Hugging Face's logo

mlx-community
/
LightOnOCR-2-1B-bf16

Image-Text-to-Text
Transformers
Safetensors
MLX
mistral3
text-generation
ocr
document-understanding
vision-language
pdf
tables
forms
conversational
Model card Files
xet
Community
aipib commited on
Commit
d34f677
·
verified ·
1 Parent(s): 4827952

Upload folder using huggingface_hub

Browse files
Files changed (12) hide show
  1. .gitattributes +1 -0
  2. README.md +38 -0
  3. added_tokens.json +28 -0
  4. chat_template.jinja +26 -0
  5. config.json +97 -0
  6. generation_config.json +13 -0
  7. model.safetensors +3 -0
  8. model.safetensors.index.json +539 -0
  9. processor_config.json +33 -0
  10. special_tokens_map.json +31 -0
  11. tokenizer.json +3 -0
  12. tokenizer_config.json +38 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ pipeline_tag: image-text-to-text
4
+ language:
5
+ - en
6
+ - fr
7
+ - de
8
+ - es
9
+ - it
10
+ - nl
11
+ - pt
12
+ - sv
13
+ - da
14
+ - zh
15
+ - ja
16
+ library_name: transformers
17
+ tags:
18
+ - ocr
19
+ - document-understanding
20
+ - vision-language
21
+ - pdf
22
+ - tables
23
+ - forms
24
+ - mlx
25
+ ---
26
+
27
+ # mlx-community/LightOnOCR-2-1B-bf16
28
+ This model was converted to MLX format from [`lightonai/LightOnOCR-2-1B`]() using mlx-vlm version **0.3.9**.
29
+ Refer to the [original model card](https://huggingface.co/lightonai/LightOnOCR-2-1B) 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 mlx-community/LightOnOCR-2-1B-bf16 --max-tokens 100 --temperature 0.0 --prompt "Describe this image." --image <path_to_image>
38
+ ```
added_tokens.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</think>": 151668,
3
+ "</tool_call>": 151658,
4
+ "</tool_response>": 151666,
5
+ "<think>": 151667,
6
+ "<tool_call>": 151657,
7
+ "<tool_response>": 151665,
8
+ "<|box_end|>": 151649,
9
+ "<|box_start|>": 151648,
10
+ "<|endoftext|>": 151643,
11
+ "<|file_sep|>": 151664,
12
+ "<|fim_middle|>": 151660,
13
+ "<|fim_pad|>": 151662,
14
+ "<|fim_prefix|>": 151659,
15
+ "<|fim_suffix|>": 151661,
16
+ "<|im_end|>": 151645,
17
+ "<|im_start|>": 151644,
18
+ "<|image_pad|>": 151655,
19
+ "<|object_ref_end|>": 151647,
20
+ "<|object_ref_start|>": 151646,
21
+ "<|quad_end|>": 151651,
22
+ "<|quad_start|>": 151650,
23
+ "<|repo_name|>": 151663,
24
+ "<|video_pad|>": 151656,
25
+ "<|vision_end|>": 151653,
26
+ "<|vision_pad|>": 151654,
27
+ "<|vision_start|>": 151652
28
+ }
chat_template.jinja ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {% set image_count = namespace(value=0) %}
2
+ {% for message in messages %}
3
+ {% if loop.first and message['role'] != 'system' %}
4
+ <|im_start|>system<|im_end|>
5
+ {% endif %}
6
+ <|im_start|>{{ message['role'] }}
7
+ {% if message['content'] is string %}
8
+ {{ message['content'] }}<|im_end|>
9
+ {% else %}
10
+ {% for content in message['content'] %}
11
+ {% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}
12
+ {% set image_count.value = image_count.value + 1 %}
13
+ {% if add_vision_id %}
14
+ Picture {{ image_count.value }}:
15
+ {% endif -%}
16
+ <|image_pad|>
17
+ {%- elif 'text' in content %}
18
+ {{ content['text'] }}
19
+ {% endif %}
20
+ {% endfor %}
21
+ <|im_end|>
22
+ {% endif %}
23
+ {% endfor %}
24
+ {% if add_generation_prompt %}
25
+ <|im_start|>assistant
26
+ {% endif %}
config.json ADDED
@@ -0,0 +1,97 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LightOnOCRForConditionalGeneration"
4
+ ],
5
+ "dtype": "bfloat16",
6
+ "eos_token_id": 151645,
7
+ "image_token_id": 151655,
8
+ "model_type": "mistral3",
9
+ "multimodal_projector_bias": false,
10
+ "pad_token_id": 151643,
11
+ "projector_hidden_act": "gelu",
12
+ "spatial_merge_size": 2,
13
+ "text_config": {
14
+ "architectures": [
15
+ "Qwen3ForCausalLM"
16
+ ],
17
+ "attention_bias": false,
18
+ "attention_dropout": 0,
19
+ "dtype": "bfloat16",
20
+ "head_dim": 128,
21
+ "hidden_act": "silu",
22
+ "hidden_size": 1024,
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 3072,
25
+ "layer_types": [
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention",
43
+ "full_attention",
44
+ "full_attention",
45
+ "full_attention",
46
+ "full_attention",
47
+ "full_attention",
48
+ "full_attention",
49
+ "full_attention",
50
+ "full_attention",
51
+ "full_attention",
52
+ "full_attention",
53
+ "full_attention"
54
+ ],
55
+ "max_position_embeddings": 16384,
56
+ "max_window_layers": 28,
57
+ "model_type": "qwen3",
58
+ "num_attention_heads": 16,
59
+ "num_hidden_layers": 28,
60
+ "num_key_value_heads": 8,
61
+ "rms_norm_eps": 1e-06,
62
+ "rope_parameters": {
63
+ "rope_theta": 1000000,
64
+ "rope_type": "default"
65
+ },
66
+ "rope_theta": 1000000,
67
+ "sliding_window": null,
68
+ "use_cache": true,
69
+ "use_sliding_window": false,
70
+ "tie_word_embeddings": true,
71
+ "vocab_size": 151936,
72
+ "use_qk_norm": true
73
+ },
74
+ "transformers_version": "5.0.0.dev0",
75
+ "use_cache": false,
76
+ "vision_config": {
77
+ "attention_dropout": 0,
78
+ "dtype": "bfloat16",
79
+ "head_dim": 64,
80
+ "hidden_act": "silu",
81
+ "hidden_size": 1024,
82
+ "image_size": 1540,
83
+ "initializer_range": 0.02,
84
+ "intermediate_size": 4096,
85
+ "model_type": "pixtral",
86
+ "num_attention_heads": 16,
87
+ "num_channels": 3,
88
+ "num_hidden_layers": 24,
89
+ "patch_size": 14,
90
+ "rope_parameters": {
91
+ "rope_theta": 10000,
92
+ "rope_type": "default"
93
+ },
94
+ "rope_theta": 10000
95
+ },
96
+ "vision_feature_layer": -1
97
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "temperature": 0.2,
10
+ "top_k": 0,
11
+ "top_p": 0.9,
12
+ "transformers_version": "5.0.0.dev0"
13
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:408b75617f0bfc4231518561b32c7053b72e259ecd97c4c45d6bd68f3a371814
3
+ size 2011368288
model.safetensors.index.json ADDED
@@ -0,0 +1,539 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 2011295744
4
+ },
5
+ "weight_map": {
6
+ "language_model.model.embed_tokens.weight": "model.safetensors",
7
+ "language_model.model.layers.0.input_layernorm.weight": "model.safetensors",
8
+ "language_model.model.layers.0.mlp.down_proj.weight": "model.safetensors",
9
+ "language_model.model.layers.0.mlp.gate_proj.weight": "model.safetensors",
10
+ "language_model.model.layers.0.mlp.up_proj.weight": "model.safetensors",
11
+ "language_model.model.layers.0.post_attention_layernorm.weight": "model.safetensors",
12
+ "language_model.model.layers.0.self_attn.k_norm.weight": "model.safetensors",
13
+ "language_model.model.layers.0.self_attn.k_proj.weight": "model.safetensors",
14
+ "language_model.model.layers.0.self_attn.o_proj.weight": "model.safetensors",
15
+ "language_model.model.layers.0.self_attn.q_norm.weight": "model.safetensors",
16
+ "language_model.model.layers.0.self_attn.q_proj.weight": "model.safetensors",
17
+ "language_model.model.layers.0.self_attn.v_proj.weight": "model.safetensors",
18
+ "language_model.model.layers.1.input_layernorm.weight": "model.safetensors",
19
+ "language_model.model.layers.1.mlp.down_proj.weight": "model.safetensors",
20
+ "language_model.model.layers.1.mlp.gate_proj.weight": "model.safetensors",
