hermeschen-ezcon commited on
Commit
025f76c
·
verified ·
1 Parent(s): 1d989bf

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ datasets:
5
+ - HuggingFaceM4/the_cauldron
6
+ - HuggingFaceM4/Docmatix
7
+ - lmms-lab/LLaVA-OneVision-Data
8
+ - lmms-lab/M4-Instruct-Data
9
+ - HuggingFaceFV/finevideo
10
+ - MAmmoTH-VL/MAmmoTH-VL-Instruct-12M
11
+ - lmms-lab/LLaVA-Video-178K
12
+ - orrzohar/Video-STaR
13
+ - Mutonix/Vript
14
+ - TIGER-Lab/VISTA-400K
15
+ - Enxin/MovieChat-1K_train
16
+ - ShareGPT4Video/ShareGPT4Video
17
+ pipeline_tag: image-text-to-text
18
+ tags:
19
+ - video-text-to-text
20
+ - mlx
21
+ language:
22
+ - en
23
+ base_model:
24
+ - HuggingFaceTB/SmolVLM-Instruct
25
+ ---
26
+
27
+ # EZCon/SmolVLM2-2.2B-Instruct-4bit-mlx
28
+ This model was converted to MLX format from [`HuggingFaceTB/SmolVLM2-2.2B-Instruct`]() using mlx-vlm version **0.3.2**.
29
+ Refer to the [original model card](https://huggingface.co/HuggingFaceTB/SmolVLM2-2.2B-Instruct) for more details on the model.
30
+ ## Use with mlx
31
+
32
+ ```bash
33
+ pip install -U mlx-vlm
34
+ ```
35
+
36
+ ```bash
37
+ python -m mlx_vlm.generate --model EZCon/SmolVLM2-2.2B-Instruct-4bit-mlx --max-tokens 100 --temperature 0.0 --prompt "Describe this image." --image <path_to_image>
38
+ ```
added_tokens.json ADDED
@@ -0,0 +1,130 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<end_of_utterance>": 49279,
3
+ "<fake_token_around_image>": 49189,
4
+ "<global-img>": 49152,
5
+ "<image>": 49190,
6
+ "<row_1_col_1>": 49153,
7
+ "<row_1_col_2>": 49154,
8
+ "<row_1_col_3>": 49155,
9
+ "<row_1_col_4>": 49156,
10
+ "<row_1_col_5>": 49157,
11
+ "<row_1_col_6>": 49158,
12
+ "<row_2_col_1>": 49159,
13
+ "<row_2_col_2>": 49160,
14
+ "<row_2_col_3>": 49161,
15
+ "<row_2_col_4>": 49162,
16
+ "<row_2_col_5>": 49163,
17
+ "<row_2_col_6>": 49164,
18
+ "<row_3_col_1>": 49165,
19
+ "<row_3_col_2>": 49166,
20
+ "<row_3_col_3>": 49167,
21
+ "<row_3_col_4>": 49168,
22
+ "<row_3_col_5>": 49169,
23
+ "<row_3_col_6>": 49170,
24
+ "<row_4_col_1>": 49171,
25
+ "<row_4_col_2>": 49172,
26
+ "<row_4_col_3>": 49173,
27
+ "<row_4_col_4>": 49174,
28
+ "<row_4_col_5>": 49175,
29
+ "<row_4_col_6>": 49176,
30
+ "<row_5_col_1>": 49177,
31
+ "<row_5_col_2>": 49178,
32
+ "<row_5_col_3>": 49179,
33
+ "<row_5_col_4>": 49180,
34
+ "<row_5_col_5>": 49181,
35
+ "<row_5_col_6>": 49182,
36
+ "<row_6_col_1>": 49183,
37
+ "<row_6_col_2>": 49184,
38
+ "<row_6_col_3>": 49185,
39
+ "<row_6_col_4>": 49186,
40
+ "<row_6_col_5>": 49187,
41
+ "<row_6_col_6>": 49188,
42
+ "<|reserved_special_token_0|>": 49191,
43
+ "<|reserved_special_token_10|>": 49201,
44
+ "<|reserved_special_token_11|>": 49202,
45
+ "<|reserved_special_token_12|>": 49203,
46
+ "<|reserved_special_token_13|>": 49204,
47
+ "<|reserved_special_token_14|>": 49205,
48
+ "<|reserved_special_token_15|>": 49206,
49
+ "<|reserved_special_token_16|>": 49207,
50
+ "<|reserved_special_token_17|>": 49208,
51
+ "<|reserved_special_token_18|>": 49209,
52
+ "<|reserved_special_token_19|>": 49210,
53
+ "<|reserved_special_token_1|>": 49192,
54
+ "<|reserved_special_token_20|>": 49211,
55
+ "<|reserved_special_token_21|>": 49212,
56
+ "<|reserved_special_token_22|>": 49213,
57
+ "<|reserved_special_token_23|>": 49214,
58
+ "<|reserved_special_token_24|>": 49215,
59
+ "<|reserved_special_token_25|>": 49216,
60
+ "<|reserved_special_token_26|>": 49217,
61
+ "<|reserved_special_token_27|>": 49218,
62
+ "<|reserved_special_token_28|>": 49219,
63
+ "<|reserved_special_token_29|>": 49220,
64
+ "<|reserved_special_token_2|>": 49193,
65
+ "<|reserved_special_token_30|>": 49221,
66
+ "<|reserved_special_token_31|>": 49222,
67
+ "<|reserved_special_token_32|>": 49223,
68
+ "<|reserved_special_token_33|>": 49224,
69
+ "<|reserved_special_token_34|>": 49225,
70
+ "<|reserved_special_token_35|>": 49226,
71
+ "<|reserved_special_token_36|>": 49227,
72
+ "<|reserved_special_token_37|>": 49228,
73
+ "<|reserved_special_token_38|>": 49229,
74
+ "<|reserved_special_token_39|>": 49230,
75
+ "<|reserved_special_token_3|>": 49194,
76
+ "<|reserved_special_token_40|>": 49231,
77
+ "<|reserved_special_token_41|>": 49232,
78
+ "<|reserved_special_token_42|>": 49233,
79
+ "<|reserved_special_token_43|>": 49234,
80
+ "<|reserved_special_token_44|>": 49235,
81
+ "<|reserved_special_token_45|>": 49236,
82
+ "<|reserved_special_token_46|>": 49237,
83
+ "<|reserved_special_token_47|>": 49238,
84
+ "<|reserved_special_token_48|>": 49239,
85
+ "<|reserved_special_token_49|>": 49240,
86
+ "<|reserved_special_token_4|>": 49195,
87
+ "<|reserved_special_token_50|>": 49241,
88
+ "<|reserved_special_token_51|>": 49242,
89
+ "<|reserved_special_token_52|>": 49243,
90
+ "<|reserved_special_token_53|>": 49244,
91
+ "<|reserved_special_token_54|>": 49245,
92
+ "<|reserved_special_token_55|>": 49246,
93
+ "<|reserved_special_token_56|>": 49247,
94
+ "<|reserved_special_token_57|>": 49248,
95
+ "<|reserved_special_token_58|>": 49249,
96
+ "<|reserved_special_token_59|>": 49250,
97
+ "<|reserved_special_token_5|>": 49196,
98
+ "<|reserved_special_token_60|>": 49251,
99
+ "<|reserved_special_token_61|>": 49252,
100
+ "<|reserved_special_token_62|>": 49253,
101
+ "<|reserved_special_token_63|>": 49254,
102
+ "<|reserved_special_token_64|>": 49255,
103
+ "<|reserved_special_token_65|>": 49256,
104
+ "<|reserved_special_token_66|>": 49257,
105
+ "<|reserved_special_token_67|>": 49258,
106
+ "<|reserved_special_token_68|>": 49259,
107
+ "<|reserved_special_token_69|>": 49260,
108
+ "<|reserved_special_token_6|>": 49197,
109
+ "<|reserved_special_token_70|>": 49261,
110
+ "<|reserved_special_token_71|>": 49262,
111
+ "<|reserved_special_token_72|>": 49263,
112
+ "<|reserved_special_token_73|>": 49264,
113
+ "<|reserved_special_token_74|>": 49265,
114
+ "<|reserved_special_token_75|>": 49266,
115
+ "<|reserved_special_token_76|>": 49267,
116
+ "<|reserved_special_token_77|>": 49268,
117
+ "<|reserved_special_token_78|>": 49269,
118
+ "<|reserved_special_token_79|>": 49270,
119
+ "<|reserved_special_token_7|>": 49198,
120
+ "<|reserved_special_token_80|>": 49271,
121
+ "<|reserved_special_token_81|>": 49272,
122
+ "<|reserved_special_token_82|>": 49273,
123
+ "<|reserved_special_token_83|>": 49274,
124
+ "<|reserved_special_token_84|>": 49275,
125
+ "<|reserved_special_token_85|>": 49276,
126
+ "<|reserved_special_token_86|>": 49277,
127
+ "<|reserved_special_token_87|>": 49278,
128
+ "<|reserved_special_token_8|>": 49199,
129
+ "<|reserved_special_token_9|>": 49200
130
+ }
chat_template.jinja ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ <|im_start|>{% for message in messages %}{{message['role'] | capitalize}}{% if message['content'][0]['type'] == 'image' %}{{':'}}{% else %}{{': '}}{% endif %}{% for line in message['content'] %}{% if line['type'] == 'text' %}{{line['text']}}{% elif line['type'] == 'image' %}{{ '<image>' }}{% endif %}{% endfor %}<end_of_utterance>
2
+ {% endfor %}{% if add_generation_prompt %}{{ 'Assistant:' }}{% endif %}
chat_template.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "chat_template": "<|im_start|>{% for message in messages %}{{message['role'] | capitalize}}{% if message['content'][0]['type'] == 'image' %}{{':'}}{% else %}{{': '}}{% endif %}{% for line in message['content'] %}{% if line['type'] == 'text' %}{{line['text']}}{% elif line['type'] == 'image' %}{{ '<image>' }}{% endif %}{% endfor %}<end_of_utterance>\n{% endfor %}{% if add_generation_prompt %}{{ 'Assistant:' }}{% endif %}"
3
+ }
config.json ADDED
@@ -0,0 +1,1305 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_cross_attention": false,
3
+ "architectures": [
4
+ "SmolVLMForConditionalGeneration"
5
+ ],
6
+ "bad_words_ids": null,
7
+ "begin_suppress_tokens": null,
8
+ "bos_token_id": null,
9
+ "chunk_size_feed_forward": 0,
10
+ "cross_attention_hidden_size": null,
11
+ "decoder_start_token_id": null,
12
+ "diversity_penalty": 0.0,
13
+ "do_sample": false,
14
+ "early_stopping": false,
15
+ "encoder_no_repeat_ngram_size": 0,
16
+ "eos_token_id": null,
17
+ "exponential_decay_length_penalty": null,
18
+ "finetuning_task": null,
19
+ "forced_bos_token_id": null,
20
+ "forced_eos_token_id": null,
21
+ "id2label": {
22
+ "0": "LABEL_0",
23
+ "1": "LABEL_1"
24
+ },
25
+ "image_token_id": 49190,
26
+ "is_decoder": false,
27
+ "is_encoder_decoder": false,
28
+ "label2id": {
29
+ "LABEL_0": 0,
30
+ "LABEL_1": 1
31
+ },
32
+ "length_penalty": 1.0,
33
+ "max_length": 20,
34
+ "min_length": 0,
35
+ "model_type": "smolvlm",
36
+ "no_repeat_ngram_size": 0,
37
+ "num_beam_groups": 1,
38
+ "num_beams": 1,
39
+ "num_return_sequences": 1,
40
+ "output_attentions": false,
41
+ "output_hidden_states": false,
42
+ "output_scores": false,
43
+ "pad_token_id": 128002,
44
+ "prefix": null,
45
+ "problem_type": null,
46
+ "pruned_heads": {},
47
+ "quantization": {
48
+ "group_size": 64,
49
+ "bits": 4,
50
+ "vision_model.embeddings.patch_embedding": false,
51
+ "vision_model.embeddings.position_embedding": false,
52
+ "vision_model.encoder.layers.0.self_attn.q_proj": false,
53
+ "vision_model.encoder.layers.0.self_attn.k_proj": false,
54
+ "vision_model.encoder.layers.0.self_attn.v_proj": false,
55
+ "vision_model.encoder.layers.0.self_attn.out_proj": false,
56
+ "vision_model.encoder.layers.0.layer_norm1": false,
57
+ "vision_model.encoder.layers.0.mlp.activation_fn": false,
58
+ "vision_model.encoder.layers.0.mlp.fc1": false,
59
+ "vision_model.encoder.layers.0.mlp.fc2": false,
60
+ "vision_model.encoder.layers.0.layer_norm2": false,
61
+ "vision_model.encoder.layers.1.self_attn.q_proj": false,
62
+ "vision_model.encoder.layers.1.self_attn.k_proj": false,
63
+ "vision_model.encoder.layers.1.self_attn.v_proj": false,
64
+ "vision_model.encoder.layers.1.self_attn.out_proj": false,
65
+ "vision_model.encoder.layers.1.layer_norm1": false,
66
+ "vision_model.encoder.layers.1.mlp.activation_fn": false,
67
+ "vision_model.encoder.layers.1.mlp.fc1": false,
68
+ "vision_model.encoder.layers.1.mlp.fc2": false,
69
+ "vision_model.encoder.layers.1.layer_norm2": false,
70
+ "vision_model.encoder.layers.2.self_attn.q_proj": false,
71
+ "vision_model.encoder.layers.2.self_attn.k_proj": false,
72
+ "vision_model.encoder.layers.2.self_attn.v_proj": false,
73
+ "vision_model.encoder.layers.2.self_attn.out_proj": false,
74
+ "vision_model.encoder.layers.2.layer_norm1": false,
75
+ "vision_model.encoder.layers.2.mlp.activation_fn": false,
76
+ "vision_model.encoder.layers.2.mlp.fc1": false,
77
+ "vision_model.encoder.layers.2.mlp.fc2": false,
78
+ "vision_model.encoder.layers.2.layer_norm2": false,
79
+ "vision_model.encoder.layers.3.self_attn.q_proj": false,
80
+ "vision_model.encoder.layers.3.self_attn.k_proj": false,
81
+ "vision_model.encoder.layers.3.self_attn.v_proj": false,
82
+ "vision_model.encoder.layers.3.self_attn.out_proj": false,
83
+ "vision_model.encoder.layers.3.layer_norm1": false,
84
+ "vision_model.encoder.layers.3.mlp.activation_fn": false,
85
+ "vision_model.encoder.layers.3.mlp.fc1": false,
86
+ "vision_model.encoder.layers.3.mlp.fc2": false,
87
+ "vision_model.encoder.layers.3.layer_norm2": false,
88
+ "vision_model.encoder.layers.4.self_attn.q_proj": false,
89
+ "vision_model.encoder.layers.4.self_attn.k_proj": false,
90
+ "vision_model.encoder.layers.4.self_attn.v_proj": false,
91
+ "vision_model.encoder.layers.4.self_attn.out_proj": false,
92
+ "vision_model.encoder.layers.4.layer_norm1": false,
93
+ "vision_model.encoder.layers.4.mlp.activation_fn": false,
94
+ "vision_model.encoder.layers.4.mlp.fc1": false,
95
+ "vision_model.encoder.layers.4.mlp.fc2": false,
96
+ "vision_model.encoder.layers.4.layer_norm2": false,
97
+ "vision_model.encoder.layers.5.self_attn.q_proj": false,
98
+ "vision_model.encoder.layers.5.self_attn.k_proj": false,
99
+ "vision_model.encoder.layers.5.self_attn.v_proj": false,
100
+ "vision_model.encoder.layers.5.self_attn.out_proj": false,
101
+ "vision_model.encoder.layers.5.layer_norm1": false,
102
+ "vision_model.encoder.layers.5.mlp.activation_fn": false,
103
+ "vision_model.encoder.layers.5.mlp.fc1": false,
104
+ "vision_model.encoder.layers.5.mlp.fc2": false,
105
+ "vision_model.encoder.layers.5.layer_norm2": false,
106
+ "vision_model.encoder.layers.6.self_attn.q_proj": false,
107
+ "vision_model.encoder.layers.6.self_attn.k_proj": false,
108
+ "vision_model.encoder.layers.6.self_attn.v_proj": false,
109
+ "vision_model.encoder.layers.6.self_attn.out_proj": false,
110
+ "vision_model.encoder.layers.6.layer_norm1": false,
111
+ "vision_model.encoder.layers.6.mlp.activation_fn": false,
112
+ "vision_model.encoder.layers.6.mlp.fc1": false,
113
+ "vision_model.encoder.layers.6.mlp.fc2": false,
114
+ "vision_model.encoder.layers.6.layer_norm2": false,
115
+ "vision_model.encoder.layers.7.self_attn.q_proj": false,
116
+ "vision_model.encoder.layers.7.self_attn.k_proj": false,
117
+ "vision_model.encoder.layers.7.self_attn.v_proj": false,
118
+ "vision_model.encoder.layers.7.self_attn.out_proj": false,
119
+ "vision_model.encoder.layers.7.layer_norm1": false,
120
+ "vision_model.encoder.layers.7.mlp.activation_fn": false,
121
+ "vision_model.encoder.layers.7.mlp.fc1": false,
122
+ "vision_model.encoder.layers.7.mlp.fc2": false,
123
+ "vision_model.encoder.layers.7.layer_norm2": false,
124
+ "vision_model.encoder.layers.8.self_attn.q_proj": false,
125
+ "vision_model.encoder.layers.8.self_attn.k_proj": false,
126
+ "vision_model.encoder.layers.8.self_attn.v_proj": false,
127
+ "vision_model.encoder.layers.8.self_attn.out_proj": false,
128
+ "vision_model.encoder.layers.8.layer_norm1": false,
129
+ "vision_model.encoder.layers.8.mlp.activation_fn": false,
130
+ "vision_model.encoder.layers.8.mlp.fc1": false,
131
+ "vision_model.encoder.layers.8.mlp.fc2": false,
132
+ "vision_model.encoder.layers.8.layer_norm2": false,
133
+ "vision_model.encoder.layers.9.self_attn.q_proj": false,
134
+ "vision_model.encoder.layers.9.self_attn.k_proj": false,
135
+ "vision_model.encoder.layers.9.self_attn.v_proj": false,
136
+ "vision_model.encoder.layers.9.self_attn.out_proj": false,
137
+ "vision_model.encoder.layers.9.layer_norm1": false,
138
+ "vision_model.encoder.layers.9.mlp.activation_fn": false,
139
+ "vision_model.encoder.layers.9.mlp.fc1": false,
140
+ "vision_model.encoder.layers.9.mlp.fc2": false,
141
+ "vision_model.encoder.layers.9.layer_norm2": false,
142
+ "vision_model.encoder.layers.10.self_attn.q_proj": false,
143
+ "vision_model.encoder.layers.10.self_attn.k_proj": false,
144
+ "vision_model.encoder.layers.10.self_attn.v_proj": false,
145
+ "vision_model.encoder.layers.10.self_attn.out_proj": false,
146
+ "vision_model.encoder.layers.10.layer_norm1": false,
147
+ "vision_model.encoder.layers.10.mlp.activation_fn": false,
148
+ "vision_model.encoder.layers.10.mlp.fc1": false,
149
+ "vision_model.encoder.layers.10.mlp.fc2": false,
150
+ "vision_model.encoder.layers.10.layer_norm2": false,
151
+ "vision_model.encoder.layers.11.self_attn.q_proj": false,
152
+ "vision_model.encoder.layers.11.self_attn.k_proj": false,
153
+ "vision_model.encoder.layers.11.self_attn.v_proj": false,
154
+ "vision_model.encoder.layers.11.self_attn.out_proj": false,
155
+ "vision_model.encoder.layers.11.layer_norm1": false,
156
+ "vision_model.encoder.layers.11.mlp.activation_fn": false,
157
+ "vision_model.encoder.layers.11.mlp.fc1": false,
158
+ "vision_model.encoder.layers.11.mlp.fc2": false,
159
+ "vision_model.encoder.layers.11.layer_norm2": false,
160
+ "vision_model.encoder.layers.12.self_attn.q_proj": false,
161
+ "vision_model.encoder.layers.12.self_attn.k_proj": false,
162
+ "vision_model.encoder.layers.12.self_attn.v_proj": false,
163
+ "vision_model.encoder.layers.12.self_attn.out_proj": false,
164
+ "vision_model.encoder.layers.12.layer_norm1": false,
165
+ "vision_model.encoder.layers.12.mlp.activation_fn": false,
166
+ "vision_model.encoder.layers.12.mlp.fc1": false,
167
+ "vision_model.encoder.layers.12.mlp.fc2": false,
168
+ "vision_model.encoder.layers.12.layer_norm2": false,
169
+ "vision_model.encoder.layers.13.self_attn.q_proj": false,
170
+ "vision_model.encoder.layers.13.self_attn.k_proj": false,
171
+ "vision_model.encoder.layers.13.self_attn.v_proj": false,
172
+ "vision_model.encoder.layers.13.self_attn.out_proj": false,
173
+ "vision_model.encoder.layers.13.layer_norm1": false,
174
+ "vision_model.encoder.layers.13.mlp.activation_fn": false,
175
+ "vision_model.encoder.layers.13.mlp.fc1": false,
176
+ "vision_model.encoder.layers.13.mlp.fc2": false,
177
+ "vision_model.encoder.layers.13.layer_norm2": false,
178
+ "vision_model.encoder.layers.14.self_attn.q_proj": false,
179
+ "vision_model.encoder.layers.14.self_attn.k_proj": false,
180
+ "vision_model.encoder.layers.14.self_attn.v_proj": false,
181
+ "vision_model.encoder.layers.14.self_attn.out_proj": false,
182
+ "vision_model.encoder.layers.14.layer_norm1": false,
183
+ "vision_model.encoder.layers.14.mlp.activation_fn": false,
184
+ "vision_model.encoder.layers.14.mlp.fc1": false,
185
+ "vision_model.encoder.layers.14.mlp.fc2": false,
186
+ "vision_model.encoder.layers.14.layer_norm2": false,
187
+ "vision_model.encoder.layers.15.self_attn.q_proj": false,
188
+ "vision_model.encoder.layers.15.self_attn.k_proj": false,
189
+ "vision_model.encoder.layers.15.self_attn.v_proj": false,
190
+ "vision_model.encoder.layers.15.self_attn.out_proj": false,
191
+ "vision_model.encoder.layers.15.layer_norm1": false,
192
+ "vision_model.encoder.layers.15.mlp.activation_fn": false,
193
+ "vision_model.encoder.layers.15.mlp.fc1": false,
194
+ "vision_model.encoder.layers.15.mlp.fc2": false,
195
+ "vision_model.encoder.layers.15.layer_norm2": false,
196
+ "vision_model.encoder.layers.16.self_attn.q_proj": false,
197
+ "vision_model.encoder.layers.16.self_attn.k_proj": false,
198
+ "vision_model.encoder.layers.16.self_attn.v_proj": false,
199
+ "vision_model.encoder.layers.16.self_attn.out_proj": false,
200
+ "vision_model.encoder.layers.16.layer_norm1": false,
201
+ "vision_model.encoder.layers.16.mlp.activation_fn": false,
202
+ "vision_model.encoder.layers.16.mlp.fc1": false,
203
+ "vision_model.encoder.layers.16.mlp.fc2": false,
204
+ "vision_model.encoder.layers.16.layer_norm2": false,
205
+ "vision_model.encoder.layers.17.self_attn.q_proj": false,
206
+ "vision_model.encoder.layers.17.self_attn.k_proj": false,
207
+ "vision_model.encoder.layers.17.self_attn.v_proj": false,
208
+ "vision_model.encoder.layers.17.self_attn.out_proj": false,
209
+ "vision_model.encoder.layers.17.layer_norm1": false,
210
+ "vision_model.encoder.layers.17.mlp.activation_fn": false,
211
+ "vision_model.encoder.layers.17.mlp.fc1": false,
212
+ "vision_model.encoder.layers.17.mlp.fc2": false,
213
+ "vision_model.encoder.layers.17.layer_norm2": false,
214
+ "vision_model.encoder.layers.18.self_attn.q_proj": false,
215
+ "vision_model.encoder.layers.18.self_attn.k_proj": false,
216
+ "vision_model.encoder.layers.18.self_attn.v_proj": false,
217
+ "vision_model.encoder.layers.18.self_attn.out_proj": false,
218
+ "vision_model.encoder.layers.18.layer_norm1": false,
219
+ "vision_model.encoder.layers.18.mlp.activation_fn": false,
220
+ "vision_model.encoder.layers.18.mlp.fc1": false,
221
+ "vision_model.encoder.layers.18.mlp.fc2": false,
222
+ "vision_model.encoder.layers.18.layer_norm2": false,
223
+ "vision_model.encoder.layers.19.self_attn.q_proj": false,
224
+ "vision_model.encoder.layers.19.self_attn.k_proj": false,
225
+ "vision_model.encoder.layers.19.self_attn.v_proj": false,
226
+ "vision_model.encoder.layers.19.self_attn.out_proj": false,
