lakelee commited on
Commit
130f120
1 Parent(s): cb1c102

Model save

Browse files
README.md ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ base_model: state-spaces/mamba2-2.7b
5
+ tags:
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: video-ma2mba-3.1b-clip
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # video-ma2mba-3.1b-clip
16
+
17
+ This model is a fine-tuned version of [state-spaces/mamba2-2.7b](https://huggingface.co/state-spaces/mamba2-2.7b) on an unknown dataset.
18
+
19
+ ## Model description
20
+
21
+ More information needed
22
+
23
+ ## Intended uses & limitations
24
+
25
+ More information needed
26
+
27
+ ## Training and evaluation data
28
+
29
+ More information needed
30
+
31
+ ## Training procedure
32
+
33
+ ### Training hyperparameters
34
+
35
+ The following hyperparameters were used during training:
36
+ - learning_rate: 4e-05
37
+ - train_batch_size: 1
38
+ - eval_batch_size: 1
39
+ - seed: 42
40
+ - distributed_type: multi-GPU
41
+ - num_devices: 8
42
+ - gradient_accumulation_steps: 4
43
+ - total_train_batch_size: 32
44
+ - total_eval_batch_size: 8
45
+ - optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-08
46
+ - lr_scheduler_type: cosine
47
+ - lr_scheduler_warmup_ratio: 0.2
48
+ - num_epochs: 2.0
49
+
50
+ ### Training results
51
+
52
+
53
+
54
+ ### Framework versions
55
+
56
+ - Transformers 4.44.2
57
+ - Pytorch 2.1.2+cu121
58
+ - Datasets 2.16.1
59
+ - Tokenizers 0.19.1
config.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "state-spaces/mamba2-2.7b",
3
+ "add_faster_video": false,
4
+ "add_time_instruction": false,
5
+ "architectures": [
6
+ "LlavaMambaForCausalLM"
7
+ ],
8
+ "attn_cfg": {},
9
+ "attn_layer_idx": [],
10
+ "d_intermediate": 0,
11
+ "d_model": 2560,
12
+ "faster_token_stride": 10,
13
+ "force_sample": false,
14
+ "fused_add_norm": true,
15
+ "image_aspect_ratio": "square",
16
+ "image_crop_resolution": null,
17
+ "image_grid_pinpoints": null,
18
+ "image_split_resolution": null,
19
+ "label_top_k": 5,
20
+ "mm_hidden_size": 1024,
21
+ "mm_newline_position": "grid",
22
+ "mm_patch_merge_type": "flat",
23
+ "mm_projector_lr": null,
24
+ "mm_projector_type": "mlp2x_gelu",
25
+ "mm_spatial_pool_mode": "bilinear",
26
+ "mm_spatial_pool_stride": null,
27
+ "mm_tunable_parts": "mm_vision_tower,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": "openai/clip-vit-large-patch14",
33
+ "mm_vision_tower_lr": 4e-06,
34
+ "model_type": "llava_mamba",
35
+ "n_layer": 64,
36
+ "pad_vocab_size_multiple": 16,
37
+ "pos_skipping_range": 4096,
38
+ "residual_in_fp32": true,
39
+ "rms_norm": true,
40
+ "ssm_cfg": {
41
+ "layer": "Mamba2"
42
+ },
43
+ "tie_embeddings": true,
44
+ "tokenizer_model_max_length": 1048576,
45
+ "tokenizer_padding_side": "right",
46
+ "torch_dtype": "bfloat16",
47
+ "transformers_version": "4.44.2",
48
+ "use_cache": true,
49
+ "use_mm_proj": true,
50
+ "use_pos_skipping": false,
51
+ "vision_tower_pretrained": null,
52
+ "vocab_size": 50277
53
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d4430a5c514e4e12ad7e7d126078ba0aaa5cd03ed0831c4887246a74388b13d
3
+ size 4976871936
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d872b1d158bf9575e1f4f36c17ad2897735eb33c9034040aae49c03885a44ea4
3
+ size 1310647288
model.safetensors.index.json ADDED
@@ -0,0 +1,981 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 6287393792
4
+ },
5
+ "weight_map": {
6
+ "backbone.embedding.weight": "model-00001-of-00002.safetensors",
7
+ "backbone.layers.0.mixer.A_log": "model-00001-of-00002.safetensors",
8
+ "backbone.layers.0.mixer.D": "model-00001-of-00002.safetensors",
9
+ "backbone.layers.0.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
10
+ "backbone.layers.0.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
11
+ "backbone.layers.0.mixer.dt_bias": "model-00001-of-00002.safetensors",
12
+ "backbone.layers.0.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
13
+ "backbone.layers.0.mixer.norm.weight": "model-00001-of-00002.safetensors",
14
+ "backbone.layers.0.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
15
+ "backbone.layers.0.norm.weight": "model-00001-of-00002.safetensors",
16
+ "backbone.layers.1.mixer.A_log": "model-00001-of-00002.safetensors",
17
+ "backbone.layers.1.mixer.D": "model-00001-of-00002.safetensors",
18
+ "backbone.layers.1.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
19
+ "backbone.layers.1.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
20
+ "backbone.layers.1.mixer.dt_bias": "model-00001-of-00002.safetensors",
21
+ "backbone.layers.1.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
22
+ "backbone.layers.1.mixer.norm.weight": "model-00001-of-00002.safetensors",
23
+ "backbone.layers.1.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
24
+ "backbone.layers.1.norm.weight": "model-00001-of-00002.safetensors",
25
+ "backbone.layers.10.mixer.A_log": "model-00001-of-00002.safetensors",
26
+ "backbone.layers.10.mixer.D": "model-00001-of-00002.safetensors",
27
+ "backbone.layers.10.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
28
+ "backbone.layers.10.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
29
+ "backbone.layers.10.mixer.dt_bias": "model-00001-of-00002.safetensors",
30
+ "backbone.layers.10.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
31
+ "backbone.layers.10.mixer.norm.weight": "model-00001-of-00002.safetensors",
32
+ "backbone.layers.10.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
33
+ "backbone.layers.10.norm.weight": "model-00001-of-00002.safetensors",
34
+ "backbone.layers.11.mixer.A_log": "model-00001-of-00002.safetensors",
35
+ "backbone.layers.11.mixer.D": "model-00001-of-00002.safetensors",
36
+ "backbone.layers.11.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
37
+ "backbone.layers.11.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
38
+ "backbone.layers.11.mixer.dt_bias": "model-00001-of-00002.safetensors",
39
+ "backbone.layers.11.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
40
+ "backbone.layers.11.mixer.norm.weight": "model-00001-of-00002.safetensors",
41
+ "backbone.layers.11.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
42
+ "backbone.layers.11.norm.weight": "model-00001-of-00002.safetensors",
43
+ "backbone.layers.12.mixer.A_log": "model-00001-of-00002.safetensors",
44
+ "backbone.layers.12.mixer.D": "model-00001-of-00002.safetensors",
45
+ "backbone.layers.12.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
46
+ "backbone.layers.12.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
47
+ "backbone.layers.12.mixer.dt_bias": "model-00001-of-00002.safetensors",
48
+ "backbone.layers.12.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
49
+ "backbone.layers.12.mixer.norm.weight": "model-00001-of-00002.safetensors",
50
+ "backbone.layers.12.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
51
+ "backbone.layers.12.norm.weight": "model-00001-of-00002.safetensors",
52
+ "backbone.layers.13.mixer.A_log": "model-00001-of-00002.safetensors",
53
+ "backbone.layers.13.mixer.D": "model-00001-of-00002.safetensors",
54
+ "backbone.layers.13.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
55
+ "backbone.layers.13.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
56
+ "backbone.layers.13.mixer.dt_bias": "model-00001-of-00002.safetensors",
57
+ "backbone.layers.13.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
58
+ "backbone.layers.13.mixer.norm.weight": "model-00001-of-00002.safetensors",
59
+ "backbone.layers.13.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
60
+ "backbone.layers.13.norm.weight": "model-00001-of-00002.safetensors",
61
+ "backbone.layers.14.mixer.A_log": "model-00001-of-00002.safetensors",
62
+ "backbone.layers.14.mixer.D": "model-00001-of-00002.safetensors",
63
+ "backbone.layers.14.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
64
+ "backbone.layers.14.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
65
+ "backbone.layers.14.mixer.dt_bias": "model-00001-of-00002.safetensors",
66
+ "backbone.layers.14.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
67
+ "backbone.layers.14.mixer.norm.weight": "model-00001-of-00002.safetensors",
68
+ "backbone.layers.14.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
69
+ "backbone.layers.14.norm.weight": "model-00001-of-00002.safetensors",
70
+ "backbone.layers.15.mixer.A_log": "model-00001-of-00002.safetensors",
71
+ "backbone.layers.15.mixer.D": "model-00001-of-00002.safetensors",
72
+ "backbone.layers.15.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
73
+ "backbone.layers.15.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
74
+ "backbone.layers.15.mixer.dt_bias": "model-00001-of-00002.safetensors",
75
+ "backbone.layers.15.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
76
+ "backbone.layers.15.mixer.norm.weight": "model-00001-of-00002.safetensors",
77
+ "backbone.layers.15.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
78
+ "backbone.layers.15.norm.weight": "model-00001-of-00002.safetensors",
79
+ "backbone.layers.16.mixer.A_log": "model-00001-of-00002.safetensors",
80
+ "backbone.layers.16.mixer.D": "model-00001-of-00002.safetensors",
81
+ "backbone.layers.16.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
82
+ "backbone.layers.16.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
83
+ "backbone.layers.16.mixer.dt_bias": "model-00001-of-00002.safetensors",
84
+ "backbone.layers.16.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
85
+ "backbone.layers.16.mixer.norm.weight": "model-00001-of-00002.safetensors",
86
+ "backbone.layers.16.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
87
+ "backbone.layers.16.norm.weight": "model-00001-of-00002.safetensors",
88
+ "backbone.layers.17.mixer.A_log": "model-00001-of-00002.safetensors",
89
+ "backbone.layers.17.mixer.D": "model-00001-of-00002.safetensors",
90
+ "backbone.layers.17.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
91
+ "backbone.layers.17.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
92
+ "backbone.layers.17.mixer.dt_bias": "model-00001-of-00002.safetensors",
93
+ "backbone.layers.17.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
94
+ "backbone.layers.17.mixer.norm.weight": "model-00001-of-00002.safetensors",
