mjbuehler commited on
Commit
76d9c3c
1 Parent(s): 41edb19

Upload Phi3VForCausalLM

Browse files
README.md CHANGED
@@ -1,19 +1,19 @@
1
  ---
2
- license: apache-2.0
3
  language:
4
  - multilingual
5
- pipeline_tag: text-generation
6
  tags:
7
  - nlp
8
  - code
9
  - vision
 
10
  inference:
11
  parameters:
12
  temperature: 0.3
13
  widget:
14
- - messages:
15
- - role: user
16
- content: <|image_1|>Can you describe what you see in the image?
17
  ---
18
  ## Model Summary
19
 
 
1
  ---
 
2
  language:
3
  - multilingual
4
+ license: apache-2.0
5
  tags:
6
  - nlp
7
  - code
8
  - vision
9
+ pipeline_tag: text-generation
10
  inference:
11
  parameters:
12
  temperature: 0.3
13
  widget:
14
+ - messages:
15
+ - role: user
16
+ content: <|image_1|>Can you describe what you see in the image?
17
  ---
18
  ## Model Summary
19
 
config.json ADDED
@@ -0,0 +1,150 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "lamm-mit/Phi3-Vision-128k-V200-checkpoint-3862-merged",
3
+ "architectures": [
4
+ "Phi3VForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "auto_map": {
8
+ "AutoConfig": "microsoft/Phi-3-vision-128k-instruct--configuration_phi3_v.Phi3VConfig",
9
+ "AutoModelForCausalLM": "microsoft/Phi-3-vision-128k-instruct--modeling_phi3_v.Phi3VForCausalLM"
10
+ },
11
+ "bos_token_id": 1,
12
+ "embd_layer": {
13
+ "embedding_cls": "image",
14
+ "hd_transform_order": "sub_glb",
15
+ "projection_cls": "mlp",
16
+ "use_hd_transform": true,
17
+ "with_learnable_separator": true
18
+ },
19
+ "embd_pdrop": 0.0,
20
+ "eos_token_id": 2,
21
+ "hidden_act": "silu",
22
+ "hidden_size": 3072,
23
+ "img_processor": {
24
+ "image_dim_out": 1024,
25
+ "model_name": "openai/clip-vit-large-patch14-336",
26
+ "name": "clip_vision_model",
27
+ "num_img_tokens": 144
28
+ },
29
+ "initializer_range": 0.02,
30
+ "intermediate_size": 8192,
31
+ "max_position_embeddings": 131072,
32
+ "model_type": "phi3_v",
33
+ "num_attention_heads": 32,
34
+ "num_hidden_layers": 32,
35
+ "num_key_value_heads": 32,
36
+ "original_max_position_embeddings": 4096,
37
+ "pad_token_id": 32000,
38
+ "resid_pdrop": 0.0,
39
+ "rms_norm_eps": 1e-05,
40
+ "rope_scaling": {
41
+ "long_factor": [
42
+ 1.0299999713897705,
43
+ 1.0499999523162842,
44
+ 1.0499999523162842,
45
+ 1.0799999237060547,
46
+ 1.2299998998641968,
47
+ 1.2299998998641968,
48
+ 1.2999999523162842,
49
+ 1.4499999284744263,
50
+ 1.5999999046325684,
51
+ 1.6499998569488525,
52
+ 1.8999998569488525,
53
+ 2.859999895095825,
54
+ 3.68999981880188,
55
+ 5.419999599456787,
56
+ 5.489999771118164,
57
+ 5.489999771118164,
58
+ 9.09000015258789,
59
+ 11.579999923706055,
60
+ 15.65999984741211,
61
+ 15.769999504089355,
62
+ 15.789999961853027,
63
+ 18.360000610351562,
64
+ 21.989999771118164,
65
+ 23.079999923706055,
66
+ 30.009998321533203,
67
+ 32.35000228881836,
68
+ 32.590003967285156,
69
+ 35.56000518798828,
70
+ 39.95000457763672,
71
+ 53.840003967285156,
72
+ 56.20000457763672,
73
+ 57.95000457763672,
74
+ 59.29000473022461,
75
+ 59.77000427246094,
76
+ 59.920005798339844,
77
+ 61.190006256103516,
78
+ 61.96000671386719,
79
+ 62.50000762939453,
80
+ 63.3700065612793,
81
+ 63.48000717163086,
82
+ 63.48000717163086,
83
+ 63.66000747680664,
84
+ 63.850006103515625,
85
+ 64.08000946044922,
86
+ 64.760009765625,
87
+ 64.80001068115234,
88
+ 64.81001281738281,
89
+ 64.81001281738281
90
+ ],
91
+ "short_factor": [
92
+ 1.05,
93
+ 1.05,
94
+ 1.05,
95
+ 1.1,
96
+ 1.1,
97
+ 1.1,
98
+ 1.2500000000000002,
99
+ 1.2500000000000002,
100
+ 1.4000000000000004,
101
+ 1.4500000000000004,
102
+ 1.5500000000000005,
103
+ 1.8500000000000008,
104
+ 1.9000000000000008,
105
+ 2.000000000000001,
106
+ 2.000000000000001,
107
+ 2.000000000000001,
108
+ 2.000000000000001,
109
+ 2.000000000000001,
110
+ 2.000000000000001,
111
+ 2.000000000000001,
112
+ 2.000000000000001,
113
+ 2.000000000000001,
114
+ 2.000000000000001,
115
+ 2.000000000000001,
116
+ 2.000000000000001,
117
+ 2.000000000000001,
118
+ 2.000000000000001,
119
+ 2.000000000000001,
120
+ 2.000000000000001,
121
+ 2.000000000000001,
122
+ 2.000000000000001,
123
+ 2.000000000000001,
124
+ 2.1000000000000005,
125
+ 2.1000000000000005,
126
+ 2.2,
127
+ 2.3499999999999996,
128
+ 2.3499999999999996,
129
+ 2.3499999999999996,
130
+ 2.3499999999999996,
131
+ 2.3999999999999995,
132
+ 2.3999999999999995,
133
+ 2.6499999999999986,
134
+ 2.6999999999999984,
135
+ 2.8999999999999977,
136
+ 2.9499999999999975,
137
+ 3.049999999999997,
138
+ 3.049999999999997,
139
+ 3.049999999999997
140
+ ],
141
+ "type": "su"
142
+ },
143
+ "rope_theta": 10000.0,
144
+ "sliding_window": 131072,
145
+ "tie_word_embeddings": false,
146
+ "torch_dtype": "bfloat16",
147
+ "transformers_version": "4.42.0.dev0",
148
+ "use_cache": true,
149
+ "vocab_size": 32064
150
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 32000,
6
+ "transformers_version": "4.42.0.dev0"
7
+ }
pytorch_model-00001-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9284b076b7140ac0b11e07f5a36ad02d374cf099e1f9dc463a6a9aaf938bf8a
3
+ size 4944243099
pytorch_model-00002-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38463f3c6735ac5e1d78e9bb21ea6877db0b41b491018c2a0dc9f42517a25463
3
+ size 3349229092
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,600 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 8293242880
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00002-of-00002.bin",
7
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
8
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
9
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
10
+ "model.layers.0.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00002.bin",
11
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
12
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
13
+ "model.layers.0.self_attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
14
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
15
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
16
+ "model.layers.1.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00002.bin",
17
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
18
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
19
+ "model.layers.1.self_attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
20
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
21
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
22
+ "model.layers.10.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00002.bin",
23
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
24
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
25
+ "model.layers.10.self_attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
26
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
27
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
28
+ "model.layers.11.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00002.bin",
29
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
30
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
31
+ "model.layers.11.self_attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
32
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
33
+ "model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
34
+ "model.layers.12.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00002.bin",
35
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
36
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
37
+ "model.layers.12.self_attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
38
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
39
+ "model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
40
+ "model.layers.13.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00002.bin",
41
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
42
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
43
+ "model.layers.13.self_attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
44
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
45
+ "model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
46
+ "model.layers.14.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00002.bin",
47
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
48
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
49
+ "model.layers.14.self_attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
50
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
51
+ "model.layers.15.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
52
+ "model.layers.15.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00002.bin",
53
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
54
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
55
+ "model.layers.15.self_attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
56
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
57
+ "model.layers.16.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
58
+ "model.layers.16.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00002.bin",
59
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
60
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
61
+ "model.layers.16.self_attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
62
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
63
+ "model.layers.17.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
64
+ "model.layers.17.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00002.bin",
65
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
66
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
67
+ "model.layers.17.self_attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
68
+ "model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
69
+ "model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
70
+ "model.layers.18.mlp.gate_up_proj.weight": "pytorch_model-00002-of-00002.bin",
71
+ "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
72
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
73
+ "model.layers.18.self_attn.qkv_proj.weight": "pytorch_model-00002-of-00002.bin",
74
+ "model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
75
+ "model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
76
+ "model.layers.19.mlp.gate_up_proj.weight": "pytorch_model-00002-of-00002.bin",
