saxon commited on
Commit
dac7512
·
verified ·
1 Parent(s): 4728b64

Upload folder using huggingface_hub

Browse files
saxon/TEST-multillavafinal-vicuna-siglip-PT.l3e-5.d0.a0-S15.l0.d0.a0/checkpoint-lmfaooooo/meme.txt ADDED
File without changes
saxon/TEST-multillavafinal-vicuna-siglip-PT.l3e-5.d0.a0-S15.l0.d0.a0/config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "lmsys/vicuna-7b-v1.5",
3
+ "architectures": [
4
+ "MultiLlavaLlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "image_aspect_ratio": "square",
13
+ "image_crop_resolution": null,
14
+ "image_grid_pinpoints": null,
15
+ "image_split_resolution": null,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 11008,
18
+ "max_position_embeddings": 4096,
19
+ "mlp_bias": false,
20
+ "mm_hidden_size": 1152,
21
+ "mm_newline_position": "one_token",
22
+ "mm_patch_merge_type": "flat",
23
+ "mm_projector_lr": null,
24
+ "mm_projector_type": "mlp2x_gelu",
25
+ "mm_resampler_type": null,
26
+ "mm_spatial_pool_mode": "bilinear",
27
+ "mm_tunable_parts": "mm_mlp_adapter,mm_language_model",
28
+ "mm_use_im_patch_token": false,
29
+ "mm_use_im_start_end": false,
30
+ "mm_vision_select_feature": "patch",
31
+ "mm_vision_select_layer": -2,
32
+ "mm_vision_tower": "google/siglip-so400m-patch14-384",
33
+ "mm_vision_tower_lr": null,
34
+ "model_type": "llama",
35
+ "num_attention_heads": 32,
36
+ "num_hidden_layers": 32,
37
+ "num_key_value_heads": 32,
38
+ "pad_token_id": 0,
39
+ "pos_skipping_range": 4096,
40
+ "pretraining_tp": 1,
41
+ "rms_norm_eps": 1e-05,
42
+ "rope_scaling": null,
43
+ "rope_theta": 10000.0,
44
+ "tie_word_embeddings": false,
45
+ "tokenizer_model_max_length": 32768,
46
+ "tokenizer_padding_side": "right",
47
+ "torch_dtype": "bfloat16",
48
+ "transformers_version": "4.44.2",
49
+ "use_cache": true,
50
+ "use_mm_proj": true,
51
+ "use_pos_skipping": false,
52
+ "vision_tower_pretrained": null,
53
+ "vocab_size": 32000
54
+ }
saxon/TEST-multillavafinal-vicuna-siglip-PT.l3e-5.d0.a0-S15.l0.d0.a0/generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 1,
3
+ "eos_token_id": 2,
4
+ "max_length": 4096,
5
+ "pad_token_id": 0,
6
+ "temperature": 0.9,
7
+ "top_p": 0.6,
8
+ "transformers_version": "4.44.2"
9
+ }
saxon/TEST-multillavafinal-vicuna-siglip-PT.l3e-5.d0.a0-S15.l0.d0.a0/model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7f0e48fb6b18aad949c76f0f0ea889c063bc31f879e1c18e612ecdc8bdb3d17
3
+ size 4938985352
saxon/TEST-multillavafinal-vicuna-siglip-PT.l3e-5.d0.a0-S15.l0.d0.a0/model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcb5d3784ecc0ce1956fb463712c71980653b0ec684cf19ec818103d2fe31906
3
+ size 4947390880
saxon/TEST-multillavafinal-vicuna-siglip-PT.l3e-5.d0.a0-S15.l0.d0.a0/model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3d27e4e1e422f4a761ad6422e69d8a7452636cd165e41d6701320ad9c7064ce
3
+ size 4496184560
saxon/TEST-multillavafinal-vicuna-siglip-PT.l3e-5.d0.a0-S15.l0.d0.a0/model.safetensors.index.json ADDED
@@ -0,0 +1,727 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 14382459968
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00003-of-00003.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
242
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
243
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
244
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
245
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
246
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
247
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
248
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
249
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
250
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
251
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
252
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
253
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
254
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
255
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
256
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
257
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
258
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
259
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
260
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
261
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
262
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
263
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
264
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
265
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
266
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
267
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
268
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
269
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
270
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
271
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
272
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
273
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
274
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
275
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
276
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
277
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
278
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
279
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
280
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
281
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
282
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
283
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
284
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
285
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
286
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
287
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
288
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
289
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
290
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
291
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
292
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
293
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
294
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
295
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
296
+ "model.mm_output_projector.0.bias": "model-00003-of-00003.safetensors",
297
+ "model.mm_output_projector.0.weight": "model-00003-of-00003.safetensors",
298
+ "model.mm_output_projector.2.bias": "model-00003-of-00003.safetensors",
299
+ "model.mm_output_projector.2.weight": "model-00003-of-00003.safetensors",
300
+ "model.mm_projector.0.bias": "model-00003-of-00003.safetensors",
301
+ "model.mm_projector.0.weight": "model-00003-of-00003.safetensors",
302
+ "model.mm_projector.2.bias": "model-00003-of-00003.safetensors",
303
+ "model.mm_projector.2.weight": "model-00003-of-00003.safetensors",
304
+ "model.norm.weight": "model-00003-of-00003.safetensors",
305
