Hugging Face's logo

luodian
/
OTTER-Image-MPT7B

Text2Text Generation
Transformers
PyTorch
otter
Inference Endpoints
Model card Files Community
2
luodian commited on
Commit
3188128
•
1 Parent(s): 7279421

update

Browse files
Files changed (7) hide show
  1. config.json +196 -0
  2. final_weights.pt +3 -0
  3. pytorch_model-00001-of-00004.bin +3 -0
  4. pytorch_model-00002-of-00004.bin +3 -0
  5. pytorch_model-00003-of-00004.bin +3 -0
  6. pytorch_model-00004-of-00004.bin +3 -0
  7. pytorch_model.bin.index.json +750 -0
config.json ADDED
@@ -0,0 +1,196 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": null,
3
+ "_name_or_path": "/mnt/petrelfs/zhangyuanhan/weights/flamingo-mpt-7B",
4
+ "architectures": [
5
+ "OtterForConditionalGeneration"
6
+ ],
7
+ "cross_attn_every_n_layers": 4,
8
+ "model_type": "otter",
9
+ "text_config": {
10
+ "_name_or_path": "",
11
+ "add_cross_attention": false,
12
+ "architectures": [
13
+ "MPTForCausalLM"
14
+ ],
15
+ "attn_config": {
16
+ "alibi": true,
17
+ "alibi_bias_max": 8,
18
+ "attn_impl": "torch",
19
+ "attn_pdrop": 0,
20
+ "attn_type": "multihead_attention",
21
+ "attn_uses_sequence_id": false,
22
+ "clip_qkv": null,
23
+ "prefix_lm": false,
24
+ "qk_ln": false,
25
+ "softmax_scale": null
26
+ },
27
+ "bad_words_ids": null,
28
+ "begin_suppress_tokens": null,
29
+ "bos_token_id": null,
30
+ "chunk_size_feed_forward": 0,
31
+ "cross_attention_hidden_size": null,
32
+ "d_model": 4096,
33
+ "decoder_start_token_id": null,
34
+ "diversity_penalty": 0.0,
35
+ "do_sample": false,
36
+ "early_stopping": false,
37
+ "emb_pdrop": 0,
38
+ "embedding_fraction": 1.0,
39
+ "encoder_no_repeat_ngram_size": 0,
40
+ "eos_token_id": null,
41
+ "expansion_ratio": 4,
42
+ "exponential_decay_length_penalty": null,
43
+ "finetuning_task": null,
44
+ "forced_bos_token_id": null,
45
+ "forced_eos_token_id": null,
46
+ "hidden_size": 4096,
47
+ "id2label": {
48
+ "0": "LABEL_0",
49
+ "1": "LABEL_1"
50
+ },
51
+ "init_config": {
52
+ "emb_init_std": null,
53
+ "emb_init_uniform_lim": null,
54
+ "fan_mode": "fan_in",
55
+ "init_div_is_residual": true,
56
+ "init_gain": 0,
57
+ "init_nonlinearity": "relu",
58
+ "init_std": 0.02,
59
+ "name": "kaiming_normal_",
60
+ "verbose": 0
61
+ },
62
+ "init_device": "cpu",
63
+ "is_decoder": false,
64
+ "is_encoder_decoder": false,
65
+ "label2id": {
66
+ "LABEL_0": 0,
67
+ "LABEL_1": 1
68
+ },
69
+ "learned_pos_emb": true,
70
+ "length_penalty": 1.0,
71
+ "logit_scale": null,
72
+ "max_length": 20,
73
+ "max_seq_len": 2048,
74
+ "min_length": 0,
75
+ "model_type": "mpt",
76
+ "n_heads": 32,
77
+ "n_layers": 32,
78
+ "no_bias": true,
79
+ "no_repeat_ngram_size": 0,
80
+ "norm_type": "low_precision_layernorm",
81
+ "num_beam_groups": 1,
82
+ "num_beams": 1,
83
+ "num_return_sequences": 1,
84
+ "output_attentions": false,
85
+ "output_hidden_states": false,
86
+ "output_scores": false,
87
+ "pad_token_id": null,
88
+ "prefix": null,
89
+ "problem_type": null,
90
+ "pruned_heads": {},
91
+ "remove_invalid_values": false,
92
+ "repetition_penalty": 1.0,
93
+ "resid_pdrop": 0,
94
+ "return_dict": true,
95
+ "return_dict_in_generate": false,
96
+ "sep_token_id": null,
97
+ "suppress_tokens": null,
98
+ "task_specific_params": null,
99
+ "temperature": 1.0,
100
+ "tf_legacy_loss": false,
101
+ "tie_encoder_decoder": false,
102
+ "tie_word_embeddings": true,
103
+ "tokenizer_class": null,
104
+ "tokenizer_name": "EleutherAI/gpt-neox-20b",
105
+ "top_k": 50,
106
+ "top_p": 1.0,
107
+ "torch_dtype": "bfloat16",
108
+ "torchscript": false,
109
+ "transformers_version": "4.30.1",
110
+ "typical_p": 1.0,
111
+ "use_bfloat16": false,
112
+ "use_cache": false,
113
+ "verbose": 0,
114
+ "vocab_size": 50432
115
+ },
116
+ "torch_dtype": "float32",
117
+ "transformers_version": null,
118
+ "use_media_placement_augmentation": true,
119
+ "vision_config": {
120
+ "_name_or_path": "openai/clip-vit-large-patch14",
121
+ "add_cross_attention": false,
122
+ "architectures": null,
123
+ "attention_dropout": 0.0,
124
+ "bad_words_ids": null,
125
+ "begin_suppress_tokens": null,
126
+ "bos_token_id": null,
127
+ "chunk_size_feed_forward": 0,
128
+ "cross_attention_hidden_size": null,
129
+ "decoder_start_token_id": null,
130
+ "diversity_penalty": 0.0,
131
+ "do_sample": false,
132
+ "early_stopping": false,
133
+ "encoder_no_repeat_ngram_size": 0,
134
+ "eos_token_id": null,
135
+ "exponential_decay_length_penalty": null,
136
+ "finetuning_task": null,
137
+ "forced_bos_token_id": null,
138
+ "forced_eos_token_id": null,
139
+ "hidden_act": "quick_gelu",
140
+ "hidden_size": 1024,
141
+ "id2label": {
142
+ "0": "LABEL_0",
143
+ "1": "LABEL_1"
144
+ },
145
+ "image_size": 224,
146
+ "initializer_factor": 1.0,
147
+ "initializer_range": 0.02,
148
+ "intermediate_size": 4096,
149
+ "is_decoder": false,
150
+ "is_encoder_decoder": false,
151
+ "label2id": {
152
+ "LABEL_0": 0,
153
+ "LABEL_1": 1
154
+ },
155
+ "layer_norm_eps": 1e-05,
156
+ "length_penalty": 1.0,
157
+ "max_length": 20,
158
+ "min_length": 0,
159
+ "model_type": "clip_vision_model",
160
+ "no_repeat_ngram_size": 0,
161
+ "num_attention_heads": 16,
162
+ "num_beam_groups": 1,
163
+ "num_beams": 1,
164
+ "num_channels": 3,
165
+ "num_hidden_layers": 24,
166
+ "num_return_sequences": 1,
167
+ "output_attentions": false,
168
+ "output_hidden_states": false,
169
+ "output_scores": false,
170
+ "pad_token_id": null,
171
+ "patch_size": 14,
172
+ "prefix": null,
173
+ "problem_type": null,
174
+ "projection_dim": 512,
175
+ "pruned_heads": {},
176
+ "remove_invalid_values": false,
177
+ "repetition_penalty": 1.0,
178
+ "return_dict": true,
179
+ "return_dict_in_generate": false,
180
+ "sep_token_id": null,
181
+ "suppress_tokens": null,
182
+ "task_specific_params": null,
183
+ "temperature": 1.0,
184
+ "tf_legacy_loss": false,
185
+ "tie_encoder_decoder": false,
186
+ "tie_word_embeddings": true,
187
+ "tokenizer_class": null,
188
+ "top_k": 50,
189
+ "top_p": 1.0,
190
+ "torch_dtype": null,
191
+ "torchscript": false,
192
+ "transformers_version": "4.30.1",
193
+ "typical_p": 1.0,
194
+ "use_bfloat16": false
195
+ }
196
+ }
final_weights.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f0a2f8c6d11afd31a370bbe2f2fb2a8bb6db50f489f4270274af1b75c6700ad
3
+ size 5541743623
pytorch_model-00001-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a6aa17784c95f4aefb7074ac905a1845ebbdece1bbd218192aefdb4fd7748a7
3
+ size 9995531709
pytorch_model-00002-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49c022d070b2158c3376b436dea7235a1681c8a8238a765d03d11f13bf7ab8a6
3
+ size 9995601857
pytorch_model-00003-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19b60027e397c4a62f6aeb1e69eddeb1ee121c254ec65c2eaf788cb7a6619efe
3
+ size 9995584639
pytorch_model-00004-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d9501073d4a3745089a4fba5ad36475cf943d1f9b08d55a5b9d996fe0c46b7e
3
+ size 2538751703
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,750 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 32525207624
4
+ },
5
+ "weight_map": {
6
+ "lang_encoder.transformer.blocks.0.decoder_layer.attn.Wqkv.weight": "pytorch_model-00001-of-00004.bin",
7
+ "lang_encoder.transformer.blocks.0.decoder_layer.attn.out_proj.weight": "pytorch_model-00001-of-00004.bin",
8
+ "lang_encoder.transformer.blocks.0.decoder_layer.ffn.down_proj.weight": "pytorch_model-00001-of-00004.bin",
9
+ "lang_encoder.transformer.blocks.0.decoder_layer.ffn.up_proj.weight": "pytorch_model-00001-of-00004.bin",
10
+ "lang_encoder.transformer.blocks.0.decoder_layer.norm_1.weight": "pytorch_model-00001-of-00004.bin",
11
+ "lang_encoder.transformer.blocks.0.decoder_layer.norm_2.weight": "pytorch_model-00001-of-00004.bin",
12
+ "lang_encoder.transformer.blocks.1.decoder_layer.attn.Wqkv.weight": "pytorch_model-00001-of-00004.bin",
13
+ "lang_encoder.transformer.blocks.1.decoder_layer.attn.out_proj.weight": "pytorch_model-00001-of-00004.bin",
14
+ "lang_encoder.transformer.blocks.1.decoder_layer.ffn.down_proj.weight": "pytorch_model-00001-of-00004.bin",
15
+ "lang_encoder.transformer.blocks.1.decoder_layer.ffn.up_proj.weight": "pytorch_model-00001-of-00004.bin",
16
+ "lang_encoder.transformer.blocks.1.decoder_layer.norm_1.weight": "pytorch_model-00001-of-00004.bin",
17
+ "lang_encoder.transformer.blocks.1.decoder_layer.norm_2.weight": "pytorch_model-00001-of-00004.bin",
18
+ "lang_encoder.transformer.blocks.10.decoder_layer.attn.Wqkv.weight": "pytorch_model-00002-of-00004.bin",
19
+ "lang_encoder.transformer.blocks.10.decoder_layer.attn.out_proj.weight": "pytorch_model-00002-of-00004.bin",
20
+ "lang_encoder.transformer.blocks.10.decoder_layer.ffn.down_proj.weight": "pytorch_model-00002-of-00004.bin",
21
+ "lang_encoder.transformer.blocks.10.decoder_layer.ffn.up_proj.weight": "pytorch_model-00002-of-00004.bin",
22
+ "lang_encoder.transformer.blocks.10.decoder_layer.norm_1.weight": "pytorch_model-00001-of-00004.bin",
23
+ "lang_encoder.transformer.blocks.10.decoder_layer.norm_2.weight": "pytorch_model-00002-of-00004.bin",
24
+ "lang_encoder.transformer.blocks.11.decoder_layer.attn.Wqkv.weight": "pytorch_model-00002-of-00004.bin",
25
+ "lang_encoder.transformer.blocks.11.decoder_layer.attn.out_proj.weight": "pytorch_model-00002-of-00004.bin",
26
+ "lang_encoder.transformer.blocks.11.decoder_layer.ffn.down_proj.weight": "pytorch_model-00002-of-00004.bin",
27
+ "lang_encoder.transformer.blocks.11.decoder_layer.ffn.up_proj.weight": "pytorch_model-00002-of-00004.bin",
28
+ "lang_encoder.transformer.blocks.11.decoder_layer.norm_1.weight": "pytorch_model-00002-of-00004.bin",
29
+ "lang_encoder.transformer.blocks.11.decoder_layer.norm_2.weight": "pytorch_model-00002-of-00004.bin",
30
+ "lang_encoder.transformer.blocks.11.gated_cross_attn_layer.attn.norm.bias": "pytorch_model-00002-of-00004.bin",
31
+ "lang_encoder.transformer.blocks.11.gated_cross_attn_layer.attn.norm.weight": "pytorch_model-00002-of-00004.bin",
32
+ "lang_encoder.transformer.blocks.11.gated_cross_attn_layer.attn.to_kv.weight": "pytorch_model-00002-of-00004.bin",
33
+ "lang_encoder.transformer.blocks.11.gated_cross_attn_layer.attn.to_out.weight": "pytorch_model-00002-of-00004.bin",
34
+ "lang_encoder.transformer.blocks.11.gated_cross_attn_layer.attn.to_q.weight": "pytorch_model-00002-of-00004.bin",
35
+ "lang_encoder.transformer.blocks.11.gated_cross_attn_layer.attn_gate": "pytorch_model-00002-of-00004.bin",
36
+ "lang_encoder.transformer.blocks.11.gated_cross_attn_layer.feed_forward.0.bias": "pytorch_model-00002-of-00004.bin",
37
+ "lang_encoder.transformer.blocks.11.gated_cross_attn_layer.feed_forward.0.weight": "pytorch_model-00002-of-00004.bin",
38
+ "lang_encoder.transformer.blocks.11.gated_cross_attn_layer.feed_forward.1.weight": "pytorch_model-00002-of-00004.bin",
39
+ "lang_encoder.transformer.blocks.11.gated_cross_attn_layer.feed_forward.3.weight": "pytorch_model-00002-of-00004.bin",
40
