Hugging Face's logo

BellXP
/
otter-9b-hf

Transformers
PyTorch
otter
Inference Endpoints
Model card Files Community
BellXP commited on
Commit
613b6ac
•
1 Parent(s): baf46a5

init repo

Browse files
Files changed (6) hide show
  1. config.json +164 -0
  2. pytorch_model-00001-of-00004.bin +3 -0
  3. pytorch_model-00002-of-00004.bin +3 -0
  4. pytorch_model-00003-of-00004.bin +3 -0
  5. pytorch_model-00004-of-00004.bin +3 -0
  6. pytorch_model.bin.index.json +879 -0
config.json ADDED
@@ -0,0 +1,164 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": null,
3
+ "architectures": [
4
+ "OtterModel"
5
+ ],
6
+ "cross_attn_every_n_layers": 4,
7
+ "model_type": "otter",
8
+ "only_attend_previous": true,
9
+ "text_config": {
10
+ "_name_or_path": "luodian/llama-7b-hf",
11
+ "add_cross_attention": false,
12
+ "architectures": null,
13
+ "bad_words_ids": null,
14
+ "begin_suppress_tokens": null,
15
+ "bos_token_id": 1,
16
+ "chunk_size_feed_forward": 0,
17
+ "cross_attention_hidden_size": null,
18
+ "decoder_start_token_id": null,
19
+ "diversity_penalty": 0.0,
20
+ "do_sample": false,
21
+ "early_stopping": false,
22
+ "encoder_no_repeat_ngram_size": 0,
23
+ "eos_token_id": 2,
24
+ "exponential_decay_length_penalty": null,
25
+ "finetuning_task": null,
26
+ "forced_bos_token_id": null,
27
+ "forced_eos_token_id": null,
28
+ "hidden_act": "silu",
29
+ "hidden_size": 4096,
30
+ "id2label": {
31
+ "0": "LABEL_0",
32
+ "1": "LABEL_1"
33
+ },
34
+ "initializer_range": 0.02,
35
+ "intermediate_size": 11008,
36
+ "is_decoder": false,
37
+ "is_encoder_decoder": false,
38
+ "label2id": {
39
+ "LABEL_0": 0,
40
+ "LABEL_1": 1
41
+ },
42
+ "length_penalty": 1.0,
43
+ "max_length": 20,
44
+ "max_position_embeddings": 2048,
45
+ "min_length": 0,
46
+ "model_type": "llama",
47
+ "no_repeat_ngram_size": 0,
48
+ "num_attention_heads": 32,
49
+ "num_beam_groups": 1,
50
+ "num_beams": 1,
51
+ "num_hidden_layers": 32,
52
+ "num_return_sequences": 1,
53
+ "output_attentions": false,
54
+ "output_hidden_states": false,
55
+ "output_scores": false,
56
+ "pad_token_id": 0,
57
+ "prefix": null,
58
+ "problem_type": null,
59
+ "pruned_heads": {},
60
+ "remove_invalid_values": false,
61
+ "repetition_penalty": 1.0,
62
+ "return_dict": true,
63
+ "return_dict_in_generate": false,
64
+ "rms_norm_eps": 1e-06,
65
+ "sep_token_id": null,
66
+ "suppress_tokens": null,
67
+ "task_specific_params": null,
68
+ "temperature": 1.0,
69
+ "tf_legacy_loss": false,
70
+ "tie_encoder_decoder": false,
71
+ "tie_word_embeddings": false,
72
+ "tokenizer_class": null,
73
+ "top_k": 50,
74
+ "top_p": 1.0,
75
+ "torch_dtype": null,
76
+ "torchscript": false,
77
+ "transformers_version": "4.29.0.dev0",
78
+ "typical_p": 1.0,
79
+ "use_bfloat16": false,
80
+ "use_cache": true,
81
+ "vocab_size": 32000
82
+ },
83
+ "tie_word_embeddings": false,
84
+ "torch_dtype": "float32",
85
+ "transformers_version": null,
86
+ "use_media_placement_augmentation": true,
87
+ "vision_config": {
88
+ "_name_or_path": "openai/clip-vit-large-patch14",
89
+ "add_cross_attention": false,
90
+ "architectures": null,
91
+ "attention_dropout": 0.0,
92
+ "bad_words_ids": null,
93
+ "begin_suppress_tokens": null,
94
+ "bos_token_id": null,
95
+ "chunk_size_feed_forward": 0,
96
+ "cross_attention_hidden_size": null,
97
+ "decoder_start_token_id": null,
98
+ "diversity_penalty": 0.0,
99
+ "do_sample": false,
100
+ "early_stopping": false,
101
+ "encoder_no_repeat_ngram_size": 0,
102
+ "eos_token_id": null,
103
+ "exponential_decay_length_penalty": null,
104
+ "finetuning_task": null,
105
+ "forced_bos_token_id": null,
106
+ "forced_eos_token_id": null,
107
+ "hidden_act": "quick_gelu",
108
+ "hidden_size": 1024,
109
+ "id2label": {
110
+ "0": "LABEL_0",
111
+ "1": "LABEL_1"
112
+ },
113
+ "image_size": 224,
114
+ "initializer_factor": 1.0,
115
+ "initializer_range": 0.02,
116
+ "intermediate_size": 4096,
117
+ "is_decoder": false,
118
+ "is_encoder_decoder": false,
119
+ "label2id": {
120
+ "LABEL_0": 0,
121
+ "LABEL_1": 1
122
+ },
123
+ "layer_norm_eps": 1e-05,
124
+ "length_penalty": 1.0,
125
+ "max_length": 20,
126
+ "min_length": 0,
127
+ "model_type": "clip_vision_model",
128
+ "no_repeat_ngram_size": 0,
129
+ "num_attention_heads": 16,
130
+ "num_beam_groups": 1,
131
+ "num_beams": 1,
132
+ "num_channels": 3,
133
+ "num_hidden_layers": 24,
134
+ "num_return_sequences": 1,
135
+ "output_attentions": false,
136
+ "output_hidden_states": false,
137
+ "output_scores": false,
138
+ "pad_token_id": null,
139
+ "patch_size": 14,
140
+ "prefix": null,
141
+ "problem_type": null,
142
+ "projection_dim": 512,
143
+ "pruned_heads": {},
144
+ "remove_invalid_values": false,
145
+ "repetition_penalty": 1.0,
146
+ "return_dict": true,
147
+ "return_dict_in_generate": false,
148
+ "sep_token_id": null,
149
+ "suppress_tokens": null,
150
+ "task_specific_params": null,
151
+ "temperature": 1.0,
152
+ "tf_legacy_loss": false,
153
+ "tie_encoder_decoder": false,
154
+ "tie_word_embeddings": true,
155
+ "tokenizer_class": null,
156
+ "top_k": 50,
157
+ "top_p": 1.0,
158
+ "torch_dtype": null,
159
+ "torchscript": false,
160
+ "transformers_version": "4.29.0.dev0",
161
+ "typical_p": 1.0,
162
+ "use_bfloat16": false
163
+ }
164
+ }
pytorch_model-00001-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:472ea9e2509e652d131611a11fadf9d75a68c092fb7797c6bfa3f7f517a40e0d
3
+ size 9936879657
pytorch_model-00002-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e57e7723ade197b2211c8cd323f0b0c82f34ae5657e05feb32b8b226444ebef8
3
+ size 9836220052
pytorch_model-00003-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4323636ee60c0fa1ad06096055ee0eddd0129e54ac71047cb91c14956003f3df
3
+ size 9773338283
pytorch_model-00004-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08d0aabaaa266a1adb5ad77e992bcbaa48b0e86dd55b9e934666123504acb82c
3
+ size 3335741420
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,879 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 32881862728
4
+ },
5
+ "weight_map": {
6
+ "lang_encoder.lm_head.weight": "pytorch_model-00004-of-00004.bin",
7
+ "lang_encoder.model.embed_tokens.weight": "pytorch_model-00001-of-00004.bin",
8
+ "lang_encoder.model.layers.0.decoder_layer.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
9
+ "lang_encoder.model.layers.0.decoder_layer.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
10
+ "lang_encoder.model.layers.0.decoder_layer.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
11
+ "lang_encoder.model.layers.0.decoder_layer.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
12
+ "lang_encoder.model.layers.0.decoder_layer.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
13
+ "lang_encoder.model.layers.0.decoder_layer.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
14
+ "lang_encoder.model.layers.0.decoder_layer.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
15
+ "lang_encoder.model.layers.0.decoder_layer.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
16
+ "lang_encoder.model.layers.0.decoder_layer.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00004.bin",
17
+ "lang_encoder.model.layers.0.decoder_layer.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
18
+ "lang_encoder.model.layers.1.decoder_layer.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
19
+ "lang_encoder.model.layers.1.decoder_layer.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
20
+ "lang_encoder.model.layers.1.decoder_layer.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
21
+ "lang_encoder.model.layers.1.decoder_layer.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
22
+ "lang_encoder.model.layers.1.decoder_layer.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
23
+ "lang_encoder.model.layers.1.decoder_layer.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
24
+ "lang_encoder.model.layers.1.decoder_layer.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
25
+ "lang_encoder.model.layers.1.decoder_layer.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
26
+ "lang_encoder.model.layers.1.decoder_layer.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00004.bin",
27
+ "lang_encoder.model.layers.1.decoder_layer.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
28
+ "lang_encoder.model.layers.10.decoder_layer.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
29
+ "lang_encoder.model.layers.10.decoder_layer.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
30
+ "lang_encoder.model.layers.10.decoder_layer.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
31
+ "lang_encoder.model.layers.10.decoder_layer.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
32
+ "lang_encoder.model.layers.10.decoder_layer.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
33
+ "lang_encoder.model.layers.10.decoder_layer.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
34
+ "lang_encoder.model.layers.10.decoder_layer.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
35
+ "lang_encoder.model.layers.10.decoder_layer.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
36
+ "lang_encoder.model.layers.10.decoder_layer.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00004.bin",
37
+ "lang_encoder.model.layers.10.decoder_layer.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
38
+ "lang_encoder.model.layers.11.decoder_layer.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
39
+ "lang_encoder.model.layers.11.decoder_layer.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
40
+ "lang_encoder.model.layers.11.decoder_layer.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
41
+ "lang_encoder.model.layers.11.decoder_layer.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
42
+ "lang_encoder.model.layers.11.decoder_layer.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
43
+ "lang_encoder.model.layers.11.decoder_layer.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
44
+ "lang_encoder.model.layers.11.decoder_layer.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
45
+ "lang_encoder.model.layers.11.decoder_layer.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
46
+ "lang_encoder.model.layers.11.decoder_layer.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00004.bin",
47
+ "lang_encoder.model.layers.11.decoder_layer.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
48
+ "lang_encoder.model.layers.11.gated_cross_attn_layer.attn.norm.bias": "pytorch_model-00002-of-00004.bin",
49
+ "lang_encoder.model.layers.11.gated_cross_attn_layer.attn.norm.weight": "pytorch_model-00002-of-00004.bin",
50
+ "lang_encoder.model.layers.11.gated_cross_attn_layer.attn.to_kv.weight": "pytorch_model-00002-of-00004.bin",
51
+ "lang_encoder.model.layers.11.gated_cross_attn_layer.attn.to_out.weight": "pytorch_model-00002-of-00004.bin",
52
+ "lang_encoder.model.layers.11.gated_cross_attn_layer.attn.to_q.weight": "pytorch_model-00002-of-00004.bin",
53
+ "lang_encoder.model.layers.11.gated_cross_attn_layer.attn_gate": "pytorch_model-00002-of-00004.bin",
54
+ "lang_encoder.model.layers.11.gated_cross_attn_layer.feed_forward.0.bias": "pytorch_model-00002-of-00004.bin",
55
+ "lang_encoder.model.layers.11.gated_cross_attn_layer.feed_forward.0.weight": "pytorch_model-00002-of-00004.bin",
56
+ "lang_encoder.model.layers.11.gated_cross_attn_layer.feed_forward.1.weight": "pytorch_model-00002-of-00004.bin",
57
+ "lang_encoder.model.layers.11.gated_cross_attn_layer.feed_forward.3.weight": "pytorch_model-00002-of-00004.bin",
58
+ "lang_encoder.model.layers.11.gated_cross_attn_layer.ff_gate": "pytorch_model-00002-of-00004.bin",
59
+ "lang_encoder.model.layers.12.decoder_layer.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
60
+ "lang_encoder.model.layers.12.decoder_layer.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
61
+ "lang_encoder.model.layers.12.decoder_layer.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
62
+ "lang_encoder.model.layers.12.decoder_layer.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
63
+ "lang_encoder.model.layers.12.decoder_layer.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
64
+ "lang_encoder.model.layers.12.decoder_layer.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
65
+ "lang_encoder.model.layers.12.decoder_layer.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