227
+ "vision_model.encoder.layers.19.layer_norm1": false,
228
+ "vision_model.encoder.layers.19.mlp.activation_fn": false,
229
+ "vision_model.encoder.layers.19.mlp.fc1": false,
230
+ "vision_model.encoder.layers.19.mlp.fc2": false,
231
+ "vision_model.encoder.layers.19.layer_norm2": false,
232
+ "vision_model.encoder.layers.20.self_attn.q_proj": false,
233
+ "vision_model.encoder.layers.20.self_attn.k_proj": false,
234
+ "vision_model.encoder.layers.20.self_attn.v_proj": false,
235
+ "vision_model.encoder.layers.20.self_attn.out_proj": false,
236
+ "vision_model.encoder.layers.20.layer_norm1": false,
237
+ "vision_model.encoder.layers.20.mlp.activation_fn": false,
238
+ "vision_model.encoder.layers.20.mlp.fc1": false,
239
+ "vision_model.encoder.layers.20.mlp.fc2": false,
240
+ "vision_model.encoder.layers.20.layer_norm2": false,
241
+ "vision_model.encoder.layers.21.self_attn.q_proj": false,
242
+ "vision_model.encoder.layers.21.self_attn.k_proj": false,
243
+ "vision_model.encoder.layers.21.self_attn.v_proj": false,
244
+ "vision_model.encoder.layers.21.self_attn.out_proj": false,
245
+ "vision_model.encoder.layers.21.layer_norm1": false,
246
+ "vision_model.encoder.layers.21.mlp.activation_fn": false,
247
+ "vision_model.encoder.layers.21.mlp.fc1": false,
248
+ "vision_model.encoder.layers.21.mlp.fc2": false,
249
+ "vision_model.encoder.layers.21.layer_norm2": false,
250
+ "vision_model.encoder.layers.22.self_attn.q_proj": false,
251
+ "vision_model.encoder.layers.22.self_attn.k_proj": false,
252
+ "vision_model.encoder.layers.22.self_attn.v_proj": false,
253
+ "vision_model.encoder.layers.22.self_attn.out_proj": false,
254
+ "vision_model.encoder.layers.22.layer_norm1": false,
255
+ "vision_model.encoder.layers.22.mlp.activation_fn": false,
256
+ "vision_model.encoder.layers.22.mlp.fc1": false,
257
+ "vision_model.encoder.layers.22.mlp.fc2": false,
258
+ "vision_model.encoder.layers.22.layer_norm2": false,
259
+ "vision_model.encoder.layers.23.self_attn.q_proj": false,
260
+ "vision_model.encoder.layers.23.self_attn.k_proj": false,
261
+ "vision_model.encoder.layers.23.self_attn.v_proj": false,
262
+ "vision_model.encoder.layers.23.self_attn.out_proj": false,
263
+ "vision_model.encoder.layers.23.layer_norm1": false,
264
+ "vision_model.encoder.layers.23.mlp.activation_fn": false,
265
+ "vision_model.encoder.layers.23.mlp.fc1": false,
266
+ "vision_model.encoder.layers.23.mlp.fc2": false,
267
+ "vision_model.encoder.layers.23.layer_norm2": false,
268
+ "vision_model.encoder.layers.24.self_attn.q_proj": false,
269
+ "vision_model.encoder.layers.24.self_attn.k_proj": false,
270
+ "vision_model.encoder.layers.24.self_attn.v_proj": false,
271
+ "vision_model.encoder.layers.24.self_attn.out_proj": false,
272
+ "vision_model.encoder.layers.24.layer_norm1": false,
273
+ "vision_model.encoder.layers.24.mlp.activation_fn": false,
274
+ "vision_model.encoder.layers.24.mlp.fc1": false,
275
+ "vision_model.encoder.layers.24.mlp.fc2": false,
276
+ "vision_model.encoder.layers.24.layer_norm2": false,
277
+ "vision_model.encoder.layers.25.self_attn.q_proj": false,
278
+ "vision_model.encoder.layers.25.self_attn.k_proj": false,
279
+ "vision_model.encoder.layers.25.self_attn.v_proj": false,
280
+ "vision_model.encoder.layers.25.self_attn.out_proj": false,
281
+ "vision_model.encoder.layers.25.layer_norm1": false,
282
+ "vision_model.encoder.layers.25.mlp.activation_fn": false,
283
+ "vision_model.encoder.layers.25.mlp.fc1": false,
284
+ "vision_model.encoder.layers.25.mlp.fc2": false,
285
+ "vision_model.encoder.layers.25.layer_norm2": false,
286
+ "vision_model.encoder.layers.26.self_attn.q_proj": false,
287
+ "vision_model.encoder.layers.26.self_attn.k_proj": false,
288
+ "vision_model.encoder.layers.26.self_attn.v_proj": false,
289
+ "vision_model.encoder.layers.26.self_attn.out_proj": false,
290
+ "vision_model.encoder.layers.26.layer_norm1": false,
291
+ "vision_model.encoder.layers.26.mlp.activation_fn": false,
292
+ "vision_model.encoder.layers.26.mlp.fc1": false,
293
+ "vision_model.encoder.layers.26.mlp.fc2": false,
294
+ "vision_model.encoder.layers.26.layer_norm2": false,
295
+ "vision_model.post_layernorm": false,
296
+ "language_model.embed_tokens": true,
297
+ "language_model.layers.0.self_attn.q_proj": true,
298
+ "language_model.layers.0.self_attn.k_proj": true,
299
+ "language_model.layers.0.self_attn.v_proj": true,
300
+ "language_model.layers.0.self_attn.o_proj": true,
301
+ "language_model.layers.0.self_attn.rope": false,
302
+ "language_model.layers.0.mlp.gate_proj": true,
303
+ "language_model.layers.0.mlp.down_proj": true,
304
+ "language_model.layers.0.mlp.up_proj": true,
305
+ "language_model.layers.0.input_layernorm": false,
306
+ "language_model.layers.0.post_attention_layernorm": false,
307
+ "language_model.layers.1.self_attn.q_proj": true,
308
+ "language_model.layers.1.self_attn.k_proj": true,
309
+ "language_model.layers.1.self_attn.v_proj": true,
310
+ "language_model.layers.1.self_attn.o_proj": true,
311
+ "language_model.layers.1.self_attn.rope": false,
312
+ "language_model.layers.1.mlp.gate_proj": true,
313
+ "language_model.layers.1.mlp.down_proj": true,
314
+ "language_model.layers.1.mlp.up_proj": true,
315
+ "language_model.layers.1.input_layernorm": false,
316
+ "language_model.layers.1.post_attention_layernorm": false,
317
+ "language_model.layers.2.self_attn.q_proj": true,
318
+ "language_model.layers.2.self_attn.k_proj": true,
319
+ "language_model.layers.2.self_attn.v_proj": true,
320
+ "language_model.layers.2.self_attn.o_proj": true,
321
+ "language_model.layers.2.self_attn.rope": false,
322
+ "language_model.layers.2.mlp.gate_proj": true,
323
+ "language_model.layers.2.mlp.down_proj": true,
324
+ "language_model.layers.2.mlp.up_proj": true,
325
+ "language_model.layers.2.input_layernorm": false,
326
+ "language_model.layers.2.post_attention_layernorm": false,
327
+ "language_model.layers.3.self_attn.q_proj": true,
328
+ "language_model.layers.3.self_attn.k_proj": true,
329
+ "language_model.layers.3.self_attn.v_proj": true,
330
+ "language_model.layers.3.self_attn.o_proj": true,
331
+ "language_model.layers.3.self_attn.rope": false,
332
+ "language_model.layers.3.mlp.gate_proj": true,
333
+ "language_model.layers.3.mlp.down_proj": true,
334
+ "language_model.layers.3.mlp.up_proj": true,
335
+ "language_model.layers.3.input_layernorm": false,
336
+ "language_model.layers.3.post_attention_layernorm": false,
337
+ "language_model.layers.4.self_attn.q_proj": true,
338
+ "language_model.layers.4.self_attn.k_proj": true,
339
+ "language_model.layers.4.self_attn.v_proj": true,
340
+ "language_model.layers.4.self_attn.o_proj": true,
341
+ "language_model.layers.4.self_attn.rope": false,
342
+ "language_model.layers.4.mlp.gate_proj": true,
343
+ "language_model.layers.4.mlp.down_proj": true,
344
+ "language_model.layers.4.mlp.up_proj": true,
345
+ "language_model.layers.4.input_layernorm": false,
346
+ "language_model.layers.4.post_attention_layernorm": false,
347
+ "language_model.layers.5.self_attn.q_proj": true,
348
+ "language_model.layers.5.self_attn.k_proj": true,
349
+ "language_model.layers.5.self_attn.v_proj": true,
350
+ "language_model.layers.5.self_attn.o_proj": true,
351
+ "language_model.layers.5.self_attn.rope": false,
352
+ "language_model.layers.5.mlp.gate_proj": true,
353
+ "language_model.layers.5.mlp.down_proj": true,
354
+ "language_model.layers.5.mlp.up_proj": true,
355
+ "language_model.layers.5.input_layernorm": false,
356
+ "language_model.layers.5.post_attention_layernorm": false,
357
+ "language_model.layers.6.self_attn.q_proj": true,
358
+ "language_model.layers.6.self_attn.k_proj": true,
359
+ "language_model.layers.6.self_attn.v_proj": true,
360
+ "language_model.layers.6.self_attn.o_proj": true,
361
+ "language_model.layers.6.self_attn.rope": false,
362
+ "language_model.layers.6.mlp.gate_proj": true,
363
+ "language_model.layers.6.mlp.down_proj": true,
364
+ "language_model.layers.6.mlp.up_proj": true,
365
+ "language_model.layers.6.input_layernorm": false,
366
+ "language_model.layers.6.post_attention_layernorm": false,
367
+ "language_model.layers.7.self_attn.q_proj": true,
368
+ "language_model.layers.7.self_attn.k_proj": true,
369
+ "language_model.layers.7.self_attn.v_proj": true,
370
+ "language_model.layers.7.self_attn.o_proj": true,
371
+ "language_model.layers.7.self_attn.rope": false,
372
+ "language_model.layers.7.mlp.gate_proj": true,
373
+ "language_model.layers.7.mlp.down_proj": true,
374
+ "language_model.layers.7.mlp.up_proj": true,
375
+ "language_model.layers.7.input_layernorm": false,
376
+ "language_model.layers.7.post_attention_layernorm": false,
377
+ "language_model.layers.8.self_attn.q_proj": true,
378
+ "language_model.layers.8.self_attn.k_proj": true,
379
+ "language_model.layers.8.self_attn.v_proj": true,
380
+ "language_model.layers.8.self_attn.o_proj": true,
381
+ "language_model.layers.8.self_attn.rope": false,
382
+ "language_model.layers.8.mlp.gate_proj": true,
383
+ "language_model.layers.8.mlp.down_proj": true,
384
+ "language_model.layers.8.mlp.up_proj": true,
385
+ "language_model.layers.8.input_layernorm": false,
386
+ "language_model.layers.8.post_attention_layernorm": false,
387
+ "language_model.layers.9.self_attn.q_proj": true,
388
+ "language_model.layers.9.self_attn.k_proj": true,
389
+ "language_model.layers.9.self_attn.v_proj": true,
390
+ "language_model.layers.9.self_attn.o_proj": true,
391
+ "language_model.layers.9.self_attn.rope": false,
392
+ "language_model.layers.9.mlp.gate_proj": true,
393
+ "language_model.layers.9.mlp.down_proj": true,
394
+ "language_model.layers.9.mlp.up_proj": true,
395
+ "language_model.layers.9.input_layernorm": false,
396
+ "language_model.layers.9.post_attention_layernorm": false,
397
+ "language_model.layers.10.self_attn.q_proj": true,
398
+ "language_model.layers.10.self_attn.k_proj": true,
399
+ "language_model.layers.10.self_attn.v_proj": true,
400
+ "language_model.layers.10.self_attn.o_proj": true,
401
+ "language_model.layers.10.self_attn.rope": false,
402
+ "language_model.layers.10.mlp.gate_proj": true,
403
+ "language_model.layers.10.mlp.down_proj": true,
404
+ "language_model.layers.10.mlp.up_proj": true,
405
+ "language_model.layers.10.input_layernorm": false,
406
+ "language_model.layers.10.post_attention_layernorm": false,
407
+ "language_model.layers.11.self_attn.q_proj": true,
408
+ "language_model.layers.11.self_attn.k_proj": true,
409
+ "language_model.layers.11.self_attn.v_proj": true,
410
+ "language_model.layers.11.self_attn.o_proj": true,
411
+ "language_model.layers.11.self_attn.rope": false,
412
+ "language_model.layers.11.mlp.gate_proj": true,
413
+ "language_model.layers.11.mlp.down_proj": true,
414
+ "language_model.layers.11.mlp.up_proj": true,
415
+ "language_model.layers.11.input_layernorm": false,
416
+ "language_model.layers.11.post_attention_layernorm": false,
417
+ "language_model.layers.12.self_attn.q_proj": true,
418
+ "language_model.layers.12.self_attn.k_proj": true,
419
+ "language_model.layers.12.self_attn.v_proj": true,
420
+ "language_model.layers.12.self_attn.o_proj": true,
421
+ "language_model.layers.12.self_attn.rope": false,
422
+ "language_model.layers.12.mlp.gate_proj": true,
423
+ "language_model.layers.12.mlp.down_proj": true,
424
+ "language_model.layers.12.mlp.up_proj": true,
425
+ "language_model.layers.12.input_layernorm": false,
426
+ "language_model.layers.12.post_attention_layernorm": false,
427
+ "language_model.layers.13.self_attn.q_proj": true,
428
+ "language_model.layers.13.self_attn.k_proj": true,
429
+ "language_model.layers.13.self_attn.v_proj": true,
430
+ "language_model.layers.13.self_attn.o_proj": true,
431
+ "language_model.layers.13.self_attn.rope": false,
432
+ "language_model.layers.13.mlp.gate_proj": true,
433
+ "language_model.layers.13.mlp.down_proj": true,
434
+ "language_model.layers.13.mlp.up_proj": true,
435
+ "language_model.layers.13.input_layernorm": false,
436
+ "language_model.layers.13.post_attention_layernorm": false,
437
+ "language_model.layers.14.self_attn.q_proj": true,
438
+ "language_model.layers.14.self_attn.k_proj": true,
439
+ "language_model.layers.14.self_attn.v_proj": true,
440
+ "language_model.layers.14.self_attn.o_proj": true,
441
+ "language_model.layers.14.self_attn.rope": false,
442
+ "language_model.layers.14.mlp.gate_proj": true,
443
+ "language_model.layers.14.mlp.down_proj": true,
444
+ "language_model.layers.14.mlp.up_proj": true,
445
+ "language_model.layers.14.input_layernorm": false,
446
+ "language_model.layers.14.post_attention_layernorm": false,
447
+ "language_model.layers.15.self_attn.q_proj": true,
448
+ "language_model.layers.15.self_attn.k_proj": true,
449
+ "language_model.layers.15.self_attn.v_proj": true,
450
+ "language_model.layers.15.self_attn.o_proj": true,
451
+ "language_model.layers.15.self_attn.rope": false,
452
+ "language_model.layers.15.mlp.gate_proj": true,
453
+ "language_model.layers.15.mlp.down_proj": true,
454
+ "language_model.layers.15.mlp.up_proj": true,
455
+ "language_model.layers.15.input_layernorm": false,
456
+ "language_model.layers.15.post_attention_layernorm": false,
457
+ "language_model.layers.16.self_attn.q_proj": true,
458
+ "language_model.layers.16.self_attn.k_proj": true,
459
+ "language_model.layers.16.self_attn.v_proj": true,
460
+ "language_model.layers.16.self_attn.o_proj": true,
461
+ "language_model.layers.16.self_attn.rope": false,
462
+ "language_model.layers.16.mlp.gate_proj": true,
463
+ "language_model.layers.16.mlp.down_proj": true,
464
+ "language_model.layers.16.mlp.up_proj": true,
465
+ "language_model.layers.16.input_layernorm": false,
466
+ "language_model.layers.16.post_attention_layernorm": false,
467
+ "language_model.layers.17.self_attn.q_proj": true,
468
+ "language_model.layers.17.self_attn.k_proj": true,
469
+ "language_model.layers.17.self_attn.v_proj": true,
470
+ "language_model.layers.17.self_attn.o_proj": true,
471
+ "language_model.layers.17.self_attn.rope": false,
472
+ "language_model.layers.17.mlp.gate_proj": true,
473
+ "language_model.layers.17.mlp.down_proj": true,
474
+ "language_model.layers.17.mlp.up_proj": true,
475
+ "language_model.layers.17.input_layernorm": false,
476
+ "language_model.layers.17.post_attention_layernorm": false,
477
+ "language_model.layers.18.self_attn.q_proj": true,
478
+ "language_model.layers.18.self_attn.k_proj": true,
479
+ "language_model.layers.18.self_attn.v_proj": true,
480
+ "language_model.layers.18.self_attn.o_proj": true,
481
+ "language_model.layers.18.self_attn.rope": false,
482
+ "language_model.layers.18.mlp.gate_proj": true,
483
+ "language_model.layers.18.mlp.down_proj": true,
484
+ "language_model.layers.18.mlp.up_proj": true,
485
+ "language_model.layers.18.input_layernorm": false,
486
+ "language_model.layers.18.post_attention_layernorm": false,
487
+ "language_model.layers.19.self_attn.q_proj": true,
488
+ "language_model.layers.19.self_attn.k_proj": true,
489
+ "language_model.layers.19.self_attn.v_proj": true,
490
+ "language_model.layers.19.self_attn.o_proj": true,
491
+ "language_model.layers.19.self_attn.rope": false,
492
+ "language_model.layers.19.mlp.gate_proj": true,
493
+ "language_model.layers.19.mlp.down_proj": true,
494
+ "language_model.layers.19.mlp.up_proj": true,
495
+ "language_model.layers.19.input_layernorm": false,
496
+ "language_model.layers.19.post_attention_layernorm": false,
497
+ "language_model.layers.20.self_attn.q_proj": true,
498
+ "language_model.layers.20.self_attn.k_proj": true,
499
+ "language_model.layers.20.self_attn.v_proj": true,
500
+ "language_model.layers.20.self_attn.o_proj": true,
501
+ "language_model.layers.20.self_attn.rope": false,
502
+ "language_model.layers.20.mlp.gate_proj": true,
503
+ "language_model.layers.20.mlp.down_proj": true,
504
+ "language_model.layers.20.mlp.up_proj": true,
505
+ "language_model.layers.20.input_layernorm": false,
506
+ "language_model.layers.20.post_attention_layernorm": false,
507
+ "language_model.layers.21.self_attn.q_proj": true,
508
+ "language_model.layers.21.self_attn.k_proj": true,
509
+ "language_model.layers.21.self_attn.v_proj": true,
510
+ "language_model.layers.21.self_attn.o_proj": true,
511
+ "language_model.layers.21.self_attn.rope": false,
512
+ "language_model.layers.21.mlp.gate_proj": true,
513
+ "language_model.layers.21.mlp.down_proj": true,
514
+ "language_model.layers.21.mlp.up_proj": true,
515
+ "language_model.layers.21.input_layernorm": false,
516
+ "language_model.layers.21.post_attention_layernorm": false,
517
+ "language_model.layers.22.self_attn.q_proj": true,
518
+ "language_model.layers.22.self_attn.k_proj": true,
519
+ "language_model.layers.22.self_attn.v_proj": true,
520
+ "language_model.layers.22.self_attn.o_proj": true,
521
+ "language_model.layers.22.self_attn.rope": false,
522
+ "language_model.layers.22.mlp.gate_proj": true,
523
+ "language_model.layers.22.mlp.down_proj": true,
524
+ "language_model.layers.22.mlp.up_proj": true,
525
+ "language_model.layers.22.input_layernorm": false,
526
+ "language_model.layers.22.post_attention_layernorm": false,
527
+ "language_model.layers.23.self_attn.q_proj": true,
528
+ "language_model.layers.23.self_attn.k_proj": true,
529
+ "language_model.layers.23.self_attn.v_proj": true,
530
+ "language_model.layers.23.self_attn.o_proj": true,
531
+ "language_model.layers.23.self_attn.rope": false,
532
+ "language_model.layers.23.mlp.gate_proj": true,
533
+ "language_model.layers.23.mlp.down_proj": true,
534
+ "language_model.layers.23.mlp.up_proj": true,
535
+ "language_model.layers.23.input_layernorm": false,
536
+ "language_model.layers.23.post_attention_layernorm": false,
537
+ "language_model.norm": false,
538
+ "language_model.lm_head": true,
539
+ "connector.modality_projection.proj": true
540
+ },
541
+ "quantization_config": {
542
+ "group_size": 64,
543
+ "bits": 4,
544
+ "vision_model.embeddings.patch_embedding": false,
545
+ "vision_model.embeddings.position_embedding": false,
546
+ "vision_model.encoder.layers.0.self_attn.q_proj": false,
547
+ "vision_model.encoder.layers.0.self_attn.k_proj": false,
548
+ "vision_model.encoder.layers.0.self_attn.v_proj": false,
549
+ "vision_model.encoder.layers.0.self_attn.out_proj": false,
550
+ "vision_model.encoder.layers.0.layer_norm1": false,
551
+ "vision_model.encoder.layers.0.mlp.activation_fn": false,
552
+ "vision_model.encoder.layers.0.mlp.fc1": false,
553
+ "vision_model.encoder.layers.0.mlp.fc2": false,
554
+ "vision_model.encoder.layers.0.layer_norm2": false,
555
+ "vision_model.encoder.layers.1.self_attn.q_proj": false,
556
+ "vision_model.encoder.layers.1.self_attn.k_proj": false,
557
+ "vision_model.encoder.layers.1.self_attn.v_proj": false,
558
+ "vision_model.encoder.layers.1.self_attn.out_proj": false,
559
+ "vision_model.encoder.layers.1.layer_norm1": false,
560
+ "vision_model.encoder.layers.1.mlp.activation_fn": false,
561
+ "vision_model.encoder.layers.1.mlp.fc1": false,
562
+ "vision_model.encoder.layers.1.mlp.fc2": false,
563
+ "vision_model.encoder.layers.1.layer_norm2": false,
564
+ "vision_model.encoder.layers.2.self_attn.q_proj": false,
565
+ "vision_model.encoder.layers.2.self_attn.k_proj": false,
566
+ "vision_model.encoder.layers.2.self_attn.v_proj": false,
567
+ "vision_model.encoder.layers.2.self_attn.out_proj": false,
568
+ "vision_model.encoder.layers.2.layer_norm1": false,
569
+ "vision_model.encoder.layers.2.mlp.activation_fn": false,
570
+ "vision_model.encoder.layers.2.mlp.fc1": false,