+ "lang_encoder.transformer.blocks.11.gated_cross_attn_layer.ff_gate": "pytorch_model-00002-of-00004.bin",
41
+ "lang_encoder.transformer.blocks.12.decoder_layer.attn.Wqkv.weight": "pytorch_model-00002-of-00004.bin",
42
+ "lang_encoder.transformer.blocks.12.decoder_layer.attn.out_proj.weight": "pytorch_model-00002-of-00004.bin",
43
+ "lang_encoder.transformer.blocks.12.decoder_layer.ffn.down_proj.weight": "pytorch_model-00002-of-00004.bin",
44
+ "lang_encoder.transformer.blocks.12.decoder_layer.ffn.up_proj.weight": "pytorch_model-00002-of-00004.bin",
45
+ "lang_encoder.transformer.blocks.12.decoder_layer.norm_1.weight": "pytorch_model-00002-of-00004.bin",
46
+ "lang_encoder.transformer.blocks.12.decoder_layer.norm_2.weight": "pytorch_model-00002-of-00004.bin",
47
+ "lang_encoder.transformer.blocks.13.decoder_layer.attn.Wqkv.weight": "pytorch_model-00002-of-00004.bin",
48
+ "lang_encoder.transformer.blocks.13.decoder_layer.attn.out_proj.weight": "pytorch_model-00002-of-00004.bin",
49
+ "lang_encoder.transformer.blocks.13.decoder_layer.ffn.down_proj.weight": "pytorch_model-00002-of-00004.bin",
50
+ "lang_encoder.transformer.blocks.13.decoder_layer.ffn.up_proj.weight": "pytorch_model-00002-of-00004.bin",
51
+ "lang_encoder.transformer.blocks.13.decoder_layer.norm_1.weight": "pytorch_model-00002-of-00004.bin",
52
+ "lang_encoder.transformer.blocks.13.decoder_layer.norm_2.weight": "pytorch_model-00002-of-00004.bin",
53
+ "lang_encoder.transformer.blocks.14.decoder_layer.attn.Wqkv.weight": "pytorch_model-00002-of-00004.bin",
54
+ "lang_encoder.transformer.blocks.14.decoder_layer.attn.out_proj.weight": "pytorch_model-00002-of-00004.bin",
55
+ "lang_encoder.transformer.blocks.14.decoder_layer.ffn.down_proj.weight": "pytorch_model-00002-of-00004.bin",
56
+ "lang_encoder.transformer.blocks.14.decoder_layer.ffn.up_proj.weight": "pytorch_model-00002-of-00004.bin",
57
+ "lang_encoder.transformer.blocks.14.decoder_layer.norm_1.weight": "pytorch_model-00002-of-00004.bin",
58
+ "lang_encoder.transformer.blocks.14.decoder_layer.norm_2.weight": "pytorch_model-00002-of-00004.bin",
59
+ "lang_encoder.transformer.blocks.15.decoder_layer.attn.Wqkv.weight": "pytorch_model-00002-of-00004.bin",
60
+ "lang_encoder.transformer.blocks.15.decoder_layer.attn.out_proj.weight": "pytorch_model-00002-of-00004.bin",
61
+ "lang_encoder.transformer.blocks.15.decoder_layer.ffn.down_proj.weight": "pytorch_model-00002-of-00004.bin",
62
+ "lang_encoder.transformer.blocks.15.decoder_layer.ffn.up_proj.weight": "pytorch_model-00002-of-00004.bin",
63
+ "lang_encoder.transformer.blocks.15.decoder_layer.norm_1.weight": "pytorch_model-00002-of-00004.bin",
64
+ "lang_encoder.transformer.blocks.15.decoder_layer.norm_2.weight": "pytorch_model-00002-of-00004.bin",
65
+ "lang_encoder.transformer.blocks.15.gated_cross_attn_layer.attn.norm.bias": "pytorch_model-00002-of-00004.bin",
66
+ "lang_encoder.transformer.blocks.15.gated_cross_attn_layer.attn.norm.weight": "pytorch_model-00002-of-00004.bin",
67
+ "lang_encoder.transformer.blocks.15.gated_cross_attn_layer.attn.to_kv.weight": "pytorch_model-00002-of-00004.bin",
68
+ "lang_encoder.transformer.blocks.15.gated_cross_attn_layer.attn.to_out.weight": "pytorch_model-00002-of-00004.bin",
69
+ "lang_encoder.transformer.blocks.15.gated_cross_attn_layer.attn.to_q.weight": "pytorch_model-00002-of-00004.bin",
70
+ "lang_encoder.transformer.blocks.15.gated_cross_attn_layer.attn_gate": "pytorch_model-00002-of-00004.bin",
71
+ "lang_encoder.transformer.blocks.15.gated_cross_attn_layer.feed_forward.0.bias": "pytorch_model-00002-of-00004.bin",
72
+ "lang_encoder.transformer.blocks.15.gated_cross_attn_layer.feed_forward.0.weight": "pytorch_model-00002-of-00004.bin",
73
+ "lang_encoder.transformer.blocks.15.gated_cross_attn_layer.feed_forward.1.weight": "pytorch_model-00002-of-00004.bin",
74
+ "lang_encoder.transformer.blocks.15.gated_cross_attn_layer.feed_forward.3.weight": "pytorch_model-00002-of-00004.bin",
75
+ "lang_encoder.transformer.blocks.15.gated_cross_attn_layer.ff_gate": "pytorch_model-00002-of-00004.bin",
76
+ "lang_encoder.transformer.blocks.16.decoder_layer.attn.Wqkv.weight": "pytorch_model-00002-of-00004.bin",
77
+ "lang_encoder.transformer.blocks.16.decoder_layer.attn.out_proj.weight": "pytorch_model-00002-of-00004.bin",
78
+ "lang_encoder.transformer.blocks.16.decoder_layer.ffn.down_proj.weight": "pytorch_model-00002-of-00004.bin",
79
+ "lang_encoder.transformer.blocks.16.decoder_layer.ffn.up_proj.weight": "pytorch_model-00002-of-00004.bin",
80
+ "lang_encoder.transformer.blocks.16.decoder_layer.norm_1.weight": "pytorch_model-00002-of-00004.bin",
81
+ "lang_encoder.transformer.blocks.16.decoder_layer.norm_2.weight": "pytorch_model-00002-of-00004.bin",
82
+ "lang_encoder.transformer.blocks.17.decoder_layer.attn.Wqkv.weight": "pytorch_model-00002-of-00004.bin",
83
+ "lang_encoder.transformer.blocks.17.decoder_layer.attn.out_proj.weight": "pytorch_model-00002-of-00004.bin",
84
+ "lang_encoder.transformer.blocks.17.decoder_layer.ffn.down_proj.weight": "pytorch_model-00002-of-00004.bin",
85
+ "lang_encoder.transformer.blocks.17.decoder_layer.ffn.up_proj.weight": "pytorch_model-00002-of-00004.bin",
86
+ "lang_encoder.transformer.blocks.17.decoder_layer.norm_1.weight": "pytorch_model-00002-of-00004.bin",
87
+ "lang_encoder.transformer.blocks.17.decoder_layer.norm_2.weight": "pytorch_model-00002-of-00004.bin",
88
+ "lang_encoder.transformer.blocks.18.decoder_layer.attn.Wqkv.weight": "pytorch_model-00002-of-00004.bin",
89
+ "lang_encoder.transformer.blocks.18.decoder_layer.attn.out_proj.weight": "pytorch_model-00002-of-00004.bin",
90
+ "lang_encoder.transformer.blocks.18.decoder_layer.ffn.down_proj.weight": "pytorch_model-00002-of-00004.bin",
91
+ "lang_encoder.transformer.blocks.18.decoder_layer.ffn.up_proj.weight": "pytorch_model-00002-of-00004.bin",
92
+ "lang_encoder.transformer.blocks.18.decoder_layer.norm_1.weight": "pytorch_model-00002-of-00004.bin",
93
+ "lang_encoder.transformer.blocks.18.decoder_layer.norm_2.weight": "pytorch_model-00002-of-00004.bin",
94
+ "lang_encoder.transformer.blocks.19.decoder_layer.attn.Wqkv.weight": "pytorch_model-00002-of-00004.bin",
95
+ "lang_encoder.transformer.blocks.19.decoder_layer.attn.out_proj.weight": "pytorch_model-00002-of-00004.bin",
96
+ "lang_encoder.transformer.blocks.19.decoder_layer.ffn.down_proj.weight": "pytorch_model-00002-of-00004.bin",
97
+ "lang_encoder.transformer.blocks.19.decoder_layer.ffn.up_proj.weight": "pytorch_model-00002-of-00004.bin",
98
+ "lang_encoder.transformer.blocks.19.decoder_layer.norm_1.weight": "pytorch_model-00002-of-00004.bin",
99
+ "lang_encoder.transformer.blocks.19.decoder_layer.norm_2.weight": "pytorch_model-00002-of-00004.bin",
100
+ "lang_encoder.transformer.blocks.19.gated_cross_attn_layer.attn.norm.bias": "pytorch_model-00002-of-00004.bin",
101
+ "lang_encoder.transformer.blocks.19.gated_cross_attn_layer.attn.norm.weight": "pytorch_model-00002-of-00004.bin",
102
+ "lang_encoder.transformer.blocks.19.gated_cross_attn_layer.attn.to_kv.weight": "pytorch_model-00002-of-00004.bin",
103
+ "lang_encoder.transformer.blocks.19.gated_cross_attn_layer.attn.to_out.weight": "pytorch_model-00002-of-00004.bin",
104
+ "lang_encoder.transformer.blocks.19.gated_cross_attn_layer.attn.to_q.weight": "pytorch_model-00002-of-00004.bin",
105
+ "lang_encoder.transformer.blocks.19.gated_cross_attn_layer.attn_gate": "pytorch_model-00002-of-00004.bin",
106
+ "lang_encoder.transformer.blocks.19.gated_cross_attn_layer.feed_forward.0.bias": "pytorch_model-00002-of-00004.bin",
107
+ "lang_encoder.transformer.blocks.19.gated_cross_attn_layer.feed_forward.0.weight": "pytorch_model-00002-of-00004.bin",
108
+ "lang_encoder.transformer.blocks.19.gated_cross_attn_layer.feed_forward.1.weight": "pytorch_model-00002-of-00004.bin",
109
+ "lang_encoder.transformer.blocks.19.gated_cross_attn_layer.feed_forward.3.weight": "pytorch_model-00002-of-00004.bin",
110
+ "lang_encoder.transformer.blocks.19.gated_cross_attn_layer.ff_gate": "pytorch_model-00002-of-00004.bin",
111
+ "lang_encoder.transformer.blocks.2.decoder_layer.attn.Wqkv.weight": "pytorch_model-00001-of-00004.bin",
112
+ "lang_encoder.transformer.blocks.2.decoder_layer.attn.out_proj.weight": "pytorch_model-00001-of-00004.bin",
113
+ "lang_encoder.transformer.blocks.2.decoder_layer.ffn.down_proj.weight": "pytorch_model-00001-of-00004.bin",
114
+ "lang_encoder.transformer.blocks.2.decoder_layer.ffn.up_proj.weight": "pytorch_model-00001-of-00004.bin",
115
+ "lang_encoder.transformer.blocks.2.decoder_layer.norm_1.weight": "pytorch_model-00001-of-00004.bin",
116
+ "lang_encoder.transformer.blocks.2.decoder_layer.norm_2.weight": "pytorch_model-00001-of-00004.bin",
117
+ "lang_encoder.transformer.blocks.20.decoder_layer.attn.Wqkv.weight": "pytorch_model-00002-of-00004.bin",
118
+ "lang_encoder.transformer.blocks.20.decoder_layer.attn.out_proj.weight": "pytorch_model-00002-of-00004.bin",
119
+ "lang_encoder.transformer.blocks.20.decoder_layer.ffn.down_proj.weight": "pytorch_model-00003-of-00004.bin",
120
+ "lang_encoder.transformer.blocks.20.decoder_layer.ffn.up_proj.weight": "pytorch_model-00003-of-00004.bin",
121
+ "lang_encoder.transformer.blocks.20.decoder_layer.norm_1.weight": "pytorch_model-00002-of-00004.bin",
122
+ "lang_encoder.transformer.blocks.20.decoder_layer.norm_2.weight": "pytorch_model-00002-of-00004.bin",
123
+ "lang_encoder.transformer.blocks.21.decoder_layer.attn.Wqkv.weight": "pytorch_model-00003-of-00004.bin",
124
+ "lang_encoder.transformer.blocks.21.decoder_layer.attn.out_proj.weight": "pytorch_model-00003-of-00004.bin",
125
+ "lang_encoder.transformer.blocks.21.decoder_layer.ffn.down_proj.weight": "pytorch_model-00003-of-00004.bin",
126
+ "lang_encoder.transformer.blocks.21.decoder_layer.ffn.up_proj.weight": "pytorch_model-00003-of-00004.bin",
127
+ "lang_encoder.transformer.blocks.21.decoder_layer.norm_1.weight": "pytorch_model-00003-of-00004.bin",
128
+ "lang_encoder.transformer.blocks.21.decoder_layer.norm_2.weight": "pytorch_model-00003-of-00004.bin",
129
+ "lang_encoder.transformer.blocks.22.decoder_layer.attn.Wqkv.weight": "pytorch_model-00003-of-00004.bin",
130
+ "lang_encoder.transformer.blocks.22.decoder_layer.attn.out_proj.weight": "pytorch_model-00003-of-00004.bin",
131
+ "lang_encoder.transformer.blocks.22.decoder_layer.ffn.down_proj.weight": "pytorch_model-00003-of-00004.bin",
132
+ "lang_encoder.transformer.blocks.22.decoder_layer.ffn.up_proj.weight": "pytorch_model-00003-of-00004.bin",
133
+ "lang_encoder.transformer.blocks.22.decoder_layer.norm_1.weight": "pytorch_model-00003-of-00004.bin",
134
+ "lang_encoder.transformer.blocks.22.decoder_layer.norm_2.weight": "pytorch_model-00003-of-00004.bin",
135
+ "lang_encoder.transformer.blocks.23.decoder_layer.attn.Wqkv.weight": "pytorch_model-00003-of-00004.bin",
136
+ "lang_encoder.transformer.blocks.23.decoder_layer.attn.out_proj.weight": "pytorch_model-00003-of-00004.bin",
137