66
+ "lang_encoder.model.layers.12.decoder_layer.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
67
+ "lang_encoder.model.layers.12.decoder_layer.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00004.bin",
68
+ "lang_encoder.model.layers.12.decoder_layer.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
69
+ "lang_encoder.model.layers.13.decoder_layer.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
70
+ "lang_encoder.model.layers.13.decoder_layer.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
71
+ "lang_encoder.model.layers.13.decoder_layer.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
72
+ "lang_encoder.model.layers.13.decoder_layer.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
73
+ "lang_encoder.model.layers.13.decoder_layer.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
74
+ "lang_encoder.model.layers.13.decoder_layer.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
75
+ "lang_encoder.model.layers.13.decoder_layer.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
76
+ "lang_encoder.model.layers.13.decoder_layer.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
77
+ "lang_encoder.model.layers.13.decoder_layer.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00004.bin",
78
+ "lang_encoder.model.layers.13.decoder_layer.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
79
+ "lang_encoder.model.layers.14.decoder_layer.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
80
+ "lang_encoder.model.layers.14.decoder_layer.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
81
+ "lang_encoder.model.layers.14.decoder_layer.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
82
+ "lang_encoder.model.layers.14.decoder_layer.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
83
+ "lang_encoder.model.layers.14.decoder_layer.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
84
+ "lang_encoder.model.layers.14.decoder_layer.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
85
+ "lang_encoder.model.layers.14.decoder_layer.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
86
+ "lang_encoder.model.layers.14.decoder_layer.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
87
+ "lang_encoder.model.layers.14.decoder_layer.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00004.bin",
88
+ "lang_encoder.model.layers.14.decoder_layer.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
89
+ "lang_encoder.model.layers.15.decoder_layer.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
90
+ "lang_encoder.model.layers.15.decoder_layer.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
91
+ "lang_encoder.model.layers.15.decoder_layer.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
92
+ "lang_encoder.model.layers.15.decoder_layer.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
93
+ "lang_encoder.model.layers.15.decoder_layer.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
94
+ "lang_encoder.model.layers.15.decoder_layer.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
95
+ "lang_encoder.model.layers.15.decoder_layer.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
96
+ "lang_encoder.model.layers.15.decoder_layer.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
97
+ "lang_encoder.model.layers.15.decoder_layer.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00004.bin",
98
+ "lang_encoder.model.layers.15.decoder_layer.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
99
+ "lang_encoder.model.layers.15.gated_cross_attn_layer.attn.norm.bias": "pytorch_model-00002-of-00004.bin",
100
+ "lang_encoder.model.layers.15.gated_cross_attn_layer.attn.norm.weight": "pytorch_model-00002-of-00004.bin",
101
+ "lang_encoder.model.layers.15.gated_cross_attn_layer.attn.to_kv.weight": "pytorch_model-00002-of-00004.bin",
102
+ "lang_encoder.model.layers.15.gated_cross_attn_layer.attn.to_out.weight": "pytorch_model-00002-of-00004.bin",
103
+ "lang_encoder.model.layers.15.gated_cross_attn_layer.attn.to_q.weight": "pytorch_model-00002-of-00004.bin",
104
+ "lang_encoder.model.layers.15.gated_cross_attn_layer.attn_gate": "pytorch_model-00002-of-00004.bin",
105
+ "lang_encoder.model.layers.15.gated_cross_attn_layer.feed_forward.0.bias": "pytorch_model-00002-of-00004.bin",
106
+ "lang_encoder.model.layers.15.gated_cross_attn_layer.feed_forward.0.weight": "pytorch_model-00002-of-00004.bin",
107
+ "lang_encoder.model.layers.15.gated_cross_attn_layer.feed_forward.1.weight": "pytorch_model-00002-of-00004.bin",
108
+ "lang_encoder.model.layers.15.gated_cross_attn_layer.feed_forward.3.weight": "pytorch_model-00002-of-00004.bin",
109
+ "lang_encoder.model.layers.15.gated_cross_attn_layer.ff_gate": "pytorch_model-00002-of-00004.bin",
110
+ "lang_encoder.model.layers.16.decoder_layer.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
111
+ "lang_encoder.model.layers.16.decoder_layer.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
112
+ "lang_encoder.model.layers.16.decoder_layer.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
113
+ "lang_encoder.model.layers.16.decoder_layer.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
114
+ "lang_encoder.model.layers.16.decoder_layer.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
115
+ "lang_encoder.model.layers.16.decoder_layer.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
116
+ "lang_encoder.model.layers.16.decoder_layer.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
117
+ "lang_encoder.model.layers.16.decoder_layer.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
118
+ "lang_encoder.model.layers.16.decoder_layer.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00004.bin",
119
+ "lang_encoder.model.layers.16.decoder_layer.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
120
+ "lang_encoder.model.layers.17.decoder_layer.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
121
+ "lang_encoder.model.layers.17.decoder_layer.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
122
+ "lang_encoder.model.layers.17.decoder_layer.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
123
+ "lang_encoder.model.layers.17.decoder_layer.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
124
+ "lang_encoder.model.layers.17.decoder_layer.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
125
+ "lang_encoder.model.layers.17.decoder_layer.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
126
+ "lang_encoder.model.layers.17.decoder_layer.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
127
+ "lang_encoder.model.layers.17.decoder_layer.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
128
+ "lang_encoder.model.layers.17.decoder_layer.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00004.bin",
129
+ "lang_encoder.model.layers.17.decoder_layer.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
130
+ "lang_encoder.model.layers.18.decoder_layer.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
131
+ "lang_encoder.model.layers.18.decoder_layer.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
132
+ "lang_encoder.model.layers.18.decoder_layer.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
133
+ "lang_encoder.model.layers.18.decoder_layer.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
134
+ "lang_encoder.model.layers.18.decoder_layer.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
135
+ "lang_encoder.model.layers.18.decoder_layer.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
136
+ "lang_encoder.model.layers.18.decoder_layer.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
137
+ "lang_encoder.model.layers.18.decoder_layer.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
138
+ "lang_encoder.model.layers.18.decoder_layer.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00004.bin",
139
+ "lang_encoder.model.layers.18.decoder_layer.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
140
+ "lang_encoder.model.layers.19.decoder_layer.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
141
+ "lang_encoder.model.layers.19.decoder_layer.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
142
+ "lang_encoder.model.layers.19.decoder_layer.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
143
+ "lang_encoder.model.layers.19.decoder_layer.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
144
+ "lang_encoder.model.layers.19.decoder_layer.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
145
+ "lang_encoder.model.layers.19.decoder_layer.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
146
+ "lang_encoder.model.layers.19.decoder_layer.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
147
+ "lang_encoder.model.layers.19.decoder_layer.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
148
+ "lang_encoder.model.layers.19.decoder_layer.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00004.bin",
149
+ "lang_encoder.model.layers.19.decoder_layer.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
150
+ "lang_encoder.model.layers.19.gated_cross_attn_layer.attn.norm.bias": "pytorch_model-00002-of-00004.bin",
151
+ "lang_encoder.model.layers.19.gated_cross_attn_layer.attn.norm.weight": "pytorch_model-00002-of-00004.bin",
152
+ "lang_encoder.model.layers.19.gated_cross_attn_layer.attn.to_kv.weight": "pytorch_model-00002-of-00004.bin",
153
+ "lang_encoder.model.layers.19.gated_cross_attn_layer.attn.to_out.weight": "pytorch_model-00002-of-00004.bin",
154
+ "lang_encoder.model.layers.19.gated_cross_attn_layer.attn.to_q.weight": "pytorch_model-00002-of-00004.bin",
155
+ "lang_encoder.model.layers.19.gated_cross_attn_layer.attn_gate": "pytorch_model-00002-of-00004.bin",
156
+ "lang_encoder.model.layers.19.gated_cross_attn_layer.feed_forward.0.bias": "pytorch_model-00002-of-00004.bin",
157
+ "lang_encoder.model.layers.19.gated_cross_attn_layer.feed_forward.0.weight": "pytorch_model-00002-of-00004.bin",
158
+ "lang_encoder.model.layers.19.gated_cross_attn_layer.feed_forward.1.weight": "pytorch_model-00002-of-00004.bin",
159
+ "lang_encoder.model.layers.19.gated_cross_attn_layer.feed_forward.3.weight": "pytorch_model-00002-of-00004.bin",
160
+ "lang_encoder.model.layers.19.gated_cross_attn_layer.ff_gate": "pytorch_model-00002-of-00004.bin",
161
+ "lang_encoder.model.layers.2.decoder_layer.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
162
+ "lang_encoder.model.layers.2.decoder_layer.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
163
+ "lang_encoder.model.layers.2.decoder_layer.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
164
+ "lang_encoder.model.layers.2.decoder_layer.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
165
+ "lang_encoder.model.layers.2.decoder_layer.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
166
+ "lang_encoder.model.layers.2.decoder_layer.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
167
+ "lang_encoder.model.layers.2.decoder_layer.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
168
+ "lang_encoder.model.layers.2.decoder_layer.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
169
+ "lang_encoder.model.layers.2.decoder_layer.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00004.bin",
170
+ "lang_encoder.model.layers.2.decoder_layer.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
171
+ "lang_encoder.model.layers.20.decoder_layer.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
172
+ "lang_encoder.model.layers.20.decoder_layer.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
173
+ "lang_encoder.model.layers.20.decoder_layer.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
174
+ "lang_encoder.model.layers.20.decoder_layer.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
175
+ "lang_encoder.model.layers.20.decoder_layer.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
176
+ "lang_encoder.model.layers.20.decoder_layer.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
177
+ "lang_encoder.model.layers.20.decoder_layer.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
178
+ "lang_encoder.model.layers.20.decoder_layer.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
179
+ "lang_encoder.model.layers.20.decoder_layer.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00004.bin",
180
+ "lang_encoder.model.layers.20.decoder_layer.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