95
+ "backbone.layers.17.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
96
+ "backbone.layers.17.norm.weight": "model-00001-of-00002.safetensors",
97
+ "backbone.layers.18.mixer.A_log": "model-00001-of-00002.safetensors",
98
+ "backbone.layers.18.mixer.D": "model-00001-of-00002.safetensors",
99
+ "backbone.layers.18.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
100
+ "backbone.layers.18.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
101
+ "backbone.layers.18.mixer.dt_bias": "model-00001-of-00002.safetensors",
102
+ "backbone.layers.18.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
103
+ "backbone.layers.18.mixer.norm.weight": "model-00001-of-00002.safetensors",
104
+ "backbone.layers.18.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
105
+ "backbone.layers.18.norm.weight": "model-00001-of-00002.safetensors",
106
+ "backbone.layers.19.mixer.A_log": "model-00001-of-00002.safetensors",
107
+ "backbone.layers.19.mixer.D": "model-00001-of-00002.safetensors",
108
+ "backbone.layers.19.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
109
+ "backbone.layers.19.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
110
+ "backbone.layers.19.mixer.dt_bias": "model-00001-of-00002.safetensors",
111
+ "backbone.layers.19.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
112
+ "backbone.layers.19.mixer.norm.weight": "model-00001-of-00002.safetensors",
113
+ "backbone.layers.19.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
114
+ "backbone.layers.19.norm.weight": "model-00001-of-00002.safetensors",
115
+ "backbone.layers.2.mixer.A_log": "model-00001-of-00002.safetensors",
116
+ "backbone.layers.2.mixer.D": "model-00001-of-00002.safetensors",
117
+ "backbone.layers.2.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
118
+ "backbone.layers.2.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
119
+ "backbone.layers.2.mixer.dt_bias": "model-00001-of-00002.safetensors",
120
+ "backbone.layers.2.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
121
+ "backbone.layers.2.mixer.norm.weight": "model-00001-of-00002.safetensors",
122
+ "backbone.layers.2.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
123
+ "backbone.layers.2.norm.weight": "model-00001-of-00002.safetensors",
124
+ "backbone.layers.20.mixer.A_log": "model-00001-of-00002.safetensors",
125
+ "backbone.layers.20.mixer.D": "model-00001-of-00002.safetensors",
126
+ "backbone.layers.20.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
127
+ "backbone.layers.20.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
128
+ "backbone.layers.20.mixer.dt_bias": "model-00001-of-00002.safetensors",
129
+ "backbone.layers.20.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
130
+ "backbone.layers.20.mixer.norm.weight": "model-00001-of-00002.safetensors",
131
+ "backbone.layers.20.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
132
+ "backbone.layers.20.norm.weight": "model-00001-of-00002.safetensors",
133
+ "backbone.layers.21.mixer.A_log": "model-00001-of-00002.safetensors",
134
+ "backbone.layers.21.mixer.D": "model-00001-of-00002.safetensors",
135
+ "backbone.layers.21.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
136
+ "backbone.layers.21.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
137
+ "backbone.layers.21.mixer.dt_bias": "model-00001-of-00002.safetensors",
138
+ "backbone.layers.21.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
139
+ "backbone.layers.21.mixer.norm.weight": "model-00001-of-00002.safetensors",
140
+ "backbone.layers.21.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
141
+ "backbone.layers.21.norm.weight": "model-00001-of-00002.safetensors",
142
+ "backbone.layers.22.mixer.A_log": "model-00001-of-00002.safetensors",
143
+ "backbone.layers.22.mixer.D": "model-00001-of-00002.safetensors",
144
+ "backbone.layers.22.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
145
+ "backbone.layers.22.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
146
+ "backbone.layers.22.mixer.dt_bias": "model-00001-of-00002.safetensors",
147
+ "backbone.layers.22.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
148
+ "backbone.layers.22.mixer.norm.weight": "model-00001-of-00002.safetensors",
149
+ "backbone.layers.22.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
150
+ "backbone.layers.22.norm.weight": "model-00001-of-00002.safetensors",
151
+ "backbone.layers.23.mixer.A_log": "model-00001-of-00002.safetensors",
152
+ "backbone.layers.23.mixer.D": "model-00001-of-00002.safetensors",
153
+ "backbone.layers.23.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
154
+ "backbone.layers.23.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
155
+ "backbone.layers.23.mixer.dt_bias": "model-00001-of-00002.safetensors",
156
+ "backbone.layers.23.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
157
+ "backbone.layers.23.mixer.norm.weight": "model-00001-of-00002.safetensors",
158
+ "backbone.layers.23.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
159
+ "backbone.layers.23.norm.weight": "model-00001-of-00002.safetensors",
160
+ "backbone.layers.24.mixer.A_log": "model-00001-of-00002.safetensors",
161
+ "backbone.layers.24.mixer.D": "model-00001-of-00002.safetensors",
162
+ "backbone.layers.24.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
163
+ "backbone.layers.24.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
164
+ "backbone.layers.24.mixer.dt_bias": "model-00001-of-00002.safetensors",
165
+ "backbone.layers.24.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
166
+ "backbone.layers.24.mixer.norm.weight": "model-00001-of-00002.safetensors",
167
+ "backbone.layers.24.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
168
+ "backbone.layers.24.norm.weight": "model-00001-of-00002.safetensors",
169
+ "backbone.layers.25.mixer.A_log": "model-00001-of-00002.safetensors",
170
+ "backbone.layers.25.mixer.D": "model-00001-of-00002.safetensors",
171
+ "backbone.layers.25.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
172
+ "backbone.layers.25.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
173
+ "backbone.layers.25.mixer.dt_bias": "model-00001-of-00002.safetensors",
174
+ "backbone.layers.25.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
175
+ "backbone.layers.25.mixer.norm.weight": "model-00001-of-00002.safetensors",
176
+ "backbone.layers.25.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
177
+ "backbone.layers.25.norm.weight": "model-00001-of-00002.safetensors",
178
+ "backbone.layers.26.mixer.A_log": "model-00001-of-00002.safetensors",
179
+ "backbone.layers.26.mixer.D": "model-00001-of-00002.safetensors",
180
+ "backbone.layers.26.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
181
+ "backbone.layers.26.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
182
+ "backbone.layers.26.mixer.dt_bias": "model-00001-of-00002.safetensors",
183
+ "backbone.layers.26.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
184
+ "backbone.layers.26.mixer.norm.weight": "model-00001-of-00002.safetensors",
185
+ "backbone.layers.26.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
186
+ "backbone.layers.26.norm.weight": "model-00001-of-00002.safetensors",
187
+ "backbone.layers.27.mixer.A_log": "model-00001-of-00002.safetensors",
188
+ "backbone.layers.27.mixer.D": "model-00001-of-00002.safetensors",
189
+ "backbone.layers.27.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
190
+ "backbone.layers.27.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
191
+ "backbone.layers.27.mixer.dt_bias": "model-00001-of-00002.safetensors",
192
+ "backbone.layers.27.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
193
+ "backbone.layers.27.mixer.norm.weight": "model-00001-of-00002.safetensors",
194
+ "backbone.layers.27.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
195
+ "backbone.layers.27.norm.weight": "model-00001-of-00002.safetensors",
196
+ "backbone.layers.28.mixer.A_log": "model-00001-of-00002.safetensors",
197
+ "backbone.layers.28.mixer.D": "model-00001-of-00002.safetensors",
198
+ "backbone.layers.28.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
199
+ "backbone.layers.28.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
200
+ "backbone.layers.28.mixer.dt_bias": "model-00001-of-00002.safetensors",
201
+ "backbone.layers.28.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
202
+ "backbone.layers.28.mixer.norm.weight": "model-00001-of-00002.safetensors",
203
+ "backbone.layers.28.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
204
+ "backbone.layers.28.norm.weight": "model-00001-of-00002.safetensors",
205
+ "backbone.layers.29.mixer.A_log": "model-00001-of-00002.safetensors",
206
+ "backbone.layers.29.mixer.D": "model-00001-of-00002.safetensors",
207
+ "backbone.layers.29.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
208
+ "backbone.layers.29.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
209
+ "backbone.layers.29.mixer.dt_bias": "model-00001-of-00002.safetensors",
210
+ "backbone.layers.29.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
211
+ "backbone.layers.29.mixer.norm.weight": "model-00001-of-00002.safetensors",
212
+ "backbone.layers.29.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
213
+ "backbone.layers.29.norm.weight": "model-00001-of-00002.safetensors",
214
+ "backbone.layers.3.mixer.A_log": "model-00001-of-00002.safetensors",
215
+ "backbone.layers.3.mixer.D": "model-00001-of-00002.safetensors",
216
+ "backbone.layers.3.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
217
+ "backbone.layers.3.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
218
+ "backbone.layers.3.mixer.dt_bias": "model-00001-of-00002.safetensors",
219
+ "backbone.layers.3.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
220
+ "backbone.layers.3.mixer.norm.weight": "model-00001-of-00002.safetensors",
221
+ "backbone.layers.3.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
222
+ "backbone.layers.3.norm.weight": "model-00001-of-00002.safetensors",
223
+ "backbone.layers.30.mixer.A_log": "model-00001-of-00002.safetensors",
224
+ "backbone.layers.30.mixer.D": "model-00001-of-00002.safetensors",
225
+ "backbone.layers.30.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