+ "model.vision_tower.vision_tower.vision_model.embeddings.patch_embedding.bias": "model-00003-of-00003.safetensors",
306
+ "model.vision_tower.vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00003-of-00003.safetensors",
307
+ "model.vision_tower.vision_tower.vision_model.embeddings.position_embedding.weight": "model-00003-of-00003.safetensors",
308
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00003-of-00003.safetensors",
309
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00003-of-00003.safetensors",
310
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00003-of-00003.safetensors",
311
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00003-of-00003.safetensors",
312
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00003-of-00003.safetensors",
313
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00003-of-00003.safetensors",
314
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00003-of-00003.safetensors",
315
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00003-of-00003.safetensors",
316
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
317
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
318
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
319
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
320
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
321
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
322
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
323
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
324
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00003-of-00003.safetensors",
325
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00003-of-00003.safetensors",
326
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00003-of-00003.safetensors",
327
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00003-of-00003.safetensors",
328
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00003-of-00003.safetensors",
329
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00003-of-00003.safetensors",
330
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00003-of-00003.safetensors",
331
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00003-of-00003.safetensors",
332
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
333
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
334
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
335
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
336
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
337
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
338
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
339
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
340
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00003-of-00003.safetensors",
341
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00003-of-00003.safetensors",
342
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00003-of-00003.safetensors",
343
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00003-of-00003.safetensors",
344
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00003-of-00003.safetensors",
345
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00003-of-00003.safetensors",
346
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00003-of-00003.safetensors",
347
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00003-of-00003.safetensors",
348
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
349
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
350
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
351
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
352
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
353
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
354
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
355
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
356
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00003-of-00003.safetensors",
357
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00003-of-00003.safetensors",
358
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00003-of-00003.safetensors",
359
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00003-of-00003.safetensors",
360
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00003-of-00003.safetensors",
361
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00003-of-00003.safetensors",
362
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00003-of-00003.safetensors",
363
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00003-of-00003.safetensors",
364
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
365
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
366
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
367
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
368
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
369
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
370
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
371
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
372
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00003-of-00003.safetensors",
373
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00003-of-00003.safetensors",
374
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00003-of-00003.safetensors",
375
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00003-of-00003.safetensors",
376
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00003-of-00003.safetensors",
377
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00003-of-00003.safetensors",
378
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00003-of-00003.safetensors",
379
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00003-of-00003.safetensors",
380
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
381
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
382
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
383
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
384
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
385
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
386
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
387
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
388
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00003-of-00003.safetensors",
389
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00003-of-00003.safetensors",
390
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00003-of-00003.safetensors",
391
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00003-of-00003.safetensors",
392
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00003-of-00003.safetensors",
393
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00003-of-00003.safetensors",
394
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00003-of-00003.safetensors",
395
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00003-of-00003.safetensors",
396
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
397
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
398
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
399
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
400