181
+ "lang_encoder.model.layers.21.decoder_layer.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
182
+ "lang_encoder.model.layers.21.decoder_layer.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
183
+ "lang_encoder.model.layers.21.decoder_layer.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
184
+ "lang_encoder.model.layers.21.decoder_layer.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
185
+ "lang_encoder.model.layers.21.decoder_layer.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
186
+ "lang_encoder.model.layers.21.decoder_layer.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
187
+ "lang_encoder.model.layers.21.decoder_layer.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
188
+ "lang_encoder.model.layers.21.decoder_layer.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
189
+ "lang_encoder.model.layers.21.decoder_layer.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00004.bin",
190
+ "lang_encoder.model.layers.21.decoder_layer.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
191
+ "lang_encoder.model.layers.22.decoder_layer.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
192
+ "lang_encoder.model.layers.22.decoder_layer.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
193
+ "lang_encoder.model.layers.22.decoder_layer.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
194
+ "lang_encoder.model.layers.22.decoder_layer.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
195
+ "lang_encoder.model.layers.22.decoder_layer.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
196
+ "lang_encoder.model.layers.22.decoder_layer.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
197
+ "lang_encoder.model.layers.22.decoder_layer.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
198
+ "lang_encoder.model.layers.22.decoder_layer.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
199
+ "lang_encoder.model.layers.22.decoder_layer.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00004.bin",
200
+ "lang_encoder.model.layers.22.decoder_layer.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
201
+ "lang_encoder.model.layers.23.decoder_layer.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
202
+ "lang_encoder.model.layers.23.decoder_layer.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
203
+ "lang_encoder.model.layers.23.decoder_layer.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
204
+ "lang_encoder.model.layers.23.decoder_layer.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
205
+ "lang_encoder.model.layers.23.decoder_layer.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
206
+ "lang_encoder.model.layers.23.decoder_layer.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
207
+ "lang_encoder.model.layers.23.decoder_layer.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
208
+ "lang_encoder.model.layers.23.decoder_layer.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
209
+ "lang_encoder.model.layers.23.decoder_layer.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00004.bin",
210
+ "lang_encoder.model.layers.23.decoder_layer.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
211
+ "lang_encoder.model.layers.23.gated_cross_attn_layer.attn.norm.bias": "pytorch_model-00003-of-00004.bin",
212
+ "lang_encoder.model.layers.23.gated_cross_attn_layer.attn.norm.weight": "pytorch_model-00003-of-00004.bin",
213
+ "lang_encoder.model.layers.23.gated_cross_attn_layer.attn.to_kv.weight": "pytorch_model-00003-of-00004.bin",
214
+ "lang_encoder.model.layers.23.gated_cross_attn_layer.attn.to_out.weight": "pytorch_model-00003-of-00004.bin",
215
+ "lang_encoder.model.layers.23.gated_cross_attn_layer.attn.to_q.weight": "pytorch_model-00003-of-00004.bin",
216
+ "lang_encoder.model.layers.23.gated_cross_attn_layer.attn_gate": "pytorch_model-00003-of-00004.bin",
217
+ "lang_encoder.model.layers.23.gated_cross_attn_layer.feed_forward.0.bias": "pytorch_model-00003-of-00004.bin",
218
+ "lang_encoder.model.layers.23.gated_cross_attn_layer.feed_forward.0.weight": "pytorch_model-00003-of-00004.bin",
219
+ "lang_encoder.model.layers.23.gated_cross_attn_layer.feed_forward.1.weight": "pytorch_model-00003-of-00004.bin",
220
+ "lang_encoder.model.layers.23.gated_cross_attn_layer.feed_forward.3.weight": "pytorch_model-00003-of-00004.bin",
221
+ "lang_encoder.model.layers.23.gated_cross_attn_layer.ff_gate": "pytorch_model-00003-of-00004.bin",
222
+ "lang_encoder.model.layers.24.decoder_layer.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
223
+ "lang_encoder.model.layers.24.decoder_layer.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
224
+ "lang_encoder.model.layers.24.decoder_layer.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
225
+ "lang_encoder.model.layers.24.decoder_layer.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
226
+ "lang_encoder.model.layers.24.decoder_layer.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
227
+ "lang_encoder.model.layers.24.decoder_layer.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
228
+ "lang_encoder.model.layers.24.decoder_layer.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
229
+ "lang_encoder.model.layers.24.decoder_layer.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
230
+ "lang_encoder.model.layers.24.decoder_layer.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00004.bin",
231
+ "lang_encoder.model.layers.24.decoder_layer.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
232
+ "lang_encoder.model.layers.25.decoder_layer.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
233
+ "lang_encoder.model.layers.25.decoder_layer.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
234
+ "lang_encoder.model.layers.25.decoder_layer.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
235
+ "lang_encoder.model.layers.25.decoder_layer.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
236
+ "lang_encoder.model.layers.25.decoder_layer.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
237
+ "lang_encoder.model.layers.25.decoder_layer.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
238
+ "lang_encoder.model.layers.25.decoder_layer.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
239
+ "lang_encoder.model.layers.25.decoder_layer.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
240
+ "lang_encoder.model.layers.25.decoder_layer.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00004.bin",
241
+ "lang_encoder.model.layers.25.decoder_layer.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
242
+ "lang_encoder.model.layers.26.decoder_layer.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
243
+ "lang_encoder.model.layers.26.decoder_layer.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
244
+ "lang_encoder.model.layers.26.decoder_layer.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
245
+ "lang_encoder.model.layers.26.decoder_layer.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
246
+ "lang_encoder.model.layers.26.decoder_layer.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
247
+ "lang_encoder.model.layers.26.decoder_layer.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
248
+ "lang_encoder.model.layers.26.decoder_layer.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
249
+ "lang_encoder.model.layers.26.decoder_layer.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
250
+ "lang_encoder.model.layers.26.decoder_layer.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00004.bin",
251
+ "lang_encoder.model.layers.26.decoder_layer.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
252
+ "lang_encoder.model.layers.27.decoder_layer.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
253
+ "lang_encoder.model.layers.27.decoder_layer.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
254
+ "lang_encoder.model.layers.27.decoder_layer.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
255
+ "lang_encoder.model.layers.27.decoder_layer.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
256
+ "lang_encoder.model.layers.27.decoder_layer.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
257
+ "lang_encoder.model.layers.27.decoder_layer.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
258
+ "lang_encoder.model.layers.27.decoder_layer.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
259
+ "lang_encoder.model.layers.27.decoder_layer.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
260
+ "lang_encoder.model.layers.27.decoder_layer.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00004.bin",
261
+ "lang_encoder.model.layers.27.decoder_layer.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
262
+ "lang_encoder.model.layers.27.gated_cross_attn_layer.attn.norm.bias": "pytorch_model-00003-of-00004.bin",
263
+ "lang_encoder.model.layers.27.gated_cross_attn_layer.attn.norm.weight": "pytorch_model-00003-of-00004.bin",
264
+ "lang_encoder.model.layers.27.gated_cross_attn_layer.attn.to_kv.weight": "pytorch_model-00003-of-00004.bin",
265
+ "lang_encoder.model.layers.27.gated_cross_attn_layer.attn.to_out.weight": "pytorch_model-00003-of-00004.bin",
266
+ "lang_encoder.model.layers.27.gated_cross_attn_layer.attn.to_q.weight": "pytorch_model-00003-of-00004.bin",
267
+ "lang_encoder.model.layers.27.gated_cross_attn_layer.attn_gate": "pytorch_model-00003-of-00004.bin",
268
+ "lang_encoder.model.layers.27.gated_cross_attn_layer.feed_forward.0.bias": "pytorch_model-00003-of-00004.bin",
269
+ "lang_encoder.model.layers.27.gated_cross_attn_layer.feed_forward.0.weight": "pytorch_model-00003-of-00004.bin",
270
+ "lang_encoder.model.layers.27.gated_cross_attn_layer.feed_forward.1.weight": "pytorch_model-00003-of-00004.bin",
271
+ "lang_encoder.model.layers.27.gated_cross_attn_layer.feed_forward.3.weight": "pytorch_model-00003-of-00004.bin",
272
+ "lang_encoder.model.layers.27.gated_cross_attn_layer.ff_gate": "pytorch_model-00003-of-00004.bin",
273
+ "lang_encoder.model.layers.28.decoder_layer.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
274
+ "lang_encoder.model.layers.28.decoder_layer.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
275
+ "lang_encoder.model.layers.28.decoder_layer.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
276
+ "lang_encoder.model.layers.28.decoder_layer.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
277
+ "lang_encoder.model.layers.28.decoder_layer.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
278
+ "lang_encoder.model.layers.28.decoder_layer.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
279
+ "lang_encoder.model.layers.28.decoder_layer.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
280
+ "lang_encoder.model.layers.28.decoder_layer.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
281
+ "lang_encoder.model.layers.28.decoder_layer.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00004.bin",
282
+ "lang_encoder.model.layers.28.decoder_layer.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
283
+ "lang_encoder.model.layers.29.decoder_layer.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
284
+ "lang_encoder.model.layers.29.decoder_layer.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
285
+ "lang_encoder.model.layers.29.decoder_layer.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
286
+ "lang_encoder.model.layers.29.decoder_layer.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
287
+ "lang_encoder.model.layers.29.decoder_layer.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
288
+ "lang_encoder.model.layers.29.decoder_layer.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
289
+ "lang_encoder.model.layers.29.decoder_layer.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
290
+ "lang_encoder.model.layers.29.decoder_layer.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
291
+ "lang_encoder.model.layers.29.decoder_layer.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00004.bin",
292
+ "lang_encoder.model.layers.29.decoder_layer.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
293
+ "lang_encoder.model.layers.3.decoder_layer.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
294
+ "lang_encoder.model.layers.3.decoder_layer.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
295
+ "lang_encoder.model.layers.3.decoder_layer.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