571
+ "vision_model.encoder.layers.2.mlp.fc2": false,
572
+ "vision_model.encoder.layers.2.layer_norm2": false,
573
+ "vision_model.encoder.layers.3.self_attn.q_proj": false,
574
+ "vision_model.encoder.layers.3.self_attn.k_proj": false,
575
+ "vision_model.encoder.layers.3.self_attn.v_proj": false,
576
+ "vision_model.encoder.layers.3.self_attn.out_proj": false,
577
+ "vision_model.encoder.layers.3.layer_norm1": false,
578
+ "vision_model.encoder.layers.3.mlp.activation_fn": false,
579
+ "vision_model.encoder.layers.3.mlp.fc1": false,
580
+ "vision_model.encoder.layers.3.mlp.fc2": false,
581
+ "vision_model.encoder.layers.3.layer_norm2": false,
582
+ "vision_model.encoder.layers.4.self_attn.q_proj": false,
583
+ "vision_model.encoder.layers.4.self_attn.k_proj": false,
584
+ "vision_model.encoder.layers.4.self_attn.v_proj": false,
585
+ "vision_model.encoder.layers.4.self_attn.out_proj": false,
586
+ "vision_model.encoder.layers.4.layer_norm1": false,
587
+ "vision_model.encoder.layers.4.mlp.activation_fn": false,
588
+ "vision_model.encoder.layers.4.mlp.fc1": false,
589
+ "vision_model.encoder.layers.4.mlp.fc2": false,
590
+ "vision_model.encoder.layers.4.layer_norm2": false,
591
+ "vision_model.encoder.layers.5.self_attn.q_proj": false,
592
+ "vision_model.encoder.layers.5.self_attn.k_proj": false,
593
+ "vision_model.encoder.layers.5.self_attn.v_proj": false,
594
+ "vision_model.encoder.layers.5.self_attn.out_proj": false,
595
+ "vision_model.encoder.layers.5.layer_norm1": false,
596
+ "vision_model.encoder.layers.5.mlp.activation_fn": false,
597
+ "vision_model.encoder.layers.5.mlp.fc1": false,
598
+ "vision_model.encoder.layers.5.mlp.fc2": false,
599
+ "vision_model.encoder.layers.5.layer_norm2": false,
600
+ "vision_model.encoder.layers.6.self_attn.q_proj": false,
601
+ "vision_model.encoder.layers.6.self_attn.k_proj": false,
602
+ "vision_model.encoder.layers.6.self_attn.v_proj": false,
603
+ "vision_model.encoder.layers.6.self_attn.out_proj": false,
604
+ "vision_model.encoder.layers.6.layer_norm1": false,
605
+ "vision_model.encoder.layers.6.mlp.activation_fn": false,
606
+ "vision_model.encoder.layers.6.mlp.fc1": false,
607
+ "vision_model.encoder.layers.6.mlp.fc2": false,
608
+ "vision_model.encoder.layers.6.layer_norm2": false,
609
+ "vision_model.encoder.layers.7.self_attn.q_proj": false,
610
+ "vision_model.encoder.layers.7.self_attn.k_proj": false,
611
+ "vision_model.encoder.layers.7.self_attn.v_proj": false,
612
+ "vision_model.encoder.layers.7.self_attn.out_proj": false,
613
+ "vision_model.encoder.layers.7.layer_norm1": false,
614
+ "vision_model.encoder.layers.7.mlp.activation_fn": false,
615
+ "vision_model.encoder.layers.7.mlp.fc1": false,
616
+ "vision_model.encoder.layers.7.mlp.fc2": false,
617
+ "vision_model.encoder.layers.7.layer_norm2": false,
618
+ "vision_model.encoder.layers.8.self_attn.q_proj": false,
619
+ "vision_model.encoder.layers.8.self_attn.k_proj": false,
620
+ "vision_model.encoder.layers.8.self_attn.v_proj": false,
621
+ "vision_model.encoder.layers.8.self_attn.out_proj": false,
622
+ "vision_model.encoder.layers.8.layer_norm1": false,
623
+ "vision_model.encoder.layers.8.mlp.activation_fn": false,
624
+ "vision_model.encoder.layers.8.mlp.fc1": false,
625
+ "vision_model.encoder.layers.8.mlp.fc2": false,
626
+ "vision_model.encoder.layers.8.layer_norm2": false,
627
+ "vision_model.encoder.layers.9.self_attn.q_proj": false,
628
+ "vision_model.encoder.layers.9.self_attn.k_proj": false,
629
+ "vision_model.encoder.layers.9.self_attn.v_proj": false,
630
+ "vision_model.encoder.layers.9.self_attn.out_proj": false,
631
+ "vision_model.encoder.layers.9.layer_norm1": false,
632
+ "vision_model.encoder.layers.9.mlp.activation_fn": false,
633
+ "vision_model.encoder.layers.9.mlp.fc1": false,
634
+ "vision_model.encoder.layers.9.mlp.fc2": false,
635
+ "vision_model.encoder.layers.9.layer_norm2": false,
636
+ "vision_model.encoder.layers.10.self_attn.q_proj": false,
637
+ "vision_model.encoder.layers.10.self_attn.k_proj": false,
638
+ "vision_model.encoder.layers.10.self_attn.v_proj": false,
639
+ "vision_model.encoder.layers.10.self_attn.out_proj": false,
640
+ "vision_model.encoder.layers.10.layer_norm1": false,
641
+ "vision_model.encoder.layers.10.mlp.activation_fn": false,
642
+ "vision_model.encoder.layers.10.mlp.fc1": false,
643
+ "vision_model.encoder.layers.10.mlp.fc2": false,
644
+ "vision_model.encoder.layers.10.layer_norm2": false,
645
+ "vision_model.encoder.layers.11.self_attn.q_proj": false,
646
+ "vision_model.encoder.layers.11.self_attn.k_proj": false,
647
+ "vision_model.encoder.layers.11.self_attn.v_proj": false,
648
+ "vision_model.encoder.layers.11.self_attn.out_proj": false,
649
+ "vision_model.encoder.layers.11.layer_norm1": false,
650
+ "vision_model.encoder.layers.11.mlp.activation_fn": false,
651
+ "vision_model.encoder.layers.11.mlp.fc1": false,
652
+ "vision_model.encoder.layers.11.mlp.fc2": false,
653
+ "vision_model.encoder.layers.11.layer_norm2": false,
654
+ "vision_model.encoder.layers.12.self_attn.q_proj": false,
655
+ "vision_model.encoder.layers.12.self_attn.k_proj": false,
656
+ "vision_model.encoder.layers.12.self_attn.v_proj": false,
657
+ "vision_model.encoder.layers.12.self_attn.out_proj": false,
658
+ "vision_model.encoder.layers.12.layer_norm1": false,
659
+ "vision_model.encoder.layers.12.mlp.activation_fn": false,
660
+ "vision_model.encoder.layers.12.mlp.fc1": false,
661
+ "vision_model.encoder.layers.12.mlp.fc2": false,
662
+ "vision_model.encoder.layers.12.layer_norm2": false,
663
+ "vision_model.encoder.layers.13.self_attn.q_proj": false,
664
+ "vision_model.encoder.layers.13.self_attn.k_proj": false,
665
+ "vision_model.encoder.layers.13.self_attn.v_proj": false,
666
+ "vision_model.encoder.layers.13.self_attn.out_proj": false,
667
+ "vision_model.encoder.layers.13.layer_norm1": false,
668
+ "vision_model.encoder.layers.13.mlp.activation_fn": false,
669
+ "vision_model.encoder.layers.13.mlp.fc1": false,
670
+ "vision_model.encoder.layers.13.mlp.fc2": false,
671
+ "vision_model.encoder.layers.13.layer_norm2": false,
672
+ "vision_model.encoder.layers.14.self_attn.q_proj": false,
673
+ "vision_model.encoder.layers.14.self_attn.k_proj": false,
674
+ "vision_model.encoder.layers.14.self_attn.v_proj": false,
675
+ "vision_model.encoder.layers.14.self_attn.out_proj": false,
676
+ "vision_model.encoder.layers.14.layer_norm1": false,
677
+ "vision_model.encoder.layers.14.mlp.activation_fn": false,
678
+ "vision_model.encoder.layers.14.mlp.fc1": false,
679
+ "vision_model.encoder.layers.14.mlp.fc2": false,
680
+ "vision_model.encoder.layers.14.layer_norm2": false,
681
+ "vision_model.encoder.layers.15.self_attn.q_proj": false,
682
+ "vision_model.encoder.layers.15.self_attn.k_proj": false,
683
+ "vision_model.encoder.layers.15.self_attn.v_proj": false,
684
+ "vision_model.encoder.layers.15.self_attn.out_proj": false,
685
+ "vision_model.encoder.layers.15.layer_norm1": false,
686
+ "vision_model.encoder.layers.15.mlp.activation_fn": false,
687
+ "vision_model.encoder.layers.15.mlp.fc1": false,
688
+ "vision_model.encoder.layers.15.mlp.fc2": false,
689
+ "vision_model.encoder.layers.15.layer_norm2": false,
690
+ "vision_model.encoder.layers.16.self_attn.q_proj": false,
691
+ "vision_model.encoder.layers.16.self_attn.k_proj": false,
692
+ "vision_model.encoder.layers.16.self_attn.v_proj": false,
693
+ "vision_model.encoder.layers.16.self_attn.out_proj": false,
694
+ "vision_model.encoder.layers.16.layer_norm1": false,
695
+ "vision_model.encoder.layers.16.mlp.activation_fn": false,
696
+ "vision_model.encoder.layers.16.mlp.fc1": false,
697
+ "vision_model.encoder.layers.16.mlp.fc2": false,
698
+ "vision_model.encoder.layers.16.layer_norm2": false,
699
+ "vision_model.encoder.layers.17.self_attn.q_proj": false,
700
+ "vision_model.encoder.layers.17.self_attn.k_proj": false,
701
+ "vision_model.encoder.layers.17.self_attn.v_proj": false,
702
+ "vision_model.encoder.layers.17.self_attn.out_proj": false,
703
+ "vision_model.encoder.layers.17.layer_norm1": false,
704
+ "vision_model.encoder.layers.17.mlp.activation_fn": false,
705
+ "vision_model.encoder.layers.17.mlp.fc1": false,
706
+ "vision_model.encoder.layers.17.mlp.fc2": false,
707
+ "vision_model.encoder.layers.17.layer_norm2": false,
708
+ "vision_model.encoder.layers.18.self_attn.q_proj": false,
709
+ "vision_model.encoder.layers.18.self_attn.k_proj": false,
710
+ "vision_model.encoder.layers.18.self_attn.v_proj": false,
711
+ "vision_model.encoder.layers.18.self_attn.out_proj": false,
712
+ "vision_model.encoder.layers.18.layer_norm1": false,
713
+ "vision_model.encoder.layers.18.mlp.activation_fn": false,
714
+ "vision_model.encoder.layers.18.mlp.fc1": false,
715
+ "vision_model.encoder.layers.18.mlp.fc2": false,
716
+ "vision_model.encoder.layers.18.layer_norm2": false,
717
+ "vision_model.encoder.layers.19.self_attn.q_proj": false,
718
+ "vision_model.encoder.layers.19.self_attn.k_proj": false,
719
+ "vision_model.encoder.layers.19.self_attn.v_proj": false,
720
+ "vision_model.encoder.layers.19.self_attn.out_proj": false,
721
+ "vision_model.encoder.layers.19.layer_norm1": false,
722
+ "vision_model.encoder.layers.19.mlp.activation_fn": false,
723
+ "vision_model.encoder.layers.19.mlp.fc1": false,
724
+ "vision_model.encoder.layers.19.mlp.fc2": false,
725
+ "vision_model.encoder.layers.19.layer_norm2": false,
726
+ "vision_model.encoder.layers.20.self_attn.q_proj": false,
727
+ "vision_model.encoder.layers.20.self_attn.k_proj": false,
728
+ "vision_model.encoder.layers.20.self_attn.v_proj": false,
729
+ "vision_model.encoder.layers.20.self_attn.out_proj": false,
730
+ "vision_model.encoder.layers.20.layer_norm1": false,
731
+ "vision_model.encoder.layers.20.mlp.activation_fn": false,
732
+ "vision_model.encoder.layers.20.mlp.fc1": false,
733
+ "vision_model.encoder.layers.20.mlp.fc2": false,
734
+ "vision_model.encoder.layers.20.layer_norm2": false,
735
+ "vision_model.encoder.layers.21.self_attn.q_proj": false,
736
+ "vision_model.encoder.layers.21.self_attn.k_proj": false,
737
+ "vision_model.encoder.layers.21.self_attn.v_proj": false,
738
+ "vision_model.encoder.layers.21.self_attn.out_proj": false,
739
+ "vision_model.encoder.layers.21.layer_norm1": false,
740
+ "vision_model.encoder.layers.21.mlp.activation_fn": false,
741
+ "vision_model.encoder.layers.21.mlp.fc1": false,
742
+ "vision_model.encoder.layers.21.mlp.fc2": false,
743
+ "vision_model.encoder.layers.21.layer_norm2": false,
744
+ "vision_model.encoder.layers.22.self_attn.q_proj": false,
745
+ "vision_model.encoder.layers.22.self_attn.k_proj": false,
746
+ "vision_model.encoder.layers.22.self_attn.v_proj": false,
747
+ "vision_model.encoder.layers.22.self_attn.out_proj": false,
748
+ "vision_model.encoder.layers.22.layer_norm1": false,
749
+ "vision_model.encoder.layers.22.mlp.activation_fn": false,
750
+ "vision_model.encoder.layers.22.mlp.fc1": false,
751
+ "vision_model.encoder.layers.22.mlp.fc2": false,
752
+ "vision_model.encoder.layers.22.layer_norm2": false,
753
+ "vision_model.encoder.layers.23.self_attn.q_proj": false,
754
+ "vision_model.encoder.layers.23.self_attn.k_proj": false,
755
+ "vision_model.encoder.layers.23.self_attn.v_proj": false,
756
+ "vision_model.encoder.layers.23.self_attn.out_proj": false,
757
+ "vision_model.encoder.layers.23.layer_norm1": false,
758
+ "vision_model.encoder.layers.23.mlp.activation_fn": false,
759
+ "vision_model.encoder.layers.23.mlp.fc1": false,
760
+ "vision_model.encoder.layers.23.mlp.fc2": false,
761
+ "vision_model.encoder.layers.23.layer_norm2": false,
762
+ "vision_model.encoder.layers.24.self_attn.q_proj": false,
763
+ "vision_model.encoder.layers.24.self_attn.k_proj": false,
764
+ "vision_model.encoder.layers.24.self_attn.v_proj": false,
765
+ "vision_model.encoder.layers.24.self_attn.out_proj": false,
766
+ "vision_model.encoder.layers.24.layer_norm1": false,
767
+ "vision_model.encoder.layers.24.mlp.activation_fn": false,
768
+ "vision_model.encoder.layers.24.mlp.fc1": false,
769
+ "vision_model.encoder.layers.24.mlp.fc2": false,
770
+ "vision_model.encoder.layers.24.layer_norm2": false,
771
+ "vision_model.encoder.layers.25.self_attn.q_proj": false,
772
+ "vision_model.encoder.layers.25.self_attn.k_proj": false,
773
+ "vision_model.encoder.layers.25.self_attn.v_proj": false,
774
+ "vision_model.encoder.layers.25.self_attn.out_proj": false,
775
+ "vision_model.encoder.layers.25.layer_norm1": false,
776
+ "vision_model.encoder.layers.25.mlp.activation_fn": false,
777
+ "vision_model.encoder.layers.25.mlp.fc1": false,
778
+ "vision_model.encoder.layers.25.mlp.fc2": false,
779
+ "vision_model.encoder.layers.25.layer_norm2": false,
780
+ "vision_model.encoder.layers.26.self_attn.q_proj": false,
781
+ "vision_model.encoder.layers.26.self_attn.k_proj": false,
782
+ "vision_model.encoder.layers.26.self_attn.v_proj": false,
783
+ "vision_model.encoder.layers.26.self_attn.out_proj": false,
784
+ "vision_model.encoder.layers.26.layer_norm1": false,
785
+ "vision_model.encoder.layers.26.mlp.activation_fn": false,
786
+ "vision_model.encoder.layers.26.mlp.fc1": false,
787
+ "vision_model.encoder.layers.26.mlp.fc2": false,
788
+ "vision_model.encoder.layers.26.layer_norm2": false,
789
+ "vision_model.post_layernorm": false,
790
+ "language_model.embed_tokens": true,
791
+ "language_model.layers.0.self_attn.q_proj": true,
792
+ "language_model.layers.0.self_attn.k_proj": true,
793
+ "language_model.layers.0.self_attn.v_proj": true,
794
+ "language_model.layers.0.self_attn.o_proj": true,
795
+ "language_model.layers.0.self_attn.rope": false,
796
+ "language_model.layers.0.mlp.gate_proj": true,
797
+ "language_model.layers.0.mlp.down_proj": true,
798
+ "language_model.layers.0.mlp.up_proj": true,
799
+ "language_model.layers.0.input_layernorm": false,
800
+ "language_model.layers.0.post_attention_layernorm": false,
801
+ "language_model.layers.1.self_attn.q_proj": true,
802
+ "language_model.layers.1.self_attn.k_proj": true,
803
+ "language_model.layers.1.self_attn.v_proj": true,
804
+ "language_model.layers.1.self_attn.o_proj": true,
805
+ "language_model.layers.1.self_attn.rope": false,
806
+ "language_model.layers.1.mlp.gate_proj": true,
807
+ "language_model.layers.1.mlp.down_proj": true,
808
+ "language_model.layers.1.mlp.up_proj": true,
809
+ "language_model.layers.1.input_layernorm": false,
810
+ "language_model.layers.1.post_attention_layernorm": false,
811
+ "language_model.layers.2.self_attn.q_proj": true,
812
+ "language_model.layers.2.self_attn.k_proj": true,
813
+ "language_model.layers.2.self_attn.v_proj": true,
814
+ "language_model.layers.2.self_attn.o_proj": true,
815
+ "language_model.layers.2.self_attn.rope": false,
816
+ "language_model.layers.2.mlp.gate_proj": true,
817
+ "language_model.layers.2.mlp.down_proj": true,
818
+ "language_model.layers.2.mlp.up_proj": true,
819
+ "language_model.layers.2.input_layernorm": false,
820
+ "language_model.layers.2.post_attention_layernorm": false,
821
+ "language_model.layers.3.self_attn.q_proj": true,
822
+ "language_model.layers.3.self_attn.k_proj": true,
823
+ "language_model.layers.3.self_attn.v_proj": true,
824
+ "language_model.layers.3.self_attn.o_proj": true,
825
+ "language_model.layers.3.self_attn.rope": false,
826
+ "language_model.layers.3.mlp.gate_proj": true,
827
+ "language_model.layers.3.mlp.down_proj": true,
828
+ "language_model.layers.3.mlp.up_proj": true,
829
+ "language_model.layers.3.input_layernorm": false,
830
+ "language_model.layers.3.post_attention_layernorm": false,
831
+ "language_model.layers.4.self_attn.q_proj": true,
832
+ "language_model.layers.4.self_attn.k_proj": true,
833
+ "language_model.layers.4.self_attn.v_proj": true,
834
+ "language_model.layers.4.self_attn.o_proj": true,
835
+ "language_model.layers.4.self_attn.rope": false,
836
+ "language_model.layers.4.mlp.gate_proj": true,
837
+ "language_model.layers.4.mlp.down_proj": true,
838
+ "language_model.layers.4.mlp.up_proj": true,
839
+ "language_model.layers.4.input_layernorm": false,
840
+ "language_model.layers.4.post_attention_layernorm": false,
841
+ "language_model.layers.5.self_attn.q_proj": true,
842
+ "language_model.layers.5.self_attn.k_proj": true,
843
+ "language_model.layers.5.self_attn.v_proj": true,
844
+ "language_model.layers.5.self_attn.o_proj": true,
845
+ "language_model.layers.5.self_attn.rope": false,
846
+ "language_model.layers.5.mlp.gate_proj": true,
847
+ "language_model.layers.5.mlp.down_proj": true,
848
+ "language_model.layers.5.mlp.up_proj": true,
849
+ "language_model.layers.5.input_layernorm": false,
850
+ "language_model.layers.5.post_attention_layernorm": false,
851
+ "language_model.layers.6.self_attn.q_proj": true,
852
+ "language_model.layers.6.self_attn.k_proj": true,
853
+ "language_model.layers.6.self_attn.v_proj": true,
854
+ "language_model.layers.6.self_attn.o_proj": true,
855
+ "language_model.layers.6.self_attn.rope": false,
856
+ "language_model.layers.6.mlp.gate_proj": true,
857
+ "language_model.layers.6.mlp.down_proj": true,
858
+ "language_model.layers.6.mlp.up_proj": true,
859
+ "language_model.layers.6.input_layernorm": false,
860
+ "language_model.layers.6.post_attention_layernorm": false,
861
+ "language_model.layers.7.self_attn.q_proj": true,
862
+ "language_model.layers.7.self_attn.k_proj": true,
863
+ "language_model.layers.7.self_attn.v_proj": true,
864
+ "language_model.layers.7.self_attn.o_proj": true,
865
+ "language_model.layers.7.self_attn.rope": false,
866
+ "language_model.layers.7.mlp.gate_proj": true,
867
+ "language_model.layers.7.mlp.down_proj": true,
868
+ "language_model.layers.7.mlp.up_proj": true,
869
+ "language_model.layers.7.input_layernorm": false,
870
+ "language_model.layers.7.post_attention_layernorm": false,
871
+ "language_model.layers.8.self_attn.q_proj": true,
872
+ "language_model.layers.8.self_attn.k_proj": true,
873
+ "language_model.layers.8.self_attn.v_proj": true,
874
+ "language_model.layers.8.self_attn.o_proj": true,
875
+ "language_model.layers.8.self_attn.rope": false,
876
+ "language_model.layers.8.mlp.gate_proj": true,
877
+ "language_model.layers.8.mlp.down_proj": true,
878
+ "language_model.layers.8.mlp.up_proj": true,
879
+ "language_model.layers.8.input_layernorm": false,
880
+ "language_model.layers.8.post_attention_layernorm": false,
881
+ "language_model.layers.9.self_attn.q_proj": true,
882
+ "language_model.layers.9.self_attn.k_proj": true,
883
+ "language_model.layers.9.self_attn.v_proj": true,
884
+ "language_model.layers.9.self_attn.o_proj": true,
885
+ "language_model.layers.9.self_attn.rope": false,
886
+ "language_model.layers.9.mlp.gate_proj": true,
887
+ "language_model.layers.9.mlp.down_proj": true,
888
+ "language_model.layers.9.mlp.up_proj": true,
889
+ "language_model.layers.9.input_layernorm": false,
890
+ "language_model.layers.9.post_attention_layernorm": false,
891
+ "language_model.layers.10.self_attn.q_proj": true,
892
+ "language_model.layers.10.self_attn.k_proj": true,
893
+ "language_model.layers.10.self_attn.v_proj": true,
894
+ "language_model.layers.10.self_attn.o_proj": true,
895
+ "language_model.layers.10.self_attn.rope": false,
896
+ "language_model.layers.10.mlp.gate_proj": true,
897
+ "language_model.layers.10.mlp.down_proj": true,
898
+ "language_model.layers.10.mlp.up_proj": true,
899
+ "language_model.layers.10.input_layernorm": false,
900
+ "language_model.layers.10.post_attention_layernorm": false,
901
+ "language_model.layers.11.self_attn.q_proj": true,