+ "lang_encoder.transformer.blocks.23.decoder_layer.ffn.down_proj.weight": "pytorch_model-00003-of-00004.bin",
138
+ "lang_encoder.transformer.blocks.23.decoder_layer.ffn.up_proj.weight": "pytorch_model-00003-of-00004.bin",
139
+ "lang_encoder.transformer.blocks.23.decoder_layer.norm_1.weight": "pytorch_model-00003-of-00004.bin",
140
+ "lang_encoder.transformer.blocks.23.decoder_layer.norm_2.weight": "pytorch_model-00003-of-00004.bin",
141
+ "lang_encoder.transformer.blocks.23.gated_cross_attn_layer.attn.norm.bias": "pytorch_model-00003-of-00004.bin",
142
+ "lang_encoder.transformer.blocks.23.gated_cross_attn_layer.attn.norm.weight": "pytorch_model-00003-of-00004.bin",
143
+ "lang_encoder.transformer.blocks.23.gated_cross_attn_layer.attn.to_kv.weight": "pytorch_model-00003-of-00004.bin",
144
+ "lang_encoder.transformer.blocks.23.gated_cross_attn_layer.attn.to_out.weight": "pytorch_model-00003-of-00004.bin",
145
+ "lang_encoder.transformer.blocks.23.gated_cross_attn_layer.attn.to_q.weight": "pytorch_model-00003-of-00004.bin",
146
+ "lang_encoder.transformer.blocks.23.gated_cross_attn_layer.attn_gate": "pytorch_model-00003-of-00004.bin",
147
+ "lang_encoder.transformer.blocks.23.gated_cross_attn_layer.feed_forward.0.bias": "pytorch_model-00003-of-00004.bin",
148
+ "lang_encoder.transformer.blocks.23.gated_cross_attn_layer.feed_forward.0.weight": "pytorch_model-00003-of-00004.bin",
149
+ "lang_encoder.transformer.blocks.23.gated_cross_attn_layer.feed_forward.1.weight": "pytorch_model-00003-of-00004.bin",
150
+ "lang_encoder.transformer.blocks.23.gated_cross_attn_layer.feed_forward.3.weight": "pytorch_model-00003-of-00004.bin",
151
+ "lang_encoder.transformer.blocks.23.gated_cross_attn_layer.ff_gate": "pytorch_model-00003-of-00004.bin",
152
+ "lang_encoder.transformer.blocks.24.decoder_layer.attn.Wqkv.weight": "pytorch_model-00003-of-00004.bin",
153
+ "lang_encoder.transformer.blocks.24.decoder_layer.attn.out_proj.weight": "pytorch_model-00003-of-00004.bin",
154
+ "lang_encoder.transformer.blocks.24.decoder_layer.ffn.down_proj.weight": "pytorch_model-00003-of-00004.bin",
155
+ "lang_encoder.transformer.blocks.24.decoder_layer.ffn.up_proj.weight": "pytorch_model-00003-of-00004.bin",
156
+ "lang_encoder.transformer.blocks.24.decoder_layer.norm_1.weight": "pytorch_model-00003-of-00004.bin",
157
+ "lang_encoder.transformer.blocks.24.decoder_layer.norm_2.weight": "pytorch_model-00003-of-00004.bin",
158
+ "lang_encoder.transformer.blocks.25.decoder_layer.attn.Wqkv.weight": "pytorch_model-00003-of-00004.bin",
159
+ "lang_encoder.transformer.blocks.25.decoder_layer.attn.out_proj.weight": "pytorch_model-00003-of-00004.bin",
160
+ "lang_encoder.transformer.blocks.25.decoder_layer.ffn.down_proj.weight": "pytorch_model-00003-of-00004.bin",
161
+ "lang_encoder.transformer.blocks.25.decoder_layer.ffn.up_proj.weight": "pytorch_model-00003-of-00004.bin",
162
+ "lang_encoder.transformer.blocks.25.decoder_layer.norm_1.weight": "pytorch_model-00003-of-00004.bin",
163
+ "lang_encoder.transformer.blocks.25.decoder_layer.norm_2.weight": "pytorch_model-00003-of-00004.bin",
164
+ "lang_encoder.transformer.blocks.26.decoder_layer.attn.Wqkv.weight": "pytorch_model-00003-of-00004.bin",
165
+ "lang_encoder.transformer.blocks.26.decoder_layer.attn.out_proj.weight": "pytorch_model-00003-of-00004.bin",
166
+ "lang_encoder.transformer.blocks.26.decoder_layer.ffn.down_proj.weight": "pytorch_model-00003-of-00004.bin",
167
+ "lang_encoder.transformer.blocks.26.decoder_layer.ffn.up_proj.weight": "pytorch_model-00003-of-00004.bin",
168
+ "lang_encoder.transformer.blocks.26.decoder_layer.norm_1.weight": "pytorch_model-00003-of-00004.bin",
169
+ "lang_encoder.transformer.blocks.26.decoder_layer.norm_2.weight": "pytorch_model-00003-of-00004.bin",
170
+ "lang_encoder.transformer.blocks.27.decoder_layer.attn.Wqkv.weight": "pytorch_model-00003-of-00004.bin",
171
+ "lang_encoder.transformer.blocks.27.decoder_layer.attn.out_proj.weight": "pytorch_model-00003-of-00004.bin",
172
+ "lang_encoder.transformer.blocks.27.decoder_layer.ffn.down_proj.weight": "pytorch_model-00003-of-00004.bin",
173
+ "lang_encoder.transformer.blocks.27.decoder_layer.ffn.up_proj.weight": "pytorch_model-00003-of-00004.bin",
174
+ "lang_encoder.transformer.blocks.27.decoder_layer.norm_1.weight": "pytorch_model-00003-of-00004.bin",
175
+ "lang_encoder.transformer.blocks.27.decoder_layer.norm_2.weight": "pytorch_model-00003-of-00004.bin",
176
+ "lang_encoder.transformer.blocks.27.gated_cross_attn_layer.attn.norm.bias": "pytorch_model-00003-of-00004.bin",
177
+ "lang_encoder.transformer.blocks.27.gated_cross_attn_layer.attn.norm.weight": "pytorch_model-00003-of-00004.bin",
178
+ "lang_encoder.transformer.blocks.27.gated_cross_attn_layer.attn.to_kv.weight": "pytorch_model-00003-of-00004.bin",
179
+ "lang_encoder.transformer.blocks.27.gated_cross_attn_layer.attn.to_out.weight": "pytorch_model-00003-of-00004.bin",
180
+ "lang_encoder.transformer.blocks.27.gated_cross_attn_layer.attn.to_q.weight": "pytorch_model-00003-of-00004.bin",
181
+ "lang_encoder.transformer.blocks.27.gated_cross_attn_layer.attn_gate": "pytorch_model-00003-of-00004.bin",
182
+ "lang_encoder.transformer.blocks.27.gated_cross_attn_layer.feed_forward.0.bias": "pytorch_model-00003-of-00004.bin",
183
+ "lang_encoder.transformer.blocks.27.gated_cross_attn_layer.feed_forward.0.weight": "pytorch_model-00003-of-00004.bin",
184
+ "lang_encoder.transformer.blocks.27.gated_cross_attn_layer.feed_forward.1.weight": "pytorch_model-00003-of-00004.bin",
185
+ "lang_encoder.transformer.blocks.27.gated_cross_attn_layer.feed_forward.3.weight": "pytorch_model-00003-of-00004.bin",
186
+ "lang_encoder.transformer.blocks.27.gated_cross_attn_layer.ff_gate": "pytorch_model-00003-of-00004.bin",
187
+ "lang_encoder.transformer.blocks.28.decoder_layer.attn.Wqkv.weight": "pytorch_model-00003-of-00004.bin",
188
+ "lang_encoder.transformer.blocks.28.decoder_layer.attn.out_proj.weight": "pytorch_model-00003-of-00004.bin",
189
+ "lang_encoder.transformer.blocks.28.decoder_layer.ffn.down_proj.weight": "pytorch_model-00003-of-00004.bin",
190
+ "lang_encoder.transformer.blocks.28.decoder_layer.ffn.up_proj.weight": "pytorch_model-00003-of-00004.bin",
191
+ "lang_encoder.transformer.blocks.28.decoder_layer.norm_1.weight": "pytorch_model-00003-of-00004.bin",
192
+ "lang_encoder.transformer.blocks.28.decoder_layer.norm_2.weight": "pytorch_model-00003-of-00004.bin",
193
+ "lang_encoder.transformer.blocks.29.decoder_layer.attn.Wqkv.weight": "pytorch_model-00003-of-00004.bin",
194
+ "lang_encoder.transformer.blocks.29.decoder_layer.attn.out_proj.weight": "pytorch_model-00003-of-00004.bin",
195
+ "lang_encoder.transformer.blocks.29.decoder_layer.ffn.down_proj.weight": "pytorch_model-00003-of-00004.bin",
196
+ "lang_encoder.transformer.blocks.29.decoder_layer.ffn.up_proj.weight": "pytorch_model-00003-of-00004.bin",
197
+ "lang_encoder.transformer.blocks.29.decoder_layer.norm_1.weight": "pytorch_model-00003-of-00004.bin",
198
+ "lang_encoder.transformer.blocks.29.decoder_layer.norm_2.weight": "pytorch_model-00003-of-00004.bin",
199
+ "lang_encoder.transformer.blocks.3.decoder_layer.attn.Wqkv.weight": "pytorch_model-00001-of-00004.bin",
200
+ "lang_encoder.transformer.blocks.3.decoder_layer.attn.out_proj.weight": "pytorch_model-00001-of-00004.bin",
201
+ "lang_encoder.transformer.blocks.3.decoder_layer.ffn.down_proj.weight": "pytorch_model-00001-of-00004.bin",
202
+ "lang_encoder.transformer.blocks.3.decoder_layer.ffn.up_proj.weight": "pytorch_model-00001-of-00004.bin",
203
+ "lang_encoder.transformer.blocks.3.decoder_layer.norm_1.weight": "pytorch_model-00001-of-00004.bin",
204
+ "lang_encoder.transformer.blocks.3.decoder_layer.norm_2.weight": "pytorch_model-00001-of-00004.bin",
205
+ "lang_encoder.transformer.blocks.3.gated_cross_attn_layer.attn.norm.bias": "pytorch_model-00001-of-00004.bin",
206
+ "lang_encoder.transformer.blocks.3.gated_cross_attn_layer.attn.norm.weight": "pytorch_model-00001-of-00004.bin",
207
+ "lang_encoder.transformer.blocks.3.gated_cross_attn_layer.attn.to_kv.weight": "pytorch_model-00001-of-00004.bin",
208
+ "lang_encoder.transformer.blocks.3.gated_cross_attn_layer.attn.to_out.weight": "pytorch_model-00001-of-00004.bin",
209
+ "lang_encoder.transformer.blocks.3.gated_cross_attn_layer.attn.to_q.weight": "pytorch_model-00001-of-00004.bin",
210
+ "lang_encoder.transformer.blocks.3.gated_cross_attn_layer.attn_gate": "pytorch_model-00001-of-00004.bin",
211
+ "lang_encoder.transformer.blocks.3.gated_cross_attn_layer.feed_forward.0.bias": "pytorch_model-00001-of-00004.bin",
212
+ "lang_encoder.transformer.blocks.3.gated_cross_attn_layer.feed_forward.0.weight": "pytorch_model-00001-of-00004.bin",
213
+ "lang_encoder.transformer.blocks.3.gated_cross_attn_layer.feed_forward.1.weight": "pytorch_model-00001-of-00004.bin",
214
+ "lang_encoder.transformer.blocks.3.gated_cross_attn_layer.feed_forward.3.weight": "pytorch_model-00001-of-00004.bin",
215
+ "lang_encoder.transformer.blocks.3.gated_cross_attn_layer.ff_gate": "pytorch_model-00001-of-00004.bin",
216
+ "lang_encoder.transformer.blocks.30.decoder_layer.attn.Wqkv.weight": "pytorch_model-00003-of-00004.bin",
217
+ "lang_encoder.transformer.blocks.30.decoder_layer.attn.out_proj.weight": "pytorch_model-00003-of-00004.bin",
218
+ "lang_encoder.transformer.blocks.30.decoder_layer.ffn.down_proj.weight": "pytorch_model-00003-of-00004.bin",
219
+ "lang_encoder.transformer.blocks.30.decoder_layer.ffn.up_proj.weight": "pytorch_model-00003-of-00004.bin",
220
+ "lang_encoder.transformer.blocks.30.decoder_layer.norm_1.weight": "pytorch_model-00003-of-00004.bin",
221
+ "lang_encoder.transformer.blocks.30.decoder_layer.norm_2.weight": "pytorch_model-00003-of-00004.bin",
222
+ "lang_encoder.transformer.blocks.31.decoder_layer.attn.Wqkv.weight": "pytorch_model-00004-of-00004.bin",
223
+ "lang_encoder.transformer.blocks.31.decoder_layer.attn.out_proj.weight": "pytorch_model-00004-of-00004.bin",
224
+ "lang_encoder.transformer.blocks.31.decoder_layer.ffn.down_proj.weight": "pytorch_model-00004-of-00004.bin",
225
+ "lang_encoder.transformer.blocks.31.decoder_layer.ffn.up_proj.weight": "pytorch_model-00004-of-00004.bin",
226
+ "lang_encoder.transformer.blocks.31.decoder_layer.norm_1.weight": "pytorch_model-00004-of-00004.bin",
227
+ "lang_encoder.transformer.blocks.31.decoder_layer.norm_2.weight": "pytorch_model-00004-of-00004.bin",
228
+ "lang_encoder.transformer.blocks.31.gated_cross_attn_layer.attn.norm.bias": "pytorch_model-00003-of-00004.bin",
229
+ "lang_encoder.transformer.blocks.31.gated_cross_attn_layer.attn.norm.weight": "pytorch_model-00003-of-00004.bin",
230
+ "lang_encoder.transformer.blocks.31.gated_cross_attn_layer.attn.to_kv.weight": "pytorch_model-00003-of-00004.bin",
231
+ "lang_encoder.transformer.blocks.31.gated_cross_attn_layer.attn.to_out.weight": "pytorch_model-00003-of-00004.bin",
232
