.2.blocks.6.attention.self.query.scales": "model.safetensors",
648
+ "encoder.encoder.layers.2.blocks.6.attention.self.query.weight": "model.safetensors",
649
+ "encoder.encoder.layers.2.blocks.6.attention.self.relative_position_bias_table": "model.safetensors",
650
+ "encoder.encoder.layers.2.blocks.6.attention.self.relative_position_index": "model.safetensors",
651
+ "encoder.encoder.layers.2.blocks.6.attention.self.value.bias": "model.safetensors",
652
+ "encoder.encoder.layers.2.blocks.6.attention.self.value.biases": "model.safetensors",
653
+ "encoder.encoder.layers.2.blocks.6.attention.self.value.scales": "model.safetensors",
654
+ "encoder.encoder.layers.2.blocks.6.attention.self.value.weight": "model.safetensors",
655
+ "encoder.encoder.layers.2.blocks.6.intermediate.dense.bias": "model.safetensors",
656
+ "encoder.encoder.layers.2.blocks.6.intermediate.dense.biases": "model.safetensors",
657
+ "encoder.encoder.layers.2.blocks.6.intermediate.dense.scales": "model.safetensors",
658
+ "encoder.encoder.layers.2.blocks.6.intermediate.dense.weight": "model.safetensors",
659
+ "encoder.encoder.layers.2.blocks.6.layernorm_after.bias": "model.safetensors",
660
+ "encoder.encoder.layers.2.blocks.6.layernorm_after.weight": "model.safetensors",
661
+ "encoder.encoder.layers.2.blocks.6.layernorm_before.bias": "model.safetensors",
662
+ "encoder.encoder.layers.2.blocks.6.layernorm_before.weight": "model.safetensors",
663
+ "encoder.encoder.layers.2.blocks.6.output.dense.bias": "model.safetensors",
664
+ "encoder.encoder.layers.2.blocks.6.output.dense.biases": "model.safetensors",
665
+ "encoder.encoder.layers.2.blocks.6.output.dense.scales": "model.safetensors",
666
+ "encoder.encoder.layers.2.blocks.6.output.dense.weight": "model.safetensors",
667
+ "encoder.encoder.layers.2.blocks.7.attention.output.dense.bias": "model.safetensors",
668
+ "encoder.encoder.layers.2.blocks.7.attention.output.dense.biases": "model.safetensors",
669
+ "encoder.encoder.layers.2.blocks.7.attention.output.dense.scales": "model.safetensors",
670
+ "encoder.encoder.layers.2.blocks.7.attention.output.dense.weight": "model.safetensors",
671
+ "encoder.encoder.layers.2.blocks.7.attention.self.key.bias": "model.safetensors",
672
+ "encoder.encoder.layers.2.blocks.7.attention.self.key.biases": "model.safetensors",
673
+ "encoder.encoder.layers.2.blocks.7.attention.self.key.scales": "model.safetensors",
674
+ "encoder.encoder.layers.2.blocks.7.attention.self.key.weight": "model.safetensors",
675
+ "encoder.encoder.layers.2.blocks.7.attention.self.query.bias": "model.safetensors",
676
+ "encoder.encoder.layers.2.blocks.7.attention.self.query.biases": "model.safetensors",
677
+ "encoder.encoder.layers.2.blocks.7.attention.self.query.scales": "model.safetensors",
678
+ "encoder.encoder.layers.2.blocks.7.attention.self.query.weight": "model.safetensors",
679
+ "encoder.encoder.layers.2.blocks.7.attention.self.relative_position_bias_table": "model.safetensors",
680
+ "encoder.encoder.layers.2.blocks.7.attention.self.relative_position_index": "model.safetensors",
681
+ "encoder.encoder.layers.2.blocks.7.attention.self.value.bias": "model.safetensors",
682
+ "encoder.encoder.layers.2.blocks.7.attention.self.value.biases": "model.safetensors",
683
+ "encoder.encoder.layers.2.blocks.7.attention.self.value.scales": "model.safetensors",
684
+ "encoder.encoder.layers.2.blocks.7.attention.self.value.weight": "model.safetensors",
685
+ "encoder.encoder.layers.2.blocks.7.intermediate.dense.bias": "model.safetensors",
686
+ "encoder.encoder.layers.2.blocks.7.intermediate.dense.biases": "model.safetensors",
687
+ "encoder.encoder.layers.2.blocks.7.intermediate.dense.scales": "model.safetensors",
688
+ "encoder.encoder.layers.2.blocks.7.intermediate.dense.weight": "model.safetensors",