226
+ "backbone.layers.30.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
227
+ "backbone.layers.30.mixer.dt_bias": "model-00001-of-00002.safetensors",
228
+ "backbone.layers.30.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
229
+ "backbone.layers.30.mixer.norm.weight": "model-00001-of-00002.safetensors",
230
+ "backbone.layers.30.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
231
+ "backbone.layers.30.norm.weight": "model-00001-of-00002.safetensors",
232
+ "backbone.layers.31.mixer.A_log": "model-00001-of-00002.safetensors",
233
+ "backbone.layers.31.mixer.D": "model-00001-of-00002.safetensors",
234
+ "backbone.layers.31.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
235
+ "backbone.layers.31.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
236
+ "backbone.layers.31.mixer.dt_bias": "model-00001-of-00002.safetensors",
237
+ "backbone.layers.31.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
238
+ "backbone.layers.31.mixer.norm.weight": "model-00001-of-00002.safetensors",
239
+ "backbone.layers.31.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
240
+ "backbone.layers.31.norm.weight": "model-00001-of-00002.safetensors",
241
+ "backbone.layers.32.mixer.A_log": "model-00001-of-00002.safetensors",
242
+ "backbone.layers.32.mixer.D": "model-00001-of-00002.safetensors",
243
+ "backbone.layers.32.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
244
+ "backbone.layers.32.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
245
+ "backbone.layers.32.mixer.dt_bias": "model-00001-of-00002.safetensors",
246
+ "backbone.layers.32.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
247
+ "backbone.layers.32.mixer.norm.weight": "model-00001-of-00002.safetensors",
248
+ "backbone.layers.32.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
249
+ "backbone.layers.32.norm.weight": "model-00001-of-00002.safetensors",
250
+ "backbone.layers.33.mixer.A_log": "model-00001-of-00002.safetensors",
251
+ "backbone.layers.33.mixer.D": "model-00001-of-00002.safetensors",
252
+ "backbone.layers.33.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
253
+ "backbone.layers.33.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
254
+ "backbone.layers.33.mixer.dt_bias": "model-00001-of-00002.safetensors",
255
+ "backbone.layers.33.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
256
+ "backbone.layers.33.mixer.norm.weight": "model-00001-of-00002.safetensors",
257
+ "backbone.layers.33.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
258
+ "backbone.layers.33.norm.weight": "model-00001-of-00002.safetensors",
259
+ "backbone.layers.34.mixer.A_log": "model-00001-of-00002.safetensors",
260
+ "backbone.layers.34.mixer.D": "model-00001-of-00002.safetensors",
261
+ "backbone.layers.34.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
262
+ "backbone.layers.34.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
263
+ "backbone.layers.34.mixer.dt_bias": "model-00001-of-00002.safetensors",
264
+ "backbone.layers.34.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
265
+ "backbone.layers.34.mixer.norm.weight": "model-00001-of-00002.safetensors",
266
+ "backbone.layers.34.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
267
+ "backbone.layers.34.norm.weight": "model-00001-of-00002.safetensors",
268
+ "backbone.layers.35.mixer.A_log": "model-00001-of-00002.safetensors",
269
+ "backbone.layers.35.mixer.D": "model-00001-of-00002.safetensors",
270
+ "backbone.layers.35.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
271
+ "backbone.layers.35.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
272
+ "backbone.layers.35.mixer.dt_bias": "model-00001-of-00002.safetensors",
273
+ "backbone.layers.35.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
274
+ "backbone.layers.35.mixer.norm.weight": "model-00001-of-00002.safetensors",
275
+ "backbone.layers.35.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
276
+ "backbone.layers.35.norm.weight": "model-00001-of-00002.safetensors",
277
+ "backbone.layers.36.mixer.A_log": "model-00001-of-00002.safetensors",
278
+ "backbone.layers.36.mixer.D": "model-00001-of-00002.safetensors",
279
+ "backbone.layers.36.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
280
+ "backbone.layers.36.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
281
+ "backbone.layers.36.mixer.dt_bias": "model-00001-of-00002.safetensors",
282
+ "backbone.layers.36.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
283
+ "backbone.layers.36.mixer.norm.weight": "model-00001-of-00002.safetensors",
284
+ "backbone.layers.36.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
285
+ "backbone.layers.36.norm.weight": "model-00001-of-00002.safetensors",
286
+ "backbone.layers.37.mixer.A_log": "model-00001-of-00002.safetensors",
287
+ "backbone.layers.37.mixer.D": "model-00001-of-00002.safetensors",
288
+ "backbone.layers.37.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
289
+ "backbone.layers.37.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
290
+ "backbone.layers.37.mixer.dt_bias": "model-00001-of-00002.safetensors",
291
+ "backbone.layers.37.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
292
+ "backbone.layers.37.mixer.norm.weight": "model-00001-of-00002.safetensors",
293
+ "backbone.layers.37.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
294
+ "backbone.layers.37.norm.weight": "model-00001-of-00002.safetensors",
295
+ "backbone.layers.38.mixer.A_log": "model-00001-of-00002.safetensors",
296
+ "backbone.layers.38.mixer.D": "model-00001-of-00002.safetensors",
297
+ "backbone.layers.38.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
298
+ "backbone.layers.38.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
299
+ "backbone.layers.38.mixer.dt_bias": "model-00001-of-00002.safetensors",
300
+ "backbone.layers.38.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
301
+ "backbone.layers.38.mixer.norm.weight": "model-00001-of-00002.safetensors",
302
+ "backbone.layers.38.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
303
+ "backbone.layers.38.norm.weight": "model-00001-of-00002.safetensors",
304
+ "backbone.layers.39.mixer.A_log": "model-00001-of-00002.safetensors",
305
+ "backbone.layers.39.mixer.D": "model-00001-of-00002.safetensors",
306
+ "backbone.layers.39.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
307
+ "backbone.layers.39.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
308
+ "backbone.layers.39.mixer.dt_bias": "model-00001-of-00002.safetensors",
309
+ "backbone.layers.39.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
310
+ "backbone.layers.39.mixer.norm.weight": "model-00001-of-00002.safetensors",
311
+ "backbone.layers.39.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
312
+ "backbone.layers.39.norm.weight": "model-00001-of-00002.safetensors",
313
+ "backbone.layers.4.mixer.A_log": "model-00001-of-00002.safetensors",
314
+ "backbone.layers.4.mixer.D": "model-00001-of-00002.safetensors",
315
+ "backbone.layers.4.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
316
+ "backbone.layers.4.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
317
+ "backbone.layers.4.mixer.dt_bias": "model-00001-of-00002.safetensors",
318
+ "backbone.layers.4.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
319
+ "backbone.layers.4.mixer.norm.weight": "model-00001-of-00002.safetensors",
320
+ "backbone.layers.4.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
321
+ "backbone.layers.4.norm.weight": "model-00001-of-00002.safetensors",
322
+ "backbone.layers.40.mixer.A_log": "model-00001-of-00002.safetensors",
323
+ "backbone.layers.40.mixer.D": "model-00001-of-00002.safetensors",
324
+ "backbone.layers.40.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
325
+ "backbone.layers.40.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
326
+ "backbone.layers.40.mixer.dt_bias": "model-00001-of-00002.safetensors",
327
+ "backbone.layers.40.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
328
+ "backbone.layers.40.mixer.norm.weight": "model-00001-of-00002.safetensors",
329
+ "backbone.layers.40.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
330
+ "backbone.layers.40.norm.weight": "model-00001-of-00002.safetensors",
331
+ "backbone.layers.41.mixer.A_log": "model-00001-of-00002.safetensors",
332
+ "backbone.layers.41.mixer.D": "model-00001-of-00002.safetensors",
333
+ "backbone.layers.41.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
334
+ "backbone.layers.41.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
335
+ "backbone.layers.41.mixer.dt_bias": "model-00001-of-00002.safetensors",
336
+ "backbone.layers.41.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
337
+ "backbone.layers.41.mixer.norm.weight": "model-00001-of-00002.safetensors",
338
+ "backbone.layers.41.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
339
+ "backbone.layers.41.norm.weight": "model-00001-of-00002.safetensors",
340
+ "backbone.layers.42.mixer.A_log": "model-00001-of-00002.safetensors",
341
+ "backbone.layers.42.mixer.D": "model-00001-of-00002.safetensors",
342
+ "backbone.layers.42.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
343
+ "backbone.layers.42.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
344
+ "backbone.layers.42.mixer.dt_bias": "model-00001-of-00002.safetensors",
345
+ "backbone.layers.42.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
346
+ "backbone.layers.42.mixer.norm.weight": "model-00001-of-00002.safetensors",
347
+ "backbone.layers.42.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
348
+ "backbone.layers.42.norm.weight": "model-00001-of-00002.safetensors",
349
+ "backbone.layers.43.mixer.A_log": "model-00001-of-00002.safetensors",
350
+ "backbone.layers.43.mixer.D": "model-00001-of-00002.safetensors",
351
+ "backbone.layers.43.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
352
+ "backbone.layers.43.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
353
+ "backbone.layers.43.mixer.dt_bias": "model-00001-of-00002.safetensors",
354
+ "backbone.layers.43.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
355
+ "backbone.layers.43.mixer.norm.weight": "model-00001-of-00002.safetensors",
356
+ "backbone.layers.43.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