+ "lang_encoder.transformer.blocks.31.gated_cross_attn_layer.attn.to_q.weight": "pytorch_model-00003-of-00004.bin",
233
+ "lang_encoder.transformer.blocks.31.gated_cross_attn_layer.attn_gate": "pytorch_model-00003-of-00004.bin",
234
+ "lang_encoder.transformer.blocks.31.gated_cross_attn_layer.feed_forward.0.bias": "pytorch_model-00003-of-00004.bin",
235
+ "lang_encoder.transformer.blocks.31.gated_cross_attn_layer.feed_forward.0.weight": "pytorch_model-00003-of-00004.bin",
236
+ "lang_encoder.transformer.blocks.31.gated_cross_attn_layer.feed_forward.1.weight": "pytorch_model-00003-of-00004.bin",
237
+ "lang_encoder.transformer.blocks.31.gated_cross_attn_layer.feed_forward.3.weight": "pytorch_model-00004-of-00004.bin",
238
+ "lang_encoder.transformer.blocks.31.gated_cross_attn_layer.ff_gate": "pytorch_model-00003-of-00004.bin",
239
+ "lang_encoder.transformer.blocks.4.decoder_layer.attn.Wqkv.weight": "pytorch_model-00001-of-00004.bin",
240
+ "lang_encoder.transformer.blocks.4.decoder_layer.attn.out_proj.weight": "pytorch_model-00001-of-00004.bin",
241
+ "lang_encoder.transformer.blocks.4.decoder_layer.ffn.down_proj.weight": "pytorch_model-00001-of-00004.bin",
242
+ "lang_encoder.transformer.blocks.4.decoder_layer.ffn.up_proj.weight": "pytorch_model-00001-of-00004.bin",
243
+ "lang_encoder.transformer.blocks.4.decoder_layer.norm_1.weight": "pytorch_model-00001-of-00004.bin",
244
+ "lang_encoder.transformer.blocks.4.decoder_layer.norm_2.weight": "pytorch_model-00001-of-00004.bin",
245
+ "lang_encoder.transformer.blocks.5.decoder_layer.attn.Wqkv.weight": "pytorch_model-00001-of-00004.bin",
246
+ "lang_encoder.transformer.blocks.5.decoder_layer.attn.out_proj.weight": "pytorch_model-00001-of-00004.bin",
247
+ "lang_encoder.transformer.blocks.5.decoder_layer.ffn.down_proj.weight": "pytorch_model-00001-of-00004.bin",
248
+ "lang_encoder.transformer.blocks.5.decoder_layer.ffn.up_proj.weight": "pytorch_model-00001-of-00004.bin",
249
+ "lang_encoder.transformer.blocks.5.decoder_layer.norm_1.weight": "pytorch_model-00001-of-00004.bin",
250
+ "lang_encoder.transformer.blocks.5.decoder_layer.norm_2.weight": "pytorch_model-00001-of-00004.bin",
251
+ "lang_encoder.transformer.blocks.6.decoder_layer.attn.Wqkv.weight": "pytorch_model-00001-of-00004.bin",
252
+ "lang_encoder.transformer.blocks.6.decoder_layer.attn.out_proj.weight": "pytorch_model-00001-of-00004.bin",
253
+ "lang_encoder.transformer.blocks.6.decoder_layer.ffn.down_proj.weight": "pytorch_model-00001-of-00004.bin",
254
+ "lang_encoder.transformer.blocks.6.decoder_layer.ffn.up_proj.weight": "pytorch_model-00001-of-00004.bin",
255
+ "lang_encoder.transformer.blocks.6.decoder_layer.norm_1.weight": "pytorch_model-00001-of-00004.bin",
256
+ "lang_encoder.transformer.blocks.6.decoder_layer.norm_2.weight": "pytorch_model-00001-of-00004.bin",
257
+ "lang_encoder.transformer.blocks.7.decoder_layer.attn.Wqkv.weight": "pytorch_model-00001-of-00004.bin",
258
+ "lang_encoder.transformer.blocks.7.decoder_layer.attn.out_proj.weight": "pytorch_model-00001-of-00004.bin",
259
+ "lang_encoder.transformer.blocks.7.decoder_layer.ffn.down_proj.weight": "pytorch_model-00001-of-00004.bin",
260
+ "lang_encoder.transformer.blocks.7.decoder_layer.ffn.up_proj.weight": "pytorch_model-00001-of-00004.bin",
261
+ "lang_encoder.transformer.blocks.7.decoder_layer.norm_1.weight": "pytorch_model-00001-of-00004.bin",
262
+ "lang_encoder.transformer.blocks.7.decoder_layer.norm_2.weight": "pytorch_model-00001-of-00004.bin",
263
+ "lang_encoder.transformer.blocks.7.gated_cross_attn_layer.attn.norm.bias": "pytorch_model-00001-of-00004.bin",
264
+ "lang_encoder.transformer.blocks.7.gated_cross_attn_layer.attn.norm.weight": "pytorch_model-00001-of-00004.bin",
265
+ "lang_encoder.transformer.blocks.7.gated_cross_attn_layer.attn.to_kv.weight": "pytorch_model-00001-of-00004.bin",
266
+ "lang_encoder.transformer.blocks.7.gated_cross_attn_layer.attn.to_out.weight": "pytorch_model-00001-of-00004.bin",
267
+ "lang_encoder.transformer.blocks.7.gated_cross_attn_layer.attn.to_q.weight": "pytorch_model-00001-of-00004.bin",
268
+ "lang_encoder.transformer.blocks.7.gated_cross_attn_layer.attn_gate": "pytorch_model-00001-of-00004.bin",
269
+ "lang_encoder.transformer.blocks.7.gated_cross_attn_layer.feed_forward.0.bias": "pytorch_model-00001-of-00004.bin",
270
+ "lang_encoder.transformer.blocks.7.gated_cross_attn_layer.feed_forward.0.weight": "pytorch_model-00001-of-00004.bin",
271
+ "lang_encoder.transformer.blocks.7.gated_cross_attn_layer.feed_forward.1.weight": "pytorch_model-00001-of-00004.bin",
272
+ "lang_encoder.transformer.blocks.7.gated_cross_attn_layer.feed_forward.3.weight": "pytorch_model-00001-of-00004.bin",
273
+ "lang_encoder.transformer.blocks.7.gated_cross_attn_layer.ff_gate": "pytorch_model-00001-of-00004.bin",
274
+ "lang_encoder.transformer.blocks.8.decoder_layer.attn.Wqkv.weight": "pytorch_model-00001-of-00004.bin",
275
+ "lang_encoder.transformer.blocks.8.decoder_layer.attn.out_proj.weight": "pytorch_model-00001-of-00004.bin",
276
+ "lang_encoder.transformer.blocks.8.decoder_layer.ffn.down_proj.weight": "pytorch_model-00001-of-00004.bin",
277
+ "lang_encoder.transformer.blocks.8.decoder_layer.ffn.up_proj.weight": "pytorch_model-00001-of-00004.bin",
278
+ "lang_encoder.transformer.blocks.8.decoder_layer.norm_1.weight": "pytorch_model-00001-of-00004.bin",
279
+ "lang_encoder.transformer.blocks.8.decoder_layer.norm_2.weight": "pytorch_model-00001-of-00004.bin",
280
+ "lang_encoder.transformer.blocks.9.decoder_layer.attn.Wqkv.weight": "pytorch_model-00001-of-00004.bin",
281
+ "lang_encoder.transformer.blocks.9.decoder_layer.attn.out_proj.weight": "pytorch_model-00001-of-00004.bin",
282
+ "lang_encoder.transformer.blocks.9.decoder_layer.ffn.down_proj.weight": "pytorch_model-00001-of-00004.bin",
283
+ "lang_encoder.transformer.blocks.9.decoder_layer.ffn.up_proj.weight": "pytorch_model-00001-of-00004.bin",
284
+ "lang_encoder.transformer.blocks.9.decoder_layer.norm_1.weight": "pytorch_model-00001-of-00004.bin",
285
+ "lang_encoder.transformer.blocks.9.decoder_layer.norm_2.weight": "pytorch_model-00001-of-00004.bin",
286
+ "lang_encoder.transformer.norm_f.weight": "pytorch_model-00004-of-00004.bin",
287
+ "lang_encoder.transformer.wte.weight": "pytorch_model-00001-of-00004.bin",
288
+ "perceiver.latents": "pytorch_model-00004-of-00004.bin",
289
+ "perceiver.layers.0.feed_forward.0.bias": "pytorch_model-00004-of-00004.bin",
290
+ "perceiver.layers.0.feed_forward.0.weight": "pytorch_model-00004-of-00004.bin",
291
+ "perceiver.layers.0.feed_forward.1.weight": "pytorch_model-00004-of-00004.bin",
292
+ "perceiver.layers.0.feed_forward.3.weight": "pytorch_model-00004-of-00004.bin",
293
+ "perceiver.layers.0.norm_latents.bias": "pytorch_model-00004-of-00004.bin",
294
+ "perceiver.layers.0.norm_latents.weight": "pytorch_model-00004-of-00004.bin",
295
+ "perceiver.layers.0.norm_media.bias": "pytorch_model-00004-of-00004.bin",
296
+ "perceiver.layers.0.norm_media.weight": "pytorch_model-00004-of-00004.bin",
297
+ "perceiver.layers.0.to_kv.weight": "pytorch_model-00004-of-00004.bin",
298
+ "perceiver.layers.0.to_out.weight": "pytorch_model-00004-of-00004.bin",
299
+ "perceiver.layers.0.to_q.weight": "pytorch_model-00004-of-00004.bin",
300
+ "perceiver.layers.1.feed_forward.0.bias": "pytorch_model-00004-of-00004.bin",
301
+ "perceiver.layers.1.feed_forward.0.weight": "pytorch_model-00004-of-00004.bin",
302
+ "perceiver.layers.1.feed_forward.1.weight": "pytorch_model-00004-of-00004.bin",
303
+ "perceiver.layers.1.feed_forward.3.weight": "pytorch_model-00004-of-00004.bin",
304
+ "perceiver.layers.1.norm_latents.bias": "pytorch_model-00004-of-00004.bin",
305
+ "perceiver.layers.1.norm_latents.weight": "pytorch_model-00004-of-00004.bin",
306
+ "perceiver.layers.1.norm_media.bias": "pytorch_model-00004-of-00004.bin",
307
+ "perceiver.layers.1.norm_media.weight": "pytorch_model-00004-of-00004.bin",
308
+ "perceiver.layers.1.to_kv.weight": "pytorch_model-00004-of-00004.bin",
309
+ "perceiver.layers.1.to_out.weight": "pytorch_model-00004-of-00004.bin",
310
+ "perceiver.layers.1.to_q.weight": "pytorch_model-00004-of-00004.bin",
311
+ "perceiver.layers.2.feed_forward.0.bias": "pytorch_model-00004-of-00004.bin",
312
+ "perceiver.layers.2.feed_forward.0.weight": "pytorch_model-00004-of-00004.bin",
313
+ "perceiver.layers.2.feed_forward.1.weight": "pytorch_model-00004-of-00004.bin",
314
+ "perceiver.layers.2.feed_forward.3.weight": "pytorch_model-00004-of-00004.bin",
315
+ "perceiver.layers.2.norm_latents.bias": "pytorch_model-00004-of-00004.bin",
316
+ "perceiver.layers.2.norm_latents.weight": "pytorch_model-00004-of-00004.bin",
317
+ "perceiver.layers.2.norm_media.bias": "pytorch_model-00004-of-00004.bin",
318
+ "perceiver.layers.2.norm_media.weight": "pytorch_model-00004-of-00004.bin",
319
+ "perceiver.layers.2.to_kv.weight": "pytorch_model-00004-of-00004.bin",
320
+ "perceiver.layers.2.to_out.weight": "pytorch_model-00004-of-00004.bin",
321
+ "perceiver.layers.2.to_q.weight": "pytorch_model-00004-of-00004.bin",
322
+ "perceiver.layers.3.feed_forward.0.bias": "pytorch_model-00004-of-00004.bin",
323
+ "perceiver.layers.3.feed_forward.0.weight": "pytorch_model-00004-of-00004.bin",
324
+ "perceiver.layers.3.feed_forward.1.weight": "pytorch_model-00004-of-00004.bin",
325
+ "perceiver.layers.3.feed_forward.3.weight": "pytorch_model-00004-of-00004.bin",
326
+ "perceiver.layers.3.norm_latents.bias": "pytorch_model-00004-of-00004.bin",
327
+ "perceiver.layers.3.norm_latents.weight": "pytorch_model-00004-of-00004.bin",
328
+ "perceiver.layers.3.norm_media.bias": "pytorch_model-00004-of-00004.bin",
329
+ "perceiver.layers.3.norm_media.weight": "pytorch_model-00004-of-00004.bin",
330
+ "perceiver.layers.3.to_kv.weight": "pytorch_model-00004-of-00004.bin",
331
+ "perceiver.layers.3.to_out.weight": "pytorch_model-00004-of-00004.bin",
332
+ "perceiver.layers.3.to_q.weight": "pytorch_model-00004-of-00004.bin",
333
+ "perceiver.layers.4.feed_forward.0.bias": "pytorch_model-00004-of-00004.bin",
334
+ "perceiver.layers.4.feed_forward.0.weight": "pytorch_model-00004-of-00004.bin",
335
+ "perceiver.layers.4.feed_forward.1.weight": "pytorch_model-00004-of-00004.bin",
336
+ "perceiver.layers.4.feed_forward.3.weight": "pytorch_model-00004-of-00004.bin",
337
+ "perceiver.layers.4.norm_latents.bias": "pytorch_model-00004-of-00004.bin",
338
+ "perceiver.layers.4.norm_latents.weight": "pytorch_model-00004-of-00004.bin",
339
+ "perceiver.layers.4.norm_media.bias": "pytorch_model-00004-of-00004.bin",
340
+ "perceiver.layers.4.norm_media.weight": "pytorch_model-00004-of-00004.bin",
341
+ "perceiver.layers.4.to_kv.weight": "pytorch_model-00004-of-00004.bin",
342
+ "perceiver.layers.4.to_out.weight": "pytorch_model-00004-of-00004.bin",
343
+ "perceiver.layers.4.to_q.weight": "pytorch_model-00004-of-00004.bin",
344
+ "perceiver.layers.5.feed_forward.0.bias": "pytorch_model-00004-of-00004.bin",
345