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
401
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
402
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
403
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
404
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00003-of-00003.safetensors",
405
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00003-of-00003.safetensors",
406
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00003-of-00003.safetensors",
407
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00003-of-00003.safetensors",
408
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00003-of-00003.safetensors",
409
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00003-of-00003.safetensors",
410
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00003-of-00003.safetensors",
411
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00003-of-00003.safetensors",
412
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
413
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
414
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
415
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
416
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
417
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
418
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
419
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
420
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00003-of-00003.safetensors",
421
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00003-of-00003.safetensors",
422
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00003-of-00003.safetensors",
423
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00003-of-00003.safetensors",
424
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00003-of-00003.safetensors",
425
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00003-of-00003.safetensors",
426
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00003-of-00003.safetensors",
427
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00003-of-00003.safetensors",
428
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
429
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
430
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
431
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
432
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
433
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
434
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
435
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
436
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00003-of-00003.safetensors",
437
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00003-of-00003.safetensors",
438
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00003-of-00003.safetensors",
439
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00003-of-00003.safetensors",
440
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00003-of-00003.safetensors",
441
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00003-of-00003.safetensors",
442
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00003-of-00003.safetensors",
443
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00003-of-00003.safetensors",
444
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
445
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
446
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
447
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
448
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
449
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
450
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
451
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
452
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00003-of-00003.safetensors",
453
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00003-of-00003.safetensors",
454
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00003-of-00003.safetensors",
455
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00003-of-00003.safetensors",
456
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00003-of-00003.safetensors",
457
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00003-of-00003.safetensors",
458
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00003-of-00003.safetensors",
459
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00003-of-00003.safetensors",
460
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
461
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
462
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
463
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
464
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
465
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
466
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
467
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
468
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00003-of-00003.safetensors",
469
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00003-of-00003.safetensors",
470
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00003-of-00003.safetensors",
471
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00003-of-00003.safetensors",
472
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00003-of-00003.safetensors",
473
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00003-of-00003.safetensors",
474
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00003-of-00003.safetensors",
475
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00003-of-00003.safetensors",
476
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
477
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
478
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
479
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
480
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
481
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
482
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
483
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
484
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00003-of-00003.safetensors",
485
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00003-of-00003.safetensors",
486
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00003-of-00003.safetensors",
487
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00003-of-00003.safetensors",
488
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00003-of-00003.safetensors",
489
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00003-of-00003.safetensors",
490
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00003-of-00003.safetensors",
491
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00003-of-00003.safetensors",
492
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
493
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
494
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
495
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
496
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
497
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