357
+ "backbone.layers.43.norm.weight": "model-00001-of-00002.safetensors",
358
+ "backbone.layers.44.mixer.A_log": "model-00001-of-00002.safetensors",
359
+ "backbone.layers.44.mixer.D": "model-00001-of-00002.safetensors",
360
+ "backbone.layers.44.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
361
+ "backbone.layers.44.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
362
+ "backbone.layers.44.mixer.dt_bias": "model-00001-of-00002.safetensors",
363
+ "backbone.layers.44.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
364
+ "backbone.layers.44.mixer.norm.weight": "model-00001-of-00002.safetensors",
365
+ "backbone.layers.44.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
366
+ "backbone.layers.44.norm.weight": "model-00001-of-00002.safetensors",
367
+ "backbone.layers.45.mixer.A_log": "model-00001-of-00002.safetensors",
368
+ "backbone.layers.45.mixer.D": "model-00001-of-00002.safetensors",
369
+ "backbone.layers.45.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
370
+ "backbone.layers.45.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
371
+ "backbone.layers.45.mixer.dt_bias": "model-00001-of-00002.safetensors",
372
+ "backbone.layers.45.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
373
+ "backbone.layers.45.mixer.norm.weight": "model-00001-of-00002.safetensors",
374
+ "backbone.layers.45.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
375
+ "backbone.layers.45.norm.weight": "model-00001-of-00002.safetensors",
376
+ "backbone.layers.46.mixer.A_log": "model-00001-of-00002.safetensors",
377
+ "backbone.layers.46.mixer.D": "model-00001-of-00002.safetensors",
378
+ "backbone.layers.46.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
379
+ "backbone.layers.46.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
380
+ "backbone.layers.46.mixer.dt_bias": "model-00001-of-00002.safetensors",
381
+ "backbone.layers.46.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
382
+ "backbone.layers.46.mixer.norm.weight": "model-00001-of-00002.safetensors",
383
+ "backbone.layers.46.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
384
+ "backbone.layers.46.norm.weight": "model-00001-of-00002.safetensors",
385
+ "backbone.layers.47.mixer.A_log": "model-00001-of-00002.safetensors",
386
+ "backbone.layers.47.mixer.D": "model-00001-of-00002.safetensors",
387
+ "backbone.layers.47.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
388
+ "backbone.layers.47.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
389
+ "backbone.layers.47.mixer.dt_bias": "model-00001-of-00002.safetensors",
390
+ "backbone.layers.47.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
391
+ "backbone.layers.47.mixer.norm.weight": "model-00001-of-00002.safetensors",
392
+ "backbone.layers.47.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
393
+ "backbone.layers.47.norm.weight": "model-00001-of-00002.safetensors",
394
+ "backbone.layers.48.mixer.A_log": "model-00001-of-00002.safetensors",
395
+ "backbone.layers.48.mixer.D": "model-00001-of-00002.safetensors",
396
+ "backbone.layers.48.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
397
+ "backbone.layers.48.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
398
+ "backbone.layers.48.mixer.dt_bias": "model-00001-of-00002.safetensors",
399
+ "backbone.layers.48.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
400
+ "backbone.layers.48.mixer.norm.weight": "model-00001-of-00002.safetensors",
401
+ "backbone.layers.48.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
402
+ "backbone.layers.48.norm.weight": "model-00001-of-00002.safetensors",
403
+ "backbone.layers.49.mixer.A_log": "model-00001-of-00002.safetensors",
404
+ "backbone.layers.49.mixer.D": "model-00001-of-00002.safetensors",
405
+ "backbone.layers.49.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
406
+ "backbone.layers.49.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
407
+ "backbone.layers.49.mixer.dt_bias": "model-00001-of-00002.safetensors",
408
+ "backbone.layers.49.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
409
+ "backbone.layers.49.mixer.norm.weight": "model-00001-of-00002.safetensors",
410
+ "backbone.layers.49.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
411
+ "backbone.layers.49.norm.weight": "model-00001-of-00002.safetensors",
412
+ "backbone.layers.5.mixer.A_log": "model-00001-of-00002.safetensors",
413
+ "backbone.layers.5.mixer.D": "model-00001-of-00002.safetensors",
414
+ "backbone.layers.5.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
415
+ "backbone.layers.5.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
416
+ "backbone.layers.5.mixer.dt_bias": "model-00001-of-00002.safetensors",
417
+ "backbone.layers.5.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
418
+ "backbone.layers.5.mixer.norm.weight": "model-00001-of-00002.safetensors",
419
+ "backbone.layers.5.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
420
+ "backbone.layers.5.norm.weight": "model-00001-of-00002.safetensors",
421
+ "backbone.layers.50.mixer.A_log": "model-00001-of-00002.safetensors",
422
+ "backbone.layers.50.mixer.D": "model-00001-of-00002.safetensors",
423
+ "backbone.layers.50.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
424
+ "backbone.layers.50.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
425
+ "backbone.layers.50.mixer.dt_bias": "model-00001-of-00002.safetensors",
426
+ "backbone.layers.50.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
427
+ "backbone.layers.50.mixer.norm.weight": "model-00001-of-00002.safetensors",
428
+ "backbone.layers.50.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
429
+ "backbone.layers.50.norm.weight": "model-00001-of-00002.safetensors",
430
+ "backbone.layers.51.mixer.A_log": "model-00001-of-00002.safetensors",
431
+ "backbone.layers.51.mixer.D": "model-00001-of-00002.safetensors",
432
+ "backbone.layers.51.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
433
+ "backbone.layers.51.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
434
+ "backbone.layers.51.mixer.dt_bias": "model-00001-of-00002.safetensors",
435
+ "backbone.layers.51.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
436
+ "backbone.layers.51.mixer.norm.weight": "model-00001-of-00002.safetensors",
437
+ "backbone.layers.51.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
438
+ "backbone.layers.51.norm.weight": "model-00001-of-00002.safetensors",
439
+ "backbone.layers.52.mixer.A_log": "model-00001-of-00002.safetensors",
440
+ "backbone.layers.52.mixer.D": "model-00001-of-00002.safetensors",
441
+ "backbone.layers.52.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
442
+ "backbone.layers.52.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
443
+ "backbone.layers.52.mixer.dt_bias": "model-00001-of-00002.safetensors",
444
+ "backbone.layers.52.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
445
+ "backbone.layers.52.mixer.norm.weight": "model-00001-of-00002.safetensors",
446
+ "backbone.layers.52.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
447
+ "backbone.layers.52.norm.weight": "model-00001-of-00002.safetensors",
448
+ "backbone.layers.53.mixer.A_log": "model-00001-of-00002.safetensors",
449
+ "backbone.layers.53.mixer.D": "model-00001-of-00002.safetensors",
450
+ "backbone.layers.53.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
451
+ "backbone.layers.53.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
452
+ "backbone.layers.53.mixer.dt_bias": "model-00001-of-00002.safetensors",
453
+ "backbone.layers.53.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
454
+ "backbone.layers.53.mixer.norm.weight": "model-00001-of-00002.safetensors",
455
+ "backbone.layers.53.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
456
+ "backbone.layers.53.norm.weight": "model-00001-of-00002.safetensors",
457
+ "backbone.layers.54.mixer.A_log": "model-00001-of-00002.safetensors",
458
+ "backbone.layers.54.mixer.D": "model-00001-of-00002.safetensors",
459
+ "backbone.layers.54.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
460
+ "backbone.layers.54.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
461
+ "backbone.layers.54.mixer.dt_bias": "model-00001-of-00002.safetensors",
462
+ "backbone.layers.54.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
463
+ "backbone.layers.54.mixer.norm.weight": "model-00001-of-00002.safetensors",
464
+ "backbone.layers.54.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
465
+ "backbone.layers.54.norm.weight": "model-00001-of-00002.safetensors",
466
+ "backbone.layers.55.mixer.A_log": "model-00001-of-00002.safetensors",
467
+ "backbone.layers.55.mixer.D": "model-00001-of-00002.safetensors",
468
+ "backbone.layers.55.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
469
+ "backbone.layers.55.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
470
+ "backbone.layers.55.mixer.dt_bias": "model-00001-of-00002.safetensors",
471
+ "backbone.layers.55.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
472
+ "backbone.layers.55.mixer.norm.weight": "model-00001-of-00002.safetensors",
473
+ "backbone.layers.55.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
474
+ "backbone.layers.55.norm.weight": "model-00001-of-00002.safetensors",
475
+ "backbone.layers.56.mixer.A_log": "model-00001-of-00002.safetensors",
476
+ "backbone.layers.56.mixer.D": "model-00001-of-00002.safetensors",
477
+ "backbone.layers.56.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
478
+ "backbone.layers.56.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
479
+ "backbone.layers.56.mixer.dt_bias": "model-00001-of-00002.safetensors",
480
+ "backbone.layers.56.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
481
+ "backbone.layers.56.mixer.norm.weight": "model-00001-of-00002.safetensors",
482
+ "backbone.layers.56.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
483
+ "backbone.layers.56.norm.weight": "model-00001-of-00002.safetensors",
484
+ "backbone.layers.57.mixer.A_log": "model-00001-of-00002.safetensors",
485
+ "backbone.layers.57.mixer.D": "model-00001-of-00002.safetensors",
486
+ "backbone.layers.57.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
487
+ "backbone.layers.57.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