689
+ "encoder.encoder.layers.2.blocks.7.layernorm_after.bias": "model.safetensors",
690
+ "encoder.encoder.layers.2.blocks.7.layernorm_after.weight": "model.safetensors",
691
+ "encoder.encoder.layers.2.blocks.7.layernorm_before.bias": "model.safetensors",
692
+ "encoder.encoder.layers.2.blocks.7.layernorm_before.weight": "model.safetensors",
693
+ "encoder.encoder.layers.2.blocks.7.output.dense.bias": "model.safetensors",
694
+ "encoder.encoder.layers.2.blocks.7.output.dense.biases": "model.safetensors",
695
+ "encoder.encoder.layers.2.blocks.7.output.dense.scales": "model.safetensors",
696
+ "encoder.encoder.layers.2.blocks.7.output.dense.weight": "model.safetensors",
697
+ "encoder.encoder.layers.2.blocks.8.attention.output.dense.bias": "model.safetensors",
698
+ "encoder.encoder.layers.2.blocks.8.attention.output.dense.biases": "model.safetensors",
699
+ "encoder.encoder.layers.2.blocks.8.attention.output.dense.scales": "model.safetensors",
700
+ "encoder.encoder.layers.2.blocks.8.attention.output.dense.weight": "model.safetensors",
701
+ "encoder.encoder.layers.2.blocks.8.attention.self.key.bias": "model.safetensors",
702
+ "encoder.encoder.layers.2.blocks.8.attention.self.key.biases": "model.safetensors",
703
+ "encoder.encoder.layers.2.blocks.8.attention.self.key.scales": "model.safetensors",
704
+ "encoder.encoder.layers.2.blocks.8.attention.self.key.weight": "model.safetensors",
705
+ "encoder.encoder.layers.2.blocks.8.attention.self.query.bias": "model.safetensors",
706
+ "encoder.encoder.layers.2.blocks.8.attention.self.query.biases": "model.safetensors",
707
+ "encoder.encoder.layers.2.blocks.8.attention.self.query.scales": "model.safetensors",
708
+ "encoder.encoder.layers.2.blocks.8.attention.self.query.weight": "model.safetensors",
709
+ "encoder.encoder.layers.2.blocks.8.attention.self.relative_position_bias_table": "model.safetensors",
710
+ "encoder.encoder.layers.2.blocks.8.attention.self.relative_position_index": "model.safetensors",
711
+ "encoder.encoder.layers.2.blocks.8.attention.self.value.bias": "model.safetensors",
712
+ "encoder.encoder.layers.2.blocks.8.attention.self.value.biases": "model.safetensors",
713
+ "encoder.encoder.layers.2.blocks.8.attention.self.value.scales": "model.safetensors",
714
+ "encoder.encoder.layers.2.blocks.8.attention.self.value.weight": "model.safetensors",
715
+ "encoder.encoder.layers.2.blocks.8.intermediate.dense.bias": "model.safetensors",
716
+ "encoder.encoder.layers.2.blocks.8.intermediate.dense.biases": "model.safetensors",
717
+ "encoder.encoder.layers.2.blocks.8.intermediate.dense.scales": "model.safetensors",
718
+ "encoder.encoder.layers.2.blocks.8.intermediate.dense.weight": "model.safetensors",
719
+ "encoder.encoder.layers.2.blocks.8.layernorm_after.bias": "model.safetensors",
720
+ "encoder.encoder.layers.2.blocks.8.layernorm_after.weight": "model.safetensors",
721
+ "encoder.encoder.layers.2.blocks.8.layernorm_before.bias": "model.safetensors",
722
+ "encoder.encoder.layers.2.blocks.8.layernorm_before.weight": "model.safetensors",
723
+ "encoder.encoder.layers.2.blocks.8.output.dense.bias": "model.safetensors",
724
+ "encoder.encoder.layers.2.blocks.8.output.dense.biases": "model.safetensors",
725
+ "encoder.encoder.layers.2.blocks.8.output.dense.scales": "model.safetensors",
726
+ "encoder.encoder.layers.2.blocks.8.output.dense.weight": "model.safetensors",
727
+ "encoder.encoder.layers.2.blocks.9.attention.output.dense.bias": "model.safetensors",
728
+ "encoder.encoder.layers.2.blocks.9.attention.output.dense.biases": "model.safetensors",
729
+ "encoder.encoder.layers.2.blocks.9.attention.output.dense.scales": "model.safetensors",
730
+ "encoder.encoder.layers.2.blocks.9.attention.output.dense.weight": "model.safetensors",
731