902
+ "language_model.layers.11.self_attn.k_proj": true,
903
+ "language_model.layers.11.self_attn.v_proj": true,
904
+ "language_model.layers.11.self_attn.o_proj": true,
905
+ "language_model.layers.11.self_attn.rope": false,
906
+ "language_model.layers.11.mlp.gate_proj": true,
907
+ "language_model.layers.11.mlp.down_proj": true,
908
+ "language_model.layers.11.mlp.up_proj": true,
909
+ "language_model.layers.11.input_layernorm": false,
910
+ "language_model.layers.11.post_attention_layernorm": false,
911
+ "language_model.layers.12.self_attn.q_proj": true,
912
+ "language_model.layers.12.self_attn.k_proj": true,
913
+ "language_model.layers.12.self_attn.v_proj": true,
914
+ "language_model.layers.12.self_attn.o_proj": true,
915
+ "language_model.layers.12.self_attn.rope": false,
916
+ "language_model.layers.12.mlp.gate_proj": true,
917
+ "language_model.layers.12.mlp.down_proj": true,
918
+ "language_model.layers.12.mlp.up_proj": true,
919
+ "language_model.layers.12.input_layernorm": false,
920
+ "language_model.layers.12.post_attention_layernorm": false,
921
+ "language_model.layers.13.self_attn.q_proj": true,
922
+ "language_model.layers.13.self_attn.k_proj": true,
923
+ "language_model.layers.13.self_attn.v_proj": true,
924
+ "language_model.layers.13.self_attn.o_proj": true,
925
+ "language_model.layers.13.self_attn.rope": false,
926
+ "language_model.layers.13.mlp.gate_proj": true,
927
+ "language_model.layers.13.mlp.down_proj": true,
928
+ "language_model.layers.13.mlp.up_proj": true,
929
+ "language_model.layers.13.input_layernorm": false,
930
+ "language_model.layers.13.post_attention_layernorm": false,
931
+ "language_model.layers.14.self_attn.q_proj": true,
932
+ "language_model.layers.14.self_attn.k_proj": true,
933
+ "language_model.layers.14.self_attn.v_proj": true,
934
+ "language_model.layers.14.self_attn.o_proj": true,
935
+ "language_model.layers.14.self_attn.rope": false,
936
+ "language_model.layers.14.mlp.gate_proj": true,
937
+ "language_model.layers.14.mlp.down_proj": true,
938
+ "language_model.layers.14.mlp.up_proj": true,
939
+ "language_model.layers.14.input_layernorm": false,
940
+ "language_model.layers.14.post_attention_layernorm": false,
941
+ "language_model.layers.15.self_attn.q_proj": true,
942
+ "language_model.layers.15.self_attn.k_proj": true,
943
+ "language_model.layers.15.self_attn.v_proj": true,
944
+ "language_model.layers.15.self_attn.o_proj": true,
945
+ "language_model.layers.15.self_attn.rope": false,
946
+ "language_model.layers.15.mlp.gate_proj": true,
947
+ "language_model.layers.15.mlp.down_proj": true,
948
+ "language_model.layers.15.mlp.up_proj": true,
949
+ "language_model.layers.15.input_layernorm": false,
950
+ "language_model.layers.15.post_attention_layernorm": false,
951
+ "language_model.layers.16.self_attn.q_proj": true,
952
+ "language_model.layers.16.self_attn.k_proj": true,
953
+ "language_model.layers.16.self_attn.v_proj": true,
954
+ "language_model.layers.16.self_attn.o_proj": true,
955
+ "language_model.layers.16.self_attn.rope": false,
956
+ "language_model.layers.16.mlp.gate_proj": true,
957
+ "language_model.layers.16.mlp.down_proj": true,
958
+ "language_model.layers.16.mlp.up_proj": true,
959
+ "language_model.layers.16.input_layernorm": false,
960
+ "language_model.layers.16.post_attention_layernorm": false,
961
+ "language_model.layers.17.self_attn.q_proj": true,
962
+ "language_model.layers.17.self_attn.k_proj": true,
963
+ "language_model.layers.17.self_attn.v_proj": true,
964
+ "language_model.layers.17.self_attn.o_proj": true,
965
+ "language_model.layers.17.self_attn.rope": false,
966
+ "language_model.layers.17.mlp.gate_proj": true,
967
+ "language_model.layers.17.mlp.down_proj": true,
968
+ "language_model.layers.17.mlp.up_proj": true,
969
+ "language_model.layers.17.input_layernorm": false,
970
+ "language_model.layers.17.post_attention_layernorm": false,
971
+ "language_model.layers.18.self_attn.q_proj": true,
972
+ "language_model.layers.18.self_attn.k_proj": true,
973
+ "language_model.layers.18.self_attn.v_proj": true,
974
+ "language_model.layers.18.self_attn.o_proj": true,
975
+ "language_model.layers.18.self_attn.rope": false,
976
+ "language_model.layers.18.mlp.gate_proj": true,
977
+ "language_model.layers.18.mlp.down_proj": true,
978
+ "language_model.layers.18.mlp.up_proj": true,
979
+ "language_model.layers.18.input_layernorm": false,
980
+ "language_model.layers.18.post_attention_layernorm": false,
981
+ "language_model.layers.19.self_attn.q_proj": true,
982
+ "language_model.layers.19.self_attn.k_proj": true,
983
+ "language_model.layers.19.self_attn.v_proj": true,
984
+ "language_model.layers.19.self_attn.o_proj": true,
985
+ "language_model.layers.19.self_attn.rope": false,
986
+ "language_model.layers.19.mlp.gate_proj": true,
987
+ "language_model.layers.19.mlp.down_proj": true,
988
+ "language_model.layers.19.mlp.up_proj": true,
989
+ "language_model.layers.19.input_layernorm": false,
990
+ "language_model.layers.19.post_attention_layernorm": false,
991
+ "language_model.layers.20.self_attn.q_proj": true,
992
+ "language_model.layers.20.self_attn.k_proj": true,
993
+ "language_model.layers.20.self_attn.v_proj": true,
994
+ "language_model.layers.20.self_attn.o_proj": true,
995
+ "language_model.layers.20.self_attn.rope": false,
996
+ "language_model.layers.20.mlp.gate_proj": true,
997
+ "language_model.layers.20.mlp.down_proj": true,
998
+ "language_model.layers.20.mlp.up_proj": true,
999
+ "language_model.layers.20.input_layernorm": false,
1000
+ "language_model.layers.20.post_attention_layernorm": false,
1001
+ "language_model.layers.21.self_attn.q_proj": true,
1002
+ "language_model.layers.21.self_attn.k_proj": true,
1003
+ "language_model.layers.21.self_attn.v_proj": true,
1004
+ "language_model.layers.21.self_attn.o_proj": true,
1005
+ "language_model.layers.21.self_attn.rope": false,
1006
+ "language_model.layers.21.mlp.gate_proj": true,
1007
+ "language_model.layers.21.mlp.down_proj": true,
1008
+ "language_model.layers.21.mlp.up_proj": true,
1009
+ "language_model.layers.21.input_layernorm": false,
1010
+ "language_model.layers.21.post_attention_layernorm": false,
1011
+ "language_model.layers.22.self_attn.q_proj": true,
1012
+ "language_model.layers.22.self_attn.k_proj": true,
1013
+ "language_model.layers.22.self_attn.v_proj": true,
1014
+ "language_model.layers.22.self_attn.o_proj": true,
1015
+ "language_model.layers.22.self_attn.rope": false,
1016
+ "language_model.layers.22.mlp.gate_proj": true,
1017
+ "language_model.layers.22.mlp.down_proj": true,
1018
+ "language_model.layers.22.mlp.up_proj": true,
1019
+ "language_model.layers.22.input_layernorm": false,
1020
+ "language_model.layers.22.post_attention_layernorm": false,
1021
+ "language_model.layers.23.self_attn.q_proj": true,
1022
+ "language_model.layers.23.self_attn.k_proj": true,
1023
+ "language_model.layers.23.self_attn.v_proj": true,
1024
+ "language_model.layers.23.self_attn.o_proj": true,
1025
+ "language_model.layers.23.self_attn.rope": false,
1026
+ "language_model.layers.23.mlp.gate_proj": true,
1027
+ "language_model.layers.23.mlp.down_proj": true,
1028
+ "language_model.layers.23.mlp.up_proj": true,
1029
+ "language_model.layers.23.input_layernorm": false,
1030
+ "language_model.layers.23.post_attention_layernorm": false,
1031
+ "language_model.norm": false,
1032
+ "language_model.lm_head": true,
1033
+ "connector.modality_projection.proj": true
1034
+ },
1035
+ "remove_invalid_values": false,
1036
+ "repetition_penalty": 1.0,
1037
+ "return_dict": true,
1038
+ "return_dict_in_generate": false,
1039
+ "scale_factor": 3,
1040
+ "sep_token_id": null,
1041
+ "suppress_tokens": null,
1042
+ "task_specific_params": null,
1043
+ "temperature": 1.0,
1044
+ "text_config": {
1045
+ "vocab_size": 49280,
1046
+ "max_position_embeddings": 8192,
1047
+ "hidden_size": 2048,
1048
+ "intermediate_size": 8192,
1049
+ "num_hidden_layers": 24,
1050
+ "num_attention_heads": 32,
1051
+ "num_key_value_heads": 32,
1052
+ "hidden_act": "silu",
1053
+ "initializer_range": 0.02,
1054
+ "rms_norm_eps": 1e-05,
1055
+ "pretraining_tp": 1,
1056
+ "use_cache": true,
1057
+ "rope_theta": 130000,
1058
+ "rope_scaling": null,
1059
+ "attention_bias": false,
1060
+ "attention_dropout": 0.0,
1061
+ "mlp_bias": false,
1062
+ "head_dim": 64,
1063
+ "return_dict": true,
1064
+ "output_hidden_states": false,
1065
+ "torchscript": false,
1066
+ "torch_dtype": "bfloat16",
1067
+ "pruned_heads": {},
1068
+ "tie_word_embeddings": false,
1069
+ "chunk_size_feed_forward": 0,
1070
+ "is_encoder_decoder": false,
1071
+ "is_decoder": false,
1072
+ "cross_attention_hidden_size": null,
1073
+ "add_cross_attention": false,
1074
+ "tie_encoder_decoder": false,
1075
+ "architectures": [
1076
+ "VLlama3ForCausalLM"
1077
+ ],
1078
+ "finetuning_task": null,
1079
+ "id2label": {
1080
+ "0": "LABEL_0",
1081
+ "1": "LABEL_1"
1082
+ },
1083
+ "label2id": {
1084
+ "LABEL_0": 0,
1085
+ "LABEL_1": 1
1086
+ },
1087
+ "task_specific_params": null,
1088
+ "problem_type": null,
1089
+ "tokenizer_class": null,
1090
+ "prefix": null,
1091
+ "bos_token_id": 1,
1092
+ "pad_token_id": 2,
1093
+ "eos_token_id": 2,
1094
+ "sep_token_id": null,
1095
+ "decoder_start_token_id": null,
1096
+ "max_length": 20,
1097
+ "min_length": 0,
1098
+ "do_sample": false,
1099
+ "early_stopping": false,
1100
+ "num_beams": 1,
1101
+ "num_beam_groups": 1,
1102
+ "diversity_penalty": 0.0,
1103
+ "temperature": 1.0,
1104
+ "top_k": 50,
1105
+ "top_p": 1.0,
1106
+ "typical_p": 1.0,
1107
+ "repetition_penalty": 1.0,
1108
+ "length_penalty": 1.0,
1109
+ "no_repeat_ngram_size": 0,
1110
+ "encoder_no_repeat_ngram_size": 0,
1111
+ "bad_words_ids": null,
1112
+ "num_return_sequences": 1,
1113
+ "output_scores": false,
1114
+ "return_dict_in_generate": false,
1115
+ "forced_bos_token_id": null,
1116
+ "forced_eos_token_id": null,
1117
+ "remove_invalid_values": false,
1118
+ "exponential_decay_length_penalty": null,
1119
+ "suppress_tokens": null,
1120
+ "begin_suppress_tokens": null,
1121
+ "_name_or_path": "None",
1122
+ "_flash_attn_2_enabled": true,
1123
+ "model_type": "llama",
1124
+ "neftune_noise_alpha": 0.0,
1125
+ "perceiver_config": {
1126
+ "_attn_implementation_autoset": false,
1127
+ "_name_or_path": "",
1128
+ "add_cross_attention": false,
1129
+ "architectures": null,
1130
+ "attention_dropout": 0.0,
1131
+ "bad_words_ids": null,
1132
+ "begin_suppress_tokens": null,
1133
+ "bos_token_id": null,
1134
+ "chunk_size_feed_forward": 0,
1135
+ "cross_attention_hidden_size": null,
1136
+ "decoder_start_token_id": null,
1137
+ "diversity_penalty": 0.0,
1138
+ "do_sample": false,
1139
+ "early_stopping": false,
1140
+ "encoder_no_repeat_ngram_size": 0,
1141
+ "eos_token_id": null,
1142
+ "exponential_decay_length_penalty": null,
1143
+ "finetuning_task": null,
1144
+ "forced_bos_token_id": null,
1145
+ "forced_eos_token_id": null,
1146
+ "hidden_act": "silu",
1147
+ "id2label": {
1148
+ "0": "LABEL_0",
1149
+ "1": "LABEL_1"
1150
+ },
1151
+ "is_decoder": false,
1152
+ "is_encoder_decoder": false,
1153
+ "label2id": {
1154
+ "LABEL_0": 0,
1155
+ "LABEL_1": 1
1156
+ },
1157
+ "length_penalty": 1.0,
1158
+ "max_length": 20,
1159
+ "min_length": 0,
1160
+ "model_type": "vllama3",
1161
+ "no_repeat_ngram_size": 0,
1162
+ "num_beam_groups": 1,
1163
+ "num_beams": 1,
1164
+ "num_key_value_heads": 1,
1165
+ "num_return_sequences": 1,
1166
+ "output_attentions": false,
1167
+ "output_hidden_states": false,
1168
+ "output_scores": false,
1169
+ "pad_token_id": null,
1170
+ "prefix": null,
1171
+ "problem_type": null,
1172
+ "pruned_heads": {},
1173
+ "qk_layer_norms_perceiver": false,
1174
+ "remove_invalid_values": false,
1175
+ "repetition_penalty": 1.0,
1176
+ "resampler_depth": 6,
1177
+ "resampler_head_dim": 96,
1178
+ "resampler_n_heads": 16,
1179
+ "resampler_n_latents": 64,
1180
+ "return_dict": true,
1181
+ "return_dict_in_generate": false,
1182
+ "sep_token_id": null,
1183
+ "suppress_tokens": null,
1184
+ "task_specific_params": null,
1185
+ "temperature": 1.0,
1186
+ "tf_legacy_loss": false,
1187
+ "tie_encoder_decoder": false,
1188
+ "tie_word_embeddings": true,
1189
+ "tokenizer_class": null,
1190
+ "top_k": 50,
1191
+ "top_p": 1.0,
1192
+ "torch_dtype": null,
1193
+ "torchscript": false,
1194
+ "transformers_version": "4.46.0",
1195
+ "typical_p": 1.0,
1196
+ "use_bfloat16": false
1197
+ },
1198
+ "pixel_shuffle_factor": 3,
1199
+ "qk_layer_norms": false,
1200
+ "transformers.js_config": {
1201
+ "kv_cache_dtype": {
1202
+ "fp16": "float16",
1203
+ "q4f16": "float16"
1204
+ }
1205
+ },
1206
+ "use_resampler": false,
1207
+ "tf_legacy_loss": false,
1208
+ "use_bfloat16": false,
1209
+ "output_attentions": false
1210
+ },
1211
+ "tf_legacy_loss": false,
1212
+ "tie_encoder_decoder": false,
1213
+ "tie_word_embeddings": false,
1214
+ "tokenizer_class": null,
1215
+ "top_k": 50,
1216
+ "top_p": 1.0,
1217
+ "torchscript": false,
1218
+ "transformers_version": "4.55.0.dev0",
1219
+ "typical_p": 1.0,
1220
+ "use_bfloat16": false,
1221
+ "use_cache": false,
1222
+ "use_reentrant_checkpointing": false,
1223
+ "vision_config": {
1224
+ "return_dict": true,
1225
+ "output_hidden_states": false,
1226
+ "torchscript": false,
1227
+ "torch_dtype": null,
1228
+ "pruned_heads": {},
1229
+ "tie_word_embeddings": false,
1230
+ "chunk_size_feed_forward": 0,
1231
+ "is_encoder_decoder": false,
1232
+ "is_decoder": false,
1233
+ "cross_attention_hidden_size": null,
1234
+ "add_cross_attention": false,
1235
+ "tie_encoder_decoder": false,
1236
+ "architectures": null,
1237
+ "finetuning_task": null,
1238
+ "id2label": {
1239
+ "0": "LABEL_0",
1240
+ "1": "LABEL_1"
1241
+ },
1242
+ "label2id": {
1243
+ "LABEL_0": 0,
1244
+ "LABEL_1": 1
1245
+ },
1246
+ "task_specific_params": null,
1247
+ "problem_type": null,
1248
+ "tokenizer_class": null,
1249
+ "prefix": null,
1250
+ "bos_token_id": null,
1251
+ "pad_token_id": null,
1252
+ "eos_token_id": null,
1253
+ "sep_token_id": null,
1254
+ "decoder_start_token_id": null,
1255
+ "max_length": 20,
1256
+ "min_length": 0,
1257
+ "do_sample": false,
1258
+ "early_stopping": false,
1259
+ "num_beams": 1,
1260
+ "num_beam_groups": 1,
1261
+ "diversity_penalty": 0.0,
1262
+ "temperature": 1.0,
1263
+ "top_k": 50,
1264
+ "top_p": 1.0,
1265
+ "typical_p": 1.0,
1266
+ "repetition_penalty": 1.0,
1267
+ "length_penalty": 1.0,
1268
+ "no_repeat_ngram_size": 0,
1269
+ "encoder_no_repeat_ngram_size": 0,
1270
+ "bad_words_ids": null,
1271
+ "num_return_sequences": 1,
1272
+ "output_scores": false,
1273
+ "return_dict_in_generate": false,
1274
+ "forced_bos_token_id": null,
1275
+ "forced_eos_token_id": null,
1276
+ "remove_invalid_values": false,
1277
+ "exponential_decay_length_penalty": null,
1278
+ "suppress_tokens": null,
1279
+ "begin_suppress_tokens": null,
1280
+ "_name_or_path": "",
1281
+ "max_image_size": {
1282
+ "longest_edge": 384
1283
+ },
1284
+ "model_type": "smolvlm_vision",
1285
+ "size": {
1286
+ "longest_edge": 1920
1287
+ },
1288
+ "use_base_siglip": false,
1289
+ "tf_legacy_loss": false,
1290
+ "use_bfloat16": false,
1291
+ "hidden_size": 1152,
1292
+ "intermediate_size": 4304,
1293
+ "num_hidden_layers": 27,
1294
+ "num_attention_heads": 16,
1295
+ "num_channels": 3,
1296
+ "patch_size": 14,
1297
+ "image_size": 384,
1298
+ "attention_dropout": 0.0,
1299
+ "layer_norm_eps": 1e-06,
1300
+ "hidden_act": "gelu_pytorch_tanh",
1301
+ "initializer_range": 0.02,
1302
+ "output_attentions": false
1303
+ },
1304
+ "vocab_size": 49280
1305
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 49279,
5
+ "pad_token_id": 2,
6
+ "transformers_version": "4.47.1"
7
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c89a426007c6e66935f65e6cdcaab26ba2773ce5d19a7c6cb7314d4dca016ea5
3
+ size 1857752759
model.safetensors.index.json ADDED
@@ -0,0 +1,664 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 8987139520
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00002-of-00002.safetensors",
7
+ "model.connector.modality_projection.proj.weight": "model-00001-of-00002.safetensors",
8
+ "model.text_model.embed_tokens.weight": "model-00001-of-00002.safetensors",
9
+ "model.text_model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
10
+ "model.text_model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
11
+ "model.text_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
12
+ "model.text_model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
13
+ "model.text_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
14
+ "model.text_model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
15
+ "model.text_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
16
+ "model.text_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
17
+ "model.text_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
18
+ "model.text_model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
19
+ "model.text_model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
20
+ "model.text_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
21
+ "model.text_model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
22
+ "model.text_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
23
+ "model.text_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
24
+ "model.text_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
25
+ "model.text_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
26
+ "model.text_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
27
+ "model.text_model.layers.10.input_layernorm.weight": "model-00002-of-00002.safetensors",
28
+ "model.text_model.layers.10.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
29
+ "model.text_model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
30
+ "model.text_model.layers.10.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
31
+ "model.text_model.layers.10.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
32
+ "model.text_model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
33
+ "model.text_model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
34
+ "model.text_model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
35
+ "model.text_model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
36
+ "model.text_model.layers.11.input_layernorm.weight": "model-00002-of-00002.safetensors",
37
+ "model.text_model.layers.11.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
38
+ "model.text_model.layers.11.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
39
+ "model.text_model.layers.11.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
40
+ "model.text_model.layers.11.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
41
+ "model.text_model.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
42
+ "model.text_model.layers.11.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
43
+ "model.text_model.layers.11.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
44
+ "model.text_model.layers.11.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
45
+ "model.text_model.layers.12.input_layernorm.weight": "model-00002-of-00002.safetensors",
46
+ "model.text_model.layers.12.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
47
+ "model.text_model.layers.12.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
48
+ "model.text_model.layers.12.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
49
+ "model.text_model.layers.12.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
50
+ "model.text_model.layers.12.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
51