77
+ "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
78
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
79
+ "model.layers.19.self_attn.qkv_proj.weight": "pytorch_model-00002-of-00002.bin",
80
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
81
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
82
+ "model.layers.2.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00002.bin",
83
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
84
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
85
+ "model.layers.2.self_attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
86
+ "model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
87
+ "model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
88
+ "model.layers.20.mlp.gate_up_proj.weight": "pytorch_model-00002-of-00002.bin",
89
+ "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
90
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
91
+ "model.layers.20.self_attn.qkv_proj.weight": "pytorch_model-00002-of-00002.bin",
92
+ "model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
93
+ "model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
94
+ "model.layers.21.mlp.gate_up_proj.weight": "pytorch_model-00002-of-00002.bin",
95
+ "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
96
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
97
+ "model.layers.21.self_attn.qkv_proj.weight": "pytorch_model-00002-of-00002.bin",
98
+ "model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
99
+ "model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
100
+ "model.layers.22.mlp.gate_up_proj.weight": "pytorch_model-00002-of-00002.bin",
101
+ "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
102
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
103
+ "model.layers.22.self_attn.qkv_proj.weight": "pytorch_model-00002-of-00002.bin",
104
+ "model.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
105
+ "model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
106
+ "model.layers.23.mlp.gate_up_proj.weight": "pytorch_model-00002-of-00002.bin",
107
+ "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
108
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
109
+ "model.layers.23.self_attn.qkv_proj.weight": "pytorch_model-00002-of-00002.bin",
110
+ "model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
111
+ "model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
112
+ "model.layers.24.mlp.gate_up_proj.weight": "pytorch_model-00002-of-00002.bin",
113
+ "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
114
+ "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
115
+ "model.layers.24.self_attn.qkv_proj.weight": "pytorch_model-00002-of-00002.bin",
116
+ "model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
117
+ "model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
118
+ "model.layers.25.mlp.gate_up_proj.weight": "pytorch_model-00002-of-00002.bin",
119
+ "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
120
+ "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
121
+ "model.layers.25.self_attn.qkv_proj.weight": "pytorch_model-00002-of-00002.bin",
122
+ "model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
123
+ "model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
124
+ "model.layers.26.mlp.gate_up_proj.weight": "pytorch_model-00002-of-00002.bin",
125
+ "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
126
+ "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
127
+ "model.layers.26.self_attn.qkv_proj.weight": "pytorch_model-00002-of-00002.bin",
128
+ "model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
129
+ "model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
130
+ "model.layers.27.mlp.gate_up_proj.weight": "pytorch_model-00002-of-00002.bin",
131
+ "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
132
+ "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
133
+ "model.layers.27.self_attn.qkv_proj.weight": "pytorch_model-00002-of-00002.bin",
134
+ "model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
135
+ "model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
136
+ "model.layers.28.mlp.gate_up_proj.weight": "pytorch_model-00002-of-00002.bin",
137
+ "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
138
+ "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
139
+ "model.layers.28.self_attn.qkv_proj.weight": "pytorch_model-00002-of-00002.bin",
140
+ "model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
141
+ "model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
142
+ "model.layers.29.mlp.gate_up_proj.weight": "pytorch_model-00002-of-00002.bin",
143
+ "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
144
+ "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
145
+ "model.layers.29.self_attn.qkv_proj.weight": "pytorch_model-00002-of-00002.bin",
146
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
147
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
148
+ "model.layers.3.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00002.bin",
149
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
150
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
151
+ "model.layers.3.self_attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
152
+ "model.layers.30.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
153
+ "model.layers.30.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
154
+ "model.layers.30.mlp.gate_up_proj.weight": "pytorch_model-00002-of-00002.bin",
155
+ "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
156
+ "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
157
+ "model.layers.30.self_attn.qkv_proj.weight": "pytorch_model-00002-of-00002.bin",
158
+ "model.layers.31.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
159
+ "model.layers.31.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
160
+ "model.layers.31.mlp.gate_up_proj.weight": "pytorch_model-00002-of-00002.bin",
161
+ "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
162
+ "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
163
+ "model.layers.31.self_attn.qkv_proj.weight": "pytorch_model-00002-of-00002.bin",
164
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
165
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
166
+ "model.layers.4.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00002.bin",
167
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
168
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
169
+ "model.layers.4.self_attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
170
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
171
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
172
+ "model.layers.5.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00002.bin",
173
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
174
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
175
+ "model.layers.5.self_attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
176
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
177
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
178
+ "model.layers.6.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00002.bin",
179
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
180
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
181
+ "model.layers.6.self_attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
182
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
183
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
184
+ "model.layers.7.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00002.bin",
185
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
186
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
187
+ "model.layers.7.self_attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
188
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
189
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
190
+ "model.layers.8.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00002.bin",
191
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
192
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
193
+ "model.layers.8.self_attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
194
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
195
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
196
+ "model.layers.9.mlp.gate_up_proj.weight": "pytorch_model-00001-of-00002.bin",
197
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
198
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
199
+ "model.layers.9.self_attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
200
+ "model.norm.weight": "pytorch_model-00002-of-00002.bin",
201
+ "model.vision_embed_tokens.glb_GN": "pytorch_model-00001-of-00002.bin",
202
+ "model.vision_embed_tokens.img_processor.vision_model.embeddings.class_embedding": "pytorch_model-00001-of-00002.bin",
203
+ "model.vision_embed_tokens.img_processor.vision_model.embeddings.patch_embedding.weight": "pytorch_model-00001-of-00002.bin",
204
+ "model.vision_embed_tokens.img_processor.vision_model.embeddings.position_embedding.weight": "pytorch_model-00001-of-00002.bin",
205
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.0.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
206
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.0.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
207
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.0.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
208
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.0.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
209
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.0.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
210
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.0.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
211
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.0.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
212
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.0.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
213
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.0.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
214