488
+ "backbone.layers.57.mixer.dt_bias": "model-00001-of-00002.safetensors",
489
+ "backbone.layers.57.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
490
+ "backbone.layers.57.mixer.norm.weight": "model-00001-of-00002.safetensors",
491
+ "backbone.layers.57.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
492
+ "backbone.layers.57.norm.weight": "model-00001-of-00002.safetensors",
493
+ "backbone.layers.58.mixer.A_log": "model-00001-of-00002.safetensors",
494
+ "backbone.layers.58.mixer.D": "model-00001-of-00002.safetensors",
495
+ "backbone.layers.58.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
496
+ "backbone.layers.58.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
497
+ "backbone.layers.58.mixer.dt_bias": "model-00001-of-00002.safetensors",
498
+ "backbone.layers.58.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
499
+ "backbone.layers.58.mixer.norm.weight": "model-00001-of-00002.safetensors",
500
+ "backbone.layers.58.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
501
+ "backbone.layers.58.norm.weight": "model-00001-of-00002.safetensors",
502
+ "backbone.layers.59.mixer.A_log": "model-00002-of-00002.safetensors",
503
+ "backbone.layers.59.mixer.D": "model-00002-of-00002.safetensors",
504
+ "backbone.layers.59.mixer.conv1d.bias": "model-00002-of-00002.safetensors",
505
+ "backbone.layers.59.mixer.conv1d.weight": "model-00002-of-00002.safetensors",
506
+ "backbone.layers.59.mixer.dt_bias": "model-00002-of-00002.safetensors",
507
+ "backbone.layers.59.mixer.in_proj.weight": "model-00002-of-00002.safetensors",
508
+ "backbone.layers.59.mixer.norm.weight": "model-00002-of-00002.safetensors",
509
+ "backbone.layers.59.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
510
+ "backbone.layers.59.norm.weight": "model-00002-of-00002.safetensors",
511
+ "backbone.layers.6.mixer.A_log": "model-00001-of-00002.safetensors",
512
+ "backbone.layers.6.mixer.D": "model-00001-of-00002.safetensors",
513
+ "backbone.layers.6.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
514
+ "backbone.layers.6.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
515
+ "backbone.layers.6.mixer.dt_bias": "model-00001-of-00002.safetensors",
516
+ "backbone.layers.6.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
517
+ "backbone.layers.6.mixer.norm.weight": "model-00001-of-00002.safetensors",
518
+ "backbone.layers.6.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
519
+ "backbone.layers.6.norm.weight": "model-00001-of-00002.safetensors",
520
+ "backbone.layers.60.mixer.A_log": "model-00002-of-00002.safetensors",
521
+ "backbone.layers.60.mixer.D": "model-00002-of-00002.safetensors",
522
+ "backbone.layers.60.mixer.conv1d.bias": "model-00002-of-00002.safetensors",
523
+ "backbone.layers.60.mixer.conv1d.weight": "model-00002-of-00002.safetensors",
524
+ "backbone.layers.60.mixer.dt_bias": "model-00002-of-00002.safetensors",
525
+ "backbone.layers.60.mixer.in_proj.weight": "model-00002-of-00002.safetensors",
526
+ "backbone.layers.60.mixer.norm.weight": "model-00002-of-00002.safetensors",
527
+ "backbone.layers.60.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
528
+ "backbone.layers.60.norm.weight": "model-00002-of-00002.safetensors",
529
+ "backbone.layers.61.mixer.A_log": "model-00002-of-00002.safetensors",
530
+ "backbone.layers.61.mixer.D": "model-00002-of-00002.safetensors",
531
+ "backbone.layers.61.mixer.conv1d.bias": "model-00002-of-00002.safetensors",
532
+ "backbone.layers.61.mixer.conv1d.weight": "model-00002-of-00002.safetensors",
533
+ "backbone.layers.61.mixer.dt_bias": "model-00002-of-00002.safetensors",
534
+ "backbone.layers.61.mixer.in_proj.weight": "model-00002-of-00002.safetensors",
535
+ "backbone.layers.61.mixer.norm.weight": "model-00002-of-00002.safetensors",
536
+ "backbone.layers.61.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
537
+ "backbone.layers.61.norm.weight": "model-00002-of-00002.safetensors",
538
+ "backbone.layers.62.mixer.A_log": "model-00002-of-00002.safetensors",
539
+ "backbone.layers.62.mixer.D": "model-00002-of-00002.safetensors",
540
+ "backbone.layers.62.mixer.conv1d.bias": "model-00002-of-00002.safetensors",
541
+ "backbone.layers.62.mixer.conv1d.weight": "model-00002-of-00002.safetensors",
542
+ "backbone.layers.62.mixer.dt_bias": "model-00002-of-00002.safetensors",
543
+ "backbone.layers.62.mixer.in_proj.weight": "model-00002-of-00002.safetensors",
544
+ "backbone.layers.62.mixer.norm.weight": "model-00002-of-00002.safetensors",
545
+ "backbone.layers.62.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
546
+ "backbone.layers.62.norm.weight": "model-00002-of-00002.safetensors",
547
+ "backbone.layers.63.mixer.A_log": "model-00002-of-00002.safetensors",
548
+ "backbone.layers.63.mixer.D": "model-00002-of-00002.safetensors",
549
+ "backbone.layers.63.mixer.conv1d.bias": "model-00002-of-00002.safetensors",
550
+ "backbone.layers.63.mixer.conv1d.weight": "model-00002-of-00002.safetensors",
551
+ "backbone.layers.63.mixer.dt_bias": "model-00002-of-00002.safetensors",
552
+ "backbone.layers.63.mixer.in_proj.weight": "model-00002-of-00002.safetensors",
553
+ "backbone.layers.63.mixer.norm.weight": "model-00002-of-00002.safetensors",
554
+ "backbone.layers.63.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
555
+ "backbone.layers.63.norm.weight": "model-00002-of-00002.safetensors",
556
+ "backbone.layers.7.mixer.A_log": "model-00001-of-00002.safetensors",
557
+ "backbone.layers.7.mixer.D": "model-00001-of-00002.safetensors",
558
+ "backbone.layers.7.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
559
+ "backbone.layers.7.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
560
+ "backbone.layers.7.mixer.dt_bias": "model-00001-of-00002.safetensors",
561
+ "backbone.layers.7.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
562
+ "backbone.layers.7.mixer.norm.weight": "model-00001-of-00002.safetensors",
563
+ "backbone.layers.7.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
564
+ "backbone.layers.7.norm.weight": "model-00001-of-00002.safetensors",
565
+ "backbone.layers.8.mixer.A_log": "model-00001-of-00002.safetensors",
566
+ "backbone.layers.8.mixer.D": "model-00001-of-00002.safetensors",
567
+ "backbone.layers.8.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
568
+ "backbone.layers.8.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
569
+ "backbone.layers.8.mixer.dt_bias": "model-00001-of-00002.safetensors",
570
+ "backbone.layers.8.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
571
+ "backbone.layers.8.mixer.norm.weight": "model-00001-of-00002.safetensors",
572
+ "backbone.layers.8.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
573
+ "backbone.layers.8.norm.weight": "model-00001-of-00002.safetensors",
574
+ "backbone.layers.9.mixer.A_log": "model-00001-of-00002.safetensors",
575
+ "backbone.layers.9.mixer.D": "model-00001-of-00002.safetensors",
576
+ "backbone.layers.9.mixer.conv1d.bias": "model-00001-of-00002.safetensors",
577
+ "backbone.layers.9.mixer.conv1d.weight": "model-00001-of-00002.safetensors",
578
+ "backbone.layers.9.mixer.dt_bias": "model-00001-of-00002.safetensors",
579
+ "backbone.layers.9.mixer.in_proj.weight": "model-00001-of-00002.safetensors",
580
+ "backbone.layers.9.mixer.norm.weight": "model-00001-of-00002.safetensors",
581
+ "backbone.layers.9.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
582
+ "backbone.layers.9.norm.weight": "model-00001-of-00002.safetensors",
583
+ "backbone.norm_f.weight": "model-00002-of-00002.safetensors",
584
+ "lm_head.weight": "model-00002-of-00002.safetensors",
585
+ "mm_model.mm_projector.0.bias": "model-00002-of-00002.safetensors",
586
+ "mm_model.mm_projector.0.weight": "model-00002-of-00002.safetensors",
587
+ "mm_model.mm_projector.2.bias": "model-00002-of-00002.safetensors",
588
+ "mm_model.mm_projector.2.weight": "model-00002-of-00002.safetensors",
589
+ "mm_model.vision_tower.vision_tower.vision_model.embeddings.class_embedding": "model-00002-of-00002.safetensors",
590
+ "mm_model.vision_tower.vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00002-of-00002.safetensors",
591
+ "mm_model.vision_tower.vision_tower.vision_model.embeddings.position_embedding.weight": "model-00002-of-00002.safetensors",
592
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00002-of-00002.safetensors",
593
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00002-of-00002.safetensors",
594
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00002-of-00002.safetensors",
595
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00002-of-00002.safetensors",
596
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00002-of-00002.safetensors",
597
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00002-of-00002.safetensors",
598
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00002-of-00002.safetensors",
599
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00002-of-00002.safetensors",
600
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
601
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
602
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
603
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
604
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
605
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
606
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
607
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
608
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00002-of-00002.safetensors",
609
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00002-of-00002.safetensors",
610
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00002-of-00002.safetensors",
611
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00002-of-00002.safetensors",
612
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00002-of-00002.safetensors",
613
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00002-of-00002.safetensors",
614
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00002-of-00002.safetensors",
615
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00002-of-00002.safetensors",
616
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
617
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
618