+ "model.text_model.layers.12.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
52
+ "model.text_model.layers.12.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
53
+ "model.text_model.layers.12.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
54
+ "model.text_model.layers.13.input_layernorm.weight": "model-00002-of-00002.safetensors",
55
+ "model.text_model.layers.13.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
56
+ "model.text_model.layers.13.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
57
+ "model.text_model.layers.13.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
58
+ "model.text_model.layers.13.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
59
+ "model.text_model.layers.13.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
60
+ "model.text_model.layers.13.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
61
+ "model.text_model.layers.13.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
62
+ "model.text_model.layers.13.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
63
+ "model.text_model.layers.14.input_layernorm.weight": "model-00002-of-00002.safetensors",
64
+ "model.text_model.layers.14.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
65
+ "model.text_model.layers.14.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
66
+ "model.text_model.layers.14.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
67
+ "model.text_model.layers.14.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
68
+ "model.text_model.layers.14.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
69
+ "model.text_model.layers.14.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
70
+ "model.text_model.layers.14.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
71
+ "model.text_model.layers.14.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
72
+ "model.text_model.layers.15.input_layernorm.weight": "model-00002-of-00002.safetensors",
73
+ "model.text_model.layers.15.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
74
+ "model.text_model.layers.15.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
75
+ "model.text_model.layers.15.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
76
+ "model.text_model.layers.15.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
77
+ "model.text_model.layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
78
+ "model.text_model.layers.15.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
79
+ "model.text_model.layers.15.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
80
+ "model.text_model.layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
81
+ "model.text_model.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors",
82
+ "model.text_model.layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
83
+ "model.text_model.layers.16.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
84
+ "model.text_model.layers.16.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
85
+ "model.text_model.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
86
+ "model.text_model.layers.16.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
87
+ "model.text_model.layers.16.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
88
+ "model.text_model.layers.16.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
89
+ "model.text_model.layers.16.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
90
+ "model.text_model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
91
+ "model.text_model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
92
+ "model.text_model.layers.17.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
93
+ "model.text_model.layers.17.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
94
+ "model.text_model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
95
+ "model.text_model.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
96
+ "model.text_model.layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
97
+ "model.text_model.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
98
+ "model.text_model.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
99
+ "model.text_model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
100
+ "model.text_model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
101
+ "model.text_model.layers.18.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
102
+ "model.text_model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
103
+ "model.text_model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
104
+ "model.text_model.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
105
+ "model.text_model.layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
106
+ "model.text_model.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
107
+ "model.text_model.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
108
+ "model.text_model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
109
+ "model.text_model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
110
+ "model.text_model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
111
+ "model.text_model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
112
+ "model.text_model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
113
+ "model.text_model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
114
+ "model.text_model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
115
+ "model.text_model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
116
+ "model.text_model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
117
+ "model.text_model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
118
+ "model.text_model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
119
+ "model.text_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
120
+ "model.text_model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
121
+ "model.text_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
122
+ "model.text_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
123
+ "model.text_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
124
+ "model.text_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
125
+ "model.text_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
126
+ "model.text_model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
127
+ "model.text_model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
128
+ "model.text_model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
129
+ "model.text_model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
130
+ "model.text_model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
131
+ "model.text_model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
132
+ "model.text_model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
133
+ "model.text_model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
134
+ "model.text_model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
135
+ "model.text_model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
136
+ "model.text_model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
137
+ "model.text_model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
138
+ "model.text_model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
139
+ "model.text_model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
140
+ "model.text_model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
141
+ "model.text_model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
142
+ "model.text_model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
143
+ "model.text_model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
144
+ "model.text_model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
145
+ "model.text_model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
146
+ "model.text_model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
147
+ "model.text_model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
148
+ "model.text_model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
149
+ "model.text_model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
150
+ "model.text_model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
151
+ "model.text_model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
152
+ "model.text_model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
153
+ "model.text_model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
154
+ "model.text_model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
155
+ "model.text_model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
156
+ "model.text_model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
157
+ "model.text_model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
158
+ "model.text_model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
159
+ "model.text_model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
160
+ "model.text_model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
161
+ "model.text_model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
162
+ "model.text_model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
163
+ "model.text_model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
164
+ "model.text_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
165
+ "model.text_model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
166
+ "model.text_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
167
+ "model.text_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
168
+ "model.text_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
169
+ "model.text_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
170
+ "model.text_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
171
+ "model.text_model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
172
+ "model.text_model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
173
+ "model.text_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
174
+ "model.text_model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
175
+ "model.text_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
176
+ "model.text_model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
177
+ "model.text_model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
178
+ "model.text_model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
179
+ "model.text_model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
180
+ "model.text_model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
181
+ "model.text_model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
182
+ "model.text_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
183
+ "model.text_model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
184
+ "model.text_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
185
+ "model.text_model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
186
+ "model.text_model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
187
+ "model.text_model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
188
+ "model.text_model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
189
+ "model.text_model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
190
+ "model.text_model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
191
+ "model.text_model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
192
+ "model.text_model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
193
+ "model.text_model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
194
+ "model.text_model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
195
+ "model.text_model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
196
+ "model.text_model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
197
+ "model.text_model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
198
+ "model.text_model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
199
+ "model.text_model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
200
+ "model.text_model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
201
+ "model.text_model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
202
+ "model.text_model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
203
+ "model.text_model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
204
+ "model.text_model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
205
+ "model.text_model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
206
+ "model.text_model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
207
+ "model.text_model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
208
+ "model.text_model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
209
+ "model.text_model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
210
+ "model.text_model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
211
+ "model.text_model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
212
+ "model.text_model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
213
+ "model.text_model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
214
+ "model.text_model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
215
+ "model.text_model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
216
+ "model.text_model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
217
+ "model.text_model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
218
+ "model.text_model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
219
+ "model.text_model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
220
+ "model.text_model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
221
+ "model.text_model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
222
+ "model.text_model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
223
+ "model.text_model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
224
+ "model.text_model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
225
+ "model.text_model.norm.weight": "model-00002-of-00002.safetensors",
226
+ "model.vision_model.embeddings.patch_embedding.bias": "model-00001-of-00002.safetensors",
227
+ "model.vision_model.embeddings.patch_embedding.weight": "model-00001-of-00002.safetensors",
228
+ "model.vision_model.embeddings.position_embedding.weight": "model-00001-of-00002.safetensors",
229
+ "model.vision_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00002.safetensors",
230
+ "model.vision_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00002.safetensors",
231
+ "model.vision_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00002.safetensors",
232
+ "model.vision_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00002.safetensors",
233
+ "model.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00002.safetensors",
234
+ "model.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00002.safetensors",
235
+ "model.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00002.safetensors",
236
+ "model.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00002.safetensors",
237
+ "model.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
238
+ "model.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
239
+ "model.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
240
+ "model.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
241
+ "model.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
242
+ "model.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
243
+ "model.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
244
+ "model.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
245
+ "model.vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00002.safetensors",
246
+ "model.vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00002.safetensors",
247
+ "model.vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00002.safetensors",
248
+ "model.vision_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00002.safetensors",
249
+ "model.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00002.safetensors",
250
+ "model.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00002.safetensors",
251
+ "model.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00002.safetensors",
252
+ "model.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00002.safetensors",
253
+ "model.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
254
+ "model.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
255
+ "model.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
256
+ "model.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
257
+ "model.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
258
+ "model.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
259
+ "model.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
260
+ "model.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
261
+ "model.vision_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00002.safetensors",
262
+ "model.vision_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00002.safetensors",
263
+ "model.vision_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00002.safetensors",
264
+ "model.vision_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00002.safetensors",
265
+ "model.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00002.safetensors",
266
+ "model.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00002.safetensors",
267
+ "model.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00002.safetensors",
268
+ "model.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00002.safetensors",
269
+ "model.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
270
+ "model.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
271
+ "model.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
272
+ "model.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
273
+ "model.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
274
+ "model.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
275
+ "model.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
276
+ "model.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
277
+ "model.vision_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00002.safetensors",
278
+ "model.vision_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00002.safetensors",
279
+ "model.vision_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00002.safetensors",
280
+ "model.vision_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00002.safetensors",
281
+ "model.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00002.safetensors",
282
+ "model.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00002.safetensors",
283
+ "model.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00002.safetensors",
284
+ "model.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00002.safetensors",
285
+ "model.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
286
+ "model.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
287
+ "model.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
288
+ "model.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
289
+ "model.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
290
+ "model.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
291
+ "model.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
292
+ "model.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
293
+ "model.vision_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00002.safetensors",
294
+ "model.vision_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00002.safetensors",
295
+ "model.vision_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00002.safetensors",
296
+ "model.vision_model.encoder.layers.12.layer_norm2.weight": "model-00001-of-00002.safetensors",
297
+ "model.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00002.safetensors",
298