498
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
499
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
500
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00003-of-00003.safetensors",
501
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00003-of-00003.safetensors",
502
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00003-of-00003.safetensors",
503
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00003-of-00003.safetensors",
504
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00003-of-00003.safetensors",
505
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00003-of-00003.safetensors",
506
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00003-of-00003.safetensors",
507
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00003-of-00003.safetensors",
508
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
509
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
510
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
511
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
512
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
513
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
514
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
515
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
516
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00003-of-00003.safetensors",
517
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00003-of-00003.safetensors",
518
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00003-of-00003.safetensors",
519
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00003-of-00003.safetensors",
520
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00003-of-00003.safetensors",
521
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00003-of-00003.safetensors",
522
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00003-of-00003.safetensors",
523
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00003-of-00003.safetensors",
524
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
525
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
526
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
527
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
528
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
529
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
530
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
531
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
532
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00003-of-00003.safetensors",
533
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00003-of-00003.safetensors",
534
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00003-of-00003.safetensors",
535
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00003-of-00003.safetensors",
536
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00003-of-00003.safetensors",
537
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00003-of-00003.safetensors",
538
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00003-of-00003.safetensors",
539
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00003-of-00003.safetensors",
540
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
541
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
542
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
543
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
544
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
545
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
546
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
547
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
548
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00003-of-00003.safetensors",
549
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00003-of-00003.safetensors",
550
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00003-of-00003.safetensors",
551
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00003-of-00003.safetensors",
552
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00003-of-00003.safetensors",
553
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00003-of-00003.safetensors",
554
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00003-of-00003.safetensors",
555
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00003-of-00003.safetensors",
556
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
557
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
558
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
559
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
560
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
561
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
562
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
563
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
564
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00003-of-00003.safetensors",
565
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00003-of-00003.safetensors",
566
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00003-of-00003.safetensors",
567
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00003-of-00003.safetensors",
568
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00003-of-00003.safetensors",
569
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00003-of-00003.safetensors",
570
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00003-of-00003.safetensors",
571
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00003-of-00003.safetensors",
572
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
573
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
574
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
575
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
576
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
577
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
578
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
579
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
580
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.layer_norm1.bias": "model-00003-of-00003.safetensors",
581
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.layer_norm1.weight": "model-00003-of-00003.safetensors",
582
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.layer_norm2.bias": "model-00003-of-00003.safetensors",
583
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.layer_norm2.weight": "model-00003-of-00003.safetensors",
584
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.mlp.fc1.bias": "model-00003-of-00003.safetensors",
585
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.mlp.fc1.weight": "model-00003-of-00003.safetensors",
586
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.mlp.fc2.bias": "model-00003-of-00003.safetensors",
587
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.mlp.fc2.weight": "model-00003-of-00003.safetensors",
588
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
589
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
590
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
591