+ "perceiver.layers.5.feed_forward.0.weight": "pytorch_model-00004-of-00004.bin",
346
+ "perceiver.layers.5.feed_forward.1.weight": "pytorch_model-00004-of-00004.bin",
347
+ "perceiver.layers.5.feed_forward.3.weight": "pytorch_model-00004-of-00004.bin",
348
+ "perceiver.layers.5.norm_latents.bias": "pytorch_model-00004-of-00004.bin",
349
+ "perceiver.layers.5.norm_latents.weight": "pytorch_model-00004-of-00004.bin",
350
+ "perceiver.layers.5.norm_media.bias": "pytorch_model-00004-of-00004.bin",
351
+ "perceiver.layers.5.norm_media.weight": "pytorch_model-00004-of-00004.bin",
352
+ "perceiver.layers.5.to_kv.weight": "pytorch_model-00004-of-00004.bin",
353
+ "perceiver.layers.5.to_out.weight": "pytorch_model-00004-of-00004.bin",
354
+ "perceiver.layers.5.to_q.weight": "pytorch_model-00004-of-00004.bin",
355
+ "perceiver.norm.bias": "pytorch_model-00004-of-00004.bin",
356
+ "perceiver.norm.weight": "pytorch_model-00004-of-00004.bin",
357
+ "vision_encoder.vision_model.embeddings.class_embedding": "pytorch_model-00004-of-00004.bin",
358
+ "vision_encoder.vision_model.embeddings.patch_embedding.weight": "pytorch_model-00004-of-00004.bin",
359
+ "vision_encoder.vision_model.embeddings.position_embedding.weight": "pytorch_model-00004-of-00004.bin",
360
+ "vision_encoder.vision_model.embeddings.position_ids": "pytorch_model-00004-of-00004.bin",
361
+ "vision_encoder.vision_model.encoder.layers.0.layer_norm1.bias": "pytorch_model-00004-of-00004.bin",
362
+ "vision_encoder.vision_model.encoder.layers.0.layer_norm1.weight": "pytorch_model-00004-of-00004.bin",
363
+ "vision_encoder.vision_model.encoder.layers.0.layer_norm2.bias": "pytorch_model-00004-of-00004.bin",
364
+ "vision_encoder.vision_model.encoder.layers.0.layer_norm2.weight": "pytorch_model-00004-of-00004.bin",
365
+ "vision_encoder.vision_model.encoder.layers.0.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
366
+ "vision_encoder.vision_model.encoder.layers.0.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
367
+ "vision_encoder.vision_model.encoder.layers.0.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
368
+ "vision_encoder.vision_model.encoder.layers.0.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
369
+ "vision_encoder.vision_model.encoder.layers.0.self_attn.k_proj.bias": "pytorch_model-00004-of-00004.bin",
370
+ "vision_encoder.vision_model.encoder.layers.0.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
371
+ "vision_encoder.vision_model.encoder.layers.0.self_attn.out_proj.bias": "pytorch_model-00004-of-00004.bin",
372
+ "vision_encoder.vision_model.encoder.layers.0.self_attn.out_proj.weight": "pytorch_model-00004-of-00004.bin",
373
+ "vision_encoder.vision_model.encoder.layers.0.self_attn.q_proj.bias": "pytorch_model-00004-of-00004.bin",
374
+ "vision_encoder.vision_model.encoder.layers.0.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
375
+ "vision_encoder.vision_model.encoder.layers.0.self_attn.v_proj.bias": "pytorch_model-00004-of-00004.bin",
376
+ "vision_encoder.vision_model.encoder.layers.0.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
377
+ "vision_encoder.vision_model.encoder.layers.1.layer_norm1.bias": "pytorch_model-00004-of-00004.bin",
378
+ "vision_encoder.vision_model.encoder.layers.1.layer_norm1.weight": "pytorch_model-00004-of-00004.bin",
379
+ "vision_encoder.vision_model.encoder.layers.1.layer_norm2.bias": "pytorch_model-00004-of-00004.bin",
380
+ "vision_encoder.vision_model.encoder.layers.1.layer_norm2.weight": "pytorch_model-00004-of-00004.bin",
381
+ "vision_encoder.vision_model.encoder.layers.1.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
382
+ "vision_encoder.vision_model.encoder.layers.1.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
383
+ "vision_encoder.vision_model.encoder.layers.1.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
384
+ "vision_encoder.vision_model.encoder.layers.1.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
385
+ "vision_encoder.vision_model.encoder.layers.1.self_attn.k_proj.bias": "pytorch_model-00004-of-00004.bin",
386
+ "vision_encoder.vision_model.encoder.layers.1.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
387
+ "vision_encoder.vision_model.encoder.layers.1.self_attn.out_proj.bias": "pytorch_model-00004-of-00004.bin",
388
+ "vision_encoder.vision_model.encoder.layers.1.self_attn.out_proj.weight": "pytorch_model-00004-of-00004.bin",
389
+ "vision_encoder.vision_model.encoder.layers.1.self_attn.q_proj.bias": "pytorch_model-00004-of-00004.bin",
390
+ "vision_encoder.vision_model.encoder.layers.1.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
391
+ "vision_encoder.vision_model.encoder.layers.1.self_attn.v_proj.bias": "pytorch_model-00004-of-00004.bin",
392
+ "vision_encoder.vision_model.encoder.layers.1.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
393
+ "vision_encoder.vision_model.encoder.layers.10.layer_norm1.bias": "pytorch_model-00004-of-00004.bin",
394
+ "vision_encoder.vision_model.encoder.layers.10.layer_norm1.weight": "pytorch_model-00004-of-00004.bin",
395
+ "vision_encoder.vision_model.encoder.layers.10.layer_norm2.bias": "pytorch_model-00004-of-00004.bin",
396
+ "vision_encoder.vision_model.encoder.layers.10.layer_norm2.weight": "pytorch_model-00004-of-00004.bin",
397
+ "vision_encoder.vision_model.encoder.layers.10.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
398
+ "vision_encoder.vision_model.encoder.layers.10.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
399
+ "vision_encoder.vision_model.encoder.layers.10.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
400
+ "vision_encoder.vision_model.encoder.layers.10.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
401
+ "vision_encoder.vision_model.encoder.layers.10.self_attn.k_proj.bias": "pytorch_model-00004-of-00004.bin",
402
+ "vision_encoder.vision_model.encoder.layers.10.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
403
+ "vision_encoder.vision_model.encoder.layers.10.self_attn.out_proj.bias": "pytorch_model-00004-of-00004.bin",
404
+ "vision_encoder.vision_model.encoder.layers.10.self_attn.out_proj.weight": "pytorch_model-00004-of-00004.bin",
405
+ "vision_encoder.vision_model.encoder.layers.10.self_attn.q_proj.bias": "pytorch_model-00004-of-00004.bin",
406
+ "vision_encoder.vision_model.encoder.layers.10.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
407
+ "vision_encoder.vision_model.encoder.layers.10.self_attn.v_proj.bias": "pytorch_model-00004-of-00004.bin",
408
+ "vision_encoder.vision_model.encoder.layers.10.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
409
+ "vision_encoder.vision_model.encoder.layers.11.layer_norm1.bias": "pytorch_model-00004-of-00004.bin",
410
+ "vision_encoder.vision_model.encoder.layers.11.layer_norm1.weight": "pytorch_model-00004-of-00004.bin",
411
+ "vision_encoder.vision_model.encoder.layers.11.layer_norm2.bias": "pytorch_model-00004-of-00004.bin",
412
+ "vision_encoder.vision_model.encoder.layers.11.layer_norm2.weight": "pytorch_model-00004-of-00004.bin",
413
+ "vision_encoder.vision_model.encoder.layers.11.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
414
+ "vision_encoder.vision_model.encoder.layers.11.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
415
+ "vision_encoder.vision_model.encoder.layers.11.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
416
+ "vision_encoder.vision_model.encoder.layers.11.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
417
+ "vision_encoder.vision_model.encoder.layers.11.self_attn.k_proj.bias": "pytorch_model-00004-of-00004.bin",
418
+ "vision_encoder.vision_model.encoder.layers.11.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
419
+ "vision_encoder.vision_model.encoder.layers.11.self_attn.out_proj.bias": "pytorch_model-00004-of-00004.bin",
420
+ "vision_encoder.vision_model.encoder.layers.11.self_attn.out_proj.weight": "pytorch_model-00004-of-00004.bin",
421
+ "vision_encoder.vision_model.encoder.layers.11.self_attn.q_proj.bias": "pytorch_model-00004-of-00004.bin",
422
+ "vision_encoder.vision_model.encoder.layers.11.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
423
+ "vision_encoder.vision_model.encoder.layers.11.self_attn.v_proj.bias": "pytorch_model-00004-of-00004.bin",
424
+ "vision_encoder.vision_model.encoder.layers.11.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
425
+ "vision_encoder.vision_model.encoder.layers.12.layer_norm1.bias": "pytorch_model-00004-of-00004.bin",
426
+ "vision_encoder.vision_model.encoder.layers.12.layer_norm1.weight": "pytorch_model-00004-of-00004.bin",
427
+ "vision_encoder.vision_model.encoder.layers.12.layer_norm2.bias": "pytorch_model-00004-of-00004.bin",
428
+ "vision_encoder.vision_model.encoder.layers.12.layer_norm2.weight": "pytorch_model-00004-of-00004.bin",
429
+ "vision_encoder.vision_model.encoder.layers.12.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
430
+ "vision_encoder.vision_model.encoder.layers.12.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
431
+ "vision_encoder.vision_model.encoder.layers.12.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
432
+ "vision_encoder.vision_model.encoder.layers.12.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
433
+ "vision_encoder.vision_model.encoder.layers.12.self_attn.k_proj.bias": "pytorch_model-00004-of-00004.bin",
434
+ "vision_encoder.vision_model.encoder.layers.12.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
435
+ "vision_encoder.vision_model.encoder.layers.12.self_attn.out_proj.bias": "pytorch_model-00004-of-00004.bin",
436
+ "vision_encoder.vision_model.encoder.layers.12.self_attn.out_proj.weight": "pytorch_model-00004-of-00004.bin",
437
+ "vision_encoder.vision_model.encoder.layers.12.self_attn.q_proj.bias": "pytorch_model-00004-of-00004.bin",
438
+ "vision_encoder.vision_model.encoder.layers.12.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
439
+ "vision_encoder.vision_model.encoder.layers.12.self_attn.v_proj.bias": "pytorch_model-00004-of-00004.bin",
440
+ "vision_encoder.vision_model.encoder.layers.12.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
441
+ "vision_encoder.vision_model.encoder.layers.13.layer_norm1.bias": "pytorch_model-00004-of-00004.bin",
442
+ "vision_encoder.vision_model.encoder.layers.13.layer_norm1.weight": "pytorch_model-00004-of-00004.bin",
443
+ "vision_encoder.vision_model.encoder.layers.13.layer_norm2.bias": "pytorch_model-00004-of-00004.bin",
444
+ "vision_encoder.vision_model.encoder.layers.13.layer_norm2.weight": "pytorch_model-00004-of-00004.bin",
445
+ "vision_encoder.vision_model.encoder.layers.13.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
446
+ "vision_encoder.vision_model.encoder.layers.13.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
447
+ "vision_encoder.vision_model.encoder.layers.13.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
448
+ "vision_encoder.vision_model.encoder.layers.13.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