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
215
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.0.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
216
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.0.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
217
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.0.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
218
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
219
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.0.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
220
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
221
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.1.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
222
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.1.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
223
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.1.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
224
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.1.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
225
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.1.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
226
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.1.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
227
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.1.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
228
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.1.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
229
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.1.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
230
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
231
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.1.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
232
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.1.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
233
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.1.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
234
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
235
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.1.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
236
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
237
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.10.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
238
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.10.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
239
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.10.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
240
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.10.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
241
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.10.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
242
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.10.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
243
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.10.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
244
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.10.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
245
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.10.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
246
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
247
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.10.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
248
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.10.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
249
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.10.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
250
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
251
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.10.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
252
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
253
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.11.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
254
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.11.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
255
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.11.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
256
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.11.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
257
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.11.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
258
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.11.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
259
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.11.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
260
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.11.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
261
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.11.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
262
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
263
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.11.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
264
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.11.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
265
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.11.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
266
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
267
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.11.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
268
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
269
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.12.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
270
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.12.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
271
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.12.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
272
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.12.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
273
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.12.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
274
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.12.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
275
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.12.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
276
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.12.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
277
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.12.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
278
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
279
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.12.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
280
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.12.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
281
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.12.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
282
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
283
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.12.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
284
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
285
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.13.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
286
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.13.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
287
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.13.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
288
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.13.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
289
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.13.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
290
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.13.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
291
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.13.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
292
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.13.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
293
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.13.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
294
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
295
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.13.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
296
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.13.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
297
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.13.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
298
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
299
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.13.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
300
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
301
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.14.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
302
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.14.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
303
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.14.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
304
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.14.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
305
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.14.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
306
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.14.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
307
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.14.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
308
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.14.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
309
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.14.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
310
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
311
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.14.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