296
+ "lang_encoder.model.layers.3.decoder_layer.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
297
+ "lang_encoder.model.layers.3.decoder_layer.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
298
+ "lang_encoder.model.layers.3.decoder_layer.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
299
+ "lang_encoder.model.layers.3.decoder_layer.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
300
+ "lang_encoder.model.layers.3.decoder_layer.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
301
+ "lang_encoder.model.layers.3.decoder_layer.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00004.bin",
302
+ "lang_encoder.model.layers.3.decoder_layer.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
303
+ "lang_encoder.model.layers.3.gated_cross_attn_layer.attn.norm.bias": "pytorch_model-00001-of-00004.bin",
304
+ "lang_encoder.model.layers.3.gated_cross_attn_layer.attn.norm.weight": "pytorch_model-00001-of-00004.bin",
305
+ "lang_encoder.model.layers.3.gated_cross_attn_layer.attn.to_kv.weight": "pytorch_model-00001-of-00004.bin",
306
+ "lang_encoder.model.layers.3.gated_cross_attn_layer.attn.to_out.weight": "pytorch_model-00001-of-00004.bin",
307
+ "lang_encoder.model.layers.3.gated_cross_attn_layer.attn.to_q.weight": "pytorch_model-00001-of-00004.bin",
308
+ "lang_encoder.model.layers.3.gated_cross_attn_layer.attn_gate": "pytorch_model-00001-of-00004.bin",
309
+ "lang_encoder.model.layers.3.gated_cross_attn_layer.feed_forward.0.bias": "pytorch_model-00001-of-00004.bin",
310
+ "lang_encoder.model.layers.3.gated_cross_attn_layer.feed_forward.0.weight": "pytorch_model-00001-of-00004.bin",
311
+ "lang_encoder.model.layers.3.gated_cross_attn_layer.feed_forward.1.weight": "pytorch_model-00001-of-00004.bin",
312
+ "lang_encoder.model.layers.3.gated_cross_attn_layer.feed_forward.3.weight": "pytorch_model-00001-of-00004.bin",
313
+ "lang_encoder.model.layers.3.gated_cross_attn_layer.ff_gate": "pytorch_model-00001-of-00004.bin",
314
+ "lang_encoder.model.layers.30.decoder_layer.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
315
+ "lang_encoder.model.layers.30.decoder_layer.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
316
+ "lang_encoder.model.layers.30.decoder_layer.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
317
+ "lang_encoder.model.layers.30.decoder_layer.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
318
+ "lang_encoder.model.layers.30.decoder_layer.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
319
+ "lang_encoder.model.layers.30.decoder_layer.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
320
+ "lang_encoder.model.layers.30.decoder_layer.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
321
+ "lang_encoder.model.layers.30.decoder_layer.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
322
+ "lang_encoder.model.layers.30.decoder_layer.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00004.bin",
323
+ "lang_encoder.model.layers.30.decoder_layer.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
324
+ "lang_encoder.model.layers.31.decoder_layer.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
325
+ "lang_encoder.model.layers.31.decoder_layer.mlp.down_proj.weight": "pytorch_model-00004-of-00004.bin",
326
+ "lang_encoder.model.layers.31.decoder_layer.mlp.gate_proj.weight": "pytorch_model-00004-of-00004.bin",
327
+ "lang_encoder.model.layers.31.decoder_layer.mlp.up_proj.weight": "pytorch_model-00004-of-00004.bin",
328
+ "lang_encoder.model.layers.31.decoder_layer.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
329
+ "lang_encoder.model.layers.31.decoder_layer.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
330
+ "lang_encoder.model.layers.31.decoder_layer.self_attn.o_proj.weight": "pytorch_model-00004-of-00004.bin",
331
+ "lang_encoder.model.layers.31.decoder_layer.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
332
+ "lang_encoder.model.layers.31.decoder_layer.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00004.bin",
333
+ "lang_encoder.model.layers.31.decoder_layer.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
334
+ "lang_encoder.model.layers.31.gated_cross_attn_layer.attn.norm.bias": "pytorch_model-00003-of-00004.bin",
335
+ "lang_encoder.model.layers.31.gated_cross_attn_layer.attn.norm.weight": "pytorch_model-00003-of-00004.bin",
336
+ "lang_encoder.model.layers.31.gated_cross_attn_layer.attn.to_kv.weight": "pytorch_model-00003-of-00004.bin",
337
+ "lang_encoder.model.layers.31.gated_cross_attn_layer.attn.to_out.weight": "pytorch_model-00003-of-00004.bin",
338
+ "lang_encoder.model.layers.31.gated_cross_attn_layer.attn.to_q.weight": "pytorch_model-00003-of-00004.bin",
339
+ "lang_encoder.model.layers.31.gated_cross_attn_layer.attn_gate": "pytorch_model-00003-of-00004.bin",
340
+ "lang_encoder.model.layers.31.gated_cross_attn_layer.feed_forward.0.bias": "pytorch_model-00003-of-00004.bin",
341
+ "lang_encoder.model.layers.31.gated_cross_attn_layer.feed_forward.0.weight": "pytorch_model-00003-of-00004.bin",
342
+ "lang_encoder.model.layers.31.gated_cross_attn_layer.feed_forward.1.weight": "pytorch_model-00004-of-00004.bin",
343
+ "lang_encoder.model.layers.31.gated_cross_attn_layer.feed_forward.3.weight": "pytorch_model-00004-of-00004.bin",
344
+ "lang_encoder.model.layers.31.gated_cross_attn_layer.ff_gate": "pytorch_model-00003-of-00004.bin",
345
+ "lang_encoder.model.layers.4.decoder_layer.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
346
+ "lang_encoder.model.layers.4.decoder_layer.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
347
+ "lang_encoder.model.layers.4.decoder_layer.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
348
+ "lang_encoder.model.layers.4.decoder_layer.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
349
+ "lang_encoder.model.layers.4.decoder_layer.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
350
+ "lang_encoder.model.layers.4.decoder_layer.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
351
+ "lang_encoder.model.layers.4.decoder_layer.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
352
+ "lang_encoder.model.layers.4.decoder_layer.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
353
+ "lang_encoder.model.layers.4.decoder_layer.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00004.bin",
354
+ "lang_encoder.model.layers.4.decoder_layer.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
355
+ "lang_encoder.model.layers.5.decoder_layer.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
356
+ "lang_encoder.model.layers.5.decoder_layer.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
357
+ "lang_encoder.model.layers.5.decoder_layer.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
358
+ "lang_encoder.model.layers.5.decoder_layer.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
359
+ "lang_encoder.model.layers.5.decoder_layer.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
360
+ "lang_encoder.model.layers.5.decoder_layer.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
361
+ "lang_encoder.model.layers.5.decoder_layer.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
362
+ "lang_encoder.model.layers.5.decoder_layer.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
363
+ "lang_encoder.model.layers.5.decoder_layer.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00004.bin",
364
+ "lang_encoder.model.layers.5.decoder_layer.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
365
+ "lang_encoder.model.layers.6.decoder_layer.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
366
+ "lang_encoder.model.layers.6.decoder_layer.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
367
+ "lang_encoder.model.layers.6.decoder_layer.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
368
+ "lang_encoder.model.layers.6.decoder_layer.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
369
+ "lang_encoder.model.layers.6.decoder_layer.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
370
+ "lang_encoder.model.layers.6.decoder_layer.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
371
+ "lang_encoder.model.layers.6.decoder_layer.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
372
+ "lang_encoder.model.layers.6.decoder_layer.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
373
+ "lang_encoder.model.layers.6.decoder_layer.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00004.bin",
374
+ "lang_encoder.model.layers.6.decoder_layer.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
375
+ "lang_encoder.model.layers.7.decoder_layer.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
376
+ "lang_encoder.model.layers.7.decoder_layer.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
377
+ "lang_encoder.model.layers.7.decoder_layer.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
378
+ "lang_encoder.model.layers.7.decoder_layer.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
379
+ "lang_encoder.model.layers.7.decoder_layer.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
380
+ "lang_encoder.model.layers.7.decoder_layer.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
381
+ "lang_encoder.model.layers.7.decoder_layer.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
382
+ "lang_encoder.model.layers.7.decoder_layer.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
383
+ "lang_encoder.model.layers.7.decoder_layer.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00004.bin",
384
+ "lang_encoder.model.layers.7.decoder_layer.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
385
+ "lang_encoder.model.layers.7.gated_cross_attn_layer.attn.norm.bias": "pytorch_model-00001-of-00004.bin",
386
+ "lang_encoder.model.layers.7.gated_cross_attn_layer.attn.norm.weight": "pytorch_model-00001-of-00004.bin",
387
+ "lang_encoder.model.layers.7.gated_cross_attn_layer.attn.to_kv.weight": "pytorch_model-00001-of-00004.bin",
388
+ "lang_encoder.model.layers.7.gated_cross_attn_layer.attn.to_out.weight": "pytorch_model-00001-of-00004.bin",
389
+ "lang_encoder.model.layers.7.gated_cross_attn_layer.attn.to_q.weight": "pytorch_model-00001-of-00004.bin",
390
+ "lang_encoder.model.layers.7.gated_cross_attn_layer.attn_gate": "pytorch_model-00001-of-00004.bin",
391
+ "lang_encoder.model.layers.7.gated_cross_attn_layer.feed_forward.0.bias": "pytorch_model-00001-of-00004.bin",
392
+ "lang_encoder.model.layers.7.gated_cross_attn_layer.feed_forward.0.weight": "pytorch_model-00001-of-00004.bin",
393
+ "lang_encoder.model.layers.7.gated_cross_attn_layer.feed_forward.1.weight": "pytorch_model-00001-of-00004.bin",
394
+ "lang_encoder.model.layers.7.gated_cross_attn_layer.feed_forward.3.weight": "pytorch_model-00001-of-00004.bin",
395
+ "lang_encoder.model.layers.7.gated_cross_attn_layer.ff_gate": "pytorch_model-00001-of-00004.bin",
396
+ "lang_encoder.model.layers.8.decoder_layer.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
397
+ "lang_encoder.model.layers.8.decoder_layer.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
398
+ "lang_encoder.model.layers.8.decoder_layer.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
399
+ "lang_encoder.model.layers.8.decoder_layer.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
400
+ "lang_encoder.model.layers.8.decoder_layer.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
401
+ "lang_encoder.model.layers.8.decoder_layer.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
402
+ "lang_encoder.model.layers.8.decoder_layer.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
403
+ "lang_encoder.model.layers.8.decoder_layer.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
404
+ "lang_encoder.model.layers.8.decoder_layer.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00004.bin",
405
+ "lang_encoder.model.layers.8.decoder_layer.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
406
+ "lang_encoder.model.layers.9.decoder_layer.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
407
+ "lang_encoder.model.layers.9.decoder_layer.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
408
+ "lang_encoder.model.layers.9.decoder_layer.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
409
+ "lang_encoder.model.layers.9.decoder_layer.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
410