+ "encoder.encoder.layers.2.blocks.9.attention.self.key.bias": "model.safetensors",
732
+ "encoder.encoder.layers.2.blocks.9.attention.self.key.biases": "model.safetensors",
733
+ "encoder.encoder.layers.2.blocks.9.attention.self.key.scales": "model.safetensors",
734
+ "encoder.encoder.layers.2.blocks.9.attention.self.key.weight": "model.safetensors",
735
+ "encoder.encoder.layers.2.blocks.9.attention.self.query.bias": "model.safetensors",
736
+ "encoder.encoder.layers.2.blocks.9.attention.self.query.biases": "model.safetensors",
737
+ "encoder.encoder.layers.2.blocks.9.attention.self.query.scales": "model.safetensors",
738
+ "encoder.encoder.layers.2.blocks.9.attention.self.query.weight": "model.safetensors",
739
+ "encoder.encoder.layers.2.blocks.9.attention.self.relative_position_bias_table": "model.safetensors",
740
+ "encoder.encoder.layers.2.blocks.9.attention.self.relative_position_index": "model.safetensors",
741
+ "encoder.encoder.layers.2.blocks.9.attention.self.value.bias": "model.safetensors",
742
+ "encoder.encoder.layers.2.blocks.9.attention.self.value.biases": "model.safetensors",
743
+ "encoder.encoder.layers.2.blocks.9.attention.self.value.scales": "model.safetensors",
744
+ "encoder.encoder.layers.2.blocks.9.attention.self.value.weight": "model.safetensors",
745
+ "encoder.encoder.layers.2.blocks.9.intermediate.dense.bias": "model.safetensors",
746
+ "encoder.encoder.layers.2.blocks.9.intermediate.dense.biases": "model.safetensors",
747
+ "encoder.encoder.layers.2.blocks.9.intermediate.dense.scales": "model.safetensors",
748
+ "encoder.encoder.layers.2.blocks.9.intermediate.dense.weight": "model.safetensors",
749
+ "encoder.encoder.layers.2.blocks.9.layernorm_after.bias": "model.safetensors",
750
+ "encoder.encoder.layers.2.blocks.9.layernorm_after.weight": "model.safetensors",
751
+ "encoder.encoder.layers.2.blocks.9.layernorm_before.bias": "model.safetensors",
752
+ "encoder.encoder.layers.2.blocks.9.layernorm_before.weight": "model.safetensors",
753
+ "encoder.encoder.layers.2.blocks.9.output.dense.bias": "model.safetensors",
754
+ "encoder.encoder.layers.2.blocks.9.output.dense.biases": "model.safetensors",
755
+ "encoder.encoder.layers.2.blocks.9.output.dense.scales": "model.safetensors",
756
+ "encoder.encoder.layers.2.blocks.9.output.dense.weight": "model.safetensors",
757
+ "encoder.encoder.layers.2.downsample.norm.bias": "model.safetensors",
758
+ "encoder.encoder.layers.2.downsample.norm.weight": "model.safetensors",
759
+ "encoder.encoder.layers.2.downsample.reduction.biases": "model.safetensors",
760
+ "encoder.encoder.layers.2.downsample.reduction.scales": "model.safetensors",
761
+ "encoder.encoder.layers.2.downsample.reduction.weight": "model.safetensors",
762
+ "encoder.encoder.layers.3.blocks.0.attention.output.dense.bias": "model.safetensors",
763
+ "encoder.encoder.layers.3.blocks.0.attention.output.dense.biases": "model.safetensors",
764
+ "encoder.encoder.layers.3.blocks.0.attention.output.dense.scales": "model.safetensors",
765
+ "encoder.encoder.layers.3.blocks.0.attention.output.dense.weight": "model.safetensors",
766
+ "encoder.encoder.layers.3.blocks.0.attention.self.key.bias": "model.safetensors",
767
+ "encoder.encoder.layers.3.blocks.0.attention.self.key.biases": "model.safetensors",
768
+ "encoder.encoder.layers.3.blocks.0.attention.self.key.scales": "model.safetensors",
769
+ "encoder.encoder.layers.3.blocks.0.attention.self.key.weight": "model.safetensors",
770
+ "encoder.encoder.layers.3.blocks.0.attention.self.query.bias": "model.safetensors",
771
+ "encoder.encoder.layers.3.blocks.0.attention.self.query.biases": "model.safetensors",
772
+ "encoder.encoder.layers.3.blocks.0.attention.self.query.scales": "model.safetensors",
773
+ "encoder.encoder.layers.3.blocks.0.attention.self.query.weight": "model.safetensors",