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
592
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
593
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
594
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
595
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
596
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.layer_norm1.bias": "model-00003-of-00003.safetensors",
597
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.layer_norm1.weight": "model-00003-of-00003.safetensors",
598
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.layer_norm2.bias": "model-00003-of-00003.safetensors",
599
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.layer_norm2.weight": "model-00003-of-00003.safetensors",
600
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.mlp.fc1.bias": "model-00003-of-00003.safetensors",
601
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.mlp.fc1.weight": "model-00003-of-00003.safetensors",
602
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.mlp.fc2.bias": "model-00003-of-00003.safetensors",
603
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.mlp.fc2.weight": "model-00003-of-00003.safetensors",
604
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
605
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
606
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
607
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
608
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
609
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
610
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
611
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
612
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00003-of-00003.safetensors",
613
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00003-of-00003.safetensors",
614
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00003-of-00003.safetensors",
615
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00003-of-00003.safetensors",
616
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00003-of-00003.safetensors",
617
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00003-of-00003.safetensors",
618
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00003-of-00003.safetensors",
619
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00003-of-00003.safetensors",
620
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
621
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
622
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
623
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
624
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
625
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
626
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
627
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
628
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00003-of-00003.safetensors",
629
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00003-of-00003.safetensors",
630
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00003-of-00003.safetensors",
631
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00003-of-00003.safetensors",
632
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00003-of-00003.safetensors",
633
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00003-of-00003.safetensors",
634
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00003-of-00003.safetensors",
635
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00003-of-00003.safetensors",
636
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
637
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
638
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
639
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
640
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
641
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
642
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
643
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
644
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00003-of-00003.safetensors",
645
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00003-of-00003.safetensors",
646
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00003-of-00003.safetensors",
647
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00003-of-00003.safetensors",
648
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00003-of-00003.safetensors",
649
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00003-of-00003.safetensors",
650
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00003-of-00003.safetensors",
651
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00003-of-00003.safetensors",
652
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
653
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
654
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
655
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
656
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
657
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
658
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
659
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
660
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00003-of-00003.safetensors",
661
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00003-of-00003.safetensors",
662
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00003-of-00003.safetensors",
663
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00003-of-00003.safetensors",
664
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00003-of-00003.safetensors",
665
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00003-of-00003.safetensors",
666
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00003-of-00003.safetensors",
667
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00003-of-00003.safetensors",
668
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
669
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
670
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
671
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
672
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
673
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
674
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
675
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
676
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00003-of-00003.safetensors",
677
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00003-of-00003.safetensors",
678
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00003-of-00003.safetensors",
679
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00003-of-00003.safetensors",
680
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00003-of-00003.safetensors",
681
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00003-of-00003.safetensors",
682
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00003-of-00003.safetensors",
683
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00003-of-00003.safetensors",
684
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
685