+ "lang_encoder.model.layers.9.decoder_layer.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
411
+ "lang_encoder.model.layers.9.decoder_layer.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
412
+ "lang_encoder.model.layers.9.decoder_layer.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
413
+ "lang_encoder.model.layers.9.decoder_layer.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
414
+ "lang_encoder.model.layers.9.decoder_layer.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00004.bin",
415
+ "lang_encoder.model.layers.9.decoder_layer.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
416
+ "lang_encoder.model.norm.weight": "pytorch_model-00004-of-00004.bin",
417
+ "perceiver.latents": "pytorch_model-00004-of-00004.bin",
418
+ "perceiver.layers.0.feed_forward.0.bias": "pytorch_model-00004-of-00004.bin",
419
+ "perceiver.layers.0.feed_forward.0.weight": "pytorch_model-00004-of-00004.bin",
420
+ "perceiver.layers.0.feed_forward.1.weight": "pytorch_model-00004-of-00004.bin",
421
+ "perceiver.layers.0.feed_forward.3.weight": "pytorch_model-00004-of-00004.bin",
422
+ "perceiver.layers.0.norm_latents.bias": "pytorch_model-00004-of-00004.bin",
423
+ "perceiver.layers.0.norm_latents.weight": "pytorch_model-00004-of-00004.bin",
424
+ "perceiver.layers.0.norm_media.bias": "pytorch_model-00004-of-00004.bin",
425
+ "perceiver.layers.0.norm_media.weight": "pytorch_model-00004-of-00004.bin",
426
+ "perceiver.layers.0.to_kv.weight": "pytorch_model-00004-of-00004.bin",
427
+ "perceiver.layers.0.to_out.weight": "pytorch_model-00004-of-00004.bin",
428
+ "perceiver.layers.0.to_q.weight": "pytorch_model-00004-of-00004.bin",
429
+ "perceiver.layers.1.feed_forward.0.bias": "pytorch_model-00004-of-00004.bin",
430
+ "perceiver.layers.1.feed_forward.0.weight": "pytorch_model-00004-of-00004.bin",
431
+ "perceiver.layers.1.feed_forward.1.weight": "pytorch_model-00004-of-00004.bin",
432
+ "perceiver.layers.1.feed_forward.3.weight": "pytorch_model-00004-of-00004.bin",
433
+ "perceiver.layers.1.norm_latents.bias": "pytorch_model-00004-of-00004.bin",
434
+ "perceiver.layers.1.norm_latents.weight": "pytorch_model-00004-of-00004.bin",
435
+ "perceiver.layers.1.norm_media.bias": "pytorch_model-00004-of-00004.bin",
436
+ "perceiver.layers.1.norm_media.weight": "pytorch_model-00004-of-00004.bin",
437
+ "perceiver.layers.1.to_kv.weight": "pytorch_model-00004-of-00004.bin",
438
+ "perceiver.layers.1.to_out.weight": "pytorch_model-00004-of-00004.bin",
439
+ "perceiver.layers.1.to_q.weight": "pytorch_model-00004-of-00004.bin",
440
+ "perceiver.layers.2.feed_forward.0.bias": "pytorch_model-00004-of-00004.bin",
441
+ "perceiver.layers.2.feed_forward.0.weight": "pytorch_model-00004-of-00004.bin",
442
+ "perceiver.layers.2.feed_forward.1.weight": "pytorch_model-00004-of-00004.bin",
443
+ "perceiver.layers.2.feed_forward.3.weight": "pytorch_model-00004-of-00004.bin",
444
+ "perceiver.layers.2.norm_latents.bias": "pytorch_model-00004-of-00004.bin",
445
+ "perceiver.layers.2.norm_latents.weight": "pytorch_model-00004-of-00004.bin",
446
+ "perceiver.layers.2.norm_media.bias": "pytorch_model-00004-of-00004.bin",
447
+ "perceiver.layers.2.norm_media.weight": "pytorch_model-00004-of-00004.bin",
448
+ "perceiver.layers.2.to_kv.weight": "pytorch_model-00004-of-00004.bin",
449
+ "perceiver.layers.2.to_out.weight": "pytorch_model-00004-of-00004.bin",
450
+ "perceiver.layers.2.to_q.weight": "pytorch_model-00004-of-00004.bin",
451
+ "perceiver.layers.3.feed_forward.0.bias": "pytorch_model-00004-of-00004.bin",
452
+ "perceiver.layers.3.feed_forward.0.weight": "pytorch_model-00004-of-00004.bin",
453
+ "perceiver.layers.3.feed_forward.1.weight": "pytorch_model-00004-of-00004.bin",
454
+ "perceiver.layers.3.feed_forward.3.weight": "pytorch_model-00004-of-00004.bin",
455
+ "perceiver.layers.3.norm_latents.bias": "pytorch_model-00004-of-00004.bin",
456
+ "perceiver.layers.3.norm_latents.weight": "pytorch_model-00004-of-00004.bin",
457
+ "perceiver.layers.3.norm_media.bias": "pytorch_model-00004-of-00004.bin",
458
+ "perceiver.layers.3.norm_media.weight": "pytorch_model-00004-of-00004.bin",
459
+ "perceiver.layers.3.to_kv.weight": "pytorch_model-00004-of-00004.bin",
460
+ "perceiver.layers.3.to_out.weight": "pytorch_model-00004-of-00004.bin",
461
+ "perceiver.layers.3.to_q.weight": "pytorch_model-00004-of-00004.bin",
462
+ "perceiver.layers.4.feed_forward.0.bias": "pytorch_model-00004-of-00004.bin",
463
+ "perceiver.layers.4.feed_forward.0.weight": "pytorch_model-00004-of-00004.bin",
464
+ "perceiver.layers.4.feed_forward.1.weight": "pytorch_model-00004-of-00004.bin",
465
+ "perceiver.layers.4.feed_forward.3.weight": "pytorch_model-00004-of-00004.bin",
466
+ "perceiver.layers.4.norm_latents.bias": "pytorch_model-00004-of-00004.bin",
467
+ "perceiver.layers.4.norm_latents.weight": "pytorch_model-00004-of-00004.bin",
468
+ "perceiver.layers.4.norm_media.bias": "pytorch_model-00004-of-00004.bin",
469
+ "perceiver.layers.4.norm_media.weight": "pytorch_model-00004-of-00004.bin",
470
+ "perceiver.layers.4.to_kv.weight": "pytorch_model-00004-of-00004.bin",
471
+ "perceiver.layers.4.to_out.weight": "pytorch_model-00004-of-00004.bin",
472
+ "perceiver.layers.4.to_q.weight": "pytorch_model-00004-of-00004.bin",
473
+ "perceiver.layers.5.feed_forward.0.bias": "pytorch_model-00004-of-00004.bin",
474
+ "perceiver.layers.5.feed_forward.0.weight": "pytorch_model-00004-of-00004.bin",
475
+ "perceiver.layers.5.feed_forward.1.weight": "pytorch_model-00004-of-00004.bin",
476
+ "perceiver.layers.5.feed_forward.3.weight": "pytorch_model-00004-of-00004.bin",
477
+ "perceiver.layers.5.norm_latents.bias": "pytorch_model-00004-of-00004.bin",
478
+ "perceiver.layers.5.norm_latents.weight": "pytorch_model-00004-of-00004.bin",
479
+ "perceiver.layers.5.norm_media.bias": "pytorch_model-00004-of-00004.bin",
480
+ "perceiver.layers.5.norm_media.weight": "pytorch_model-00004-of-00004.bin",
481
+ "perceiver.layers.5.to_kv.weight": "pytorch_model-00004-of-00004.bin",
482
+ "perceiver.layers.5.to_out.weight": "pytorch_model-00004-of-00004.bin",
483
+ "perceiver.layers.5.to_q.weight": "pytorch_model-00004-of-00004.bin",
484
+ "perceiver.norm.bias": "pytorch_model-00004-of-00004.bin",
485
+ "perceiver.norm.weight": "pytorch_model-00004-of-00004.bin",
486
+ "vision_encoder.vision_model.embeddings.class_embedding": "pytorch_model-00004-of-00004.bin",
487
+ "vision_encoder.vision_model.embeddings.patch_embedding.weight": "pytorch_model-00004-of-00004.bin",
488
+ "vision_encoder.vision_model.embeddings.position_embedding.weight": "pytorch_model-00004-of-00004.bin",
489
+ "vision_encoder.vision_model.embeddings.position_ids": "pytorch_model-00004-of-00004.bin",
490
+ "vision_encoder.vision_model.encoder.layers.0.layer_norm1.bias": "pytorch_model-00004-of-00004.bin",
491
+ "vision_encoder.vision_model.encoder.layers.0.layer_norm1.weight": "pytorch_model-00004-of-00004.bin",
492
+ "vision_encoder.vision_model.encoder.layers.0.layer_norm2.bias": "pytorch_model-00004-of-00004.bin",
493
+ "vision_encoder.vision_model.encoder.layers.0.layer_norm2.weight": "pytorch_model-00004-of-00004.bin",
494
+ "vision_encoder.vision_model.encoder.layers.0.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
495
+ "vision_encoder.vision_model.encoder.layers.0.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
496
+ "vision_encoder.vision_model.encoder.layers.0.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
497
+ "vision_encoder.vision_model.encoder.layers.0.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
498
+ "vision_encoder.vision_model.encoder.layers.0.self_attn.k_proj.bias": "pytorch_model-00004-of-00004.bin",
499
+ "vision_encoder.vision_model.encoder.layers.0.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
500
+ "vision_encoder.vision_model.encoder.layers.0.self_attn.out_proj.bias": "pytorch_model-00004-of-00004.bin",
501
+ "vision_encoder.vision_model.encoder.layers.0.self_attn.out_proj.weight": "pytorch_model-00004-of-00004.bin",
502
+ "vision_encoder.vision_model.encoder.layers.0.self_attn.q_proj.bias": "pytorch_model-00004-of-00004.bin",
503
+ "vision_encoder.vision_model.encoder.layers.0.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
504
+ "vision_encoder.vision_model.encoder.layers.0.self_attn.v_proj.bias": "pytorch_model-00004-of-00004.bin",
505
+ "vision_encoder.vision_model.encoder.layers.0.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
506
+ "vision_encoder.vision_model.encoder.layers.1.layer_norm1.bias": "pytorch_model-00004-of-00004.bin",
507
+ "vision_encoder.vision_model.encoder.layers.1.layer_norm1.weight": "pytorch_model-00004-of-00004.bin",
508
+ "vision_encoder.vision_model.encoder.layers.1.layer_norm2.bias": "pytorch_model-00004-of-00004.bin",
509
+ "vision_encoder.vision_model.encoder.layers.1.layer_norm2.weight": "pytorch_model-00004-of-00004.bin",
510
+ "vision_encoder.vision_model.encoder.layers.1.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
511
+ "vision_encoder.vision_model.encoder.layers.1.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
512
+ "vision_encoder.vision_model.encoder.layers.1.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
513
+ "vision_encoder.vision_model.encoder.layers.1.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
514
+ "vision_encoder.vision_model.encoder.layers.1.self_attn.k_proj.bias": "pytorch_model-00004-of-00004.bin",
515
+ "vision_encoder.vision_model.encoder.layers.1.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
516
+ "vision_encoder.vision_model.encoder.layers.1.self_attn.out_proj.bias": "pytorch_model-00004-of-00004.bin",
517
+ "vision_encoder.vision_model.encoder.layers.1.self_attn.out_proj.weight": "pytorch_model-00004-of-00004.bin",
518
+ "vision_encoder.vision_model.encoder.layers.1.self_attn.q_proj.bias": "pytorch_model-00004-of-00004.bin",
519
+ "vision_encoder.vision_model.encoder.layers.1.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
520
+ "vision_encoder.vision_model.encoder.layers.1.self_attn.v_proj.bias": "pytorch_model-00004-of-00004.bin",
521
+ "vision_encoder.vision_model.encoder.layers.1.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
522
+ "vision_encoder.vision_model.encoder.layers.10.layer_norm1.bias": "pytorch_model-00004-of-00004.bin",
523
+ "vision_encoder.vision_model.encoder.layers.10.layer_norm1.weight": "pytorch_model-00004-of-00004.bin",
524
+ "vision_encoder.vision_model.encoder.layers.10.layer_norm2.bias": "pytorch_model-00004-of-00004.bin",
525
+ "vision_encoder.vision_model.encoder.layers.10.layer_norm2.weight": "pytorch_model-00004-of-00004.bin",
526
+ "vision_encoder.vision_model.encoder.layers.10.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
527
+ "vision_encoder.vision_model.encoder.layers.10.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
528
+ "vision_encoder.vision_model.encoder.layers.10.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
529
+ "vision_encoder.vision_model.encoder.layers.10.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
530
+ "vision_encoder.vision_model.encoder.layers.10.self_attn.k_proj.bias": "pytorch_model-00004-of-00004.bin",
531
+ "vision_encoder.vision_model.encoder.layers.10.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
532
+ "vision_encoder.vision_model.encoder.layers.10.self_attn.out_proj.bias": "pytorch_model-00004-of-00004.bin",
533
+ "vision_encoder.vision_model.encoder.layers.10.self_attn.out_proj.weight": "pytorch_model-00004-of-00004.bin",
534
+ "vision_encoder.vision_model.encoder.layers.10.self_attn.q_proj.bias": "pytorch_model-00004-of-00004.bin",
535
+ "vision_encoder.vision_model.encoder.layers.10.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
536
+ "vision_encoder.vision_model.encoder.layers.10.self_attn.v_proj.bias": "pytorch_model-00004-of-00004.bin",
537
+ "vision_encoder.vision_model.encoder.layers.10.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
538
+ "vision_encoder.vision_model.encoder.layers.11.layer_norm1.bias": "pytorch_model-00004-of-00004.bin",
539
+ "vision_encoder.vision_model.encoder.layers.11.layer_norm1.weight": "pytorch_model-00004-of-00004.bin",
540
+ "vision_encoder.vision_model.encoder.layers.11.layer_norm2.bias": "pytorch_model-00004-of-00004.bin",
541