449
+ "vision_encoder.vision_model.encoder.layers.13.self_attn.k_proj.bias": "pytorch_model-00004-of-00004.bin",
450
+ "vision_encoder.vision_model.encoder.layers.13.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
451
+ "vision_encoder.vision_model.encoder.layers.13.self_attn.out_proj.bias": "pytorch_model-00004-of-00004.bin",
452
+ "vision_encoder.vision_model.encoder.layers.13.self_attn.out_proj.weight": "pytorch_model-00004-of-00004.bin",
453
+ "vision_encoder.vision_model.encoder.layers.13.self_attn.q_proj.bias": "pytorch_model-00004-of-00004.bin",
454
+ "vision_encoder.vision_model.encoder.layers.13.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
455
+ "vision_encoder.vision_model.encoder.layers.13.self_attn.v_proj.bias": "pytorch_model-00004-of-00004.bin",
456
+ "vision_encoder.vision_model.encoder.layers.13.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
457
+ "vision_encoder.vision_model.encoder.layers.14.layer_norm1.bias": "pytorch_model-00004-of-00004.bin",
458
+ "vision_encoder.vision_model.encoder.layers.14.layer_norm1.weight": "pytorch_model-00004-of-00004.bin",
459
+ "vision_encoder.vision_model.encoder.layers.14.layer_norm2.bias": "pytorch_model-00004-of-00004.bin",
460
+ "vision_encoder.vision_model.encoder.layers.14.layer_norm2.weight": "pytorch_model-00004-of-00004.bin",
461
+ "vision_encoder.vision_model.encoder.layers.14.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
462
+ "vision_encoder.vision_model.encoder.layers.14.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
463
+ "vision_encoder.vision_model.encoder.layers.14.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
464
+ "vision_encoder.vision_model.encoder.layers.14.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
465
+ "vision_encoder.vision_model.encoder.layers.14.self_attn.k_proj.bias": "pytorch_model-00004-of-00004.bin",
466
+ "vision_encoder.vision_model.encoder.layers.14.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
467
+ "vision_encoder.vision_model.encoder.layers.14.self_attn.out_proj.bias": "pytorch_model-00004-of-00004.bin",
468
+ "vision_encoder.vision_model.encoder.layers.14.self_attn.out_proj.weight": "pytorch_model-00004-of-00004.bin",
469
+ "vision_encoder.vision_model.encoder.layers.14.self_attn.q_proj.bias": "pytorch_model-00004-of-00004.bin",
470
+ "vision_encoder.vision_model.encoder.layers.14.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
471
+ "vision_encoder.vision_model.encoder.layers.14.self_attn.v_proj.bias": "pytorch_model-00004-of-00004.bin",
472
+ "vision_encoder.vision_model.encoder.layers.14.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
473
+ "vision_encoder.vision_model.encoder.layers.15.layer_norm1.bias": "pytorch_model-00004-of-00004.bin",
474
+ "vision_encoder.vision_model.encoder.layers.15.layer_norm1.weight": "pytorch_model-00004-of-00004.bin",
475
+ "vision_encoder.vision_model.encoder.layers.15.layer_norm2.bias": "pytorch_model-00004-of-00004.bin",
476
+ "vision_encoder.vision_model.encoder.layers.15.layer_norm2.weight": "pytorch_model-00004-of-00004.bin",
477
+ "vision_encoder.vision_model.encoder.layers.15.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
478
+ "vision_encoder.vision_model.encoder.layers.15.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
479
+ "vision_encoder.vision_model.encoder.layers.15.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
480
+ "vision_encoder.vision_model.encoder.layers.15.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
481
+ "vision_encoder.vision_model.encoder.layers.15.self_attn.k_proj.bias": "pytorch_model-00004-of-00004.bin",
482
+ "vision_encoder.vision_model.encoder.layers.15.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
483
+ "vision_encoder.vision_model.encoder.layers.15.self_attn.out_proj.bias": "pytorch_model-00004-of-00004.bin",
484
+ "vision_encoder.vision_model.encoder.layers.15.self_attn.out_proj.weight": "pytorch_model-00004-of-00004.bin",
485
+ "vision_encoder.vision_model.encoder.layers.15.self_attn.q_proj.bias": "pytorch_model-00004-of-00004.bin",
486
+ "vision_encoder.vision_model.encoder.layers.15.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
487
+ "vision_encoder.vision_model.encoder.layers.15.self_attn.v_proj.bias": "pytorch_model-00004-of-00004.bin",
488
+ "vision_encoder.vision_model.encoder.layers.15.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
489
+ "vision_encoder.vision_model.encoder.layers.16.layer_norm1.bias": "pytorch_model-00004-of-00004.bin",
490
+ "vision_encoder.vision_model.encoder.layers.16.layer_norm1.weight": "pytorch_model-00004-of-00004.bin",
491
+ "vision_encoder.vision_model.encoder.layers.16.layer_norm2.bias": "pytorch_model-00004-of-00004.bin",
492
+ "vision_encoder.vision_model.encoder.layers.16.layer_norm2.weight": "pytorch_model-00004-of-00004.bin",
493
+ "vision_encoder.vision_model.encoder.layers.16.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
494
+ "vision_encoder.vision_model.encoder.layers.16.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
495
+ "vision_encoder.vision_model.encoder.layers.16.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
496
+ "vision_encoder.vision_model.encoder.layers.16.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
497
+ "vision_encoder.vision_model.encoder.layers.16.self_attn.k_proj.bias": "pytorch_model-00004-of-00004.bin",
498
+ "vision_encoder.vision_model.encoder.layers.16.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
499
+ "vision_encoder.vision_model.encoder.layers.16.self_attn.out_proj.bias": "pytorch_model-00004-of-00004.bin",
500
+ "vision_encoder.vision_model.encoder.layers.16.self_attn.out_proj.weight": "pytorch_model-00004-of-00004.bin",
501
+ "vision_encoder.vision_model.encoder.layers.16.self_attn.q_proj.bias": "pytorch_model-00004-of-00004.bin",
502
+ "vision_encoder.vision_model.encoder.layers.16.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
503
+ "vision_encoder.vision_model.encoder.layers.16.self_attn.v_proj.bias": "pytorch_model-00004-of-00004.bin",
504
+ "vision_encoder.vision_model.encoder.layers.16.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
505
+ "vision_encoder.vision_model.encoder.layers.17.layer_norm1.bias": "pytorch_model-00004-of-00004.bin",
506
+ "vision_encoder.vision_model.encoder.layers.17.layer_norm1.weight": "pytorch_model-00004-of-00004.bin",
507
+ "vision_encoder.vision_model.encoder.layers.17.layer_norm2.bias": "pytorch_model-00004-of-00004.bin",
508
+ "vision_encoder.vision_model.encoder.layers.17.layer_norm2.weight": "pytorch_model-00004-of-00004.bin",
509
+ "vision_encoder.vision_model.encoder.layers.17.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
510
+ "vision_encoder.vision_model.encoder.layers.17.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
511
+ "vision_encoder.vision_model.encoder.layers.17.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
512
+ "vision_encoder.vision_model.encoder.layers.17.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
513
+ "vision_encoder.vision_model.encoder.layers.17.self_attn.k_proj.bias": "pytorch_model-00004-of-00004.bin",
514
+ "vision_encoder.vision_model.encoder.layers.17.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
515
+ "vision_encoder.vision_model.encoder.layers.17.self_attn.out_proj.bias": "pytorch_model-00004-of-00004.bin",
516
+ "vision_encoder.vision_model.encoder.layers.17.self_attn.out_proj.weight": "pytorch_model-00004-of-00004.bin",
517
+ "vision_encoder.vision_model.encoder.layers.17.self_attn.q_proj.bias": "pytorch_model-00004-of-00004.bin",
518
+ "vision_encoder.vision_model.encoder.layers.17.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
519
+ "vision_encoder.vision_model.encoder.layers.17.self_attn.v_proj.bias": "pytorch_model-00004-of-00004.bin",
520
+ "vision_encoder.vision_model.encoder.layers.17.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
521
+ "vision_encoder.vision_model.encoder.layers.18.layer_norm1.bias": "pytorch_model-00004-of-00004.bin",
522
+ "vision_encoder.vision_model.encoder.layers.18.layer_norm1.weight": "pytorch_model-00004-of-00004.bin",
523
+ "vision_encoder.vision_model.encoder.layers.18.layer_norm2.bias": "pytorch_model-00004-of-00004.bin",
524
+ "vision_encoder.vision_model.encoder.layers.18.layer_norm2.weight": "pytorch_model-00004-of-00004.bin",
525
+ "vision_encoder.vision_model.encoder.layers.18.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
526
+ "vision_encoder.vision_model.encoder.layers.18.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
527
+ "vision_encoder.vision_model.encoder.layers.18.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
528
+ "vision_encoder.vision_model.encoder.layers.18.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
529
+ "vision_encoder.vision_model.encoder.layers.18.self_attn.k_proj.bias": "pytorch_model-00004-of-00004.bin",
530
+ "vision_encoder.vision_model.encoder.layers.18.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
531
+ "vision_encoder.vision_model.encoder.layers.18.self_attn.out_proj.bias": "pytorch_model-00004-of-00004.bin",
532
+ "vision_encoder.vision_model.encoder.layers.18.self_attn.out_proj.weight": "pytorch_model-00004-of-00004.bin",
533
+ "vision_encoder.vision_model.encoder.layers.18.self_attn.q_proj.bias": "pytorch_model-00004-of-00004.bin",
534
+ "vision_encoder.vision_model.encoder.layers.18.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
535
+ "vision_encoder.vision_model.encoder.layers.18.self_attn.v_proj.bias": "pytorch_model-00004-of-00004.bin",
536
+ "vision_encoder.vision_model.encoder.layers.18.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
537
+ "vision_encoder.vision_model.encoder.layers.19.layer_norm1.bias": "pytorch_model-00004-of-00004.bin",
538
+ "vision_encoder.vision_model.encoder.layers.19.layer_norm1.weight": "pytorch_model-00004-of-00004.bin",
539
+ "vision_encoder.vision_model.encoder.layers.19.layer_norm2.bias": "pytorch_model-00004-of-00004.bin",
540
+ "vision_encoder.vision_model.encoder.layers.19.layer_norm2.weight": "pytorch_model-00004-of-00004.bin",
541
+ "vision_encoder.vision_model.encoder.layers.19.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
542
+ "vision_encoder.vision_model.encoder.layers.19.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
543
+ "vision_encoder.vision_model.encoder.layers.19.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
544
+ "vision_encoder.vision_model.encoder.layers.19.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
545
+ "vision_encoder.vision_model.encoder.layers.19.self_attn.k_proj.bias": "pytorch_model-00004-of-00004.bin",
546
+ "vision_encoder.vision_model.encoder.layers.19.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
547
+ "vision_encoder.vision_model.encoder.layers.19.self_attn.out_proj.bias": "pytorch_model-00004-of-00004.bin",
548