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
619
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
620
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
621
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
622
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
623
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
624
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00002-of-00002.safetensors",
625
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00002-of-00002.safetensors",
626
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00002-of-00002.safetensors",
627
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00002-of-00002.safetensors",
628
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00002-of-00002.safetensors",
629
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00002-of-00002.safetensors",
630
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00002-of-00002.safetensors",
631
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00002-of-00002.safetensors",
632
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
633
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
634
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
635
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
636
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
637
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
638
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
639
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
640
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00002-of-00002.safetensors",
641
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00002-of-00002.safetensors",
642
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00002-of-00002.safetensors",
643
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00002-of-00002.safetensors",
644
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00002-of-00002.safetensors",
645
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00002-of-00002.safetensors",
646
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00002-of-00002.safetensors",
647
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00002-of-00002.safetensors",
648
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
649
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
650
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
651
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
652
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
653
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
654
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
655
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
656
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00002-of-00002.safetensors",
657
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00002-of-00002.safetensors",
658
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00002-of-00002.safetensors",
659
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00002-of-00002.safetensors",
660
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00002-of-00002.safetensors",
661
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00002-of-00002.safetensors",
662
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00002-of-00002.safetensors",
663
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00002-of-00002.safetensors",
664
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
665
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
666
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
667
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
668
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
669
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
670
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
671
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
672
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00002-of-00002.safetensors",
673
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00002-of-00002.safetensors",
674
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00002-of-00002.safetensors",
675
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00002-of-00002.safetensors",
676
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00002-of-00002.safetensors",
677
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00002-of-00002.safetensors",
678
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00002-of-00002.safetensors",
679
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00002-of-00002.safetensors",
680
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
681
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
682
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
683
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
684
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
685
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
686
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
687
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
688
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00002-of-00002.safetensors",
689
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00002-of-00002.safetensors",
690
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00002-of-00002.safetensors",
691
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00002-of-00002.safetensors",
692
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00002-of-00002.safetensors",
693
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00002-of-00002.safetensors",
694
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00002-of-00002.safetensors",
695
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00002-of-00002.safetensors",
696
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
697
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
698
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
699
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
700
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
701
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
702
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
703
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
704
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00002-of-00002.safetensors",
705
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00002-of-00002.safetensors",
706
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00002-of-00002.safetensors",
707
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00002-of-00002.safetensors",
708
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00002-of-00002.safetensors",
709
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00002-of-00002.safetensors",
710
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00002-of-00002.safetensors",
711
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00002-of-00002.safetensors",
712
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
713
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
714
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
715
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
716
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
717
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
718
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
719
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
720
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00002-of-00002.safetensors",
721
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00002-of-00002.safetensors",
722
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00002-of-00002.safetensors",
723
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00002-of-00002.safetensors",
724
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00002-of-00002.safetensors",
725
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00002-of-00002.safetensors",
726
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00002-of-00002.safetensors",
727
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00002-of-00002.safetensors",
728
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
729
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
730
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
731
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
732
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
733
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
734
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
735
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
736
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00002-of-00002.safetensors",
737
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00002-of-00002.safetensors",
738
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00002-of-00002.safetensors",
739
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00002-of-00002.safetensors",
740
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00002-of-00002.safetensors",
741
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00002-of-00002.safetensors",
742
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00002-of-00002.safetensors",
743
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00002-of-00002.safetensors",
744
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
745
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
746
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
747
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
748
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
749
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
750
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
751
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
752
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00002-of-00002.safetensors",
753
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00002-of-00002.safetensors",
754
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00002-of-00002.safetensors",
755
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00002-of-00002.safetensors",
756
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00002-of-00002.safetensors",
757
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00002-of-00002.safetensors",
758
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00002-of-00002.safetensors",
759
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00002-of-00002.safetensors",