+ "vision_encoder.vision_model.encoder.layers.11.layer_norm2.weight": "pytorch_model-00004-of-00004.bin",
542
+ "vision_encoder.vision_model.encoder.layers.11.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
543
+ "vision_encoder.vision_model.encoder.layers.11.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
544
+ "vision_encoder.vision_model.encoder.layers.11.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
545
+ "vision_encoder.vision_model.encoder.layers.11.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
546
+ "vision_encoder.vision_model.encoder.layers.11.self_attn.k_proj.bias": "pytorch_model-00004-of-00004.bin",
547
+ "vision_encoder.vision_model.encoder.layers.11.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
548
+ "vision_encoder.vision_model.encoder.layers.11.self_attn.out_proj.bias": "pytorch_model-00004-of-00004.bin",
549
+ "vision_encoder.vision_model.encoder.layers.11.self_attn.out_proj.weight": "pytorch_model-00004-of-00004.bin",
550
+ "vision_encoder.vision_model.encoder.layers.11.self_attn.q_proj.bias": "pytorch_model-00004-of-00004.bin",
551
+ "vision_encoder.vision_model.encoder.layers.11.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
552
+ "vision_encoder.vision_model.encoder.layers.11.self_attn.v_proj.bias": "pytorch_model-00004-of-00004.bin",
553
+ "vision_encoder.vision_model.encoder.layers.11.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
554
+ "vision_encoder.vision_model.encoder.layers.12.layer_norm1.bias": "pytorch_model-00004-of-00004.bin",
555
+ "vision_encoder.vision_model.encoder.layers.12.layer_norm1.weight": "pytorch_model-00004-of-00004.bin",
556
+ "vision_encoder.vision_model.encoder.layers.12.layer_norm2.bias": "pytorch_model-00004-of-00004.bin",
557
+ "vision_encoder.vision_model.encoder.layers.12.layer_norm2.weight": "pytorch_model-00004-of-00004.bin",
558
+ "vision_encoder.vision_model.encoder.layers.12.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
559
+ "vision_encoder.vision_model.encoder.layers.12.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
560
+ "vision_encoder.vision_model.encoder.layers.12.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
561
+ "vision_encoder.vision_model.encoder.layers.12.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
562
+ "vision_encoder.vision_model.encoder.layers.12.self_attn.k_proj.bias": "pytorch_model-00004-of-00004.bin",
563
+ "vision_encoder.vision_model.encoder.layers.12.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
564
+ "vision_encoder.vision_model.encoder.layers.12.self_attn.out_proj.bias": "pytorch_model-00004-of-00004.bin",
565
+ "vision_encoder.vision_model.encoder.layers.12.self_attn.out_proj.weight": "pytorch_model-00004-of-00004.bin",
566
+ "vision_encoder.vision_model.encoder.layers.12.self_attn.q_proj.bias": "pytorch_model-00004-of-00004.bin",
567
+ "vision_encoder.vision_model.encoder.layers.12.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
568
+ "vision_encoder.vision_model.encoder.layers.12.self_attn.v_proj.bias": "pytorch_model-00004-of-00004.bin",
569
+ "vision_encoder.vision_model.encoder.layers.12.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
570
+ "vision_encoder.vision_model.encoder.layers.13.layer_norm1.bias": "pytorch_model-00004-of-00004.bin",
571
+ "vision_encoder.vision_model.encoder.layers.13.layer_norm1.weight": "pytorch_model-00004-of-00004.bin",
572
+ "vision_encoder.vision_model.encoder.layers.13.layer_norm2.bias": "pytorch_model-00004-of-00004.bin",
573
+ "vision_encoder.vision_model.encoder.layers.13.layer_norm2.weight": "pytorch_model-00004-of-00004.bin",
574
+ "vision_encoder.vision_model.encoder.layers.13.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
575
+ "vision_encoder.vision_model.encoder.layers.13.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
576
+ "vision_encoder.vision_model.encoder.layers.13.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
577
+ "vision_encoder.vision_model.encoder.layers.13.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
578
+ "vision_encoder.vision_model.encoder.layers.13.self_attn.k_proj.bias": "pytorch_model-00004-of-00004.bin",
579
+ "vision_encoder.vision_model.encoder.layers.13.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
580
+ "vision_encoder.vision_model.encoder.layers.13.self_attn.out_proj.bias": "pytorch_model-00004-of-00004.bin",
581
+ "vision_encoder.vision_model.encoder.layers.13.self_attn.out_proj.weight": "pytorch_model-00004-of-00004.bin",
582
+ "vision_encoder.vision_model.encoder.layers.13.self_attn.q_proj.bias": "pytorch_model-00004-of-00004.bin",
583
+ "vision_encoder.vision_model.encoder.layers.13.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
584
+ "vision_encoder.vision_model.encoder.layers.13.self_attn.v_proj.bias": "pytorch_model-00004-of-00004.bin",
585
+ "vision_encoder.vision_model.encoder.layers.13.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
586
+ "vision_encoder.vision_model.encoder.layers.14.layer_norm1.bias": "pytorch_model-00004-of-00004.bin",
587
+ "vision_encoder.vision_model.encoder.layers.14.layer_norm1.weight": "pytorch_model-00004-of-00004.bin",
588
+ "vision_encoder.vision_model.encoder.layers.14.layer_norm2.bias": "pytorch_model-00004-of-00004.bin",
589
+ "vision_encoder.vision_model.encoder.layers.14.layer_norm2.weight": "pytorch_model-00004-of-00004.bin",
590
+ "vision_encoder.vision_model.encoder.layers.14.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
591
+ "vision_encoder.vision_model.encoder.layers.14.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
592
+ "vision_encoder.vision_model.encoder.layers.14.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
593
+ "vision_encoder.vision_model.encoder.layers.14.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
594
+ "vision_encoder.vision_model.encoder.layers.14.self_attn.k_proj.bias": "pytorch_model-00004-of-00004.bin",
595
+ "vision_encoder.vision_model.encoder.layers.14.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
596
+ "vision_encoder.vision_model.encoder.layers.14.self_attn.out_proj.bias": "pytorch_model-00004-of-00004.bin",
597
+ "vision_encoder.vision_model.encoder.layers.14.self_attn.out_proj.weight": "pytorch_model-00004-of-00004.bin",
598
+ "vision_encoder.vision_model.encoder.layers.14.self_attn.q_proj.bias": "pytorch_model-00004-of-00004.bin",
599
+ "vision_encoder.vision_model.encoder.layers.14.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
600
+ "vision_encoder.vision_model.encoder.layers.14.self_attn.v_proj.bias": "pytorch_model-00004-of-00004.bin",
601
+ "vision_encoder.vision_model.encoder.layers.14.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
602
+ "vision_encoder.vision_model.encoder.layers.15.layer_norm1.bias": "pytorch_model-00004-of-00004.bin",
603
+ "vision_encoder.vision_model.encoder.layers.15.layer_norm1.weight": "pytorch_model-00004-of-00004.bin",
604
+ "vision_encoder.vision_model.encoder.layers.15.layer_norm2.bias": "pytorch_model-00004-of-00004.bin",
605
+ "vision_encoder.vision_model.encoder.layers.15.layer_norm2.weight": "pytorch_model-00004-of-00004.bin",
606
+ "vision_encoder.vision_model.encoder.layers.15.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
607
+ "vision_encoder.vision_model.encoder.layers.15.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
608
+ "vision_encoder.vision_model.encoder.layers.15.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
609
+ "vision_encoder.vision_model.encoder.layers.15.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
610
+ "vision_encoder.vision_model.encoder.layers.15.self_attn.k_proj.bias": "pytorch_model-00004-of-00004.bin",
611
+ "vision_encoder.vision_model.encoder.layers.15.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
612
+ "vision_encoder.vision_model.encoder.layers.15.self_attn.out_proj.bias": "pytorch_model-00004-of-00004.bin",
613
+ "vision_encoder.vision_model.encoder.layers.15.self_attn.out_proj.weight": "pytorch_model-00004-of-00004.bin",
614
+ "vision_encoder.vision_model.encoder.layers.15.self_attn.q_proj.bias": "pytorch_model-00004-of-00004.bin",
615
+ "vision_encoder.vision_model.encoder.layers.15.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
616
+ "vision_encoder.vision_model.encoder.layers.15.self_attn.v_proj.bias": "pytorch_model-00004-of-00004.bin",
617
+ "vision_encoder.vision_model.encoder.layers.15.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
618
+ "vision_encoder.vision_model.encoder.layers.16.layer_norm1.bias": "pytorch_model-00004-of-00004.bin",
619
+ "vision_encoder.vision_model.encoder.layers.16.layer_norm1.weight": "pytorch_model-00004-of-00004.bin",
620
+ "vision_encoder.vision_model.encoder.layers.16.layer_norm2.bias": "pytorch_model-00004-of-00004.bin",
621
+ "vision_encoder.vision_model.encoder.layers.16.layer_norm2.weight": "pytorch_model-00004-of-00004.bin",
622
+ "vision_encoder.vision_model.encoder.layers.16.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
623
+ "vision_encoder.vision_model.encoder.layers.16.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
624
+ "vision_encoder.vision_model.encoder.layers.16.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
625
+ "vision_encoder.vision_model.encoder.layers.16.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
626
+ "vision_encoder.vision_model.encoder.layers.16.self_attn.k_proj.bias": "pytorch_model-00004-of-00004.bin",
627
+ "vision_encoder.vision_model.encoder.layers.16.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
628
+ "vision_encoder.vision_model.encoder.layers.16.self_attn.out_proj.bias": "pytorch_model-00004-of-00004.bin",
629
+ "vision_encoder.vision_model.encoder.layers.16.self_attn.out_proj.weight": "pytorch_model-00004-of-00004.bin",
630
+ "vision_encoder.vision_model.encoder.layers.16.self_attn.q_proj.bias": "pytorch_model-00004-of-00004.bin",
631
+ "vision_encoder.vision_model.encoder.layers.16.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
632
+ "vision_encoder.vision_model.encoder.layers.16.self_attn.v_proj.bias": "pytorch_model-00004-of-00004.bin",
633
+ "vision_encoder.vision_model.encoder.layers.16.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
634
+ "vision_encoder.vision_model.encoder.layers.17.layer_norm1.bias": "pytorch_model-00004-of-00004.bin",
635
+ "vision_encoder.vision_model.encoder.layers.17.layer_norm1.weight": "pytorch_model-00004-of-00004.bin",
636
+ "vision_encoder.vision_model.encoder.layers.17.layer_norm2.bias": "pytorch_model-00004-of-00004.bin",
637
+ "vision_encoder.vision_model.encoder.layers.17.layer_norm2.weight": "pytorch_model-00004-of-00004.bin",
638
+ "vision_encoder.vision_model.encoder.layers.17.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
639
+ "vision_encoder.vision_model.encoder.layers.17.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
640
+ "vision_encoder.vision_model.encoder.layers.17.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
641
+ "vision_encoder.vision_model.encoder.layers.17.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
642
+ "vision_encoder.vision_model.encoder.layers.17.self_attn.k_proj.bias": "pytorch_model-00004-of-00004.bin",
643
+ "vision_encoder.vision_model.encoder.layers.17.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
644
+ "vision_encoder.vision_model.encoder.layers.17.self_attn.out_proj.bias": "pytorch_model-00004-of-00004.bin",
645
+ "vision_encoder.vision_model.encoder.layers.17.self_attn.out_proj.weight": "pytorch_model-00004-of-00004.bin",
646
+ "vision_encoder.vision_model.encoder.layers.17.self_attn.q_proj.bias": "pytorch_model-00004-of-00004.bin",
647
+ "vision_encoder.vision_model.encoder.layers.17.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
648
+ "vision_encoder.vision_model.encoder.layers.17.self_attn.v_proj.bias": "pytorch_model-00004-of-00004.bin",
649
+ "vision_encoder.vision_model.encoder.layers.17.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
650
+ "vision_encoder.vision_model.encoder.layers.18.layer_norm1.bias": "pytorch_model-00004-of-00004.bin",
651
+ "vision_encoder.vision_model.encoder.layers.18.layer_norm1.weight": "pytorch_model-00004-of-00004.bin",
652
+ "vision_encoder.vision_model.encoder.layers.18.layer_norm2.bias": "pytorch_model-00004-of-00004.bin",