312
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.14.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
313
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.14.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
314
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
315
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.14.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
316
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
317
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.15.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
318
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.15.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
319
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.15.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
320
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.15.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
321
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.15.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
322
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.15.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
323
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.15.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
324
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.15.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
325
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.15.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
326
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
327
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.15.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
328
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.15.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
329
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.15.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
330
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
331
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.15.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
332
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
333
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.16.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
334
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.16.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
335
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.16.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
336
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.16.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
337
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.16.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
338
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.16.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
339
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.16.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
340
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.16.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
341
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.16.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
342
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
343
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.16.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
344
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.16.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
345
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.16.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
346
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
347
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.16.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
348
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
349
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.17.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
350
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.17.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
351
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.17.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
352
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.17.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
353
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.17.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
354
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.17.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
355
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.17.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
356
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.17.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
357
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.17.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
358
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
359
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.17.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
360
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.17.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
361
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.17.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
362
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
363
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.17.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
364
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
365
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.18.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
366
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.18.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
367
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.18.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
368
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.18.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
369
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.18.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
370
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.18.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
371
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.18.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
372
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.18.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
373
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.18.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
374
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
375
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.18.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
376
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.18.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
377
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.18.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
378
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
379
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.18.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
380
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
381
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.19.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
382
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.19.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
383
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.19.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
384
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.19.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
385
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.19.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
386
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.19.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
387
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.19.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
388
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.19.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
389
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.19.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
390
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
391
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.19.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
392
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.19.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
393
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.19.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
394
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
395
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.19.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
396
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
397
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.2.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
398
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.2.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
399
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.2.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
400
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.2.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
401
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.2.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
402
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.2.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
403
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.2.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
404
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.2.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
405
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.2.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
406
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
407
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.2.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
408
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.2.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