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
686
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
687
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
688
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
689
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
690
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
691
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
692
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00003-of-00003.safetensors",
693
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00003-of-00003.safetensors",
694
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00003-of-00003.safetensors",
695
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00003-of-00003.safetensors",
696
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00003-of-00003.safetensors",
697
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00003-of-00003.safetensors",
698
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00003-of-00003.safetensors",
699
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00003-of-00003.safetensors",
700
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
701
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
702
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
703
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
704
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
705
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
706
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
707
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
708
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00003-of-00003.safetensors",
709
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00003-of-00003.safetensors",
710
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00003-of-00003.safetensors",
711
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00003-of-00003.safetensors",
712
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00003-of-00003.safetensors",
713
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00003-of-00003.safetensors",
714
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00003-of-00003.safetensors",
715
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00003-of-00003.safetensors",
716
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
717
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
718
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
719
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
720
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
721
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
722
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
723
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
724
+ "model.vision_tower.vision_tower.vision_model.post_layernorm.bias": "model-00003-of-00003.safetensors",
725
+ "model.vision_tower.vision_tower.vision_model.post_layernorm.weight": "model-00003-of-00003.safetensors"
726
+ }
727
+ }
saxon/TEST-multillavafinal-vicuna-siglip-PT.l3e-5.d0.a0-S15.l0.d0.a0/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<unk>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
saxon/TEST-multillavafinal-vicuna-siglip-PT.l3e-5.d0.a0-S15.l0.d0.a0/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
saxon/TEST-multillavafinal-vicuna-siglip-PT.l3e-5.d0.a0-S15.l0.d0.a0/tokenizer_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": true,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ }
30
+ },
31
+ "bos_token": "<s>",
32
+ "clean_up_tokenization_spaces": false,
33
+ "eos_token": "</s>",
34
+ "legacy": false,
35
+ "model_max_length": 32768,
36
+ "pad_token": "<unk>",
37
+ "padding_side": "right",
38
+ "sp_model_kwargs": {},
39
+ "spaces_between_special_tokens": false,
40
+ "tokenizer_class": "LlamaTokenizer",
41
+ "unk_token": "<unk>",
42
+ "use_default_system_prompt": false
43
+ }
saxon/TEST-multillavafinal-vicuna-siglip-PT.l3e-5.d0.a0-S15.l0.d0.a0/trainer_state.json ADDED
@@ -0,0 +1,791 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 5.63037021695023e-05,
5
+ "eval_steps": 500,
6
+ "global_step": 7,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0,
13
+ "lm_loss": 4.777355194091797,
14
+ "step": 0
15
+ },
16
+ {
17
+ "epoch": 0,
18
+ "img_loss": 1405.6251220703125,
19
+ "step": 0
20
+ },
21
+ {
22
+ "epoch": 0,
23
+ "img_emb_dist": 0.943795382976532,
24
+ "step": 0
25
+ },
26
+ {
27
+ "epoch": 0,
28
+ "img_divergence_loss": 0.0,
29
+ "step": 0
30
+ },
31
+ {
32
+ "activation_proximity_loss": 0.0,
33
+ "epoch": 0,
34
+ "step": 0
35
+ },
36
+ {
37
+ "epoch": 0,
38
+ "lm_loss": 3.757265567779541,
39
+ "step": 0
40
+ },
41
+ {
42
+ "epoch": 0,
43
+ "img_loss": 1323.5474853515625,
44
+ "step": 0
45
+ },
46
+ {
47
+ "epoch": 0,
48
+ "img_emb_dist": 0.9462753534317017,
49
+ "step": 0
50
+ },
51
+ {
52
+ "epoch": 0,
53
+ "img_divergence_loss": 0.0,
54
+ "step": 0
55
+ },
56
+ {
57
+ "activation_proximity_loss": 0.0,
58
+ "epoch": 0,
59
+ "step": 0
60
+ },
61
+ {
62
+ "epoch": 0,
63
+ "lm_loss": 3.2063961029052734,
64
+ "step": 0
65
+ },
66
+ {
67
+ "epoch": 0,
68
+ "img_loss": 1904.655029296875,
69
+ "step": 0
70
+ },
71
+ {
72
+ "epoch": 0,
73
+ "img_emb_dist": 0.9528577327728271,
74
+ "step": 0
75
+ },
76
+ {
77
+ "epoch": 0,
78
+ "img_divergence_loss": 0.0,
79
+ "step": 0
80
+ },
81
+ {
82
+ "activation_proximity_loss": 0.0,
83
+ "epoch": 0,
84
+ "step": 0
85
+ },
86
+ {
87
+ "epoch": 0,
88
+ "lm_loss": 4.04526424407959,
89
+ "step": 0
90
+ },
91
+ {
92
+ "epoch": 0,
93
+ "img_loss": 1414.7987060546875,
94
+ "step": 0
95
+ },
96
+ {
97
+ "epoch": 0,
98
+ "img_emb_dist": 0.9357076287269592,
99
+ "step": 0
100
+ },
101
+ {
102
+ "epoch": 0,
103
+ "img_divergence_loss": 0.0,
104
+ "step": 0
105
+ },
106
+ {
107
+ "activation_proximity_loss": 0.0,
108
+ "epoch": 0,
109
+ "step": 0
110
+ },
111
+ {
112
+ "epoch": 8.043386024214614e-06,
113
+ "grad_norm": 53.115646759579334,
114
+ "learning_rate": 1e-05,
115
+ "loss": 3.5947,
116
+ "step": 1
117
+ },
118
+ {
119
+ "epoch": 8.043386024214614e-06,
120
+ "lm_loss": 2.8514134883880615,
121
+ "step": 1
122
+ },
123
+ {
124
+ "epoch": 8.043386024214614e-06,
125
+ "img_loss": 1302.569091796875,
126
+ "step": 1
127
+ },
128
+ {
129
+ "epoch": 8.043386024214614e-06,
130
+ "img_emb_dist": 0.9393352270126343,
131
+ "step": 1
132
+ },
133
+ {
134
+ "epoch": 8.043386024214614e-06,
135
+ "img_divergence_loss": 0.0,
136
+ "step": 1
137
+ },
138
+ {
139
+ "activation_proximity_loss": 0.0,
140
+ "epoch": 8.043386024214614e-06,
141
+ "step": 1
142
+ },
143
+ {
144
+ "epoch": 8.043386024214614e-06,
145
+ "lm_loss": 4.075507164001465,
146
+ "step": 1
147
+ },
148
+ {
149
+ "epoch": 8.043386024214614e-06,
150
+ "img_loss": 1758.2935791015625,
151
+ "step": 1
152
+ },
153
+ {
154
+ "epoch": 8.043386024214614e-06,
155
+ "img_emb_dist": 0.9574013352394104,
156
+ "step": 1
157
+ },
158
+ {
159
+ "epoch": 8.043386024214614e-06,
160
+ "img_divergence_loss": 0.0,
161
+ "step": 1
162
+ },
163
+ {
164
+ "activation_proximity_loss": 0.0,
165
+ "epoch": 8.043386024214614e-06,