653
+ "vision_encoder.vision_model.encoder.layers.18.layer_norm2.weight": "pytorch_model-00004-of-00004.bin",
654
+ "vision_encoder.vision_model.encoder.layers.18.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
655
+ "vision_encoder.vision_model.encoder.layers.18.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
656
+ "vision_encoder.vision_model.encoder.layers.18.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
657
+ "vision_encoder.vision_model.encoder.layers.18.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
658
+ "vision_encoder.vision_model.encoder.layers.18.self_attn.k_proj.bias": "pytorch_model-00004-of-00004.bin",
659
+ "vision_encoder.vision_model.encoder.layers.18.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
660
+ "vision_encoder.vision_model.encoder.layers.18.self_attn.out_proj.bias": "pytorch_model-00004-of-00004.bin",
661
+ "vision_encoder.vision_model.encoder.layers.18.self_attn.out_proj.weight": "pytorch_model-00004-of-00004.bin",
662
+ "vision_encoder.vision_model.encoder.layers.18.self_attn.q_proj.bias": "pytorch_model-00004-of-00004.bin",
663
+ "vision_encoder.vision_model.encoder.layers.18.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
664
+ "vision_encoder.vision_model.encoder.layers.18.self_attn.v_proj.bias": "pytorch_model-00004-of-00004.bin",
665
+ "vision_encoder.vision_model.encoder.layers.18.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
666
+ "vision_encoder.vision_model.encoder.layers.19.layer_norm1.bias": "pytorch_model-00004-of-00004.bin",
667
+ "vision_encoder.vision_model.encoder.layers.19.layer_norm1.weight": "pytorch_model-00004-of-00004.bin",
668
+ "vision_encoder.vision_model.encoder.layers.19.layer_norm2.bias": "pytorch_model-00004-of-00004.bin",
669
+ "vision_encoder.vision_model.encoder.layers.19.layer_norm2.weight": "pytorch_model-00004-of-00004.bin",
670
+ "vision_encoder.vision_model.encoder.layers.19.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
671
+ "vision_encoder.vision_model.encoder.layers.19.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
672
+ "vision_encoder.vision_model.encoder.layers.19.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
673
+ "vision_encoder.vision_model.encoder.layers.19.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
674
+ "vision_encoder.vision_model.encoder.layers.19.self_attn.k_proj.bias": "pytorch_model-00004-of-00004.bin",
675
+ "vision_encoder.vision_model.encoder.layers.19.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
676
+ "vision_encoder.vision_model.encoder.layers.19.self_attn.out_proj.bias": "pytorch_model-00004-of-00004.bin",
677
+ "vision_encoder.vision_model.encoder.layers.19.self_attn.out_proj.weight": "pytorch_model-00004-of-00004.bin",
678
+ "vision_encoder.vision_model.encoder.layers.19.self_attn.q_proj.bias": "pytorch_model-00004-of-00004.bin",
679
+ "vision_encoder.vision_model.encoder.layers.19.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
680
+ "vision_encoder.vision_model.encoder.layers.19.self_attn.v_proj.bias": "pytorch_model-00004-of-00004.bin",
681
+ "vision_encoder.vision_model.encoder.layers.19.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
682
+ "vision_encoder.vision_model.encoder.layers.2.layer_norm1.bias": "pytorch_model-00004-of-00004.bin",
683
+ "vision_encoder.vision_model.encoder.layers.2.layer_norm1.weight": "pytorch_model-00004-of-00004.bin",
684
+ "vision_encoder.vision_model.encoder.layers.2.layer_norm2.bias": "pytorch_model-00004-of-00004.bin",
685
+ "vision_encoder.vision_model.encoder.layers.2.layer_norm2.weight": "pytorch_model-00004-of-00004.bin",
686
+ "vision_encoder.vision_model.encoder.layers.2.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
687
+ "vision_encoder.vision_model.encoder.layers.2.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
688
+ "vision_encoder.vision_model.encoder.layers.2.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
689
+ "vision_encoder.vision_model.encoder.layers.2.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
690
+ "vision_encoder.vision_model.encoder.layers.2.self_attn.k_proj.bias": "pytorch_model-00004-of-00004.bin",
691
+ "vision_encoder.vision_model.encoder.layers.2.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
692
+ "vision_encoder.vision_model.encoder.layers.2.self_attn.out_proj.bias": "pytorch_model-00004-of-00004.bin",
693
+ "vision_encoder.vision_model.encoder.layers.2.self_attn.out_proj.weight": "pytorch_model-00004-of-00004.bin",
694
+ "vision_encoder.vision_model.encoder.layers.2.self_attn.q_proj.bias": "pytorch_model-00004-of-00004.bin",
695
+ "vision_encoder.vision_model.encoder.layers.2.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
696
+ "vision_encoder.vision_model.encoder.layers.2.self_attn.v_proj.bias": "pytorch_model-00004-of-00004.bin",
697
+ "vision_encoder.vision_model.encoder.layers.2.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
698
+ "vision_encoder.vision_model.encoder.layers.20.layer_norm1.bias": "pytorch_model-00004-of-00004.bin",
699
+ "vision_encoder.vision_model.encoder.layers.20.layer_norm1.weight": "pytorch_model-00004-of-00004.bin",
700
+ "vision_encoder.vision_model.encoder.layers.20.layer_norm2.bias": "pytorch_model-00004-of-00004.bin",
701
+ "vision_encoder.vision_model.encoder.layers.20.layer_norm2.weight": "pytorch_model-00004-of-00004.bin",
702
+ "vision_encoder.vision_model.encoder.layers.20.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
703
+ "vision_encoder.vision_model.encoder.layers.20.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
704
+ "vision_encoder.vision_model.encoder.layers.20.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
705
+ "vision_encoder.vision_model.encoder.layers.20.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
706
+ "vision_encoder.vision_model.encoder.layers.20.self_attn.k_proj.bias": "pytorch_model-00004-of-00004.bin",
707
+ "vision_encoder.vision_model.encoder.layers.20.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
708
+ "vision_encoder.vision_model.encoder.layers.20.self_attn.out_proj.bias": "pytorch_model-00004-of-00004.bin",
709
+ "vision_encoder.vision_model.encoder.layers.20.self_attn.out_proj.weight": "pytorch_model-00004-of-00004.bin",
710
+ "vision_encoder.vision_model.encoder.layers.20.self_attn.q_proj.bias": "pytorch_model-00004-of-00004.bin",
711
+ "vision_encoder.vision_model.encoder.layers.20.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
712
+ "vision_encoder.vision_model.encoder.layers.20.self_attn.v_proj.bias": "pytorch_model-00004-of-00004.bin",
713
+ "vision_encoder.vision_model.encoder.layers.20.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
714
+ "vision_encoder.vision_model.encoder.layers.21.layer_norm1.bias": "pytorch_model-00004-of-00004.bin",
715
+ "vision_encoder.vision_model.encoder.layers.21.layer_norm1.weight": "pytorch_model-00004-of-00004.bin",
716
+ "vision_encoder.vision_model.encoder.layers.21.layer_norm2.bias": "pytorch_model-00004-of-00004.bin",
717
+ "vision_encoder.vision_model.encoder.layers.21.layer_norm2.weight": "pytorch_model-00004-of-00004.bin",
718
+ "vision_encoder.vision_model.encoder.layers.21.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
719
+ "vision_encoder.vision_model.encoder.layers.21.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
720
+ "vision_encoder.vision_model.encoder.layers.21.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
721
+ "vision_encoder.vision_model.encoder.layers.21.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
722
+ "vision_encoder.vision_model.encoder.layers.21.self_attn.k_proj.bias": "pytorch_model-00004-of-00004.bin",
723
+ "vision_encoder.vision_model.encoder.layers.21.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
724
+ "vision_encoder.vision_model.encoder.layers.21.self_attn.out_proj.bias": "pytorch_model-00004-of-00004.bin",
725
+ "vision_encoder.vision_model.encoder.layers.21.self_attn.out_proj.weight": "pytorch_model-00004-of-00004.bin",
726
+ "vision_encoder.vision_model.encoder.layers.21.self_attn.q_proj.bias": "pytorch_model-00004-of-00004.bin",
727
+ "vision_encoder.vision_model.encoder.layers.21.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
728
+ "vision_encoder.vision_model.encoder.layers.21.self_attn.v_proj.bias": "pytorch_model-00004-of-00004.bin",
729
+ "vision_encoder.vision_model.encoder.layers.21.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
730
+ "vision_encoder.vision_model.encoder.layers.22.layer_norm1.bias": "pytorch_model-00004-of-00004.bin",
731
+ "vision_encoder.vision_model.encoder.layers.22.layer_norm1.weight": "pytorch_model-00004-of-00004.bin",
732
+ "vision_encoder.vision_model.encoder.layers.22.layer_norm2.bias": "pytorch_model-00004-of-00004.bin",
733
+ "vision_encoder.vision_model.encoder.layers.22.layer_norm2.weight": "pytorch_model-00004-of-00004.bin",
734
+ "vision_encoder.vision_model.encoder.layers.22.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
735
+ "vision_encoder.vision_model.encoder.layers.22.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
736
+ "vision_encoder.vision_model.encoder.layers.22.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
737
+ "vision_encoder.vision_model.encoder.layers.22.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
738
+ "vision_encoder.vision_model.encoder.layers.22.self_attn.k_proj.bias": "pytorch_model-00004-of-00004.bin",
739
+ "vision_encoder.vision_model.encoder.layers.22.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
740
+ "vision_encoder.vision_model.encoder.layers.22.self_attn.out_proj.bias": "pytorch_model-00004-of-00004.bin",
741
+ "vision_encoder.vision_model.encoder.layers.22.self_attn.out_proj.weight": "pytorch_model-00004-of-00004.bin",
742
+ "vision_encoder.vision_model.encoder.layers.22.self_attn.q_proj.bias": "pytorch_model-00004-of-00004.bin",
743
+ "vision_encoder.vision_model.encoder.layers.22.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
744
+ "vision_encoder.vision_model.encoder.layers.22.self_attn.v_proj.bias": "pytorch_model-00004-of-00004.bin",
745
+ "vision_encoder.vision_model.encoder.layers.22.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
746
+ "vision_encoder.vision_model.encoder.layers.23.layer_norm1.bias": "pytorch_model-00004-of-00004.bin",
747
+ "vision_encoder.vision_model.encoder.layers.23.layer_norm1.weight": "pytorch_model-00004-of-00004.bin",
748
+ "vision_encoder.vision_model.encoder.layers.23.layer_norm2.bias": "pytorch_model-00004-of-00004.bin",
749
+ "vision_encoder.vision_model.encoder.layers.23.layer_norm2.weight": "pytorch_model-00004-of-00004.bin",
750
+ "vision_encoder.vision_model.encoder.layers.23.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
751
+ "vision_encoder.vision_model.encoder.layers.23.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
752
+ "vision_encoder.vision_model.encoder.layers.23.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
753
+ "vision_encoder.vision_model.encoder.layers.23.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
754
+ "vision_encoder.vision_model.encoder.layers.23.self_attn.k_proj.bias": "pytorch_model-00004-of-00004.bin",
755
+ "vision_encoder.vision_model.encoder.layers.23.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
756
+ "vision_encoder.vision_model.encoder.layers.23.self_attn.out_proj.bias": "pytorch_model-00004-of-00004.bin",
757
+ "vision_encoder.vision_model.encoder.layers.23.self_attn.out_proj.weight": "pytorch_model-00004-of-00004.bin",
758
+ "vision_encoder.vision_model.encoder.layers.23.self_attn.q_proj.bias": "pytorch_model-00004-of-00004.bin",
759
+ "vision_encoder.vision_model.encoder.layers.23.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
760
+ "vision_encoder.vision_model.encoder.layers.23.self_attn.v_proj.bias": "pytorch_model-00004-of-00004.bin",
761
+ "vision_encoder.vision_model.encoder.layers.23.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
762
+ "vision_encoder.vision_model.encoder.layers.3.layer_norm1.bias": "pytorch_model-00004-of-00004.bin",
763
+ "vision_encoder.vision_model.encoder.layers.3.layer_norm1.weight": "pytorch_model-00004-of-00004.bin",
764
+ "vision_encoder.vision_model.encoder.layers.3.layer_norm2.bias": "pytorch_model-00004-of-00004.bin",