760
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
761
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
762
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
763
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
764
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
765
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
766
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
767
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
768
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00002-of-00002.safetensors",
769
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00002-of-00002.safetensors",
770
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00002-of-00002.safetensors",
771
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00002-of-00002.safetensors",
772
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00002-of-00002.safetensors",
773
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00002-of-00002.safetensors",
774
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00002-of-00002.safetensors",
775
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00002-of-00002.safetensors",
776
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
777
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
778
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
779
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
780
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
781
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
782
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
783
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
784
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00002-of-00002.safetensors",
785
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00002-of-00002.safetensors",
786
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00002-of-00002.safetensors",
787
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00002-of-00002.safetensors",
788
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00002-of-00002.safetensors",
789
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00002-of-00002.safetensors",
790
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00002-of-00002.safetensors",
791
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00002-of-00002.safetensors",
792
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
793
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
794
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
795
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
796
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
797
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
798
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
799
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
800
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00002-of-00002.safetensors",
801
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00002-of-00002.safetensors",
802
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00002-of-00002.safetensors",
803
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00002-of-00002.safetensors",
804
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00002-of-00002.safetensors",
805
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00002-of-00002.safetensors",
806
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00002-of-00002.safetensors",
807
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00002-of-00002.safetensors",
808
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
809
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
810
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
811
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
812
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
813
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
814
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
815
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
816
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00002-of-00002.safetensors",
817
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00002-of-00002.safetensors",
818
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00002-of-00002.safetensors",
819
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00002-of-00002.safetensors",
820
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00002-of-00002.safetensors",
821
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00002-of-00002.safetensors",
822
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00002-of-00002.safetensors",
823
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00002-of-00002.safetensors",
824
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
825
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
826
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
827
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
828
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
829
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
830
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
831
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
832
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00002-of-00002.safetensors",
833
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00002-of-00002.safetensors",
834
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00002-of-00002.safetensors",
835
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00002-of-00002.safetensors",
836
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00002-of-00002.safetensors",
837
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00002-of-00002.safetensors",
838
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00002-of-00002.safetensors",
839
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00002-of-00002.safetensors",
840
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
841
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
842
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
843
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
844
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
845
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
846
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
847
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
848
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00002-of-00002.safetensors",
849
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00002-of-00002.safetensors",
850
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00002-of-00002.safetensors",
851
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00002-of-00002.safetensors",
852
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00002-of-00002.safetensors",
853
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00002-of-00002.safetensors",
854
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00002-of-00002.safetensors",
855
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00002-of-00002.safetensors",
856
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
857
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
858
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
859
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
860
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
861
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
862
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
863
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
864
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00002-of-00002.safetensors",
865
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00002-of-00002.safetensors",
866
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00002-of-00002.safetensors",
867
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00002-of-00002.safetensors",
868
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00002-of-00002.safetensors",
869
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00002-of-00002.safetensors",
870
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00002-of-00002.safetensors",
871
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00002-of-00002.safetensors",
872
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
873
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
874
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
875
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
876
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
877
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
878
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
879
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
880
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00002-of-00002.safetensors",
881
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00002-of-00002.safetensors",
882
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00002-of-00002.safetensors",
883
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00002-of-00002.safetensors",
884
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00002-of-00002.safetensors",
885
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00002-of-00002.safetensors",
886
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00002-of-00002.safetensors",
887
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00002-of-00002.safetensors",
888
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
889
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
890
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
891
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
892
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
893
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
894
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
895
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
896
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00002-of-00002.safetensors",
897
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00002-of-00002.safetensors",
898
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00002-of-00002.safetensors",
899
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00002-of-00002.safetensors",
900
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00002-of-00002.safetensors",
901
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00002-of-00002.safetensors",
902