774
+ "encoder.encoder.layers.3.blocks.0.attention.self.relative_position_bias_table": "model.safetensors",
775
+ "encoder.encoder.layers.3.blocks.0.attention.self.relative_position_index": "model.safetensors",
776
+ "encoder.encoder.layers.3.blocks.0.attention.self.value.bias": "model.safetensors",
777
+ "encoder.encoder.layers.3.blocks.0.attention.self.value.biases": "model.safetensors",
778
+ "encoder.encoder.layers.3.blocks.0.attention.self.value.scales": "model.safetensors",
779
+ "encoder.encoder.layers.3.blocks.0.attention.self.value.weight": "model.safetensors",
780
+ "encoder.encoder.layers.3.blocks.0.intermediate.dense.bias": "model.safetensors",
781
+ "encoder.encoder.layers.3.blocks.0.intermediate.dense.biases": "model.safetensors",
782
+ "encoder.encoder.layers.3.blocks.0.intermediate.dense.scales": "model.safetensors",
783
+ "encoder.encoder.layers.3.blocks.0.intermediate.dense.weight": "model.safetensors",
784
+ "encoder.encoder.layers.3.blocks.0.layernorm_after.bias": "model.safetensors",
785
+ "encoder.encoder.layers.3.blocks.0.layernorm_after.weight": "model.safetensors",
786
+ "encoder.encoder.layers.3.blocks.0.layernorm_before.bias": "model.safetensors",
787
+ "encoder.encoder.layers.3.blocks.0.layernorm_before.weight": "model.safetensors",
788
+ "encoder.encoder.layers.3.blocks.0.output.dense.bias": "model.safetensors",
789
+ "encoder.encoder.layers.3.blocks.0.output.dense.biases": "model.safetensors",
790
+ "encoder.encoder.layers.3.blocks.0.output.dense.scales": "model.safetensors",
791
+ "encoder.encoder.layers.3.blocks.0.output.dense.weight": "model.safetensors",
792
+ "encoder.encoder.layers.3.blocks.1.attention.output.dense.bias": "model.safetensors",
793
+ "encoder.encoder.layers.3.blocks.1.attention.output.dense.biases": "model.safetensors",
794
+ "encoder.encoder.layers.3.blocks.1.attention.output.dense.scales": "model.safetensors",
795
+ "encoder.encoder.layers.3.blocks.1.attention.output.dense.weight": "model.safetensors",
796
+ "encoder.encoder.layers.3.blocks.1.attention.self.key.bias": "model.safetensors",
797
+ "encoder.encoder.layers.3.blocks.1.attention.self.key.biases": "model.safetensors",
798
+ "encoder.encoder.layers.3.blocks.1.attention.self.key.scales": "model.safetensors",
799
+ "encoder.encoder.layers.3.blocks.1.attention.self.key.weight": "model.safetensors",
800
+ "encoder.encoder.layers.3.blocks.1.attention.self.query.bias": "model.safetensors",
801
+ "encoder.encoder.layers.3.blocks.1.attention.self.query.biases": "model.safetensors",
802
+ "encoder.encoder.layers.3.blocks.1.attention.self.query.scales": "model.safetensors",
803
+ "encoder.encoder.layers.3.blocks.1.attention.self.query.weight": "model.safetensors",
804
+ "encoder.encoder.layers.3.blocks.1.attention.self.relative_position_bias_table": "model.safetensors",
805
+ "encoder.encoder.layers.3.blocks.1.attention.self.relative_position_index": "model.safetensors",
806
+ "encoder.encoder.layers.3.blocks.1.attention.self.value.bias": "model.safetensors",
807
+ "encoder.encoder.layers.3.blocks.1.attention.self.value.biases": "model.safetensors",
808
+ "encoder.encoder.layers.3.blocks.1.attention.self.value.scales": "model.safetensors",
809
+ "encoder.encoder.layers.3.blocks.1.attention.self.value.weight": "model.safetensors",
810
+ "encoder.encoder.layers.3.blocks.1.intermediate.dense.bias": "model.safetensors",
811
+ "encoder.encoder.layers.3.blocks.1.intermediate.dense.biases": "model.safetensors",
812
+ "encoder.encoder.layers.3.blocks.1.intermediate.dense.scales": "model.safetensors",
813
+ "encoder.encoder.layers.3.blocks.1.intermediate.dense.weight": "model.safetensors",
814
+ "encoder.encoder.layers.3.blocks.1.layernorm_after.bias": "model.safetensors",
815