765
+ "vision_encoder.vision_model.encoder.layers.3.layer_norm2.weight": "pytorch_model-00004-of-00004.bin",
766
+ "vision_encoder.vision_model.encoder.layers.3.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
767
+ "vision_encoder.vision_model.encoder.layers.3.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
768
+ "vision_encoder.vision_model.encoder.layers.3.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
769
+ "vision_encoder.vision_model.encoder.layers.3.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
770
+ "vision_encoder.vision_model.encoder.layers.3.self_attn.k_proj.bias": "pytorch_model-00004-of-00004.bin",
771
+ "vision_encoder.vision_model.encoder.layers.3.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
772
+ "vision_encoder.vision_model.encoder.layers.3.self_attn.out_proj.bias": "pytorch_model-00004-of-00004.bin",
773
+ "vision_encoder.vision_model.encoder.layers.3.self_attn.out_proj.weight": "pytorch_model-00004-of-00004.bin",
774
+ "vision_encoder.vision_model.encoder.layers.3.self_attn.q_proj.bias": "pytorch_model-00004-of-00004.bin",
775
+ "vision_encoder.vision_model.encoder.layers.3.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
776
+ "vision_encoder.vision_model.encoder.layers.3.self_attn.v_proj.bias": "pytorch_model-00004-of-00004.bin",
777
+ "vision_encoder.vision_model.encoder.layers.3.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
778
+ "vision_encoder.vision_model.encoder.layers.4.layer_norm1.bias": "pytorch_model-00004-of-00004.bin",
779
+ "vision_encoder.vision_model.encoder.layers.4.layer_norm1.weight": "pytorch_model-00004-of-00004.bin",
780
+ "vision_encoder.vision_model.encoder.layers.4.layer_norm2.bias": "pytorch_model-00004-of-00004.bin",
781
+ "vision_encoder.vision_model.encoder.layers.4.layer_norm2.weight": "pytorch_model-00004-of-00004.bin",
782
+ "vision_encoder.vision_model.encoder.layers.4.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
783
+ "vision_encoder.vision_model.encoder.layers.4.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
784
+ "vision_encoder.vision_model.encoder.layers.4.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
785
+ "vision_encoder.vision_model.encoder.layers.4.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
786
+ "vision_encoder.vision_model.encoder.layers.4.self_attn.k_proj.bias": "pytorch_model-00004-of-00004.bin",
787
+ "vision_encoder.vision_model.encoder.layers.4.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
788
+ "vision_encoder.vision_model.encoder.layers.4.self_attn.out_proj.bias": "pytorch_model-00004-of-00004.bin",
789
+ "vision_encoder.vision_model.encoder.layers.4.self_attn.out_proj.weight": "pytorch_model-00004-of-00004.bin",
790
+ "vision_encoder.vision_model.encoder.layers.4.self_attn.q_proj.bias": "pytorch_model-00004-of-00004.bin",
791
+ "vision_encoder.vision_model.encoder.layers.4.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
792
+ "vision_encoder.vision_model.encoder.layers.4.self_attn.v_proj.bias": "pytorch_model-00004-of-00004.bin",
793
+ "vision_encoder.vision_model.encoder.layers.4.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
794
+ "vision_encoder.vision_model.encoder.layers.5.layer_norm1.bias": "pytorch_model-00004-of-00004.bin",
795
+ "vision_encoder.vision_model.encoder.layers.5.layer_norm1.weight": "pytorch_model-00004-of-00004.bin",
796
+ "vision_encoder.vision_model.encoder.layers.5.layer_norm2.bias": "pytorch_model-00004-of-00004.bin",
797
+ "vision_encoder.vision_model.encoder.layers.5.layer_norm2.weight": "pytorch_model-00004-of-00004.bin",
798
+ "vision_encoder.vision_model.encoder.layers.5.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
799
+ "vision_encoder.vision_model.encoder.layers.5.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
800
+ "vision_encoder.vision_model.encoder.layers.5.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
801
+ "vision_encoder.vision_model.encoder.layers.5.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
802
+ "vision_encoder.vision_model.encoder.layers.5.self_attn.k_proj.bias": "pytorch_model-00004-of-00004.bin",
803
+ "vision_encoder.vision_model.encoder.layers.5.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
804
+ "vision_encoder.vision_model.encoder.layers.5.self_attn.out_proj.bias": "pytorch_model-00004-of-00004.bin",
805
+ "vision_encoder.vision_model.encoder.layers.5.self_attn.out_proj.weight": "pytorch_model-00004-of-00004.bin",
806
+ "vision_encoder.vision_model.encoder.layers.5.self_attn.q_proj.bias": "pytorch_model-00004-of-00004.bin",
807
+ "vision_encoder.vision_model.encoder.layers.5.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
808
+ "vision_encoder.vision_model.encoder.layers.5.self_attn.v_proj.bias": "pytorch_model-00004-of-00004.bin",
809
+ "vision_encoder.vision_model.encoder.layers.5.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
810
+ "vision_encoder.vision_model.encoder.layers.6.layer_norm1.bias": "pytorch_model-00004-of-00004.bin",
811
+ "vision_encoder.vision_model.encoder.layers.6.layer_norm1.weight": "pytorch_model-00004-of-00004.bin",
812
+ "vision_encoder.vision_model.encoder.layers.6.layer_norm2.bias": "pytorch_model-00004-of-00004.bin",
813
+ "vision_encoder.vision_model.encoder.layers.6.layer_norm2.weight": "pytorch_model-00004-of-00004.bin",
814
+ "vision_encoder.vision_model.encoder.layers.6.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
815
+ "vision_encoder.vision_model.encoder.layers.6.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
816
+ "vision_encoder.vision_model.encoder.layers.6.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
817
+ "vision_encoder.vision_model.encoder.layers.6.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
818
+ "vision_encoder.vision_model.encoder.layers.6.self_attn.k_proj.bias": "pytorch_model-00004-of-00004.bin",
819
+ "vision_encoder.vision_model.encoder.layers.6.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
820
+ "vision_encoder.vision_model.encoder.layers.6.self_attn.out_proj.bias": "pytorch_model-00004-of-00004.bin",
821
+ "vision_encoder.vision_model.encoder.layers.6.self_attn.out_proj.weight": "pytorch_model-00004-of-00004.bin",
822
+ "vision_encoder.vision_model.encoder.layers.6.self_attn.q_proj.bias": "pytorch_model-00004-of-00004.bin",
823
+ "vision_encoder.vision_model.encoder.layers.6.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
824
+ "vision_encoder.vision_model.encoder.layers.6.self_attn.v_proj.bias": "pytorch_model-00004-of-00004.bin",
825
+ "vision_encoder.vision_model.encoder.layers.6.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
826
+ "vision_encoder.vision_model.encoder.layers.7.layer_norm1.bias": "pytorch_model-00004-of-00004.bin",
827
+ "vision_encoder.vision_model.encoder.layers.7.layer_norm1.weight": "pytorch_model-00004-of-00004.bin",
828
+ "vision_encoder.vision_model.encoder.layers.7.layer_norm2.bias": "pytorch_model-00004-of-00004.bin",
829
+ "vision_encoder.vision_model.encoder.layers.7.layer_norm2.weight": "pytorch_model-00004-of-00004.bin",
830
+ "vision_encoder.vision_model.encoder.layers.7.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
831
+ "vision_encoder.vision_model.encoder.layers.7.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
832
+ "vision_encoder.vision_model.encoder.layers.7.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
833
+ "vision_encoder.vision_model.encoder.layers.7.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
834
+ "vision_encoder.vision_model.encoder.layers.7.self_attn.k_proj.bias": "pytorch_model-00004-of-00004.bin",
835
+ "vision_encoder.vision_model.encoder.layers.7.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
836
+ "vision_encoder.vision_model.encoder.layers.7.self_attn.out_proj.bias": "pytorch_model-00004-of-00004.bin",
837
+ "vision_encoder.vision_model.encoder.layers.7.self_attn.out_proj.weight": "pytorch_model-00004-of-00004.bin",
838
+ "vision_encoder.vision_model.encoder.layers.7.self_attn.q_proj.bias": "pytorch_model-00004-of-00004.bin",
839
+ "vision_encoder.vision_model.encoder.layers.7.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
840
+ "vision_encoder.vision_model.encoder.layers.7.self_attn.v_proj.bias": "pytorch_model-00004-of-00004.bin",
841
+ "vision_encoder.vision_model.encoder.layers.7.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
842
+ "vision_encoder.vision_model.encoder.layers.8.layer_norm1.bias": "pytorch_model-00004-of-00004.bin",
843
+ "vision_encoder.vision_model.encoder.layers.8.layer_norm1.weight": "pytorch_model-00004-of-00004.bin",
844
+ "vision_encoder.vision_model.encoder.layers.8.layer_norm2.bias": "pytorch_model-00004-of-00004.bin",
845
+ "vision_encoder.vision_model.encoder.layers.8.layer_norm2.weight": "pytorch_model-00004-of-00004.bin",
846
+ "vision_encoder.vision_model.encoder.layers.8.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
847
+ "vision_encoder.vision_model.encoder.layers.8.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
848
+ "vision_encoder.vision_model.encoder.layers.8.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
849
+ "vision_encoder.vision_model.encoder.layers.8.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
850
+ "vision_encoder.vision_model.encoder.layers.8.self_attn.k_proj.bias": "pytorch_model-00004-of-00004.bin",
851
+ "vision_encoder.vision_model.encoder.layers.8.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
852
+ "vision_encoder.vision_model.encoder.layers.8.self_attn.out_proj.bias": "pytorch_model-00004-of-00004.bin",
853
+ "vision_encoder.vision_model.encoder.layers.8.self_attn.out_proj.weight": "pytorch_model-00004-of-00004.bin",
854
+ "vision_encoder.vision_model.encoder.layers.8.self_attn.q_proj.bias": "pytorch_model-00004-of-00004.bin",
855
+ "vision_encoder.vision_model.encoder.layers.8.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
856
+ "vision_encoder.vision_model.encoder.layers.8.self_attn.v_proj.bias": "pytorch_model-00004-of-00004.bin",
857
+ "vision_encoder.vision_model.encoder.layers.8.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
858
+ "vision_encoder.vision_model.encoder.layers.9.layer_norm1.bias": "pytorch_model-00004-of-00004.bin",
859
+ "vision_encoder.vision_model.encoder.layers.9.layer_norm1.weight": "pytorch_model-00004-of-00004.bin",
860
+ "vision_encoder.vision_model.encoder.layers.9.layer_norm2.bias": "pytorch_model-00004-of-00004.bin",
861
+ "vision_encoder.vision_model.encoder.layers.9.layer_norm2.weight": "pytorch_model-00004-of-00004.bin",
862
+ "vision_encoder.vision_model.encoder.layers.9.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
863
+ "vision_encoder.vision_model.encoder.layers.9.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
864
+ "vision_encoder.vision_model.encoder.layers.9.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
865
+ "vision_encoder.vision_model.encoder.layers.9.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
866
+ "vision_encoder.vision_model.encoder.layers.9.self_attn.k_proj.bias": "pytorch_model-00004-of-00004.bin",
867
+ "vision_encoder.vision_model.encoder.layers.9.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
868
+ "vision_encoder.vision_model.encoder.layers.9.self_attn.out_proj.bias": "pytorch_model-00004-of-00004.bin",
869
+ "vision_encoder.vision_model.encoder.layers.9.self_attn.out_proj.weight": "pytorch_model-00004-of-00004.bin",
870
+ "vision_encoder.vision_model.encoder.layers.9.self_attn.q_proj.bias": "pytorch_model-00004-of-00004.bin",
871
+ "vision_encoder.vision_model.encoder.layers.9.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
872
+ "vision_encoder.vision_model.encoder.layers.9.self_attn.v_proj.bias": "pytorch_model-00004-of-00004.bin",
873
+ "vision_encoder.vision_model.encoder.layers.9.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
874
+ "vision_encoder.vision_model.post_layernorm.bias": "pytorch_model-00004-of-00004.bin",
875
+ "vision_encoder.vision_model.post_layernorm.weight": "pytorch_model-00004-of-00004.bin",
876
+ "vision_encoder.vision_model.pre_layrnorm.bias": "pytorch_model-00004-of-00004.bin",
877
+ "vision_encoder.vision_model.pre_layrnorm.weight": "pytorch_model-00004-of-00004.bin"
878
+ }
879
+ }