21
+ "language_model.model.layers.1.mlp.up_proj.weight": "model.safetensors",
22
+ "language_model.model.layers.1.post_attention_layernorm.weight": "model.safetensors",
23
+ "language_model.model.layers.1.self_attn.k_norm.weight": "model.safetensors",
24
+ "language_model.model.layers.1.self_attn.k_proj.weight": "model.safetensors",
25
+ "language_model.model.layers.1.self_attn.o_proj.weight": "model.safetensors",
26
+ "language_model.model.layers.1.self_attn.q_norm.weight": "model.safetensors",
27
+ "language_model.model.layers.1.self_attn.q_proj.weight": "model.safetensors",
28
+ "language_model.model.layers.1.self_attn.v_proj.weight": "model.safetensors",
29
+ "language_model.model.layers.10.input_layernorm.weight": "model.safetensors",
30
+ "language_model.model.layers.10.mlp.down_proj.weight": "model.safetensors",
31
+ "language_model.model.layers.10.mlp.gate_proj.weight": "model.safetensors",
32
+ "language_model.model.layers.10.mlp.up_proj.weight": "model.safetensors",
33
+ "language_model.model.layers.10.post_attention_layernorm.weight": "model.safetensors",
34
+ "language_model.model.layers.10.self_attn.k_norm.weight": "model.safetensors",
35
+ "language_model.model.layers.10.self_attn.k_proj.weight": "model.safetensors",
36
+ "language_model.model.layers.10.self_attn.o_proj.weight": "model.safetensors",
37
+ "language_model.model.layers.10.self_attn.q_norm.weight": "model.safetensors",
38
+ "language_model.model.layers.10.self_attn.q_proj.weight": "model.safetensors",
39
+ "language_model.model.layers.10.self_attn.v_proj.weight": "model.safetensors",
40
+ "language_model.model.layers.11.input_layernorm.weight": "model.safetensors",
41
+ "language_model.model.layers.11.mlp.down_proj.weight": "model.safetensors",
42
+ "language_model.model.layers.11.mlp.gate_proj.weight": "model.safetensors",
43
+ "language_model.model.layers.11.mlp.up_proj.weight": "model.safetensors",
44
+ "language_model.model.layers.11.post_attention_layernorm.weight": "model.safetensors",
45
+ "language_model.model.layers.11.self_attn.k_norm.weight": "model.safetensors",
46
+ "language_model.model.layers.11.self_attn.k_proj.weight": "model.safetensors",
47
+ "language_model.model.layers.11.self_attn.o_proj.weight": "model.safetensors",
48
+ "language_model.model.layers.11.self_attn.q_norm.weight": "model.safetensors",
49
+ "language_model.model.layers.11.self_attn.q_proj.weight": "model.safetensors",
50
+ "language_model.model.layers.11.self_attn.v_proj.weight": "model.safetensors",
51
+ "language_model.model.layers.12.input_layernorm.weight": "model.safetensors",
52
+ "language_model.model.layers.12.mlp.down_proj.weight": "model.safetensors",
53
+ "language_model.model.layers.12.mlp.gate_proj.weight": "model.safetensors",
54
+ "language_model.model.layers.12.mlp.up_proj.weight": "model.safetensors",
55
+ "language_model.model.layers.12.post_attention_layernorm.weight": "model.safetensors",
56
+ "language_model.model.layers.12.self_attn.k_norm.weight": "model.safetensors",
57
+ "language_model.model.layers.12.self_attn.k_proj.weight": "model.safetensors",
58
+ "language_model.model.layers.12.self_attn.o_proj.weight": "model.safetensors",
59
+ "language_model.model.layers.12.self_attn.q_norm.weight": "model.safetensors",
60
+ "language_model.model.layers.12.self_attn.q_proj.weight": "model.safetensors",
61
+ "language_model.model.layers.12.self_attn.v_proj.weight": "model.safetensors",
62
+ "language_model.model.layers.13.input_layernorm.weight": "model.safetensors",
63
+ "language_model.model.layers.13.mlp.down_proj.weight": "model.safetensors",
64
+ "language_model.model.layers.13.mlp.gate_proj.weight": "model.safetensors",
65
+ "language_model.model.layers.13.mlp.up_proj.weight": "model.safetensors",
66
+ "language_model.model.layers.13.post_attention_layernorm.weight": "model.safetensors",
67
+ "language_model.model.layers.13.self_attn.k_norm.weight": "model.safetensors",
68
+ "language_model.model.layers.13.self_attn.k_proj.weight": "model.safetensors",
69
+ "language_model.model.layers.13.self_attn.o_proj.weight": "model.safetensors",
70
+ "language_model.model.layers.13.self_attn.q_norm.weight": "model.safetensors",
71
+ "language_model.model.layers.13.self_attn.q_proj.weight": "model.safetensors",
72
+ "language_model.model.layers.13.self_attn.v_proj.weight": "model.safetensors",
73
+ "language_model.model.layers.14.input_layernorm.weight": "model.safetensors",
74
+ "language_model.model.layers.14.mlp.down_proj.weight": "model.safetensors",
75
+ "language_model.model.layers.14.mlp.gate_proj.weight": "model.safetensors",
76
+ "language_model.model.layers.14.mlp.up_proj.weight": "model.safetensors",
77
+ "language_model.model.layers.14.post_attention_layernorm.weight": "model.safetensors",
78
+ "language_model.model.layers.14.self_attn.k_norm.weight": "model.safetensors",
79
+ "language_model.model.layers.14.self_attn.k_proj.weight": "model.safetensors",
80
+ "language_model.model.layers.14.self_attn.o_proj.weight": "model.safetensors",
81
+ "language_model.model.layers.14.self_attn.q_norm.weight": "model.safetensors",
82
+ "language_model.model.layers.14.self_attn.q_proj.weight": "model.safetensors",
83
+ "language_model.model.layers.14.self_attn.v_proj.weight": "model.safetensors",
84
+ "language_model.model.layers.15.input_layernorm.weight": "model.safetensors",
85
+ "language_model.model.layers.15.mlp.down_proj.weight": "model.safetensors",
86
+ "language_model.model.layers.15.mlp.gate_proj.weight": "model.safetensors",
87
+ "language_model.model.layers.15.mlp.up_proj.weight": "model.safetensors",
88
+ "language_model.model.layers.15.post_attention_layernorm.weight": "model.safetensors",
89
+ "language_model.model.layers.15.self_attn.k_norm.weight": "model.safetensors",
90
+ "language_model.model.layers.15.self_attn.k_proj.weight": "model.safetensors",
91
+ "language_model.model.layers.15.self_attn.o_proj.weight": "model.safetensors",
92
+ "language_model.model.layers.15.self_attn.q_norm.weight": "model.safetensors",
93
+ "language_model.model.layers.15.self_attn.q_proj.weight": "model.safetensors",
94
+ "language_model.model.layers.15.self_attn.v_proj.weight": "model.safetensors",
95
+ "language_model.model.layers.16.input_layernorm.weight": "model.safetensors",
96
+ "language_model.model.layers.16.mlp.down_proj.weight": "model.safetensors",
97
+ "language_model.model.layers.16.mlp.gate_proj.weight": "model.safetensors",
98
+ "language_model.model.layers.16.mlp.up_proj.weight": "model.safetensors",
99
+ "language_model.model.layers.16.post_attention_layernorm.weight": "model.safetensors",
100
+ "language_model.model.layers.16.self_attn.k_norm.weight": "model.safetensors",
101
+ "language_model.model.layers.16.self_attn.k_proj.weight": "model.safetensors",
102
+ "language_model.model.layers.16.self_attn.o_proj.weight": "model.safetensors",
103
+ "language_model.model.layers.16.self_attn.q_norm.weight": "model.safetensors",
104
+ "language_model.model.layers.16.self_attn.q_proj.weight": "model.safetensors",