+ "encoder.encoder.layers.3.blocks.1.layernorm_after.weight": "model.safetensors",
816
+ "encoder.encoder.layers.3.blocks.1.layernorm_before.bias": "model.safetensors",
817
+ "encoder.encoder.layers.3.blocks.1.layernorm_before.weight": "model.safetensors",
818
+ "encoder.encoder.layers.3.blocks.1.output.dense.bias": "model.safetensors",
819
+ "encoder.encoder.layers.3.blocks.1.output.dense.biases": "model.safetensors",
820
+ "encoder.encoder.layers.3.blocks.1.output.dense.scales": "model.safetensors",
821
+ "encoder.encoder.layers.3.blocks.1.output.dense.weight": "model.safetensors"
822
+ }
823
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_align_long_axis": false,
3
+ "do_crop_margin": true,
4
+ "do_normalize": true,
5
+ "do_pad": true,
6
+ "do_rescale": true,
7
+ "do_resize": true,
8
+ "do_thumbnail": true,
9
+ "image_mean": [
10
+ 0.485,
11
+ 0.456,
12
+ 0.406
13
+ ],
14
+ "image_processor_type": "NougatImageProcessor",
15
+ "image_std": [
16
+ 0.229,
17
+ 0.224,
18
+ 0.225
19
+ ],
20
+ "processor_class": "NougatProcessor",
21
+ "resample": 2,
22
+ "rescale_factor": 0.00392156862745098,
23
+ "size": {
24
+ "height": 896,
25
+ "width": 672
26
+ }
27
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e9e8ec3b189a102efdebbbf09017d19ff9724d54bca3a83c92b38491ea27cb1
3
+ size 990082973
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "<pad>",
5
+ "unk_token": "<unk>"
6
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,205 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "4": {
36
+ "content": "[START_REF]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "5": {
44
+ "content": "[END_REF]",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "6": {
52
+ "content": "[IMAGE]",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "7": {
60
+ "content": "<fragments>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "8": {
68
+ "content": "</fragments>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "9": {
76
+ "content": "<work>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "10": {
84
+ "content": "</work>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "11": {
92
+ "content": "[START_SUP]",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "12": {
100
+ "content": "[END_SUP]",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "13": {
108
+ "content": "[START_SUB]",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "14": {
116
+ "content": "[END_SUB]",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "15": {
124
+ "content": "[START_DNA]",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "16": {
132
+ "content": "[END_DNA]",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "17": {
140
+ "content": "[START_AMINO]",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "18": {
148
+ "content": "[END_AMINO]",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "19": {
156
+ "content": "[START_SMILES]",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "20": {
164
+ "content": "[END_SMILES]",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "21": {
172
+ "content": "[START_I_SMILES]",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "22": {
180
+ "content": "[END_I_SMILES]",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ }
187
+ },
188
+ "additional_special_tokens": [],
189
+ "bos_token": "<s>",
190
+ "clean_up_tokenization_spaces": false,
191
+ "eos_token": "</s>",
192
+ "max_length": 3584,
193
+ "model_max_length": 3584,
194
+ "pad_to_multiple_of": null,
195
+ "pad_token": "<pad>",
196
+ "pad_token_type_id": 0,
197
+ "padding_side": "right",
198
+ "processor_class": "NougatProcessor",
199
+ "stride": 0,
200
+ "tokenizer_class": "NougatTokenizer",
201
+ "truncation_side": "right",
202
+ "truncation_strategy": "longest_first",
203
+ "unk_token": "<unk>",
204
+ "vocab_file": null
205
+ }