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00002-of-00002.safetensors",
903
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00002-of-00002.safetensors",
904
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
905
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
906
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
907
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
908
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
909
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
910
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
911
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
912
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00002-of-00002.safetensors",
913
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00002-of-00002.safetensors",
914
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00002-of-00002.safetensors",
915
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00002-of-00002.safetensors",
916
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00002-of-00002.safetensors",
917
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00002-of-00002.safetensors",
918
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00002-of-00002.safetensors",
919
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00002-of-00002.safetensors",
920
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
921
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
922
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
923
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
924
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
925
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
926
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
927
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
928
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00002-of-00002.safetensors",
929
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00002-of-00002.safetensors",
930
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00002-of-00002.safetensors",
931
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00002-of-00002.safetensors",
932
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00002-of-00002.safetensors",
933
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00002-of-00002.safetensors",
934
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00002-of-00002.safetensors",
935
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00002-of-00002.safetensors",
936
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
937
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
938
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
939
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
940
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
941
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
942
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
943
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
944
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00002-of-00002.safetensors",
945
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00002-of-00002.safetensors",
946
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00002-of-00002.safetensors",
947
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00002-of-00002.safetensors",
948
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00002-of-00002.safetensors",
949
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00002-of-00002.safetensors",
950
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00002-of-00002.safetensors",
951
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00002-of-00002.safetensors",
952
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
953
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
954
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
955
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
956
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
957
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
958
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
959
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
960
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00002-of-00002.safetensors",
961
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00002-of-00002.safetensors",
962
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00002-of-00002.safetensors",
963
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00002-of-00002.safetensors",
964
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00002-of-00002.safetensors",
965
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00002-of-00002.safetensors",
966
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00002-of-00002.safetensors",
967
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00002-of-00002.safetensors",
968
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
969
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
970
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
971
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
972
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
973
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
974
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
975
+ "mm_model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
976
+ "mm_model.vision_tower.vision_tower.vision_model.post_layernorm.bias": "model-00002-of-00002.safetensors",
977
+ "mm_model.vision_tower.vision_tower.vision_model.post_layernorm.weight": "model-00002-of-00002.safetensors",
978
+ "mm_model.vision_tower.vision_tower.vision_model.pre_layrnorm.bias": "model-00002-of-00002.safetensors",
979
+ "mm_model.vision_tower.vision_tower.vision_model.pre_layrnorm.weight": "model-00002-of-00002.safetensors"
980
+ }
981
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|padding|>",
17
+ "unk_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,214 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": false,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<|endoftext|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<|padding|>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "50254": {
23
+ "content": " ",
24
+ "lstrip": false,
25
+ "normalized": true,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": false
29
+ },
30
+ "50255": {
31
+ "content": " ",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": false
37
+ },
38
+ "50256": {
39
+ "content": " ",
40
+ "lstrip": false,
41
+ "normalized": true,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": false
45
+ },
46
+ "50257": {
47
+ "content": " ",
48
+ "lstrip": false,
49
+ "normalized": true,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": false
53
+ },
54
+ "50258": {
55
+ "content": " ",
56
+ "lstrip": false,
57
+ "normalized": true,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": false
61
+ },
62
+ "50259": {
63
+ "content": " ",
64
+ "lstrip": false,
65
+ "normalized": true,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": false
69
+ },
70
+ "50260": {
71
+ "content": " ",
72
+ "lstrip": false,
73
+ "normalized": true,
74
+ "rstrip": false,
75
+ "single_word": false,
76
+ "special": false
77
+ },
78
+ "50261": {
79
+ "content": " ",
80
+ "lstrip": false,
81
+ "normalized": true,
82
+ "rstrip": false,
83
+ "single_word": false,
84
+ "special": false
85
+ },
86
+ "50262": {
87
+ "content": " ",
88
+ "lstrip": false,
89
+ "normalized": true,
90
+ "rstrip": false,
91
+ "single_word": false,
92
+ "special": false
93
+ },
94
+ "50263": {
95
+ "content": " ",
96
+ "lstrip": false,
97
+ "normalized": true,
98
+ "rstrip": false,
99
+ "single_word": false,
100
+ "special": false
101
+ },
102
+ "50264": {
103
+ "content": " ",
104
+ "lstrip": false,
105
+ "normalized": true,
106
+ "rstrip": false,
107
+ "single_word": false,
108
+ "special": false
109
+ },
110
+ "50265": {
111
+ "content": " ",
112
+ "lstrip": false,
113
+ "normalized": true,
114
+ "rstrip": false,
115
+ "single_word": false,
116
+ "special": false
117
+ },
118
+ "50266": {
119
+ "content": " ",
120
+ "lstrip": false,
121
+ "normalized": true,
122
+ "rstrip": false,
123
+ "single_word": false,
124
+ "special": false
125
+ },
126
+ "50267": {
127
+ "content": " ",
128
+ "lstrip": false,
129
+ "normalized": true,
130
+ "rstrip": false,
131
+ "single_word": false,
132
+ "special": false
133
+ },
134
+ "50268": {
135
+ "content": " ",
136
+ "lstrip": false,
137
+ "normalized": true,
138
+ "rstrip": false,
139
+ "single_word": false,
140
+ "special": false
141
+ },
142
+ "50269": {
143
+ "content": " ",
144
+ "lstrip": false,
145
+ "normalized": true,
146
+ "rstrip": false,
147
+ "single_word": false,
148
+ "special": false
149
+ },
150
+ "50270": {
151
+ "content": " ",
152
+ "lstrip": false,
153
+ "normalized": true,
154
+ "rstrip": false,
155
+ "single_word": false,
156
+ "special": false
157
+ },
158
+ "50271": {
159
+ "content": " ",
160
+ "lstrip": false,
161
+ "normalized": true,
162
+ "rstrip": false,
163
+ "single_word": false,
164
+ "special": false
165
+ },
166
+ "50272": {
167
+ "content": " ",
168
+ "lstrip": false,
169
+ "normalized": true,
170
+ "rstrip": false,
171
+ "single_word": false,
172
+ "special": false
173
+ },
174
+ "50273": {
175
+ "content": " ",
176
+ "lstrip": false,
177
+ "normalized": true,
178
+ "rstrip": false,
179
+ "single_word": false,
180
+ "special": false
181
+ },
182
+ "50274": {
183
+ "content": " ",
184
+ "lstrip": false,
185
+ "normalized": true,
186
+ "rstrip": false,
187
+ "single_word": false,
188
+ "special": false
189
+ },
190
+ "50275": {
191
+ "content": " ",
192
+ "lstrip": false,
193
+ "normalized": true,
194
+ "rstrip": false,
195
+ "single_word": false,
196
+ "special": false
197
+ },
198
+ "50276": {
199
+ "content": " ",
200
+ "lstrip": false,
201
+ "normalized": true,
202
+ "rstrip": false,
203
+ "single_word": false,
204
+ "special": false
205
+ }
206
+ },
207
+ "bos_token": "<|endoftext|>",
208
+ "clean_up_tokenization_spaces": true,
209
+ "eos_token": "<|endoftext|>",
210
+ "model_max_length": 1048576,
211
+ "pad_token": "<|padding|>",
212
+ "tokenizer_class": "GPTNeoXTokenizer",
213
+ "unk_token": "<|endoftext|>"
214
+ }
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c96d5933bc2ac3ee90be1f900722c69fda9e21240c1cc2032b817c2eccfb4b9
3
+ size 7096