105
+ "language_model.model.layers.16.self_attn.v_proj.weight": "model.safetensors",
106
+ "language_model.model.layers.17.input_layernorm.weight": "model.safetensors",
107
+ "language_model.model.layers.17.mlp.down_proj.weight": "model.safetensors",
108
+ "language_model.model.layers.17.mlp.gate_proj.weight": "model.safetensors",
109
+ "language_model.model.layers.17.mlp.up_proj.weight": "model.safetensors",
110
+ "language_model.model.layers.17.post_attention_layernorm.weight": "model.safetensors",
111
+ "language_model.model.layers.17.self_attn.k_norm.weight": "model.safetensors",
112
+ "language_model.model.layers.17.self_attn.k_proj.weight": "model.safetensors",
113
+ "language_model.model.layers.17.self_attn.o_proj.weight": "model.safetensors",
114
+ "language_model.model.layers.17.self_attn.q_norm.weight": "model.safetensors",
115
+ "language_model.model.layers.17.self_attn.q_proj.weight": "model.safetensors",
116
+ "language_model.model.layers.17.self_attn.v_proj.weight": "model.safetensors",
117
+ "language_model.model.layers.18.input_layernorm.weight": "model.safetensors",
118
+ "language_model.model.layers.18.mlp.down_proj.weight": "model.safetensors",
119
+ "language_model.model.layers.18.mlp.gate_proj.weight": "model.safetensors",
120
+ "language_model.model.layers.18.mlp.up_proj.weight": "model.safetensors",
121
+ "language_model.model.layers.18.post_attention_layernorm.weight": "model.safetensors",
122
+ "language_model.model.layers.18.self_attn.k_norm.weight": "model.safetensors",
123
+ "language_model.model.layers.18.self_attn.k_proj.weight": "model.safetensors",
124
+ "language_model.model.layers.18.self_attn.o_proj.weight": "model.safetensors",
125
+ "language_model.model.layers.18.self_attn.q_norm.weight": "model.safetensors",
126
+ "language_model.model.layers.18.self_attn.q_proj.weight": "model.safetensors",
127
+ "language_model.model.layers.18.self_attn.v_proj.weight": "model.safetensors",
128
+ "language_model.model.layers.19.input_layernorm.weight": "model.safetensors",
129
+ "language_model.model.layers.19.mlp.down_proj.weight": "model.safetensors",
130
+ "language_model.model.layers.19.mlp.gate_proj.weight": "model.safetensors",
131
+ "language_model.model.layers.19.mlp.up_proj.weight": "model.safetensors",
132
+ "language_model.model.layers.19.post_attention_layernorm.weight": "model.safetensors",
133
+ "language_model.model.layers.19.self_attn.k_norm.weight": "model.safetensors",
134
+ "language_model.model.layers.19.self_attn.k_proj.weight": "model.safetensors",
135
+ "language_model.model.layers.19.self_attn.o_proj.weight": "model.safetensors",
136
+ "language_model.model.layers.19.self_attn.q_norm.weight": "model.safetensors",
137
+ "language_model.model.layers.19.self_attn.q_proj.weight": "model.safetensors",
138
+ "language_model.model.layers.19.self_attn.v_proj.weight": "model.safetensors",
139
+ "language_model.model.layers.2.input_layernorm.weight": "model.safetensors",
140
+ "language_model.model.layers.2.mlp.down_proj.weight": "model.safetensors",
141
+ "language_model.model.layers.2.mlp.gate_proj.weight": "model.safetensors",
142
+ "language_model.model.layers.2.mlp.up_proj.weight": "model.safetensors",
143
+ "language_model.model.layers.2.post_attention_layernorm.weight": "model.safetensors",
144
+ "language_model.model.layers.2.self_attn.k_norm.weight": "model.safetensors",
145
+ "language_model.model.layers.2.self_attn.k_proj.weight": "model.safetensors",
146
+ "language_model.model.layers.2.self_attn.o_proj.weight": "model.safetensors",
147
+ "language_model.model.layers.2.self_attn.q_norm.weight": "model.safetensors",
148
+ "language_model.model.layers.2.self_attn.q_proj.weight": "model.safetensors",
149
+ "language_model.model.layers.2.self_attn.v_proj.weight": "model.safetensors",
150
+ "language_model.model.layers.20.input_layernorm.weight": "model.safetensors",
151
+ "language_model.model.layers.20.mlp.down_proj.weight": "model.safetensors",
152
+ "language_model.model.layers.20.mlp.gate_proj.weight": "model.safetensors",
153
+ "language_model.model.layers.20.mlp.up_proj.weight": "model.safetensors",
154
+ "language_model.model.layers.20.post_attention_layernorm.weight": "model.safetensors",
155
+ "language_model.model.layers.20.self_attn.k_norm.weight": "model.safetensors",
156
+ "language_model.model.layers.20.self_attn.k_proj.weight": "model.safetensors",
157
+ "language_model.model.layers.20.self_attn.o_proj.weight": "model.safetensors",
158
+ "language_model.model.layers.20.self_attn.q_norm.weight": "model.safetensors",
159
+ "language_model.model.layers.20.self_attn.q_proj.weight": "model.safetensors",
160
+ "language_model.model.layers.20.self_attn.v_proj.weight": "model.safetensors",
161
+ "language_model.model.layers.21.input_layernorm.weight": "model.safetensors",
162
+ "language_model.model.layers.21.mlp.down_proj.weight": "model.safetensors",
163
+ "language_model.model.layers.21.mlp.gate_proj.weight": "model.safetensors",
164
+ "language_model.model.layers.21.mlp.up_proj.weight": "model.safetensors",
165
+ "language_model.model.layers.21.post_attention_layernorm.weight": "model.safetensors",
166
+ "language_model.model.layers.21.self_attn.k_norm.weight": "model.safetensors",
167
+ "language_model.model.layers.21.self_attn.k_proj.weight": "model.safetensors",
168
+ "language_model.model.layers.21.self_attn.o_proj.weight": "model.safetensors",
169
+ "language_model.model.layers.21.self_attn.q_norm.weight": "model.safetensors",
170
+ "language_model.model.layers.21.self_attn.q_proj.weight": "model.safetensors",
171
+ "language_model.model.layers.21.self_attn.v_proj.weight": "model.safetensors",
172
+ "language_model.model.layers.22.input_layernorm.weight": "model.safetensors",
173
+ "language_model.model.layers.22.mlp.down_proj.weight": "model.safetensors",
174
+ "language_model.model.layers.22.mlp.gate_proj.weight": "model.safetensors",
175
+ "language_model.model.layers.22.mlp.up_proj.weight": "model.safetensors",
176
+ "language_model.model.layers.22.post_attention_layernorm.weight": "model.safetensors",
177
+ "language_model.model.layers.22.self_attn.k_norm.weight": "model.safetensors",
178
+ "language_model.model.layers.22.self_attn.k_proj.weight": "model.safetensors",
179
+ "language_model.model.layers.22.self_attn.o_proj.weight": "model.safetensors",
180
+ "language_model.model.layers.22.self_attn.q_norm.weight": "model.safetensors",
181
+ "language_model.model.layers.22.self_attn.q_proj.weight": "model.safetensors",
182
+ "language_model.model.layers.22.self_attn.v_proj.weight": "model.safetensors",
183
+ "language_model.model.layers.23.input_layernorm.weight": "model.safetensors",
184
+ "language_model.model.layers.23.mlp.down_proj.weight": "model.safetensors",
185
+ "language_model.model.layers.23.mlp.gate_proj.weight": "model.safetensors",
186
+ "language_model.model.layers.23.mlp.up_proj.weight": "model.safetensors",
187
+ "language_model.model.layers.23.post_attention_layernorm.weight": "model.safetensors",
188