+ "vision_encoder.vision_model.encoder.layers.19.self_attn.out_proj.weight": "pytorch_model-00004-of-00004.bin",
549
+ "vision_encoder.vision_model.encoder.layers.19.self_attn.q_proj.bias": "pytorch_model-00004-of-00004.bin",
550
+ "vision_encoder.vision_model.encoder.layers.19.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
551
+ "vision_encoder.vision_model.encoder.layers.19.self_attn.v_proj.bias": "pytorch_model-00004-of-00004.bin",
552
+ "vision_encoder.vision_model.encoder.layers.19.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
553
+ "vision_encoder.vision_model.encoder.layers.2.layer_norm1.bias": "pytorch_model-00004-of-00004.bin",
554
+ "vision_encoder.vision_model.encoder.layers.2.layer_norm1.weight": "pytorch_model-00004-of-00004.bin",
555
+ "vision_encoder.vision_model.encoder.layers.2.layer_norm2.bias": "pytorch_model-00004-of-00004.bin",
556
+ "vision_encoder.vision_model.encoder.layers.2.layer_norm2.weight": "pytorch_model-00004-of-00004.bin",
557
+ "vision_encoder.vision_model.encoder.layers.2.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
558
+ "vision_encoder.vision_model.encoder.layers.2.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
559
+ "vision_encoder.vision_model.encoder.layers.2.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
560
+ "vision_encoder.vision_model.encoder.layers.2.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
561
+ "vision_encoder.vision_model.encoder.layers.2.self_attn.k_proj.bias": "pytorch_model-00004-of-00004.bin",
562
+ "vision_encoder.vision_model.encoder.layers.2.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
563
+ "vision_encoder.vision_model.encoder.layers.2.self_attn.out_proj.bias": "pytorch_model-00004-of-00004.bin",
564
+ "vision_encoder.vision_model.encoder.layers.2.self_attn.out_proj.weight": "pytorch_model-00004-of-00004.bin",
565
+ "vision_encoder.vision_model.encoder.layers.2.self_attn.q_proj.bias": "pytorch_model-00004-of-00004.bin",
566
+ "vision_encoder.vision_model.encoder.layers.2.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
567
+ "vision_encoder.vision_model.encoder.layers.2.self_attn.v_proj.bias": "pytorch_model-00004-of-00004.bin",
568
+ "vision_encoder.vision_model.encoder.layers.2.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
569
+ "vision_encoder.vision_model.encoder.layers.20.layer_norm1.bias": "pytorch_model-00004-of-00004.bin",
570
+ "vision_encoder.vision_model.encoder.layers.20.layer_norm1.weight": "pytorch_model-00004-of-00004.bin",
571
+ "vision_encoder.vision_model.encoder.layers.20.layer_norm2.bias": "pytorch_model-00004-of-00004.bin",
572
+ "vision_encoder.vision_model.encoder.layers.20.layer_norm2.weight": "pytorch_model-00004-of-00004.bin",
573
+ "vision_encoder.vision_model.encoder.layers.20.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
574
+ "vision_encoder.vision_model.encoder.layers.20.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
575
+ "vision_encoder.vision_model.encoder.layers.20.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
576
+ "vision_encoder.vision_model.encoder.layers.20.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
577
+ "vision_encoder.vision_model.encoder.layers.20.self_attn.k_proj.bias": "pytorch_model-00004-of-00004.bin",
578
+ "vision_encoder.vision_model.encoder.layers.20.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
579
+ "vision_encoder.vision_model.encoder.layers.20.self_attn.out_proj.bias": "pytorch_model-00004-of-00004.bin",
580
+ "vision_encoder.vision_model.encoder.layers.20.self_attn.out_proj.weight": "pytorch_model-00004-of-00004.bin",
581
+ "vision_encoder.vision_model.encoder.layers.20.self_attn.q_proj.bias": "pytorch_model-00004-of-00004.bin",
582
+ "vision_encoder.vision_model.encoder.layers.20.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
583
+ "vision_encoder.vision_model.encoder.layers.20.self_attn.v_proj.bias": "pytorch_model-00004-of-00004.bin",
584
+ "vision_encoder.vision_model.encoder.layers.20.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
585
+ "vision_encoder.vision_model.encoder.layers.21.layer_norm1.bias": "pytorch_model-00004-of-00004.bin",
586
+ "vision_encoder.vision_model.encoder.layers.21.layer_norm1.weight": "pytorch_model-00004-of-00004.bin",
587
+ "vision_encoder.vision_model.encoder.layers.21.layer_norm2.bias": "pytorch_model-00004-of-00004.bin",
588
+ "vision_encoder.vision_model.encoder.layers.21.layer_norm2.weight": "pytorch_model-00004-of-00004.bin",
589
+ "vision_encoder.vision_model.encoder.layers.21.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
590
+ "vision_encoder.vision_model.encoder.layers.21.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
591
+ "vision_encoder.vision_model.encoder.layers.21.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
592
+ "vision_encoder.vision_model.encoder.layers.21.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
593
+ "vision_encoder.vision_model.encoder.layers.21.self_attn.k_proj.bias": "pytorch_model-00004-of-00004.bin",
594
+ "vision_encoder.vision_model.encoder.layers.21.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
595
+ "vision_encoder.vision_model.encoder.layers.21.self_attn.out_proj.bias": "pytorch_model-00004-of-00004.bin",
596
+ "vision_encoder.vision_model.encoder.layers.21.self_attn.out_proj.weight": "pytorch_model-00004-of-00004.bin",
597
+ "vision_encoder.vision_model.encoder.layers.21.self_attn.q_proj.bias": "pytorch_model-00004-of-00004.bin",
598
+ "vision_encoder.vision_model.encoder.layers.21.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
599
+ "vision_encoder.vision_model.encoder.layers.21.self_attn.v_proj.bias": "pytorch_model-00004-of-00004.bin",
600
+ "vision_encoder.vision_model.encoder.layers.21.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
601
+ "vision_encoder.vision_model.encoder.layers.22.layer_norm1.bias": "pytorch_model-00004-of-00004.bin",
602
+ "vision_encoder.vision_model.encoder.layers.22.layer_norm1.weight": "pytorch_model-00004-of-00004.bin",
603
+ "vision_encoder.vision_model.encoder.layers.22.layer_norm2.bias": "pytorch_model-00004-of-00004.bin",
604
+ "vision_encoder.vision_model.encoder.layers.22.layer_norm2.weight": "pytorch_model-00004-of-00004.bin",
605
+ "vision_encoder.vision_model.encoder.layers.22.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
606
+ "vision_encoder.vision_model.encoder.layers.22.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
607
+ "vision_encoder.vision_model.encoder.layers.22.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
608
+ "vision_encoder.vision_model.encoder.layers.22.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
609
+ "vision_encoder.vision_model.encoder.layers.22.self_attn.k_proj.bias": "pytorch_model-00004-of-00004.bin",
610
+ "vision_encoder.vision_model.encoder.layers.22.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
611
+ "vision_encoder.vision_model.encoder.layers.22.self_attn.out_proj.bias": "pytorch_model-00004-of-00004.bin",
612
+ "vision_encoder.vision_model.encoder.layers.22.self_attn.out_proj.weight": "pytorch_model-00004-of-00004.bin",
613
+ "vision_encoder.vision_model.encoder.layers.22.self_attn.q_proj.bias": "pytorch_model-00004-of-00004.bin",
614
+ "vision_encoder.vision_model.encoder.layers.22.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
615
+ "vision_encoder.vision_model.encoder.layers.22.self_attn.v_proj.bias": "pytorch_model-00004-of-00004.bin",
616
+ "vision_encoder.vision_model.encoder.layers.22.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
617
+ "vision_encoder.vision_model.encoder.layers.23.layer_norm1.bias": "pytorch_model-00004-of-00004.bin",
618
+ "vision_encoder.vision_model.encoder.layers.23.layer_norm1.weight": "pytorch_model-00004-of-00004.bin",
619
+ "vision_encoder.vision_model.encoder.layers.23.layer_norm2.bias": "pytorch_model-00004-of-00004.bin",
620
+ "vision_encoder.vision_model.encoder.layers.23.layer_norm2.weight": "pytorch_model-00004-of-00004.bin",
621
+ "vision_encoder.vision_model.encoder.layers.23.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
622
+ "vision_encoder.vision_model.encoder.layers.23.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
623
+ "vision_encoder.vision_model.encoder.layers.23.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
624
+ "vision_encoder.vision_model.encoder.layers.23.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
625
+ "vision_encoder.vision_model.encoder.layers.23.self_attn.k_proj.bias": "pytorch_model-00004-of-00004.bin",
626
+ "vision_encoder.vision_model.encoder.layers.23.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
627
+ "vision_encoder.vision_model.encoder.layers.23.self_attn.out_proj.bias": "pytorch_model-00004-of-00004.bin",
628
+ "vision_encoder.vision_model.encoder.layers.23.self_attn.out_proj.weight": "pytorch_model-00004-of-00004.bin",
629
+ "vision_encoder.vision_model.encoder.layers.23.self_attn.q_proj.bias": "pytorch_model-00004-of-00004.bin",
630
+ "vision_encoder.vision_model.encoder.layers.23.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
631
+ "vision_encoder.vision_model.encoder.layers.23.self_attn.v_proj.bias": "pytorch_model-00004-of-00004.bin",
632
+ "vision_encoder.vision_model.encoder.layers.23.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
633
+ "vision_encoder.vision_model.encoder.layers.3.layer_norm1.bias": "pytorch_model-00004-of-00004.bin",
634
+ "vision_encoder.vision_model.encoder.layers.3.layer_norm1.weight": "pytorch_model-00004-of-00004.bin",
635
+ "vision_encoder.vision_model.encoder.layers.3.layer_norm2.bias": "pytorch_model-00004-of-00004.bin",
636
+ "vision_encoder.vision_model.encoder.layers.3.layer_norm2.weight": "pytorch_model-00004-of-00004.bin",
637
+ "vision_encoder.vision_model.encoder.layers.3.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
638
+ "vision_encoder.vision_model.encoder.layers.3.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
639
+ "vision_encoder.vision_model.encoder.layers.3.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
640
+ "vision_encoder.vision_model.encoder.layers.3.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
641
+ "vision_encoder.vision_model.encoder.layers.3.self_attn.k_proj.bias": "pytorch_model-00004-of-00004.bin",
642
+ "vision_encoder.vision_model.encoder.layers.3.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
643
+ "vision_encoder.vision_model.encoder.layers.3.self_attn.out_proj.bias": "pytorch_model-00004-of-00004.bin",
644
+ "vision_encoder.vision_model.encoder.layers.3.self_attn.out_proj.weight": "pytorch_model-00004-of-00004.bin",
645
+ "vision_encoder.vision_model.encoder.layers.3.self_attn.q_proj.bias": "pytorch_model-00004-of-00004.bin",
646
+ "vision_encoder.vision_model.encoder.layers.3.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
647
+ "vision_encoder.vision_model.encoder.layers.3.self_attn.v_proj.bias": "pytorch_model-00004-of-00004.bin",