409
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.2.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
410
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
411
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.2.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
412
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
413
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.20.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
414
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.20.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
415
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.20.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
416
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.20.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
417
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.20.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
418
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.20.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
419
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.20.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
420
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.20.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
421
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.20.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
422
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
423
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.20.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
424
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.20.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
425
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.20.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
426
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
427
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.20.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
428
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
429
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.21.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
430
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.21.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
431
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.21.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
432
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.21.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
433
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.21.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
434
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.21.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
435
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.21.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
436
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.21.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
437
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.21.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
438
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.21.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
439
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.21.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
440
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.21.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
441
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.21.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
442
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.21.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
443
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.21.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
444
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.21.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
445
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.22.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
446
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.22.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
447
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.22.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
448
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.22.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
449
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.22.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
450
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.22.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
451
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.22.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
452
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.22.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
453
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.22.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
454
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.22.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
455
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.22.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
456
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.22.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
457
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.22.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
458
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.22.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
459
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.22.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
460
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.22.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
461
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.23.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
462
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.23.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
463
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.23.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
464
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.23.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
465
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.23.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
466
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.23.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
467
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.23.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
468
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.23.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
469
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.23.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
470
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.23.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
471
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.23.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
472
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.23.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
473
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.23.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
474
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.23.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
475
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.23.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
476
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.23.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
477
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.3.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
478
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.3.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
479
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.3.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
480
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.3.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
481
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.3.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
482
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.3.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
483
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.3.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
484
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.3.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
485
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.3.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
486
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
487
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.3.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
488
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.3.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
489
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.3.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
490
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
491
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.3.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
492
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
493
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.4.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
494
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.4.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
495
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.4.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
496
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.4.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
497
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.4.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
498
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.4.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
499
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.4.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
500
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.4.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
501