+ "model.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00002.safetensors",
299
+ "model.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00002.safetensors",
300
+ "model.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00002.safetensors",
301
+ "model.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
302
+ "model.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
303
+ "model.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
304
+ "model.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
305
+ "model.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
306
+ "model.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
307
+ "model.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
308
+ "model.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
309
+ "model.vision_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00002.safetensors",
310
+ "model.vision_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00002.safetensors",
311
+ "model.vision_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00002.safetensors",
312
+ "model.vision_model.encoder.layers.13.layer_norm2.weight": "model-00001-of-00002.safetensors",
313
+ "model.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00002.safetensors",
314
+ "model.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00002.safetensors",
315
+ "model.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00002.safetensors",
316
+ "model.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00002.safetensors",
317
+ "model.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
318
+ "model.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
319
+ "model.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
320
+ "model.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
321
+ "model.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
322
+ "model.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
323
+ "model.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
324
+ "model.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
325
+ "model.vision_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00002.safetensors",
326
+ "model.vision_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00002.safetensors",
327
+ "model.vision_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00002.safetensors",
328
+ "model.vision_model.encoder.layers.14.layer_norm2.weight": "model-00001-of-00002.safetensors",
329
+ "model.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00002.safetensors",
330
+ "model.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00002.safetensors",
331
+ "model.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00002.safetensors",
332
+ "model.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00002.safetensors",
333
+ "model.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
334
+ "model.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
335
+ "model.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
336
+ "model.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
337
+ "model.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
338
+ "model.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
339
+ "model.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
340
+ "model.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
341
+ "model.vision_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00002.safetensors",
342
+ "model.vision_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00002.safetensors",
343
+ "model.vision_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00002.safetensors",
344
+ "model.vision_model.encoder.layers.15.layer_norm2.weight": "model-00001-of-00002.safetensors",
345
+ "model.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00002.safetensors",
346
+ "model.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00002.safetensors",
347
+ "model.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00002.safetensors",
348
+ "model.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00002.safetensors",
349
+ "model.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
350
+ "model.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
351
+ "model.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
352
+ "model.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
353
+ "model.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
354
+ "model.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
355
+ "model.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
356
+ "model.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
357
+ "model.vision_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00002.safetensors",
358
+ "model.vision_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00002.safetensors",
359
+ "model.vision_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00002.safetensors",
360
+ "model.vision_model.encoder.layers.16.layer_norm2.weight": "model-00001-of-00002.safetensors",
361
+ "model.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00002.safetensors",
362
+ "model.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00002.safetensors",
363
+ "model.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00002.safetensors",
364
+ "model.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00002.safetensors",
365
+ "model.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
366
+ "model.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
367
+ "model.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
368
+ "model.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
369
+ "model.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
370
+ "model.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
371
+ "model.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
372
+ "model.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
373
+ "model.vision_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00002.safetensors",
374
+ "model.vision_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00002.safetensors",
375
+ "model.vision_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00002.safetensors",
376
+ "model.vision_model.encoder.layers.17.layer_norm2.weight": "model-00001-of-00002.safetensors",
377
+ "model.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00002.safetensors",
378
+ "model.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00002.safetensors",
379
+ "model.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00002.safetensors",
380
+ "model.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00002.safetensors",
381
+ "model.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
382
+ "model.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
383
+ "model.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
384
+ "model.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
385
+ "model.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
386
+ "model.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
387
+ "model.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
388
+ "model.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
389
+ "model.vision_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00002.safetensors",
390
+ "model.vision_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00002.safetensors",
391
+ "model.vision_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00002.safetensors",
392
+ "model.vision_model.encoder.layers.18.layer_norm2.weight": "model-00001-of-00002.safetensors",
393
+ "model.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00002.safetensors",
394
+ "model.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00002.safetensors",
395
+ "model.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00002.safetensors",
396
+ "model.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00002.safetensors",
397
+ "model.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
398
+ "model.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
399
+ "model.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
400
+ "model.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
401
+ "model.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
402
+ "model.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
403
+ "model.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
404
+ "model.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
405
+ "model.vision_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00002.safetensors",
406
+ "model.vision_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00002.safetensors",
407
+ "model.vision_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00002.safetensors",
408
+ "model.vision_model.encoder.layers.19.layer_norm2.weight": "model-00001-of-00002.safetensors",
409
+ "model.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00002.safetensors",
410
+ "model.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00002.safetensors",
411
+ "model.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00002.safetensors",
412
+ "model.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00002.safetensors",
413
+ "model.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
414
+ "model.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
415
+ "model.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
416
+ "model.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
417
+ "model.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
418
+ "model.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
419
+ "model.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
420
+ "model.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
421
+ "model.vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00002.safetensors",
422
+ "model.vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00002.safetensors",
423
+ "model.vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00002.safetensors",
424
+ "model.vision_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00002.safetensors",
425
+ "model.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00002.safetensors",
426
+ "model.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00002.safetensors",
427
+ "model.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00002.safetensors",
428
+ "model.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00002.safetensors",
429
+ "model.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
430
+ "model.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
431
+ "model.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
432
+ "model.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
433
+ "model.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
434
+ "model.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
435
+ "model.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
436
+ "model.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
437
+ "model.vision_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00002.safetensors",
438
+ "model.vision_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00002.safetensors",
439
+ "model.vision_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00002.safetensors",
440
+ "model.vision_model.encoder.layers.20.layer_norm2.weight": "model-00001-of-00002.safetensors",
441
+ "model.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00002.safetensors",
442
+ "model.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00002.safetensors",
443
+ "model.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00002.safetensors",
444
+ "model.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00002.safetensors",
445
+ "model.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
446
+ "model.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
447
+ "model.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
448
+ "model.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
449
+ "model.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
450
+ "model.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
451
+ "model.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
452
+ "model.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
453
+ "model.vision_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00002.safetensors",
454
+ "model.vision_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00002.safetensors",
455
+ "model.vision_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00002.safetensors",
456
+ "model.vision_model.encoder.layers.21.layer_norm2.weight": "model-00001-of-00002.safetensors",
457
+ "model.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00002.safetensors",
458
+ "model.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00002.safetensors",
459
+ "model.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00002.safetensors",
460
+ "model.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00002.safetensors",
461
+ "model.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
462
+ "model.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
463
+ "model.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
464
+ "model.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
465
+ "model.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
466
+ "model.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
467
+ "model.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
468
+ "model.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
469
+ "model.vision_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00002.safetensors",
470
+ "model.vision_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00002.safetensors",
471
+ "model.vision_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00002.safetensors",
472
+ "model.vision_model.encoder.layers.22.layer_norm2.weight": "model-00001-of-00002.safetensors",
473
+ "model.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00002.safetensors",
474
+ "model.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00002.safetensors",
475
+ "model.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00002.safetensors",
476
+ "model.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00002.safetensors",
477
+ "model.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
478
+ "model.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
479
+ "model.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
480
+ "model.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
481
+ "model.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
482
+ "model.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
483
+ "model.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
484
+ "model.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
485
+ "model.vision_model.encoder.layers.23.layer_norm1.bias": "model-00001-of-00002.safetensors",
486
+ "model.vision_model.encoder.layers.23.layer_norm1.weight": "model-00001-of-00002.safetensors",
487
+ "model.vision_model.encoder.layers.23.layer_norm2.bias": "model-00001-of-00002.safetensors",
488
+ "model.vision_model.encoder.layers.23.layer_norm2.weight": "model-00001-of-00002.safetensors",
489
+ "model.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00002.safetensors",
490
+ "model.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00002.safetensors",
491
+ "model.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00002.safetensors",
492
+ "model.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00002.safetensors",
493
+ "model.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
494
+ "model.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
495
+ "model.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
496
+ "model.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
497
+ "model.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
498
+ "model.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
499
+ "model.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
500
+ "model.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
501
+ "model.vision_model.encoder.layers.24.layer_norm1.bias": "model-00001-of-00002.safetensors",
502
+ "model.vision_model.encoder.layers.24.layer_norm1.weight": "model-00001-of-00002.safetensors",
503
+ "model.vision_model.encoder.layers.24.layer_norm2.bias": "model-00001-of-00002.safetensors",
504
+ "model.vision_model.encoder.layers.24.layer_norm2.weight": "model-00001-of-00002.safetensors",
505
+ "model.vision_model.encoder.layers.24.mlp.fc1.bias": "model-00001-of-00002.safetensors",
506
+ "model.vision_model.encoder.layers.24.mlp.fc1.weight": "model-00001-of-00002.safetensors",
507
+ "model.vision_model.encoder.layers.24.mlp.fc2.bias": "model-00001-of-00002.safetensors",
508
+ "model.vision_model.encoder.layers.24.mlp.fc2.weight": "model-00001-of-00002.safetensors",
509
+ "model.vision_model.encoder.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
510
+ "model.vision_model.encoder.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
511
+ "model.vision_model.encoder.layers.24.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
512
+ "model.vision_model.encoder.layers.24.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
513
+ "model.vision_model.encoder.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
514
+ "model.vision_model.encoder.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
515
+ "model.vision_model.encoder.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
516
+ "model.vision_model.encoder.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
517
+ "model.vision_model.encoder.layers.25.layer_norm1.bias": "model-00001-of-00002.safetensors",
518
+ "model.vision_model.encoder.layers.25.layer_norm1.weight": "model-00001-of-00002.safetensors",
519
+ "model.vision_model.encoder.layers.25.layer_norm2.bias": "model-00001-of-00002.safetensors",
520
+ "model.vision_model.encoder.layers.25.layer_norm2.weight": "model-00001-of-00002.safetensors",
521
+ "model.vision_model.encoder.layers.25.mlp.fc1.bias": "model-00001-of-00002.safetensors",
522
+ "model.vision_model.encoder.layers.25.mlp.fc1.weight": "model-00001-of-00002.safetensors",
523
+ "model.vision_model.encoder.layers.25.mlp.fc2.bias": "model-00001-of-00002.safetensors",
524
+ "model.vision_model.encoder.layers.25.mlp.fc2.weight": "model-00001-of-00002.safetensors",
525
+ "model.vision_model.encoder.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
526
+ "model.vision_model.encoder.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
527
+ "model.vision_model.encoder.layers.25.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
528
+ "model.vision_model.encoder.layers.25.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
529
+ "model.vision_model.encoder.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
530
+ "model.vision_model.encoder.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
531
+ "model.vision_model.encoder.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
532
+ "model.vision_model.encoder.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
533
+ "model.vision_model.encoder.layers.26.layer_norm1.bias": "model-00001-of-00002.safetensors",
534
+ "model.vision_model.encoder.layers.26.layer_norm1.weight": "model-00001-of-00002.safetensors",
535
+ "model.vision_model.encoder.layers.26.layer_norm2.bias": "model-00001-of-00002.safetensors",
536
+ "model.vision_model.encoder.layers.26.layer_norm2.weight": "model-00001-of-00002.safetensors",
537
+ "model.vision_model.encoder.layers.26.mlp.fc1.bias": "model-00001-of-00002.safetensors",
538
+ "model.vision_model.encoder.layers.26.mlp.fc1.weight": "model-00001-of-00002.safetensors",
539
+ "model.vision_model.encoder.layers.26.mlp.fc2.bias": "model-00001-of-00002.safetensors",