648
+ "vision_encoder.vision_model.encoder.layers.3.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
649
+ "vision_encoder.vision_model.encoder.layers.4.layer_norm1.bias": "pytorch_model-00004-of-00004.bin",
650
+ "vision_encoder.vision_model.encoder.layers.4.layer_norm1.weight": "pytorch_model-00004-of-00004.bin",
651
+ "vision_encoder.vision_model.encoder.layers.4.layer_norm2.bias": "pytorch_model-00004-of-00004.bin",
652
+ "vision_encoder.vision_model.encoder.layers.4.layer_norm2.weight": "pytorch_model-00004-of-00004.bin",
653
+ "vision_encoder.vision_model.encoder.layers.4.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
654
+ "vision_encoder.vision_model.encoder.layers.4.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
655
+ "vision_encoder.vision_model.encoder.layers.4.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
656
+ "vision_encoder.vision_model.encoder.layers.4.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
657
+ "vision_encoder.vision_model.encoder.layers.4.self_attn.k_proj.bias": "pytorch_model-00004-of-00004.bin",
658
+ "vision_encoder.vision_model.encoder.layers.4.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
659
+ "vision_encoder.vision_model.encoder.layers.4.self_attn.out_proj.bias": "pytorch_model-00004-of-00004.bin",
660
+ "vision_encoder.vision_model.encoder.layers.4.self_attn.out_proj.weight": "pytorch_model-00004-of-00004.bin",
661
+ "vision_encoder.vision_model.encoder.layers.4.self_attn.q_proj.bias": "pytorch_model-00004-of-00004.bin",
662
+ "vision_encoder.vision_model.encoder.layers.4.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
663
+ "vision_encoder.vision_model.encoder.layers.4.self_attn.v_proj.bias": "pytorch_model-00004-of-00004.bin",
664
+ "vision_encoder.vision_model.encoder.layers.4.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
665
+ "vision_encoder.vision_model.encoder.layers.5.layer_norm1.bias": "pytorch_model-00004-of-00004.bin",
666
+ "vision_encoder.vision_model.encoder.layers.5.layer_norm1.weight": "pytorch_model-00004-of-00004.bin",
667
+ "vision_encoder.vision_model.encoder.layers.5.layer_norm2.bias": "pytorch_model-00004-of-00004.bin",
668
+ "vision_encoder.vision_model.encoder.layers.5.layer_norm2.weight": "pytorch_model-00004-of-00004.bin",
669
+ "vision_encoder.vision_model.encoder.layers.5.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
670
+ "vision_encoder.vision_model.encoder.layers.5.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
671
+ "vision_encoder.vision_model.encoder.layers.5.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
672
+ "vision_encoder.vision_model.encoder.layers.5.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
673
+ "vision_encoder.vision_model.encoder.layers.5.self_attn.k_proj.bias": "pytorch_model-00004-of-00004.bin",
674
+ "vision_encoder.vision_model.encoder.layers.5.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
675
+ "vision_encoder.vision_model.encoder.layers.5.self_attn.out_proj.bias": "pytorch_model-00004-of-00004.bin",
676
+ "vision_encoder.vision_model.encoder.layers.5.self_attn.out_proj.weight": "pytorch_model-00004-of-00004.bin",
677
+ "vision_encoder.vision_model.encoder.layers.5.self_attn.q_proj.bias": "pytorch_model-00004-of-00004.bin",
678
+ "vision_encoder.vision_model.encoder.layers.5.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
679
+ "vision_encoder.vision_model.encoder.layers.5.self_attn.v_proj.bias": "pytorch_model-00004-of-00004.bin",
680
+ "vision_encoder.vision_model.encoder.layers.5.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
681
+ "vision_encoder.vision_model.encoder.layers.6.layer_norm1.bias": "pytorch_model-00004-of-00004.bin",
682
+ "vision_encoder.vision_model.encoder.layers.6.layer_norm1.weight": "pytorch_model-00004-of-00004.bin",
683
+ "vision_encoder.vision_model.encoder.layers.6.layer_norm2.bias": "pytorch_model-00004-of-00004.bin",
684
+ "vision_encoder.vision_model.encoder.layers.6.layer_norm2.weight": "pytorch_model-00004-of-00004.bin",
685
+ "vision_encoder.vision_model.encoder.layers.6.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
686
+ "vision_encoder.vision_model.encoder.layers.6.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
687
+ "vision_encoder.vision_model.encoder.layers.6.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
688
+ "vision_encoder.vision_model.encoder.layers.6.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
689
+ "vision_encoder.vision_model.encoder.layers.6.self_attn.k_proj.bias": "pytorch_model-00004-of-00004.bin",
690
+ "vision_encoder.vision_model.encoder.layers.6.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
691
+ "vision_encoder.vision_model.encoder.layers.6.self_attn.out_proj.bias": "pytorch_model-00004-of-00004.bin",
692
+ "vision_encoder.vision_model.encoder.layers.6.self_attn.out_proj.weight": "pytorch_model-00004-of-00004.bin",
693
+ "vision_encoder.vision_model.encoder.layers.6.self_attn.q_proj.bias": "pytorch_model-00004-of-00004.bin",
694
+ "vision_encoder.vision_model.encoder.layers.6.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
695
+ "vision_encoder.vision_model.encoder.layers.6.self_attn.v_proj.bias": "pytorch_model-00004-of-00004.bin",
696
+ "vision_encoder.vision_model.encoder.layers.6.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
697
+ "vision_encoder.vision_model.encoder.layers.7.layer_norm1.bias": "pytorch_model-00004-of-00004.bin",
698
+ "vision_encoder.vision_model.encoder.layers.7.layer_norm1.weight": "pytorch_model-00004-of-00004.bin",
699
+ "vision_encoder.vision_model.encoder.layers.7.layer_norm2.bias": "pytorch_model-00004-of-00004.bin",
700
+ "vision_encoder.vision_model.encoder.layers.7.layer_norm2.weight": "pytorch_model-00004-of-00004.bin",
701
+ "vision_encoder.vision_model.encoder.layers.7.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
702
+ "vision_encoder.vision_model.encoder.layers.7.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
703
+ "vision_encoder.vision_model.encoder.layers.7.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
704
+ "vision_encoder.vision_model.encoder.layers.7.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
705
+ "vision_encoder.vision_model.encoder.layers.7.self_attn.k_proj.bias": "pytorch_model-00004-of-00004.bin",
706
+ "vision_encoder.vision_model.encoder.layers.7.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
707
+ "vision_encoder.vision_model.encoder.layers.7.self_attn.out_proj.bias": "pytorch_model-00004-of-00004.bin",
708
+ "vision_encoder.vision_model.encoder.layers.7.self_attn.out_proj.weight": "pytorch_model-00004-of-00004.bin",
709
+ "vision_encoder.vision_model.encoder.layers.7.self_attn.q_proj.bias": "pytorch_model-00004-of-00004.bin",
710
+ "vision_encoder.vision_model.encoder.layers.7.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
711
+ "vision_encoder.vision_model.encoder.layers.7.self_attn.v_proj.bias": "pytorch_model-00004-of-00004.bin",
712
+ "vision_encoder.vision_model.encoder.layers.7.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
713
+ "vision_encoder.vision_model.encoder.layers.8.layer_norm1.bias": "pytorch_model-00004-of-00004.bin",
714
+ "vision_encoder.vision_model.encoder.layers.8.layer_norm1.weight": "pytorch_model-00004-of-00004.bin",
715
+ "vision_encoder.vision_model.encoder.layers.8.layer_norm2.bias": "pytorch_model-00004-of-00004.bin",
716
+ "vision_encoder.vision_model.encoder.layers.8.layer_norm2.weight": "pytorch_model-00004-of-00004.bin",
717
+ "vision_encoder.vision_model.encoder.layers.8.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
718
+ "vision_encoder.vision_model.encoder.layers.8.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
719
+ "vision_encoder.vision_model.encoder.layers.8.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
720
+ "vision_encoder.vision_model.encoder.layers.8.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
721
+ "vision_encoder.vision_model.encoder.layers.8.self_attn.k_proj.bias": "pytorch_model-00004-of-00004.bin",
722
+ "vision_encoder.vision_model.encoder.layers.8.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
723
+ "vision_encoder.vision_model.encoder.layers.8.self_attn.out_proj.bias": "pytorch_model-00004-of-00004.bin",
724
+ "vision_encoder.vision_model.encoder.layers.8.self_attn.out_proj.weight": "pytorch_model-00004-of-00004.bin",
725
+ "vision_encoder.vision_model.encoder.layers.8.self_attn.q_proj.bias": "pytorch_model-00004-of-00004.bin",
726
+ "vision_encoder.vision_model.encoder.layers.8.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
727
+ "vision_encoder.vision_model.encoder.layers.8.self_attn.v_proj.bias": "pytorch_model-00004-of-00004.bin",
728
+ "vision_encoder.vision_model.encoder.layers.8.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
729
+ "vision_encoder.vision_model.encoder.layers.9.layer_norm1.bias": "pytorch_model-00004-of-00004.bin",
730
+ "vision_encoder.vision_model.encoder.layers.9.layer_norm1.weight": "pytorch_model-00004-of-00004.bin",
731
+ "vision_encoder.vision_model.encoder.layers.9.layer_norm2.bias": "pytorch_model-00004-of-00004.bin",
732
+ "vision_encoder.vision_model.encoder.layers.9.layer_norm2.weight": "pytorch_model-00004-of-00004.bin",
733
+ "vision_encoder.vision_model.encoder.layers.9.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
734
+ "vision_encoder.vision_model.encoder.layers.9.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
735
+ "vision_encoder.vision_model.encoder.layers.9.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
736
+ "vision_encoder.vision_model.encoder.layers.9.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
737
+ "vision_encoder.vision_model.encoder.layers.9.self_attn.k_proj.bias": "pytorch_model-00004-of-00004.bin",
738
+ "vision_encoder.vision_model.encoder.layers.9.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
739
+ "vision_encoder.vision_model.encoder.layers.9.self_attn.out_proj.bias": "pytorch_model-00004-of-00004.bin",
740
+ "vision_encoder.vision_model.encoder.layers.9.self_attn.out_proj.weight": "pytorch_model-00004-of-00004.bin",
741
+ "vision_encoder.vision_model.encoder.layers.9.self_attn.q_proj.bias": "pytorch_model-00004-of-00004.bin",
742
+ "vision_encoder.vision_model.encoder.layers.9.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
743
+ "vision_encoder.vision_model.encoder.layers.9.self_attn.v_proj.bias": "pytorch_model-00004-of-00004.bin",
744
+ "vision_encoder.vision_model.encoder.layers.9.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
745
+ "vision_encoder.vision_model.post_layernorm.bias": "pytorch_model-00004-of-00004.bin",
746
+ "vision_encoder.vision_model.post_layernorm.weight": "pytorch_model-00004-of-00004.bin",
747
+ "vision_encoder.vision_model.pre_layrnorm.bias": "pytorch_model-00004-of-00004.bin",
748
+ "vision_encoder.vision_model.pre_layrnorm.weight": "pytorch_model-00004-of-00004.bin"
749
+ }
750
+ }