166
+ "step": 1
167
+ },
168
+ {
169
+ "epoch": 8.043386024214614e-06,
170
+ "lm_loss": 3.580430507659912,
171
+ "step": 1
172
+ },
173
+ {
174
+ "epoch": 8.043386024214614e-06,
175
+ "img_loss": 2152.185791015625,
176
+ "step": 1
177
+ },
178
+ {
179
+ "epoch": 8.043386024214614e-06,
180
+ "img_emb_dist": 0.9572040438652039,
181
+ "step": 1
182
+ },
183
+ {
184
+ "epoch": 8.043386024214614e-06,
185
+ "img_divergence_loss": 0.0,
186
+ "step": 1
187
+ },
188
+ {
189
+ "activation_proximity_loss": 0.0,
190
+ "epoch": 8.043386024214614e-06,
191
+ "step": 1
192
+ },
193
+ {
194
+ "epoch": 8.043386024214614e-06,
195
+ "lm_loss": 2.9565391540527344,
196
+ "step": 1
197
+ },
198
+ {
199
+ "epoch": 8.043386024214614e-06,
200
+ "img_loss": 1423.450439453125,
201
+ "step": 1
202
+ },
203
+ {
204
+ "epoch": 8.043386024214614e-06,
205
+ "img_emb_dist": 0.9312427639961243,
206
+ "step": 1
207
+ },
208
+ {
209
+ "epoch": 8.043386024214614e-06,
210
+ "img_divergence_loss": 0.0,
211
+ "step": 1
212
+ },
213
+ {
214
+ "activation_proximity_loss": 0.0,
215
+ "epoch": 8.043386024214614e-06,
216
+ "step": 1
217
+ },
218
+ {
219
+ "epoch": 1.6086772048429227e-05,
220
+ "grad_norm": 57.62378145706398,
221
+ "learning_rate": 8.535533905932739e-06,
222
+ "loss": 3.4772,
223
+ "step": 2
224
+ },
225
+ {
226
+ "epoch": 1.6086772048429227e-05,
227
+ "lm_loss": 0.19390703737735748,
228
+ "step": 2
229
+ },
230
+ {
231
+ "epoch": 1.6086772048429227e-05,
232
+ "img_loss": 0.0,
233
+ "step": 2
234
+ },
235
+ {
236
+ "epoch": 1.6086772048429227e-05,
237
+ "img_emb_dist": 0.0,
238
+ "step": 2
239
+ },
240
+ {
241
+ "epoch": 1.6086772048429227e-05,
242
+ "img_divergence_loss": 0.0,
243
+ "step": 2
244
+ },
245
+ {
246
+ "activation_proximity_loss": 0.0,
247
+ "epoch": 1.6086772048429227e-05,
248
+ "step": 2
249
+ },
250
+ {
251
+ "epoch": 1.6086772048429227e-05,
252
+ "lm_loss": 0.7974085807800293,
253
+ "step": 2
254
+ },
255
+ {
256
+ "epoch": 1.6086772048429227e-05,
257
+ "img_loss": 0.0,
258
+ "step": 2
259
+ },
260
+ {
261
+ "epoch": 1.6086772048429227e-05,
262
+ "img_emb_dist": 0.0,
263
+ "step": 2
264
+ },
265
+ {
266
+ "epoch": 1.6086772048429227e-05,
267
+ "img_divergence_loss": 0.0,
268
+ "step": 2
269
+ },
270
+ {
271
+ "activation_proximity_loss": 0.0,
272
+ "epoch": 1.6086772048429227e-05,
273
+ "step": 2
274
+ },
275
+ {
276
+ "epoch": 1.6086772048429227e-05,
277
+ "lm_loss": 0.8703616261482239,
278
+ "step": 2
279
+ },
280
+ {
281
+ "epoch": 1.6086772048429227e-05,
282
+ "img_loss": 0.0,
283
+ "step": 2
284
+ },
285
+ {
286
+ "epoch": 1.6086772048429227e-05,
287
+ "img_emb_dist": 0.0,
288
+ "step": 2
289
+ },
290
+ {
291
+ "epoch": 1.6086772048429227e-05,
292
+ "img_divergence_loss": 0.0,
293
+ "step": 2
294
+ },
295
+ {
296
+ "activation_proximity_loss": 0.0,
297
+ "epoch": 1.6086772048429227e-05,
298
+ "step": 2
299
+ },
300
+ {
301
+ "epoch": 1.6086772048429227e-05,
302
+ "lm_loss": 0.5038228631019592,
303
+ "step": 2
304
+ },
305
+ {
306
+ "epoch": 1.6086772048429227e-05,
307
+ "img_loss": 0.0,
308
+ "step": 2
309
+ },
310
+ {
311
+ "epoch": 1.6086772048429227e-05,
312
+ "img_emb_dist": 0.0,
313
+ "step": 2
314
+ },
315
+ {
316
+ "epoch": 1.6086772048429227e-05,
317
+ "img_divergence_loss": 0.0,
318
+ "step": 2
319
+ },
320
+ {
321
+ "activation_proximity_loss": 0.0,
322
+ "epoch": 1.6086772048429227e-05,
323
+ "step": 2
324
+ },
325
+ {
326
+ "epoch": 2.413015807264384e-05,
327
+ "grad_norm": 3.7870254263820486,
328
+ "learning_rate": 5e-06,
329
+ "loss": 0.6746,
330
+ "step": 3
331
+ },
332
+ {
333
+ "epoch": 2.413015807264384e-05,
334
+ "lm_loss": 1.237506628036499,
335
+ "step": 3
336
+ },
337
+ {
338
+ "epoch": 2.413015807264384e-05,
339
+ "img_loss": 1902.911376953125,
340
+ "step": 3
341
+ },
342
+ {
343
+ "epoch": 2.413015807264384e-05,
344
+ "img_emb_dist": 0.9367263913154602,
345
+ "step": 3
346
+ },
347
+ {
348
+ "epoch": 2.413015807264384e-05,
349
+ "img_divergence_loss": 0.0,
350
+ "step": 3
351
+ },
352
+ {
353
+ "activation_proximity_loss": 0.0,
354
+ "epoch": 2.413015807264384e-05,
355
+ "step": 3
356
+ },
357
+ {
358
+ "epoch": 2.413015807264384e-05,
359
+ "lm_loss": 2.4005985260009766,
360
+ "step": 3
361
+ },
362
+ {
363
+ "epoch": 2.413015807264384e-05,
364
+ "img_loss": 1548.7412109375,
365
+ "step": 3
366
+ },
367
+ {
368
+ "epoch": 2.413015807264384e-05,
369
+ "img_emb_dist": 0.9435941576957703,
370
+ "step": 3
371
+ },
372
+ {
373
+ "epoch": 2.413015807264384e-05,
374
+ "img_divergence_loss": 0.0,
375
+ "step": 3
376
+ },
377
+ {
378
+ "activation_proximity_loss": 0.0,
379
+ "epoch": 2.413015807264384e-05,
380
+ "step": 3
381
+ },
382
+ {
383
+ "epoch": 2.413015807264384e-05,
384
+ "lm_loss": 1.894577145576477,
385
+ "step": 3
386
+ },
387
+ {
388
+ "epoch": 2.413015807264384e-05,
389
+ "img_loss": 1771.75341796875,
390
+ "step": 3
391
+ },
392
+ {
393
+ "epoch": 2.413015807264384e-05,
394
+ "img_emb_dist": 0.934528112411499,
395
+ "step": 3
396
+ },
397
+ {
398
+ "epoch": 2.413015807264384e-05,
399
+ "img_divergence_loss": 0.0,
400
+ "step": 3
401
+ },
402
+ {
403
+ "activation_proximity_loss": 0.0,
404
+ "epoch": 2.413015807264384e-05,
405
+ "step": 3
406
+ },
407
+ {
408
+ "epoch": 2.413015807264384e-05,
409
+ "lm_loss": 2.4510209560394287,
410
+ "step": 3
411
+ },
412
+ {
413
+ "epoch": 2.413015807264384e-05,
414
+ "img_loss": 1807.8096923828125,
415
+ "step": 3
416
+ },
417
+ {
418
+ "epoch": 2.413015807264384e-05,
419
+ "img_emb_dist": 0.9483690857887268,
420
+ "step": 3
421
+ },
422
+ {
423
+ "epoch": 2.413015807264384e-05,
424
+ "img_divergence_loss": 0.0,
425
+ "step": 3
426
+ },
427
+ {
428
+ "activation_proximity_loss": 0.0,
429
+ "epoch": 2.413015807264384e-05,
430
+ "step": 3
431
+ },
432
+ {
433
+ "epoch": 3.2173544096858455e-05,
434
+ "grad_norm": 19.2665638835174,
435
+ "learning_rate": 1.4644660940672628e-06,
436
+ "loss": 2.4869,
437
+ "step": 4
438
+ },
439
+ {
440
+ "epoch": 3.2173544096858455e-05,
441
+ "lm_loss": 1.8891524076461792,
442
+ "step": 4
443
+ },
444
+ {
445
+ "epoch": 3.2173544096858455e-05,
446
+ "img_loss": 1784.0494384765625,
447
+ "step": 4
448
+ },
449
+ {
450
+ "epoch": 3.2173544096858455e-05,
451
+ "img_emb_dist": 0.9540425539016724,
452
+ "step": 4
453
+ },
454
+ {
455
+ "epoch": 3.2173544096858455e-05,
456
+ "img_divergence_loss": 0.0,
457
+ "step": 4
458
+ },
459
+ {
460
+ "activation_proximity_loss": 0.0,
461
+ "epoch": 3.2173544096858455e-05,
462
+ "step": 4
463
+ },
464
+ {
465
+ "epoch": 3.2173544096858455e-05,
466
+ "lm_loss": 1.705784797668457,
467
+ "step": 4
468
+ },
469
+ {
470
+ "epoch": 3.2173544096858455e-05,
471
+ "img_loss": 1783.939453125,
472
+ "step": 4
473
+ },
474
+ {
475
+ "epoch": 3.2173544096858455e-05,
476
+ "img_emb_dist": 0.9353492856025696,
477
+ "step": 4
478
+ },
479
+ {
480
+ "epoch": 3.2173544096858455e-05,
481
+ "img_divergence_loss": 0.0,
482
+ "step": 4
483
+ },
484
+ {
485
+ "activation_proximity_loss": 0.0,
486
+ "epoch": 3.2173544096858455e-05,
487
+ "step": 4
488
+ },
489