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.4.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
502
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
503
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.4.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
504
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.4.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
505
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.4.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
506
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
507
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.4.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
508
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
509
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.5.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
510
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.5.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
511
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.5.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
512
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.5.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
513
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.5.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
514
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.5.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
515
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.5.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
516
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.5.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
517
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.5.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
518
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
519
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.5.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
520
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.5.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
521
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.5.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
522
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
523
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.5.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
524
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
525
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.6.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
526
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.6.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
527
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.6.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
528
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.6.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
529
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.6.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
530
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.6.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
531
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.6.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
532
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.6.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
533
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.6.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
534
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
535
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.6.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
536
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.6.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
537
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.6.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
538
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
539
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.6.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
540
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
541
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.7.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
542
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.7.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
543
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.7.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
544
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.7.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
545
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.7.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
546
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.7.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
547
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.7.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
548
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.7.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
549
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.7.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
550
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
551
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.7.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
552
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.7.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
553
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.7.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
554
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
555
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.7.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
556
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
557
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.8.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
558
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.8.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
559
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.8.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
560
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.8.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
561
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.8.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
562
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.8.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
563
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.8.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
564
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.8.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
565
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.8.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
566
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
567
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.8.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
568
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.8.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
569
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.8.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
570
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
571
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.8.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
572
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
573
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.9.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
574
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.9.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
575
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.9.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
576
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.9.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
577
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.9.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
578
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.9.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
579
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.9.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
580
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.9.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
581
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.9.self_attn.k_proj.bias": "pytorch_model-00001-of-00002.bin",
582
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
583
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.9.self_attn.out_proj.bias": "pytorch_model-00001-of-00002.bin",
584
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.9.self_attn.out_proj.weight": "pytorch_model-00001-of-00002.bin",
585
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.9.self_attn.q_proj.bias": "pytorch_model-00001-of-00002.bin",
586
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
587
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.9.self_attn.v_proj.bias": "pytorch_model-00001-of-00002.bin",
588
+ "model.vision_embed_tokens.img_processor.vision_model.encoder.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
589
+ "model.vision_embed_tokens.img_processor.vision_model.post_layernorm.bias": "pytorch_model-00001-of-00002.bin",
590
+ "model.vision_embed_tokens.img_processor.vision_model.post_layernorm.weight": "pytorch_model-00001-of-00002.bin",
591
+ "model.vision_embed_tokens.img_processor.vision_model.pre_layrnorm.bias": "pytorch_model-00001-of-00002.bin",
592
+ "model.vision_embed_tokens.img_processor.vision_model.pre_layrnorm.weight": "pytorch_model-00001-of-00002.bin",
593
+ "model.vision_embed_tokens.img_projection.0.bias": "pytorch_model-00001-of-00002.bin",
594
+ "model.vision_embed_tokens.img_projection.0.weight": "pytorch_model-00001-of-00002.bin",
595
+ "model.vision_embed_tokens.img_projection.2.bias": "pytorch_model-00001-of-00002.bin",
596
+ "model.vision_embed_tokens.img_projection.2.weight": "pytorch_model-00001-of-00002.bin",
597
+ "model.vision_embed_tokens.sub_GN": "pytorch_model-00001-of-00002.bin",
598
+ "model.vision_embed_tokens.wte.weight": "pytorch_model-00001-of-00002.bin"
599
+ }
600
+ }