540
+ "model.vision_model.encoder.layers.26.mlp.fc2.weight": "model-00001-of-00002.safetensors",
541
+ "model.vision_model.encoder.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
542
+ "model.vision_model.encoder.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
543
+ "model.vision_model.encoder.layers.26.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
544
+ "model.vision_model.encoder.layers.26.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
545
+ "model.vision_model.encoder.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
546
+ "model.vision_model.encoder.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
547
+ "model.vision_model.encoder.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
548
+ "model.vision_model.encoder.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
549
+ "model.vision_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00002.safetensors",
550
+ "model.vision_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00002.safetensors",
551
+ "model.vision_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00002.safetensors",
552
+ "model.vision_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00002.safetensors",
553
+ "model.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00002.safetensors",
554
+ "model.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00002.safetensors",
555
+ "model.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00002.safetensors",
556
+ "model.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00002.safetensors",
557
+ "model.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
558
+ "model.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
559
+ "model.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
560
+ "model.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
561
+ "model.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
562
+ "model.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
563
+ "model.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
564
+ "model.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
565
+ "model.vision_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00002.safetensors",
566
+ "model.vision_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00002.safetensors",
567
+ "model.vision_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00002.safetensors",
568
+ "model.vision_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00002.safetensors",
569
+ "model.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00002.safetensors",
570
+ "model.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00002.safetensors",
571
+ "model.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00002.safetensors",
572
+ "model.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00002.safetensors",
573
+ "model.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
574
+ "model.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
575
+ "model.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
576
+ "model.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
577
+ "model.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
578
+ "model.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
579
+ "model.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
580
+ "model.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
581
+ "model.vision_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00002.safetensors",
582
+ "model.vision_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00002.safetensors",
583
+ "model.vision_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00002.safetensors",
584
+ "model.vision_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00002.safetensors",
585
+ "model.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00002.safetensors",
586
+ "model.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00002.safetensors",
587
+ "model.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00002.safetensors",
588
+ "model.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00002.safetensors",
589
+ "model.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
590
+ "model.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
591
+ "model.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
592
+ "model.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
593
+ "model.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
594
+ "model.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
595
+ "model.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
596
+ "model.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
597
+ "model.vision_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00002.safetensors",
598
+ "model.vision_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00002.safetensors",
599
+ "model.vision_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00002.safetensors",
600
+ "model.vision_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00002.safetensors",
601
+ "model.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00002.safetensors",
602
+ "model.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00002.safetensors",
603
+ "model.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00002.safetensors",
604
+ "model.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00002.safetensors",
605
+ "model.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
606
+ "model.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
607
+ "model.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
608
+ "model.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
609
+ "model.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
610
+ "model.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
611
+ "model.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
612
+ "model.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
613
+ "model.vision_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00002.safetensors",
614
+ "model.vision_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00002.safetensors",
615
+ "model.vision_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00002.safetensors",
616
+ "model.vision_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00002.safetensors",
617
+ "model.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00002.safetensors",
618
+ "model.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00002.safetensors",
619
+ "model.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00002.safetensors",
620
+ "model.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00002.safetensors",
621
+ "model.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
622
+ "model.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
623
+ "model.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
624
+ "model.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
625
+ "model.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
626
+ "model.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
627
+ "model.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
628
+ "model.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
629
+ "model.vision_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00002.safetensors",
630
+ "model.vision_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00002.safetensors",
631
+ "model.vision_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00002.safetensors",
632
+ "model.vision_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00002.safetensors",
633
+ "model.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00002.safetensors",
634
+ "model.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00002.safetensors",
635
+ "model.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00002.safetensors",
636
+ "model.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00002.safetensors",
637
+ "model.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
638
+ "model.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
639
+ "model.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
640
+ "model.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
641
+ "model.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
642
+ "model.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
643
+ "model.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
644
+ "model.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
645
+ "model.vision_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00002.safetensors",
646
+ "model.vision_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00002.safetensors",
647
+ "model.vision_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00002.safetensors",
648
+ "model.vision_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00002.safetensors",
649
+ "model.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00002.safetensors",
650
+ "model.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00002.safetensors",
651
+ "model.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00002.safetensors",
652
+ "model.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00002.safetensors",
653
+ "model.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
654
+ "model.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
655
+ "model.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
656
+ "model.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
657
+ "model.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
658
+ "model.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
659
+ "model.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
660
+ "model.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
661
+ "model.vision_model.post_layernorm.bias": "model-00001-of-00002.safetensors",
662
+ "model.vision_model.post_layernorm.weight": "model-00001-of-00002.safetensors"
663
+ }
664
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": true,
3
+ "do_image_splitting": true,
4
+ "do_normalize": true,
5
+ "do_pad": true,
6
+ "do_rescale": true,
7
+ "do_resize": true,
8
+ "image_mean": [
9
+ 0.5,
10
+ 0.5,
11
+ 0.5
12
+ ],
13
+ "image_processor_type": "SmolVLMImageProcessor",
14
+ "image_std": [
15
+ 0.5,
16
+ 0.5,
17
+ 0.5
18
+ ],
19
+ "max_image_size": {
20
+ "longest_edge": 384
21
+ },
22
+ "processor_class": "SmolVLMProcessor",
23
+ "resample": 1,
24
+ "rescale_factor": 0.00392156862745098,
25
+ "size": {
26
+ "longest_edge": 1536
27
+ },
28
+ "video_sampling": {
29
+ "fps": 1,
30
+ "max_frames": 64,
31
+ "video_size": {
32
+ "longest_edge": 384
33
+ }
34
+ }
35
+ }
processor_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "image_seq_len": 81,
3
+ "processor_class": "SmolVLMProcessor"
4
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<fake_token_around_image>",
4
+ "<image>",
5
+ "<end_of_utterance>"
6
+ ],
7
+ "bos_token": {
8
+ "content": "<|im_start|>",
9
+ "lstrip": false,
10
+ "normalized": false,
11
+ "rstrip": false,
12
+ "single_word": false
13
+ },
14
+ "end_of_utterance_token": "<end_of_utterance>",
15
+ "eos_token": {
16
+ "content": "<end_of_utterance>",
17
+ "lstrip": false,
18
+ "normalized": false,
19
+ "rstrip": false,
20
+ "single_word": false
21
+ },
22
+ "fake_image_token": "<fake_token_around_image>",
23
+ "global_image_token": "<global-img>",
24
+ "image_token": "<image>",
25
+ "pad_token": {
26
+ "content": "<|im_end|>",
27
+ "lstrip": false,
28
+ "normalized": false,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ },
32
+ "unk_token": {
33
+ "content": "<|endoftext|>",
34
+ "lstrip": false,
35
+ "normalized": false,
36
+ "rstrip": false,
37
+ "single_word": false
38
+ }
39
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,1191 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<repo_name>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": "<reponame>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "5": {
45
+ "content": "<file_sep>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "6": {
53
+ "content": "<filename>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "7": {
61
+ "content": "<gh_stars>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "8": {
69
+ "content": "<issue_start>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "9": {
77
+ "content": "<issue_comment>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "10": {
85
+ "content": "<issue_closed>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "11": {
93
+ "content": "<jupyter_start>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "12": {
101
+ "content": "<jupyter_text>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "13": {
109
+ "content": "<jupyter_code>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "14": {
117
+ "content": "<jupyter_output>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "15": {
125
+ "content": "<jupyter_script>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "16": {
133
+ "content": "<empty_output>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "49152": {
141
+ "content": "<global-img>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "49153": {
149
+ "content": "<row_1_col_1>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "49154": {
157
+ "content": "<row_1_col_2>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "49155": {
165
+ "content": "<row_1_col_3>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "49156": {
173
+ "content": "<row_1_col_4>",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "49157": {
181
+ "content": "<row_1_col_5>",
182
+ "lstrip": false,
183
+ "normalized": false,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": true
187
+ },
188
+ "49158": {
189
+ "content": "<row_1_col_6>",
190
+ "lstrip": false,
191
+ "normalized": false,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": true
195
+ },
196
+ "49159": {
197
+ "content": "<row_2_col_1>",
198
+ "lstrip": false,
199
+ "normalized": false,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": true
203
+ },
204
+ "49160": {
205
+ "content": "<row_2_col_2>",
206
+ "lstrip": false,
207
+ "normalized": false,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "49161": {
213
+ "content": "<row_2_col_3>",
214
+ "lstrip": false,
215
+ "normalized": false,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "49162": {
221
+ "content": "<row_2_col_4>",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "49163": {
229
+ "content": "<row_2_col_5>",
230
+ "lstrip": false,
231
+ "normalized": false,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "49164": {
237
+ "content": "<row_2_col_6>",
238
+ "lstrip": false,
239
+ "normalized": false,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "49165": {
245
+ "content": "<row_3_col_1>",
246
+ "lstrip": false,
247
+ "normalized": false,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "49166": {
253
+ "content": "<row_3_col_2>",
254
+ "lstrip": false,
255
+ "normalized": false,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "49167": {
261
+ "content": "<row_3_col_3>",
262
+ "lstrip": false,
263
+ "normalized": false,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": true
267
+ },
268
+ "49168": {
269
+ "content": "<row_3_col_4>",
270
+ "lstrip": false,
271
+ "normalized": false,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": true
275
+ },
276
+ "49169": {
277
+ "content": "<row_3_col_5>",
278
+ "lstrip": false,
279
+ "normalized": false,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": true
283
+ },
284
+ "49170": {
285
+ "content": "<row_3_col_6>",
286
+ "lstrip": false,
287
+ "normalized": false,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": true
291
+ },
292
+ "49171": {
293
+ "content": "<row_4_col_1>",
294
+ "lstrip": false,
295
+ "normalized": false,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": true
299
+ },
300
+ "49172": {
301
+ "content": "<row_4_col_2>",
302
+ "lstrip": false,
303
+ "normalized": false,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": true
307
+ },
308
+ "49173": {
309
+ "content": "<row_4_col_3>",
310
+ "lstrip": false,
311
+ "normalized": false,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": true
315
+ },
316
+ "49174": {
317
+ "content": "<row_4_col_4>",
318
+ "lstrip": false,
319
+ "normalized": false,
320
+ "rstrip": false,
321
+ "single_word": false,
322
+ "special": true
323
+ },
324
+ "49175": {
325
+ "content": "<row_4_col_5>",
326
+ "lstrip": false,
327
+ "normalized": false,
328
+ "rstrip": false,
329
+ "single_word": false,
330
+ "special": true
331
+ },
332
+ "49176": {
333
+ "content": "<row_4_col_6>",
334
+ "lstrip": false,
335
+ "normalized": false,
336
+ "rstrip": false,
337
+ "single_word": false,
338
+ "special": true
339
+ },
340
+ "49177": {
341
+ "content": "<row_5_col_1>",
342
+ "lstrip": false,
343
+ "normalized": false,
344
+ "rstrip": false,
345
+ "single_word": false,
346
+ "special": true
347
+ },
348
+ "49178": {
349
+ "content": "<row_5_col_2>",
350
+ "lstrip": false,
351
+ "normalized": false,
352
+ "rstrip": false,
353
+ "single_word": false,
354
+ "special": true
355
+ },
356
+ "49179": {
357
+ "content": "<row_5_col_3>",
358
+ "lstrip": false,
359
+ "normalized": false,
360
+ "rstrip": false,
361
+ "single_word": false,
362
+ "special": true
363
+ },
364
+ "49180": {
365
+ "content": "<row_5_col_4>",
366
+ "lstrip": false,
367
+ "normalized": false,
368
+ "rstrip": false,
369
+ "single_word": false,
370
+ "special": true
371
+ },
372
+ "49181": {
373
+ "content": "<row_5_col_5>",
374
+ "lstrip": false,
375
+ "normalized": false,
376
+ "rstrip": false,
377
+ "single_word": false,
378
+ "special": true
379
+ },
380
+ "49182": {
381
+ "content": "<row_5_col_6>",
382
+ "lstrip": false,
383
+ "normalized": false,
384
+ "rstrip": false,
385
+ "single_word": false,
386
+ "special": true
387
+ },
388
+ "49183": {
389
+ "content": "<row_6_col_1>",
390
+ "lstrip": false,
391
+ "normalized": false,
392
+ "rstrip": false,
393
+ "single_word": false,
394
+ "special": true
395
+ },
396
+ "49184": {
397
+ "content": "<row_6_col_2>",
398
+ "lstrip": false,
399
+ "normalized": false,
400
+ "rstrip": false,
401
+ "single_word": false,
402
+ "special": true
403
+ },
404
+ "49185": {
405
+ "content": "<row_6_col_3>",
406
+ "lstrip": false,
407
+ "normalized": false,
408
+ "rstrip": false,
409
+ "single_word": false,
410
+ "special": true
411
+ },
412
+ "49186": {
413
+ "content": "<row_6_col_4>",
414
+ "lstrip": false,
415
+ "normalized": false,
416
+ "rstrip": false,
417
+ "single_word": false,
418
+ "special": true
419
+ },
420
+ "49187": {
421
+ "content": "<row_6_col_5>",
422
+ "lstrip": false,
423
+ "normalized": false,
424
+ "rstrip": false,
425
+ "single_word": false,
426
+ "special": true
427
+ },
428
+ "49188": {
429
+ "content": "<row_6_col_6>",
430
+ "lstrip": false,
431
+ "normalized": false,
432
+ "rstrip": false,
433
+ "single_word": false,
434
+ "special": true
435
+ },
436
+ "49189": {
437
+ "content": "<fake_token_around_image>",
438
+ "lstrip": false,
439
+ "normalized": false,
440
+ "rstrip": false,
441
+ "single_word": false,
442
+ "special": true
443
+ },
444
+ "49190": {
445
+ "content": "<image>",
446
+ "lstrip": false,
447
+ "normalized": false,
448
+ "rstrip": false,
449
+ "single_word": false,
450
+ "special": true
451
+ },
452
+ "49191": {
453
+ "content": "<|reserved_special_token_0|>",
454
+ "lstrip": false,
455
+ "normalized": false,
456
+ "rstrip": false,
457
+ "single_word": false,
458
+ "special": true
459
+ },
460
+ "49192": {
461
+ "content": "<|reserved_special_token_1|>",
462
+ "lstrip": false,
463
+ "normalized": false,
464
+ "rstrip": false,
465
+ "single_word": false,
466
+ "special": true
467
+ },
468