+ {
490
+ "epoch": 3.2173544096858455e-05,
491
+ "lm_loss": 2.147444725036621,
492
+ "step": 4
493
+ },
494
+ {
495
+ "epoch": 3.2173544096858455e-05,
496
+ "img_loss": 1771.144775390625,
497
+ "step": 4
498
+ },
499
+ {
500
+ "epoch": 3.2173544096858455e-05,
501
+ "img_emb_dist": 0.9475650191307068,
502
+ "step": 4
503
+ },
504
+ {
505
+ "epoch": 3.2173544096858455e-05,
506
+ "img_divergence_loss": 0.0,
507
+ "step": 4
508
+ },
509
+ {
510
+ "activation_proximity_loss": 0.0,
511
+ "epoch": 3.2173544096858455e-05,
512
+ "step": 4
513
+ },
514
+ {
515
+ "epoch": 3.2173544096858455e-05,
516
+ "lm_loss": 1.7766335010528564,
517
+ "step": 4
518
+ },
519
+ {
520
+ "epoch": 3.2173544096858455e-05,
521
+ "img_loss": 1739.290771484375,
522
+ "step": 4
523
+ },
524
+ {
525
+ "epoch": 3.2173544096858455e-05,
526
+ "img_emb_dist": 0.9212236404418945,
527
+ "step": 4
528
+ },
529
+ {
530
+ "epoch": 3.2173544096858455e-05,
531
+ "img_divergence_loss": 0.0,
532
+ "step": 4
533
+ },
534
+ {
535
+ "activation_proximity_loss": 0.0,
536
+ "epoch": 3.2173544096858455e-05,
537
+ "step": 4
538
+ },
539
+ {
540
+ "epoch": 4.0216930121073067e-05,
541
+ "grad_norm": 14.006965643325264,
542
+ "learning_rate": 0.0,
543
+ "loss": 1.9976,
544
+ "step": 5
545
+ },
546
+ {
547
+ "epoch": 4.0216930121073067e-05,
548
+ "lm_loss": 1.9023319482803345,
549
+ "step": 5
550
+ },
551
+ {
552
+ "epoch": 4.0216930121073067e-05,
553
+ "img_loss": 1372.74267578125,
554
+ "step": 5
555
+ },
556
+ {
557
+ "epoch": 4.0216930121073067e-05,
558
+ "img_emb_dist": 0.9299847483634949,
559
+ "step": 5
560
+ },
561
+ {
562
+ "epoch": 4.0216930121073067e-05,
563
+ "img_divergence_loss": 0.0,
564
+ "step": 5
565
+ },
566
+ {
567
+ "activation_proximity_loss": 0.0,
568
+ "epoch": 4.0216930121073067e-05,
569
+ "step": 5
570
+ },
571
+ {
572
+ "epoch": 4.0216930121073067e-05,
573
+ "lm_loss": 1.7631384134292603,
574
+ "step": 5
575
+ },
576
+ {
577
+ "epoch": 4.0216930121073067e-05,
578
+ "img_loss": 1376.963623046875,
579
+ "step": 5
580
+ },
581
+ {
582
+ "epoch": 4.0216930121073067e-05,
583
+ "img_emb_dist": 0.9451490640640259,
584
+ "step": 5
585
+ },
586
+ {
587
+ "epoch": 4.0216930121073067e-05,
588
+ "img_divergence_loss": 0.0,
589
+ "step": 5
590
+ },
591
+ {
592
+ "activation_proximity_loss": 0.0,
593
+ "epoch": 4.0216930121073067e-05,
594
+ "step": 5
595
+ },
596
+ {
597
+ "epoch": 4.0216930121073067e-05,
598
+ "lm_loss": 2.545454740524292,
599
+ "step": 5
600
+ },
601
+ {
602
+ "epoch": 4.0216930121073067e-05,
603
+ "img_loss": 1266.8668212890625,
604
+ "step": 5
605
+ },
606
+ {
607
+ "epoch": 4.0216930121073067e-05,
608
+ "img_emb_dist": 0.9414966702461243,
609
+ "step": 5
610
+ },
611
+ {
612
+ "epoch": 4.0216930121073067e-05,
613
+ "img_divergence_loss": 0.0,
614
+ "step": 5
615
+ },
616
+ {
617
+ "activation_proximity_loss": 0.0,
618
+ "epoch": 4.0216930121073067e-05,
619
+ "step": 5
620
+ },
621
+ {
622
+ "epoch": 4.0216930121073067e-05,
623
+ "lm_loss": 1.769309401512146,
624
+ "step": 5
625
+ },
626
+ {
627
+ "epoch": 4.0216930121073067e-05,
628
+ "img_loss": 1594.673583984375,
629
+ "step": 5
630
+ },
631
+ {
632
+ "epoch": 4.0216930121073067e-05,
633
+ "img_emb_dist": 0.9373501539230347,
634
+ "step": 5
635
+ },
636
+ {
637
+ "epoch": 4.0216930121073067e-05,
638
+ "img_divergence_loss": 0.0,
639
+ "step": 5
640
+ },
641
+ {
642
+ "activation_proximity_loss": 0.0,
643
+ "epoch": 4.0216930121073067e-05,
644
+ "step": 5
645
+ },
646
+ {
647
+ "epoch": 4.826031614528768e-05,
648
+ "grad_norm": 11.965095808038788,
649
+ "learning_rate": 1.4644660940672618e-06,
650
+ "loss": 2.0957,
651
+ "step": 6
652
+ },
653
+ {
654
+ "epoch": 4.826031614528768e-05,
655
+ "lm_loss": 1.9213221073150635,
656
+ "step": 6
657
+ },
658
+ {
659
+ "epoch": 4.826031614528768e-05,
660
+ "img_loss": 1426.7342529296875,
661
+ "step": 6
662
+ },
663
+ {
664
+ "epoch": 4.826031614528768e-05,
665
+ "img_emb_dist": 0.9336810111999512,
666
+ "step": 6
667
+ },
668
+ {
669
+ "epoch": 4.826031614528768e-05,
670
+ "img_divergence_loss": 0.0,
671
+ "step": 6
672
+ },
673
+ {
674
+ "activation_proximity_loss": 0.0,
675
+ "epoch": 4.826031614528768e-05,
676
+ "step": 6
677
+ },
678
+ {
679
+ "epoch": 4.826031614528768e-05,
680
+ "lm_loss": 2.145310640335083,
681
+ "step": 6
682
+ },
683
+ {
684
+ "epoch": 4.826031614528768e-05,
685
+ "img_loss": 1640.343994140625,
686
+ "step": 6
687
+ },
688
+ {
689
+ "epoch": 4.826031614528768e-05,
690
+ "img_emb_dist": 0.9372126460075378,
691
+ "step": 6
692
+ },
693
+ {
694
+ "epoch": 4.826031614528768e-05,
695
+ "img_divergence_loss": 0.0,
696
+ "step": 6
697
+ },
698
+ {
699
+ "activation_proximity_loss": 0.0,
700
+ "epoch": 4.826031614528768e-05,
701
+ "step": 6
702
+ },
703
+ {
704
+ "epoch": 4.826031614528768e-05,
705
+ "lm_loss": 1.8134715557098389,
706
+ "step": 6
707
+ },
708
+ {
709
+ "epoch": 4.826031614528768e-05,
710
+ "img_loss": 1271.497802734375,
711
+ "step": 6
712
+ },
713
+ {
714
+ "epoch": 4.826031614528768e-05,
715
+ "img_emb_dist": 0.9268760085105896,
716
+ "step": 6
717
+ },
718
+ {
719
+ "epoch": 4.826031614528768e-05,
720
+ "img_divergence_loss": 0.0,
721
+ "step": 6
722
+ },
723
+ {
724
+ "activation_proximity_loss": 0.0,
725
+ "epoch": 4.826031614528768e-05,
726
+ "step": 6
727
+ },
728
+ {
729
+ "epoch": 4.826031614528768e-05,
730
+ "lm_loss": 1.3229186534881592,
731
+ "step": 6
732
+ },
733
+ {
734
+ "epoch": 4.826031614528768e-05,
735
+ "img_loss": 1571.52197265625,
736
+ "step": 6
737
+ },
738
+ {
739
+ "epoch": 4.826031614528768e-05,
740
+ "img_emb_dist": 0.941112220287323,
741
+ "step": 6
742
+ },
743
+ {
744
+ "epoch": 4.826031614528768e-05,
745
+ "img_divergence_loss": 0.0,
746
+ "step": 6
747
+ },
748
+ {
749
+ "activation_proximity_loss": 0.0,
750
+ "epoch": 4.826031614528768e-05,
751
+ "step": 6
752
+ },
753
+ {
754
+ "epoch": 5.63037021695023e-05,
755
+ "grad_norm": 10.590198762752882,
756
+ "learning_rate": 4.9999999999999996e-06,
757
+ "loss": 1.9311,
758
+ "step": 7
759
+ },
760
+ {
761
+ "epoch": 5.63037021695023e-05,
762
+ "step": 7,
763
+ "total_flos": 1963044749312.0,
764
+ "train_loss": 0.2758768286023821,
765
+ "train_runtime": 107.7202,
766
+ "train_samples_per_second": 1.485,
767
+ "train_steps_per_second": 0.046
768
+ }
769
+ ],
770
+ "logging_steps": 1.0,
771
+ "max_steps": 5,
772
+ "num_input_tokens_seen": 0,
773
+ "num_train_epochs": 1,
774
+ "save_steps": 3000,
775
+ "stateful_callbacks": {
776
+ "TrainerControl": {
777
+ "args": {
778
+ "should_epoch_stop": false,
779
+ "should_evaluate": false,
780
+ "should_log": false,
781
+ "should_save": true,
782
+ "should_training_stop": true
783
+ },
784
+ "attributes": {}
785
+ }
786
+ },
787
+ "total_flos": 1963044749312.0,
788
+ "train_batch_size": 1,
789
+ "trial_name": null,
790
+ "trial_params": null
791
+ }
saxon/TEST-multillavafinal-vicuna-siglip-PT.l3e-5.d0.a0-S15.l0.d0.a0/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33808aec9e53eb64122854ae345005430bd6b007bc26547359d8014cc29eef02
3
+ size 8056