+ "language_model.model.layers.23.self_attn.k_norm.weight": "model.safetensors",
189
+ "language_model.model.layers.23.self_attn.k_proj.weight": "model.safetensors",
190
+ "language_model.model.layers.23.self_attn.o_proj.weight": "model.safetensors",
191
+ "language_model.model.layers.23.self_attn.q_norm.weight": "model.safetensors",
192
+ "language_model.model.layers.23.self_attn.q_proj.weight": "model.safetensors",
193
+ "language_model.model.layers.23.self_attn.v_proj.weight": "model.safetensors",
194
+ "language_model.model.layers.24.input_layernorm.weight": "model.safetensors",
195
+ "language_model.model.layers.24.mlp.down_proj.weight": "model.safetensors",
196
+ "language_model.model.layers.24.mlp.gate_proj.weight": "model.safetensors",
197
+ "language_model.model.layers.24.mlp.up_proj.weight": "model.safetensors",
198
+ "language_model.model.layers.24.post_attention_layernorm.weight": "model.safetensors",
199
+ "language_model.model.layers.24.self_attn.k_norm.weight": "model.safetensors",
200
+ "language_model.model.layers.24.self_attn.k_proj.weight": "model.safetensors",
201
+ "language_model.model.layers.24.self_attn.o_proj.weight": "model.safetensors",
202
+ "language_model.model.layers.24.self_attn.q_norm.weight": "model.safetensors",
203
+ "language_model.model.layers.24.self_attn.q_proj.weight": "model.safetensors",
204
+ "language_model.model.layers.24.self_attn.v_proj.weight": "model.safetensors",
205
+ "language_model.model.layers.25.input_layernorm.weight": "model.safetensors",
206
+ "language_model.model.layers.25.mlp.down_proj.weight": "model.safetensors",
207
+ "language_model.model.layers.25.mlp.gate_proj.weight": "model.safetensors",
208
+ "language_model.model.layers.25.mlp.up_proj.weight": "model.safetensors",
209
+ "language_model.model.layers.25.post_attention_layernorm.weight": "model.safetensors",
210
+ "language_model.model.layers.25.self_attn.k_norm.weight": "model.safetensors",
211
+ "language_model.model.layers.25.self_attn.k_proj.weight": "model.safetensors",
212
+ "language_model.model.layers.25.self_attn.o_proj.weight": "model.safetensors",
213
+ "language_model.model.layers.25.self_attn.q_norm.weight": "model.safetensors",
214
+ "language_model.model.layers.25.self_attn.q_proj.weight": "model.safetensors",
215
+ "language_model.model.layers.25.self_attn.v_proj.weight": "model.safetensors",
216
+ "language_model.model.layers.26.input_layernorm.weight": "model.safetensors",
217
+ "language_model.model.layers.26.mlp.down_proj.weight": "model.safetensors",
218
+ "language_model.model.layers.26.mlp.gate_proj.weight": "model.safetensors",
219
+ "language_model.model.layers.26.mlp.up_proj.weight": "model.safetensors",
220
+ "language_model.model.layers.26.post_attention_layernorm.weight": "model.safetensors",
221
+ "language_model.model.layers.26.self_attn.k_norm.weight": "model.safetensors",
222
+ "language_model.model.layers.26.self_attn.k_proj.weight": "model.safetensors",
223
+ "language_model.model.layers.26.self_attn.o_proj.weight": "model.safetensors",
224
+ "language_model.model.layers.26.self_attn.q_norm.weight": "model.safetensors",
225
+ "language_model.model.layers.26.self_attn.q_proj.weight": "model.safetensors",
226
+ "language_model.model.layers.26.self_attn.v_proj.weight": "model.safetensors",
227
+ "language_model.model.layers.27.input_layernorm.weight": "model.safetensors",
228
+ "language_model.model.layers.27.mlp.down_proj.weight": "model.safetensors",
229
+ "language_model.model.layers.27.mlp.gate_proj.weight": "model.safetensors",
230
+ "language_model.model.layers.27.mlp.up_proj.weight": "model.safetensors",
231
+ "language_model.model.layers.27.post_attention_layernorm.weight": "model.safetensors",
232
+ "language_model.model.layers.27.self_attn.k_norm.weight": "model.safetensors",
233
+ "language_model.model.layers.27.self_attn.k_proj.weight": "model.safetensors",
234
+ "language_model.model.layers.27.self_attn.o_proj.weight": "model.safetensors",
235
+ "language_model.model.layers.27.self_attn.q_norm.weight": "model.safetensors",
236
+ "language_model.model.layers.27.self_attn.q_proj.weight": "model.safetensors",
237
+ "language_model.model.layers.27.self_attn.v_proj.weight": "model.safetensors",
238
+ "language_model.model.layers.3.input_layernorm.weight": "model.safetensors",
239
+ "language_model.model.layers.3.mlp.down_proj.weight": "model.safetensors",
240
+ "language_model.model.layers.3.mlp.gate_proj.weight": "model.safetensors",
241
+ "language_model.model.layers.3.mlp.up_proj.weight": "model.safetensors",
242
+ "language_model.model.layers.3.post_attention_layernorm.weight": "model.safetensors",
243
+ "language_model.model.layers.3.self_attn.k_norm.weight": "model.safetensors",
244
+ "language_model.model.layers.3.self_attn.k_proj.weight": "model.safetensors",
245
+ "language_model.model.layers.3.self_attn.o_proj.weight": "model.safetensors",
246
+ "language_model.model.layers.3.self_attn.q_norm.weight": "model.safetensors",
247
+ "language_model.model.layers.3.self_attn.q_proj.weight": "model.safetensors",
248
+ "language_model.model.layers.3.self_attn.v_proj.weight": "model.safetensors",
249
+ "language_model.model.layers.4.input_layernorm.weight": "model.safetensors",
250
+ "language_model.model.layers.4.mlp.down_proj.weight": "model.safetensors",
251
+ "language_model.model.layers.4.mlp.gate_proj.weight": "model.safetensors",
252
+ "language_model.model.layers.4.mlp.up_proj.weight": "model.safetensors",
253
+ "language_model.model.layers.4.post_attention_layernorm.weight": "model.safetensors",
254
+ "language_model.model.layers.4.self_attn.k_norm.weight": "model.safetensors",
255
+ "language_model.model.layers.4.self_attn.k_proj.weight": "model.safetensors",
256
+ "language_model.model.layers.4.self_attn.o_proj.weight": "model.safetensors",
257
+ "language_model.model.layers.4.self_attn.q_norm.weight": "model.safetensors",
258
+ "language_model.model.layers.4.self_attn.q_proj.weight": "model.safetensors",
259
+ "language_model.model.layers.4.self_attn.v_proj.weight": "model.safetensors",
260
+ "language_model.model.layers.5.input_layernorm.weight": "model.safetensors",
261
+ "language_model.model.layers.5.mlp.down_proj.weight": "model.safetensors",
262
+ "language_model.model.layers.5.mlp.gate_proj.weight": "model.safetensors",
263
+ "language_model.model.layers.5.mlp.up_proj.weight": "model.safetensors",
264
+ "language_model.model.layers.5.post_attention_layernorm.weight": "model.safetensors",
265
+ "language_model.model.layers.5.self_attn.k_norm.weight": "model.safetensors",
266
+ "language_model.model.layers.5.self_attn.k_proj.weight": "model.safetensors",
267
+ "language_model.model.layers.5.self_attn.o_proj.weight": "model.safetensors",
268
+ "language_model.model.layers.5.self_attn.q_norm.weight": "model.safetensors",
269
+ "language_model.model.layers.5.self_attn.q_proj.weight": "model.safetensors",
270
+ "language_model.model.layers.5.self_attn.v_proj.weight": "model.safetensors",
271
+ "language_model.model.layers.6.input_layernorm.weight": "model.safetensors",
272
+ "language_model.model.layers.6.mlp.down_proj.weight": "model.safetensors",
273
+ "language_model.model.layers.6.mlp.gate_proj.weight": "model.safetensors",
274
+ "language_model.model.layers.6.mlp.up_proj.weight": "model.safetensors",
275
+ "language_model.model.layers.6.post_attention_layernorm.weight": "model.safetensors",
276
+ "language_model.model.layers.6.self_attn.k_norm.weight": "model.safetensors",
277
+ "language_model.model.layers.6.self_attn.k_proj.weight": "model.safetensors",
278
+ "language_model.model.layers.6.self_attn.o_proj.weight": "model.safetensors",
279
+ "language_model.model.layers.6.self_attn.q_norm.weight": "model.safetensors",
280
+ "language_model.model.layers.6.self_attn.q_proj.weight": "model.safetensors",
281
+ "language_model.model.layers.6.self_attn.v_proj.weight": "model.safetensors",
282
+ "language_model.model.layers.7.input_layernorm.weight": "model.safetensors",
283
+ "language_model.model.layers.7.mlp.down_proj.weight": "model.safetensors",
284
+ "language_model.model.layers.7.mlp.gate_proj.weight": "model.safetensors",
285
+ "language_model.model.layers.7.mlp.up_proj.weight": "model.safetensors",
286
+ "language_model.model.layers.7.post_attention_layernorm.weight": "model.safetensors",
287
+ "language_model.model.layers.7.self_attn.k_norm.weight": "model.safetensors",
288
+ "language_model.model.layers.7.self_attn.k_proj.weight": "model.safetensors",
289
+ "language_model.model.layers.7.self_attn.o_proj.weight": "model.safetensors",
290
+ "language_model.model.layers.7.self_attn.q_norm.weight": "model.safetensors",
291
+ "language_model.model.layers.7.self_attn.q_proj.weight": "model.safetensors",
292
+ "language_model.model.layers.7.self_attn.v_proj.weight": "model.safetensors",
293
+ "language_model.model.layers.8.input_layernorm.weight": "model.safetensors",
294
+ "language_model.model.layers.8.mlp.down_proj.weight": "model.safetensors",
295
+ "language_model.model.layers.8.mlp.gate_proj.weight": "model.safetensors",
296
+ "language_model.model.layers.8.mlp.up_proj.weight": "model.safetensors",
297
+ "language_model.model.layers.8.post_attention_layernorm.weight": "model.safetensors",
298
+ "language_model.model.layers.8.self_attn.k_norm.weight": "model.safetensors",
299
+ "language_model.model.layers.8.self_attn.k_proj.weight": "model.safetensors",
300
+ "language_model.model.layers.8.self_attn.o_proj.weight": "model.safetensors",
301
+ "language_model.model.layers.8.self_attn.q_norm.weight": "model.safetensors",
302
+ "language_model.model.layers.8.self_attn.q_proj.weight": "model.safetensors",
303
+ "language_model.model.layers.8.self_attn.v_proj.weight": "model.safetensors",
304
+ "language_model.model.layers.9.input_layernorm.weight": "model.safetensors",
305
+ "language_model.model.layers.9.mlp.down_proj.weight": "model.safetensors",
306
+ "language_model.model.layers.9.mlp.gate_proj.weight": "model.safetensors",
307
+ "language_model.model.layers.9.mlp.up_proj.weight": "model.safetensors",
308
+ "language_model.model.layers.9.post_attention_layernorm.weight": "model.safetensors",
309
+ "language_model.model.layers.9.self_attn.k_norm.weight": "model.safetensors",
310
+ "language_model.model.layers.9.self_attn.k_proj.weight": "model.safetensors",
311
+ "language_model.model.layers.9.self_attn.o_proj.weight": "model.safetensors",
312
+ "language_model.model.layers.9.self_attn.q_norm.weight": "model.safetensors",
313
+ "language_model.model.layers.9.self_attn.q_proj.weight": "model.safetensors",
314
+ "language_model.model.layers.9.self_attn.v_proj.weight": "model.safetensors",
315
+ "language_model.model.norm.weight": "model.safetensors",
316
+ "multi_modal_projector.linear_1.weight": "model.safetensors",
317
+ "multi_modal_projector.linear_2.weight": "model.safetensors",
318
+ "multi_modal_projector.norm.weight": "model.safetensors",
319
+ "multi_modal_projector.patch_merger.merging_layer.weight": "model.safetensors",
320
+ "vision_tower.vision_model.ln_pre.weight": "model.safetensors",
321
+ "vision_tower.vision_model.patch_conv.weight": "model.safetensors",
322
+ "vision_tower.vision_model.transformer.layers.0.attention.k_proj.weight": "model.safetensors",
323
+ "vision_tower.vision_model.transformer.layers.0.attention.o_proj.weight": "model.safetensors",
324
+ "vision_tower.vision_model.transformer.layers.0.attention.q_proj.weight": "model.safetensors",
325
+ "vision_tower.vision_model.transformer.layers.0.attention.v_proj.weight": "model.safetensors",
326
+ "vision_tower.vision_model.transformer.layers.0.attention_norm.weight": "model.safetensors",
327
+ "vision_tower.vision_model.transformer.layers.0.feed_forward.down_proj.weight": "model.safetensors",
328
+ "vision_tower.vision_model.transformer.layers.0.feed_forward.gate_proj.weight": "model.safetensors",
329
+ "vision_tower.vision_model.transformer.layers.0.feed_forward.up_proj.weight": "model.safetensors",
330
+ "vision_tower.vision_model.transformer.layers.0.ffn_norm.weight": "model.safetensors",
331
+ "vision_tower.vision_model.transformer.layers.1.attention.k_proj.weight": "model.safetensors",
332
+ "vision_tower.vision_model.transformer.layers.1.attention.o_proj.weight": "model.safetensors",
333
+ "vision_tower.vision_model.transformer.layers.1.attention.q_proj.weight": "model.safetensors",
334
+ "vision_tower.vision_model.transformer.layers.1.attention.v_proj.weight": "model.safetensors",
335
+ "vision_tower.vision_model.transformer.layers.1.attention_norm.weight": "model.safetensors",
336
+ "vision_tower.vision_model.transformer.layers.1.feed_forward.down_proj.weight": "model.safetensors",
337
+ "vision_tower.vision_model.transformer.layers.1.feed_forward.gate_proj.weight": "model.safetensors",
338
+ "vision_tower.vision_model.transformer.layers.1.feed_forward.up_proj.weight": "model.safetensors",
339
+ "vision_tower.vision_model.transformer.layers.1.ffn_norm.weight": "model.safetensors",
340
+ "vision_tower.vision_model.transformer.layers.10.attention.k_proj.weight": "model.safetensors",
341
+ "vision_tower.vision_model.transformer.layers.10.attention.o_proj.weight": "model.safetensors",
342
+ "vision_tower.vision_model.transformer.layers.10.attention.q_proj.weight": "model.safetensors",
343
+ "vision_tower.vision_model.transformer.layers.10.attention.v_proj.weight": "model.safetensors",
344
+ "vision_tower.vision_model.transformer.layers.10.attention_norm.weight": "model.safetensors",
345
+ "vision_tower.vision_model.transformer.layers.10.feed_forward.down_proj.weight": "model.safetensors",
346
+ "vision_tower.vision_model.transformer.layers.10.feed_forward.gate_proj.weight": "model.safetensors",
347
+ "vision_tower.vision_model.transformer.layers.10.feed_forward.up_proj.weight": "model.safetensors",
348
+ "vision_tower.vision_model.transformer.layers.10.ffn_norm.weight": "model.safetensors",
349
+ "vision_tower.vision_model.transformer.layers.11.attention.k_proj.weight": "model.safetensors",
350
+ "vision_tower.vision_model.transformer.layers.11.attention.o_proj.weight": "model.safetensors",
351
+ "vision_tower.vision_model.transformer.layers.11.attention.q_proj.weight": "model.safetensors",
352
+ "vision_tower.vision_model.transformer.layers.11.attention.v_proj.weight": "model.safetensors",
353
+ "vision_tower.vision_model.transformer.layers.11.attention_norm.weight": "model.safetensors",
354
+ "vision_tower.vision_model.transformer.layers.11.feed_forward.down_proj.weight": "model.safetensors",
355
+ "vision_tower.vision_model.transformer.layers.11.feed_forward.gate_proj.weight": "model.safetensors",
356
+ "vision_tower.vision_model.transformer.layers.11.feed_forward.up_proj.weight": "model.safetensors",
357
+ "vision_tower.vision_model.transformer.layers.11.ffn_norm.weight": "model.safetensors",
358
+ "vision_tower.vision_model.transformer.layers.12.attention.k_proj.weight": "model.safetensors",
359
+ "vision_tower.vision_model.transformer.layers.12.attention.o_proj.weight": "model.safetensors",
360
+ "vision_tower.vision_model.transformer.layers.12.attention.q_proj.weight": "model.safetensors",
361
+ "vision_tower.vision_model.transformer.layers.12.attention.v_proj.weight": "model.safetensors",
362
+ "vision_tower.vision_model.transformer.layers.12.attention_norm.weight": "model.safetensors",
363
+ "vision_tower.vision_model.transformer.layers.12.feed_forward.down_proj.weight": "model.safetensors",
364
+ "vision_tower.vision_model.transformer.layers.12.feed_forward.gate_proj.weight": "model.safetensors",
365
+ "vision_tower.vision_model.transformer.layers.12.feed_forward.up_proj.weight": "model.safetensors",
366
+ "vision_tower.vision_model.transformer.layers.12.ffn_norm.weight": "model.safetensors",
367
+ "vision_tower.vision_model.transformer.layers.13.attention.k_proj.weight": "model.safetensors",
368
+ "vision_tower.vision_model.transformer.layers.13.attention.o_proj.weight": "model.safetensors",
369
+ "vision_tower.vision_model.transformer.layers.13.attention.q_proj.weight": "model.safetensors",
370
+ "vision_tower.vision_model.transformer.layers.13.attention.v_proj.weight": "model.safetensors",
371
+ "vision_tower.vision_model.transformer.layers.13.attention_norm.weight": "model.safetensors",
372
+ "vision_tower.vision_model.transformer.layers.13.feed_forward.down_proj.weight": "model.safetensors",
373
+ "vision_tower.vision_model.transformer.layers.13.feed_forward.gate_proj.weight": "model.safetensors",
374
+ "vision_tower.vision_model.transformer.layers.13.feed_forward.up_proj.weight": "model.safetensors",
375
+ "vision_tower.vision_model.transformer.layers.13.ffn_norm.weight": "model.safetensors",
376
+ "vision_tower.vision_model.transformer.layers.14.attention.k_proj.weight": "model.safetensors",
377
+ "vision_tower.vision_model.transformer.layers.14.attention.o_proj.weight": "model.safetensors",
378
+ "vision_tower.vision_model.transformer.layers.14.attention.q_proj.weight": "model.safetensors",
379
+ "vision_tower.vision_model.transformer.layers.14.attention.v_proj.weight": "model.safetensors",
380
+ "vision_tower.vision_model.transformer.layers.14.attention_norm.weight": "model.safetensors",
381
+ "vision_tower.vision_model.transformer.layers.14.feed_forward.down_proj.weight": "model.safetensors",
382
+ "vision_tower.vision_model.transformer.layers.14.feed_forward.gate_proj.weight": "model.safetensors",
383
+ "vision_tower.vision_model.transformer.layers.14.feed_forward.up_proj.weight": "model.safetensors",
384
+ "vision_tower.vision_model.transformer.layers.14.ffn_norm.weight": "model.safetensors",
385
+ "vision_tower.vision_model.transformer.layers.15.attention.k_proj.weight": "model.safetensors",
386
+ "vision_tower.vision_model.transformer.layers.15.attention.o_proj.weight": "model.safetensors",
387
+ "vision_tower.vision_model.transformer.layers.15.attention.q_proj.weight": "model.safetensors",
388
+ "vision_tower.vision_model.transformer.layers.15.attention.v_proj.weight": "model.safetensors",
389
+ "vision_tower.vision_model.transformer.layers.15.attention_norm.weight": "model.safetensors",
390
+ "vision_tower.vision_model.transformer.layers.15.feed_forward.down_proj.weight": "model.safetensors",
391
+ "vision_tower.vision_model.transformer.layers.15.feed_forward.gate_proj.weight": "model.safetensors",
392
+ "vision_tower.vision_model.transformer.layers.15.feed_forward.up_proj.weight": "model.safetensors",
393
+ "vision_tower.vision_model.transformer.layers.15.ffn_norm.weight": "model.safetensors",
394
+ "vision_tower.vision_model.transformer.layers.16.attention.k_proj.weight": "model.safetensors",
395
+ "vision_tower.vision_model.transformer.layers.16.attention.o_proj.weight": "model.safetensors",
396
+ "vision_tower.vision_model.transformer.layers.16.attention.q_proj.weight": "model.safetensors",
397
+ "vision_tower.vision_model.transformer.layers.16.attention.v_proj.weight": "model.safetensors",
398
+ "vision_tower.vision_model.transformer.layers.16.attention_norm.weight": "model.safetensors",
399
+ "vision_tower.vision_model.transformer.layers.16.feed_forward.down_proj.weight": "model.safetensors",
400
+ "vision_tower.vision_model.transformer.layers.16.feed_forward.gate_proj.weight": "model.safetensors",
401
+ "vision_tower.vision_model.transformer.layers.16.feed_forward.up_proj.weight": "model.safetensors",
402
+ "vision_tower.vision_model.transformer.layers.16.ffn_norm.weight": "model.safetensors",
403
+ "vision_tower.vision_model.transformer.layers.17.attention.k_proj.weight": "model.safetensors",
404
+ "vision_tower.vision_model.transformer.layers.17.attention.o_proj.weight": "model.safetensors",
405
+ "vision_tower.vision_model.transformer.layers.17.attention.q_proj.weight": "model.safetensors",
406
+ "vision_tower.vision_model.transformer.layers.17.attention.v_proj.weight": "model.safetensors",
407
+ "vision_tower.vision_model.transformer.layers.17.attention_norm.weight": "model.safetensors",
408
+ "vision_tower.vision_model.transformer.layers.17.feed_forward.down_proj.weight": "model.safetensors",
409
+ "vision_tower.vision_model.transformer.layers.17.feed_forward.gate_proj.weight": "model.safetensors",
410
+ "vision_tower.vision_model.transformer.layers.17.feed_forward.up_proj.weight": "model.safetensors",
411
+ "vision_tower.vision_model.transformer.layers.17.ffn_norm.weight": "model.safetensors",
412
+ "vision_tower.vision_model.transformer.layers.18.attention.k_proj.weight": "model.safetensors",
413
+ "vision_tower.vision_model.transformer.layers.18.attention.o_proj.weight": "model.safetensors",
414
+ "vision_tower.vision_model.transformer.layers.18.attention.q_proj.weight": "model.safetensors",
415
+ "vision_tower.vision_model.transformer.layers.18.attention.v_proj.weight": "model.safetensors",
416
+ "vision_tower.vision_model.transformer.layers.18.attention_norm.weight": "model.safetensors",
417
+ "vision_tower.vision_model.transformer.layers.18.feed_forward.down_proj.weight": "model.safetensors",
418
+ "vision_tower.vision_model.transformer.layers.18.feed_forward.gate_proj.weight": "model.safetensors",
419
+ "vision_tower.vision_model.transformer.layers.18.feed_forward.up_proj.weight": "model.safetensors",
420
+ "vision_tower.vision_model.transformer.layers.18.ffn_norm.weight": "model.safetensors",
421
+ "vision_tower.vision_model.transformer.layers.19.attention.k_proj.weight": "model.safetensors",
422
+ "vision_tower.vision_model.transformer.layers.19.attention.o_proj.weight": "model.safetensors",
423
+ "vision_tower.vision_model.transformer.layers.19.attention.q_proj.weight": "model.safetensors",
424
+ "vision_tower.vision_model.transformer.layers.19.attention.v_proj.weight": "model.safetensors",
425
+ "vision_tower.vision_model.transformer.layers.19.attention_norm.weight": "model.safetensors",
426
+ "vision_tower.vision_model.transformer.layers.19.feed_forward.down_proj.weight": "model.safetensors",
427
+ "vision_tower.vision_model.transformer.layers.19.feed_forward.gate_proj.weight": "model.safetensors",
428
+ "vision_tower.vision_model.transformer.layers.19.feed_forward.up_proj.weight": "model.safetensors",
429
+ "vision_tower.vision_model.transformer.layers.19.ffn_norm.weight": "model.safetensors",
430
+ "vision_tower.vision_model.transformer.layers.2.attention.k_proj.weight": "model.safetensors",
431
+ "vision_tower.vision_model.transformer.layers.2.attention.o_proj.weight": "model.safetensors",
432
+ "vision_tower.vision_model.transformer.layers.2.attention.q_proj.weight": "model.safetensors",
433
+ "vision_tower.vision_model.transformer.layers.2.attention.v_proj.weight": "model.safetensors",
434
+ "vision_tower.vision_model.transformer.layers.2.attention_norm.weight": "model.safetensors",
435
+ "vision_tower.vision_model.transformer.layers.2.feed_forward.down_proj.weight": "model.safetensors",
436
+ "vision_tower.vision_model.transformer.layers.2.feed_forward.gate_proj.weight": "model.safetensors",
437
+ "vision_tower.vision_model.transformer.layers.2.feed_forward.up_proj.weight": "model.safetensors",
438
+ "vision_tower.vision_model.transformer.layers.2.ffn_norm.weight": "model.safetensors",
439
+ "vision_tower.vision_model.transformer.layers.20.attention.k_proj.weight": "model.safetensors",
440
+ "vision_tower.vision_model.transformer.layers.20.attention.o_proj.weight": "model.safetensors",
441
+ "vision_tower.vision_model.transformer.layers.20.attention.q_proj.weight": "model.safetensors",
442
+ "vision_tower.vision_model.transformer.layers.20.attention.v_proj.weight": "model.safetensors",
443
+ "vision_tower.vision_model.transformer.layers.20.attention_norm.weight": "model.safetensors",
444
+ "vision_tower.vision_model.transformer.layers.20.feed_forward.down_proj.weight": "model.safetensors",
445
+ "vision_tower.vision_model.transformer.layers.20.feed_forward.gate_proj.weight": "model.safetensors",
446
+ "vision_tower.vision_model.transformer.layers.20.feed_forward.up_proj.weight": "model.safetensors",
447
+ "vision_tower.vision_model.transformer.layers.20.ffn_norm.weight": "model.safetensors",
448
+ "vision_tower.vision_model.transformer.layers.21.attention.k_proj.weight": "model.safetensors",
449
+ "vision_tower.vision_model.transformer.layers.21.attention.o_proj.weight": "model.safetensors",
450
+ "vision_tower.vision_model.transformer.layers.21.attention.q_proj.weight": "model.safetensors",
451
+ "vision_tower.vision_model.transformer.layers.21.attention.v_proj.weight": "model.safetensors",
452
+ "vision_tower.vision_model.transformer.layers.21.attention_norm.weight": "model.safetensors",
453
+ "vision_tower.vision_model.transformer.layers.21.feed_forward.down_proj.weight": "model.safetensors",
454
+ "vision_tower.vision_model.transformer.layers.21.feed_forward.gate_proj.weight": "model.safetensors",
455
+ "vision_tower.vision_model.transformer.layers.21.feed_forward.up_proj.weight": "model.safetensors",
456
+ "vision_tower.vision_model.transformer.layers.21.ffn_norm.weight": "model.safetensors",
457
+ "vision_tower.vision_model.transformer.layers.22.attention.k_proj.weight": "model.safetensors",
458
+ "vision_tower.vision_model.transformer.layers.22.attention.o_proj.weight": "model.safetensors",
459
+ "vision_tower.vision_model.transformer.layers.22.attention.q_proj.weight": "model.safetensors",
460
+ "vision_tower.vision_model.transformer.layers.22.attention.v_proj.weight": "model.safetensors",
461
+ "vision_tower.vision_model.transformer.layers.22.attention_norm.weight": "model.safetensors",
462
+ "vision_tower.vision_model.transformer.layers.22.feed_forward.down_proj.weight": "model.safetensors",
463
+ "vision_tower.vision_model.transformer.layers.22.feed_forward.gate_proj.weight": "model.safetensors",
464
+ "vision_tower.vision_model.transformer.layers.22.feed_forward.up_proj.weight": "model.safetensors",
465
+ "vision_tower.vision_model.transformer.layers.22.ffn_norm.weight": "model.safetensors",
466
+ "vision_tower.vision_model.transformer.layers.23.attention.k_proj.weight": "model.safetensors",
467
+ "vision_tower.vision_model.transformer.layers.23.attention.o_proj.weight": "model.safetensors",
468
+ "vision_tower.vision_model.transformer.layers.23.attention.q_proj.weight": "model.safetensors",
469
+ "vision_tower.vision_model.transformer.layers.23.attention.v_proj.weight": "model.safetensors",
470
+ "vision_tower.vision_model.transformer.layers.23.attention_norm.weight": "model.safetensors",
471
+ "vision_tower.vision_model.transformer.layers.23.feed_forward.down_proj.weight": "model.safetensors",
472
+ "vision_tower.vision_model.transformer.layers.23.feed_forward.gate_proj.weight": "model.safetensors",
473
+ "vision_tower.vision_model.transformer.layers.23.feed_forward.up_proj.weight": "model.safetensors",
474
+ "vision_tower.vision_model.transformer.layers.23.ffn_norm.weight": "model.safetensors",
475
+ "vision_tower.vision_model.transformer.layers.3.attention.k_proj.weight": "model.safetensors",
476
+ "vision_tower.vision_model.transformer.layers.3.attention.o_proj.weight": "model.safetensors",
477
+ "vision_tower.vision_model.transformer.layers.3.attention.q_proj.weight": "model.safetensors",
478
+ "vision_tower.vision_model.transformer.layers.3.attention.v_proj.weight": "model.safetensors",
479
+ "vision_tower.vision_model.transformer.layers.3.attention_norm.weight": "model.safetensors",
480
+ "vision_tower.vision_model.transformer.layers.3.feed_forward.down_proj.weight": "model.safetensors",
481
+ "vision_tower.vision_model.transformer.layers.3.feed_forward.gate_proj.weight": "model.safetensors",
482
+ "vision_tower.vision_model.transformer.layers.3.feed_forward.up_proj.weight": "model.safetensors",
483
+ "vision_tower.vision_model.transformer.layers.3.ffn_norm.weight": "model.safetensors",
484
+ "vision_tower.vision_model.transformer.layers.4.attention.k_proj.weight": "model.safetensors",
485
+ "vision_tower.vision_model.transformer.layers.4.attention.o_proj.weight": "model.safetensors",
486
+ "vision_tower.vision_model.transformer.layers.4.attention.q_proj.weight": "model.safetensors",
487
+ "vision_tower.vision_model.transformer.layers.4.attention.v_proj.weight": "model.safetensors",
488
+ "vision_tower.vision_model.transformer.layers.4.attention_norm.weight": "model.safetensors",
489
+ "vision_tower.vision_model.transformer.layers.4.feed_forward.down_proj.weight": "model.safetensors",
490
+ "vision_tower.vision_model.transformer.layers.4.feed_forward.gate_proj.weight": "model.safetensors",
491
+ "vision_tower.vision_model.transformer.layers.4.feed_forward.up_proj.weight": "model.safetensors",
492
+ "vision_tower.vision_model.transformer.layers.4.ffn_norm.weight": "model.safetensors",
493
+ "vision_tower.vision_model.transformer.layers.5.attention.k_proj.weight": "model.safetensors",
494
+ "vision_tower.vision_model.transformer.layers.5.attention.o_proj.weight": "model.safetensors",
495
+ "vision_tower.vision_model.transformer.layers.5.attention.q_proj.weight": "model.safetensors",
496
+ "vision_tower.vision_model.transformer.layers.5.attention.v_proj.weight": "model.safetensors",
497
+ "vision_tower.vision_model.transformer.layers.5.attention_norm.weight": "model.safetensors",
498
+ "vision_tower.vision_model.transformer.layers.5.feed_forward.down_proj.weight": "model.safetensors",
499
+ "vision_tower.vision_model.transformer.layers.5.feed_forward.gate_proj.weight": "model.safetensors",
500
+ "vision_tower.vision_model.transformer.layers.5.feed_forward.up_proj.weight": "model.safetensors",
501
+ "vision_tower.vision_model.transformer.layers.5.ffn_norm.weight": "model.safetensors",
502
+ "vision_tower.vision_model.transformer.layers.6.attention.k_proj.weight": "model.safetensors",
503
+ "vision_tower.vision_model.transformer.layers.6.attention.o_proj.weight": "model.safetensors",
504
+ "vision_tower.vision_model.transformer.layers.6.attention.q_proj.weight": "model.safetensors",
505
+ "vision_tower.vision_model.transformer.layers.6.attention.v_proj.weight": "model.safetensors",
506
+ "vision_tower.vision_model.transformer.layers.6.attention_norm.weight": "model.safetensors",
507
+ "vision_tower.vision_model.transformer.layers.6.feed_forward.down_proj.weight": "model.safetensors",
508
+ "vision_tower.vision_model.transformer.layers.6.feed_forward.gate_proj.weight": "model.safetensors",
509
+ "vision_tower.vision_model.transformer.layers.6.feed_forward.up_proj.weight": "model.safetensors",
510
+ "vision_tower.vision_model.transformer.layers.6.ffn_norm.weight": "model.safetensors",
511
+ "vision_tower.vision_model.transformer.layers.7.attention.k_proj.weight": "model.safetensors",
512
+ "vision_tower.vision_model.transformer.layers.7.attention.o_proj.weight": "model.safetensors",
513
+ "vision_tower.vision_model.transformer.layers.7.attention.q_proj.weight": "model.safetensors",
514
+ "vision_tower.vision_model.transformer.layers.7.attention.v_proj.weight": "model.safetensors",
515
+ "vision_tower.vision_model.transformer.layers.7.attention_norm.weight": "model.safetensors",
516
+ "vision_tower.vision_model.transformer.layers.7.feed_forward.down_proj.weight": "model.safetensors",
517
+ "vision_tower.vision_model.transformer.layers.7.feed_forward.gate_proj.weight": "model.safetensors",
518
+ "vision_tower.vision_model.transformer.layers.7.feed_forward.up_proj.weight": "model.safetensors",
519
+ "vision_tower.vision_model.transformer.layers.7.ffn_norm.weight": "model.safetensors",
520
+ "vision_tower.vision_model.transformer.layers.8.attention.k_proj.weight": "model.safetensors",
521
+ "vision_tower.vision_model.transformer.layers.8.attention.o_proj.weight": "model.safetensors",
522
+ "vision_tower.vision_model.transformer.layers.8.attention.q_proj.weight": "model.safetensors",
523
+ "vision_tower.vision_model.transformer.layers.8.attention.v_proj.weight": "model.safetensors",
524
+ "vision_tower.vision_model.transformer.layers.8.attention_norm.weight": "model.safetensors",
525
+ "vision_tower.vision_model.transformer.layers.8.feed_forward.down_proj.weight": "model.safetensors",
526
+ "vision_tower.vision_model.transformer.layers.8.feed_forward.gate_proj.weight": "model.safetensors",
527
+ "vision_tower.vision_model.transformer.layers.8.feed_forward.up_proj.weight": "model.safetensors",
528
+ "vision_tower.vision_model.transformer.layers.8.ffn_norm.weight": "model.safetensors",
529
+ "vision_tower.vision_model.transformer.layers.9.attention.k_proj.weight": "model.safetensors",
530
+ "vision_tower.vision_model.transformer.layers.9.attention.o_proj.weight": "model.safetensors",
531
+ "vision_tower.vision_model.transformer.layers.9.attention.q_proj.weight": "model.safetensors",
532
+ "vision_tower.vision_model.transformer.layers.9.attention.v_proj.weight": "model.safetensors",
533
+ "vision_tower.vision_model.transformer.layers.9.attention_norm.weight": "model.safetensors",
534
+ "vision_tower.vision_model.transformer.layers.9.feed_forward.down_proj.weight": "model.safetensors",
535
+ "vision_tower.vision_model.transformer.layers.9.feed_forward.gate_proj.weight": "model.safetensors",
536
+ "vision_tower.vision_model.transformer.layers.9.feed_forward.up_proj.weight": "model.safetensors",
537
+ "vision_tower.vision_model.transformer.layers.9.ffn_norm.weight": "model.safetensors"
538
+ }
539
+ }
processor_config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "image_break_token": "<|vision_pad|>",
3
+ "image_end_token": "<|vision_end|>",
4
+ "image_processor": {
5
+ "data_format": "channels_first",
6
+ "default_to_square": true,
7
+ "do_convert_rgb": true,
8
+ "do_normalize": true,
9
+ "do_rescale": true,
10
+ "do_resize": true,
11
+ "image_mean": [
12
+ 0.48145466,
13
+ 0.4578275,
14
+ 0.40821073
15
+ ],
16
+ "image_processor_type": "PixtralImageProcessorFast",
17
+ "image_std": [
18
+ 0.26862954,
19
+ 0.26130258,
20
+ 0.27577711
21
+ ],
22
+ "patch_size": 14,
23
+ "resample": 3,
24
+ "rescale_factor": 0.00392156862745098,
25
+ "size": {
26
+ "longest_edge": 1540
27
+ }
28
+ },
29
+ "image_token": "<|image_pad|>",
30
+ "patch_size": 14,
31
+ "processor_class": "PixtralProcessor",
32
+ "spatial_merge_size": 2
33
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f54b55fa0c3aba0c91ce09ea79ae4e62da24e2a1a630f96c4bae34aba25e234a
3
+ size 11422822
tokenizer_config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": null,
5
+ "clean_up_tokenization_spaces": false,
6
+ "eos_token": "<|im_end|>",
7
+ "errors": "replace",
8
+ "extra_special_tokens": [
9
+ "<|im_start|>",
10
+ "<|im_end|>",
11
+ "<|object_ref_start|>",
12
+ "<|object_ref_end|>",
13
+ "<|box_start|>",
14
+ "<|box_end|>",
15
+ "<|quad_start|>",
16
+ "<|quad_end|>",
17
+ "<|vision_start|>",
18
+ "<|vision_end|>",
19
+ "<|vision_pad|>",
20
+ "<|image_pad|>",
21
+ "<|video_pad|>"
22
+ ],
23
+ "image_break_token": "<|vision_pad|>",
24
+ "image_end_token": "<|vision_end|>",
25
+ "image_token": "<|image_pad|>",
26
+ "is_local": true,
27
+ "max_length": null,
28
+ "model_max_length": 131072,
29
+ "model_specific_special_tokens": {},
30
+ "pad_to_multiple_of": null,
31
+ "pad_token": "<|endoftext|>",
32
+ "pad_token_type_id": 0,
33
+ "padding_side": "right",
34
+ "processor_class": "PixtralProcessor",
35
+ "split_special_tokens": false,
36
+ "tokenizer_class": "TokenizersBackend",
37
+ "unk_token": null
38
+ }