+ "49193": {
469
+ "content": "<|reserved_special_token_2|>",
470
+ "lstrip": false,
471
+ "normalized": false,
472
+ "rstrip": false,
473
+ "single_word": false,
474
+ "special": true
475
+ },
476
+ "49194": {
477
+ "content": "<|reserved_special_token_3|>",
478
+ "lstrip": false,
479
+ "normalized": false,
480
+ "rstrip": false,
481
+ "single_word": false,
482
+ "special": true
483
+ },
484
+ "49195": {
485
+ "content": "<|reserved_special_token_4|>",
486
+ "lstrip": false,
487
+ "normalized": false,
488
+ "rstrip": false,
489
+ "single_word": false,
490
+ "special": true
491
+ },
492
+ "49196": {
493
+ "content": "<|reserved_special_token_5|>",
494
+ "lstrip": false,
495
+ "normalized": false,
496
+ "rstrip": false,
497
+ "single_word": false,
498
+ "special": true
499
+ },
500
+ "49197": {
501
+ "content": "<|reserved_special_token_6|>",
502
+ "lstrip": false,
503
+ "normalized": false,
504
+ "rstrip": false,
505
+ "single_word": false,
506
+ "special": true
507
+ },
508
+ "49198": {
509
+ "content": "<|reserved_special_token_7|>",
510
+ "lstrip": false,
511
+ "normalized": false,
512
+ "rstrip": false,
513
+ "single_word": false,
514
+ "special": true
515
+ },
516
+ "49199": {
517
+ "content": "<|reserved_special_token_8|>",
518
+ "lstrip": false,
519
+ "normalized": false,
520
+ "rstrip": false,
521
+ "single_word": false,
522
+ "special": true
523
+ },
524
+ "49200": {
525
+ "content": "<|reserved_special_token_9|>",
526
+ "lstrip": false,
527
+ "normalized": false,
528
+ "rstrip": false,
529
+ "single_word": false,
530
+ "special": true
531
+ },
532
+ "49201": {
533
+ "content": "<|reserved_special_token_10|>",
534
+ "lstrip": false,
535
+ "normalized": false,
536
+ "rstrip": false,
537
+ "single_word": false,
538
+ "special": true
539
+ },
540
+ "49202": {
541
+ "content": "<|reserved_special_token_11|>",
542
+ "lstrip": false,
543
+ "normalized": false,
544
+ "rstrip": false,
545
+ "single_word": false,
546
+ "special": true
547
+ },
548
+ "49203": {
549
+ "content": "<|reserved_special_token_12|>",
550
+ "lstrip": false,
551
+ "normalized": false,
552
+ "rstrip": false,
553
+ "single_word": false,
554
+ "special": true
555
+ },
556
+ "49204": {
557
+ "content": "<|reserved_special_token_13|>",
558
+ "lstrip": false,
559
+ "normalized": false,
560
+ "rstrip": false,
561
+ "single_word": false,
562
+ "special": true
563
+ },
564
+ "49205": {
565
+ "content": "<|reserved_special_token_14|>",
566
+ "lstrip": false,
567
+ "normalized": false,
568
+ "rstrip": false,
569
+ "single_word": false,
570
+ "special": true
571
+ },
572
+ "49206": {
573
+ "content": "<|reserved_special_token_15|>",
574
+ "lstrip": false,
575
+ "normalized": false,
576
+ "rstrip": false,
577
+ "single_word": false,
578
+ "special": true
579
+ },
580
+ "49207": {
581
+ "content": "<|reserved_special_token_16|>",
582
+ "lstrip": false,
583
+ "normalized": false,
584
+ "rstrip": false,
585
+ "single_word": false,
586
+ "special": true
587
+ },
588
+ "49208": {
589
+ "content": "<|reserved_special_token_17|>",
590
+ "lstrip": false,
591
+ "normalized": false,
592
+ "rstrip": false,
593
+ "single_word": false,
594
+ "special": true
595
+ },
596
+ "49209": {
597
+ "content": "<|reserved_special_token_18|>",
598
+ "lstrip": false,
599
+ "normalized": false,
600
+ "rstrip": false,
601
+ "single_word": false,
602
+ "special": true
603
+ },
604
+ "49210": {
605
+ "content": "<|reserved_special_token_19|>",
606
+ "lstrip": false,
607
+ "normalized": false,
608
+ "rstrip": false,
609
+ "single_word": false,
610
+ "special": true
611
+ },
612
+ "49211": {
613
+ "content": "<|reserved_special_token_20|>",
614
+ "lstrip": false,
615
+ "normalized": false,
616
+ "rstrip": false,
617
+ "single_word": false,
618
+ "special": true
619
+ },
620
+ "49212": {
621
+ "content": "<|reserved_special_token_21|>",
622
+ "lstrip": false,
623
+ "normalized": false,
624
+ "rstrip": false,
625
+ "single_word": false,
626
+ "special": true
627
+ },
628
+ "49213": {
629
+ "content": "<|reserved_special_token_22|>",
630
+ "lstrip": false,
631
+ "normalized": false,
632
+ "rstrip": false,
633
+ "single_word": false,
634
+ "special": true
635
+ },
636
+ "49214": {
637
+ "content": "<|reserved_special_token_23|>",
638
+ "lstrip": false,
639
+ "normalized": false,
640
+ "rstrip": false,
641
+ "single_word": false,
642
+ "special": true
643
+ },
644
+ "49215": {
645
+ "content": "<|reserved_special_token_24|>",
646
+ "lstrip": false,
647
+ "normalized": false,
648
+ "rstrip": false,
649
+ "single_word": false,
650
+ "special": true
651
+ },
652
+ "49216": {
653
+ "content": "<|reserved_special_token_25|>",
654
+ "lstrip": false,
655
+ "normalized": false,
656
+ "rstrip": false,
657
+ "single_word": false,
658
+ "special": true
659
+ },
660
+ "49217": {
661
+ "content": "<|reserved_special_token_26|>",
662
+ "lstrip": false,
663
+ "normalized": false,
664
+ "rstrip": false,
665
+ "single_word": false,
666
+ "special": true
667
+ },
668
+ "49218": {
669
+ "content": "<|reserved_special_token_27|>",
670
+ "lstrip": false,
671
+ "normalized": false,
672
+ "rstrip": false,
673
+ "single_word": false,
674
+ "special": true
675
+ },
676
+ "49219": {
677
+ "content": "<|reserved_special_token_28|>",
678
+ "lstrip": false,
679
+ "normalized": false,
680
+ "rstrip": false,
681
+ "single_word": false,
682
+ "special": true
683
+ },
684
+ "49220": {
685
+ "content": "<|reserved_special_token_29|>",
686
+ "lstrip": false,
687
+ "normalized": false,
688
+ "rstrip": false,
689
+ "single_word": false,
690
+ "special": true
691
+ },
692
+ "49221": {
693
+ "content": "<|reserved_special_token_30|>",
694
+ "lstrip": false,
695
+ "normalized": false,
696
+ "rstrip": false,
697
+ "single_word": false,
698
+ "special": true
699
+ },
700
+ "49222": {
701
+ "content": "<|reserved_special_token_31|>",
702
+ "lstrip": false,
703
+ "normalized": false,
704
+ "rstrip": false,
705
+ "single_word": false,
706
+ "special": true
707
+ },
708
+ "49223": {
709
+ "content": "<|reserved_special_token_32|>",
710
+ "lstrip": false,
711
+ "normalized": false,
712
+ "rstrip": false,
713
+ "single_word": false,
714
+ "special": true
715
+ },
716
+ "49224": {
717
+ "content": "<|reserved_special_token_33|>",
718
+ "lstrip": false,
719
+ "normalized": false,
720
+ "rstrip": false,
721
+ "single_word": false,
722
+ "special": true
723
+ },
724
+ "49225": {
725
+ "content": "<|reserved_special_token_34|>",
726
+ "lstrip": false,
727
+ "normalized": false,
728
+ "rstrip": false,
729
+ "single_word": false,
730
+ "special": true
731
+ },
732
+ "49226": {
733
+ "content": "<|reserved_special_token_35|>",
734
+ "lstrip": false,
735
+ "normalized": false,
736
+ "rstrip": false,
737
+ "single_word": false,
738
+ "special": true
739
+ },
740
+ "49227": {
741
+ "content": "<|reserved_special_token_36|>",
742
+ "lstrip": false,
743
+ "normalized": false,
744
+ "rstrip": false,
745
+ "single_word": false,
746
+ "special": true
747
+ },
748
+ "49228": {
749
+ "content": "<|reserved_special_token_37|>",
750
+ "lstrip": false,
751
+ "normalized": false,
752
+ "rstrip": false,
753
+ "single_word": false,
754
+ "special": true
755
+ },
756
+ "49229": {
757
+ "content": "<|reserved_special_token_38|>",
758
+ "lstrip": false,
759
+ "normalized": false,
760
+ "rstrip": false,
761
+ "single_word": false,
762
+ "special": true
763
+ },
764
+ "49230": {
765
+ "content": "<|reserved_special_token_39|>",
766
+ "lstrip": false,
767
+ "normalized": false,
768
+ "rstrip": false,
769
+ "single_word": false,
770
+ "special": true
771
+ },
772
+ "49231": {
773
+ "content": "<|reserved_special_token_40|>",
774
+ "lstrip": false,
775
+ "normalized": false,
776
+ "rstrip": false,
777
+ "single_word": false,
778
+ "special": true
779
+ },
780
+ "49232": {
781
+ "content": "<|reserved_special_token_41|>",
782
+ "lstrip": false,
783
+ "normalized": false,
784
+ "rstrip": false,
785
+ "single_word": false,
786
+ "special": true
787
+ },
788
+ "49233": {
789
+ "content": "<|reserved_special_token_42|>",
790
+ "lstrip": false,
791
+ "normalized": false,
792
+ "rstrip": false,
793
+ "single_word": false,
794
+ "special": true
795
+ },
796
+ "49234": {
797
+ "content": "<|reserved_special_token_43|>",
798
+ "lstrip": false,
799
+ "normalized": false,
800
+ "rstrip": false,
801
+ "single_word": false,
802
+ "special": true
803
+ },
804
+ "49235": {
805
+ "content": "<|reserved_special_token_44|>",
806
+ "lstrip": false,
807
+ "normalized": false,
808
+ "rstrip": false,
809
+ "single_word": false,
810
+ "special": true
811
+ },
812
+ "49236": {
813
+ "content": "<|reserved_special_token_45|>",
814
+ "lstrip": false,
815
+ "normalized": false,
816
+ "rstrip": false,
817
+ "single_word": false,
818
+ "special": true
819
+ },
820
+ "49237": {
821
+ "content": "<|reserved_special_token_46|>",
822
+ "lstrip": false,
823
+ "normalized": false,
824
+ "rstrip": false,
825
+ "single_word": false,
826
+ "special": true
827
+ },
828
+ "49238": {
829
+ "content": "<|reserved_special_token_47|>",
830
+ "lstrip": false,
831
+ "normalized": false,
832
+ "rstrip": false,
833
+ "single_word": false,
834
+ "special": true
835
+ },
836
+ "49239": {
837
+ "content": "<|reserved_special_token_48|>",
838
+ "lstrip": false,
839
+ "normalized": false,
840
+ "rstrip": false,
841
+ "single_word": false,
842
+ "special": true
843
+ },
844
+ "49240": {
845
+ "content": "<|reserved_special_token_49|>",
846
+ "lstrip": false,
847
+ "normalized": false,
848
+ "rstrip": false,
849
+ "single_word": false,
850
+ "special": true
851
+ },
852
+ "49241": {
853
+ "content": "<|reserved_special_token_50|>",
854
+ "lstrip": false,
855
+ "normalized": false,
856
+ "rstrip": false,
857
+ "single_word": false,
858
+ "special": true
859
+ },
860
+ "49242": {
861
+ "content": "<|reserved_special_token_51|>",
862
+ "lstrip": false,
863
+ "normalized": false,
864
+ "rstrip": false,
865
+ "single_word": false,
866
+ "special": true
867
+ },
868
+ "49243": {
869
+ "content": "<|reserved_special_token_52|>",
870
+ "lstrip": false,
871
+ "normalized": false,
872
+ "rstrip": false,
873
+ "single_word": false,
874
+ "special": true
875
+ },
876
+ "49244": {
877
+ "content": "<|reserved_special_token_53|>",
878
+ "lstrip": false,
879
+ "normalized": false,
880
+ "rstrip": false,
881
+ "single_word": false,
882
+ "special": true
883
+ },
884
+ "49245": {
885
+ "content": "<|reserved_special_token_54|>",
886
+ "lstrip": false,
887
+ "normalized": false,
888
+ "rstrip": false,
889
+ "single_word": false,
890
+ "special": true
891
+ },
892
+ "49246": {
893
+ "content": "<|reserved_special_token_55|>",
894
+ "lstrip": false,
895
+ "normalized": false,
896
+ "rstrip": false,
897
+ "single_word": false,
898
+ "special": true
899
+ },
900
+ "49247": {
901
+ "content": "<|reserved_special_token_56|>",
902
+ "lstrip": false,
903
+ "normalized": false,
904
+ "rstrip": false,
905
+ "single_word": false,
906
+ "special": true
907
+ },
908
+ "49248": {
909
+ "content": "<|reserved_special_token_57|>",
910
+ "lstrip": false,
911
+ "normalized": false,
912
+ "rstrip": false,
913
+ "single_word": false,
914
+ "special": true
915
+ },
916
+ "49249": {
917
+ "content": "<|reserved_special_token_58|>",
918
+ "lstrip": false,
919
+ "normalized": false,
920
+ "rstrip": false,
921
+ "single_word": false,
922
+ "special": true
923
+ },
924
+ "49250": {
925
+ "content": "<|reserved_special_token_59|>",
926
+ "lstrip": false,
927
+ "normalized": false,
928
+ "rstrip": false,
929
+ "single_word": false,
930
+ "special": true
931
+ },
932
+ "49251": {
933
+ "content": "<|reserved_special_token_60|>",
934
+ "lstrip": false,
935
+ "normalized": false,
936
+ "rstrip": false,
937
+ "single_word": false,
938
+ "special": true
939
+ },
940
+ "49252": {
941
+ "content": "<|reserved_special_token_61|>",
942
+ "lstrip": false,
943
+ "normalized": false,
944
+ "rstrip": false,
945
+ "single_word": false,
946
+ "special": true
947
+ },
948
+ "49253": {
949
+ "content": "<|reserved_special_token_62|>",
950
+ "lstrip": false,
951
+ "normalized": false,
952
+ "rstrip": false,
953
+ "single_word": false,
954
+ "special": true
955
+ },
956
+ "49254": {
957
+ "content": "<|reserved_special_token_63|>",
958
+ "lstrip": false,
959
+ "normalized": false,
960
+ "rstrip": false,
961
+ "single_word": false,
962
+ "special": true
963
+ },
964
+ "49255": {
965
+ "content": "<|reserved_special_token_64|>",
966
+ "lstrip": false,
967
+ "normalized": false,
968
+ "rstrip": false,
969
+ "single_word": false,
970
+ "special": true
971
+ },
972
+ "49256": {
973
+ "content": "<|reserved_special_token_65|>",
974
+ "lstrip": false,
975
+ "normalized": false,
976
+ "rstrip": false,
977
+ "single_word": false,
978
+ "special": true
979
+ },
980
+ "49257": {
981
+ "content": "<|reserved_special_token_66|>",
982
+ "lstrip": false,
983
+ "normalized": false,
984
+ "rstrip": false,
985
+ "single_word": false,
986
+ "special": true
987
+ },
988
+ "49258": {
989
+ "content": "<|reserved_special_token_67|>",
990
+ "lstrip": false,
991
+ "normalized": false,
992
+ "rstrip": false,
993
+ "single_word": false,
994
+ "special": true
995
+ },
996
+ "49259": {
997
+ "content": "<|reserved_special_token_68|>",
998
+ "lstrip": false,
999
+ "normalized": false,
1000
+ "rstrip": false,
1001
+ "single_word": false,
1002
+ "special": true
1003
+ },
1004
+ "49260": {
1005
+ "content": "<|reserved_special_token_69|>",
1006
+ "lstrip": false,
1007
+ "normalized": false,
1008
+ "rstrip": false,
1009
+ "single_word": false,
1010
+ "special": true
1011
+ },
1012
+ "49261": {
1013
+ "content": "<|reserved_special_token_70|>",
1014
+ "lstrip": false,
1015
+ "normalized": false,
1016
+ "rstrip": false,
1017
+ "single_word": false,
1018
+ "special": true
1019
+ },
1020
+ "49262": {
1021
+ "content": "<|reserved_special_token_71|>",
1022
+ "lstrip": false,
1023
+ "normalized": false,
1024
+ "rstrip": false,
1025
+ "single_word": false,
1026
+ "special": true
1027
+ },
1028
+ "49263": {
1029
+ "content": "<|reserved_special_token_72|>",
1030
+ "lstrip": false,
1031
+ "normalized": false,
1032
+ "rstrip": false,
1033
+ "single_word": false,
1034
+ "special": true
1035
+ },
1036
+ "49264": {
1037
+ "content": "<|reserved_special_token_73|>",
1038
+ "lstrip": false,
1039
+ "normalized": false,
1040
+ "rstrip": false,
1041
+ "single_word": false,
1042
+ "special": true
1043
+ },
1044
+ "49265": {
1045
+ "content": "<|reserved_special_token_74|>",
1046
+ "lstrip": false,
1047
+ "normalized": false,
1048
+ "rstrip": false,
1049
+ "single_word": false,
1050
+ "special": true
1051
+ },
1052
+ "49266": {
1053
+ "content": "<|reserved_special_token_75|>",
1054
+ "lstrip": false,
1055
+ "normalized": false,
1056
+ "rstrip": false,
1057
+ "single_word": false,
1058
+ "special": true
1059
+ },
1060
+ "49267": {
1061
+ "content": "<|reserved_special_token_76|>",
1062
+ "lstrip": false,
1063
+ "normalized": false,
1064
+ "rstrip": false,
1065
+ "single_word": false,
1066
+ "special": true
1067
+ },
1068
+ "49268": {
1069
+ "content": "<|reserved_special_token_77|>",
1070
+ "lstrip": false,
1071
+ "normalized": false,
1072
+ "rstrip": false,
1073
+ "single_word": false,
1074
+ "special": true
1075
+ },
1076
+ "49269": {
1077
+ "content": "<|reserved_special_token_78|>",
1078
+ "lstrip": false,
1079
+ "normalized": false,
1080
+ "rstrip": false,
1081
+ "single_word": false,
1082
+ "special": true
1083
+ },
1084
+ "49270": {
1085
+ "content": "<|reserved_special_token_79|>",
1086
+ "lstrip": false,
1087
+ "normalized": false,
1088
+ "rstrip": false,
1089
+ "single_word": false,
1090
+ "special": true
1091
+ },
1092
+ "49271": {
1093
+ "content": "<|reserved_special_token_80|>",
1094
+ "lstrip": false,
1095
+ "normalized": false,
1096
+ "rstrip": false,
1097
+ "single_word": false,
1098
+ "special": true
1099
+ },
1100
+ "49272": {
1101
+ "content": "<|reserved_special_token_81|>",
1102
+ "lstrip": false,
1103
+ "normalized": false,
1104
+ "rstrip": false,
1105
+ "single_word": false,
1106
+ "special": true
1107
+ },
1108
+ "49273": {
1109
+ "content": "<|reserved_special_token_82|>",
1110
+ "lstrip": false,
1111
+ "normalized": false,
1112
+ "rstrip": false,
1113
+ "single_word": false,
1114
+ "special": true
1115
+ },
1116
+ "49274": {
1117
+ "content": "<|reserved_special_token_83|>",
1118
+ "lstrip": false,
1119
+ "normalized": false,
1120
+ "rstrip": false,
1121
+ "single_word": false,
1122
+ "special": true
1123
+ },
1124
+ "49275": {
1125
+ "content": "<|reserved_special_token_84|>",
1126
+ "lstrip": false,
1127
+ "normalized": false,
1128
+ "rstrip": false,
1129
+ "single_word": false,
1130
+ "special": true
1131
+ },
1132
+ "49276": {
1133
+ "content": "<|reserved_special_token_85|>",
1134
+ "lstrip": false,
1135
+ "normalized": false,
1136
+ "rstrip": false,
1137
+ "single_word": false,
1138
+ "special": true
1139
+ },
1140
+ "49277": {
1141
+ "content": "<|reserved_special_token_86|>",
1142
+ "lstrip": false,
1143
+ "normalized": false,
1144
+ "rstrip": false,
1145
+ "single_word": false,
1146
+ "special": true
1147
+ },
1148
+ "49278": {
1149
+ "content": "<|reserved_special_token_87|>",
1150
+ "lstrip": false,
1151
+ "normalized": false,
1152
+ "rstrip": false,
1153
+ "single_word": false,
1154
+ "special": true
1155
+ },
1156
+ "49279": {
1157
+ "content": "<end_of_utterance>",
1158
+ "lstrip": false,
1159
+ "normalized": false,
1160
+ "rstrip": false,
1161
+ "single_word": false,
1162
+ "special": true
1163
+ }
1164
+ },
1165
+ "additional_special_tokens": [
1166
+ "<fake_token_around_image>",
1167
+ "<image>",
1168
+ "<end_of_utterance>"
1169
+ ],
1170
+ "bos_token": "<|im_start|>",
1171
+ "clean_up_tokenization_spaces": false,
1172
+ "end_of_utterance_token": "<end_of_utterance>",
1173
+ "eos_token": "<end_of_utterance>",
1174
+ "extra_special_tokens": {
1175
+ "end_of_utterance_token": "<end_of_utterance>",
1176
+ "fake_image_token": "<fake_token_around_image>",
1177
+ "global_image_token": "<global-img>",
1178
+ "image_token": "<image>"
1179
+ },
1180
+ "fake_image_token": "<fake_token_around_image>",
1181
+ "global_image_token": "<global-img>",
1182
+ "image_token": "<image>",
1183
+ "legacy": false,
1184
+ "model_max_length": 16384,
1185
+ "pad_token": "<|im_end|>",
1186
+ "processor_class": "SmolVLMProcessor",
1187
+ "tokenizer_class": "GPT2Tokenizer",
1188
+ "truncation_side": "left",
1189
+ "unk_token": "<|endoftext|>",
1190
+ "vocab_size": 49152
1191
+ }
video_preprocessor_config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": null,
3
+ "data_format": "channels_first",
4
+ "default_to_square": true,
5
+ "device": null,
6
+ "do_center_crop": null,
7
+ "do_convert_rgb": true,
8
+ "do_image_splitting": true,
9
+ "do_normalize": true,
10
+ "do_pad": true,
11
+ "do_rescale": true,
12
+ "do_resize": true,
13
+ "do_sample_frames": false,
14
+ "fps": 1,
15
+ "image_mean": [
16
+ 0.5,
17
+ 0.5,
18
+ 0.5
19
+ ],
20
+ "image_processor_type": "SmolVLMImageProcessor",
21
+ "image_std": [
22
+ 0.5,
23
+ 0.5,
24
+ 0.5
25
+ ],
26
+ "input_data_format": null,
27
+ "max_image_size": {
28
+ "longest_edge": 384
29
+ },
30
+ "num_frames": 64,
31
+ "processor_class": "SmolVLMProcessor",
32
+ "resample": 1,
33
+ "rescale_factor": 0.00392156862745098,
34
+ "size": {
35
+ "longest_edge": 1536
36
+ },
37
+ "size_divisor": null,
38
+ "video_metadata": null,
39
+ "video_processor_type": "SmolVLMVideoProcessor",
40
+ "video_sampling": {
41
+ "fps": 1,
42
+ "max_frames": 64,
43
+ "video_size": {
44
+ "longest_edge": 1536
45
+ }
46
+ }
47
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff