Hugging Face's logo

GYX97
/
ImageDoctor

Image-Text-to-Text
Safetensors
English
ImageDoctor
conversational
custom_code
Model card Files
xet
Community
GYX97 commited on
Commit
dbaffef
·
verified ·
1 Parent(s): b6564d3

Delete ImageDoctor

Browse files
Files changed (11) hide show
  1. ImageDoctor/chat_template.json +0 -3
  2. ImageDoctor/config.json +0 -57
  3. ImageDoctor/generation_config.json +0 -14
  4. ImageDoctor/model-00001-of-00002.safetensors +0 -3
  5. ImageDoctor/model-00002-of-00002.safetensors +0 -3
  6. ImageDoctor/model.safetensors.index.json +0 -990
  7. ImageDoctor/modeling_ImageDoctor.py +0 -0
  8. ImageDoctor/preprocessor_config.json +0 -36
  9. ImageDoctor/special_tokens_map.json +0 -33
  10. ImageDoctor/tokenizer.json +0 -3
  11. ImageDoctor/tokenizer_config.json +0 -228
ImageDoctor/chat_template.json DELETED
@@ -1,3 +0,0 @@
1
- {
2
- "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
3
- }
 
 
 
 
ImageDoctor/config.json DELETED
@@ -1,57 +0,0 @@
1
- {
2
- "architectures": [
3
- "ImageDoctorForConditionalGeneration"
4
- ],
5
- "auto_map": {
6
- "AutoConfig": "modeling_ImageDoctor.ImageDoctorConfig",
7
- "AutoModelForCausalLM": "modeling_ImageDoctor.ImageDoctorForConditionalGeneration"
8
- },
9
- "artifact_token_id": 151666,
10
- "attention_dropout": 0.0,
11
- "bos_token_id": 151643,
12
- "eos_token_id": 151645,
13
- "heatmap_weight": 1,
14
- "hidden_act": "silu",
15
- "hidden_size": 2048,
16
- "image_token_id": 151655,
17
- "initializer_range": 0.02,
18
- "intermediate_size": 11008,
19
- "max_position_embeddings": 128000,
20
- "max_window_layers": 70,
21
- "misalignment_token_id": 151665,
22
- "model_type": "ImageDoctor",
23
- "num_attention_heads": 16,
24
- "num_hidden_layers": 36,
25
- "num_key_value_heads": 2,
26
- "rms_norm_eps": 1e-06,
27
- "rope_scaling": {
28
- "mrope_section": [
29
- 16,
30
- 24,
31
- 24
32
- ],
33
- "rope_type": "default",
34
- "type": "default"
35
- },
36
- "rope_theta": 1000000.0,
37
- "sliding_window": 32768,
38
- "tie_word_embeddings": true,
39
- "torch_dtype": "bfloat16",
40
- "transformers_version": "4.49.0",
41
- "use_cache": null,
42
- "use_sliding_window": false,
43
- "video_token_id": 151656,
44
- "vision_config": {
45
- "hidden_size": 1280,
46
- "in_chans": 3,
47
- "model_type": "ImageDoctor",
48
- "out_hidden_size": 2048,
49
- "spatial_patch_size": 14,
50
- "tokens_per_second": 2,
51
- "torch_dtype": "bfloat16"
52
- },
53
- "vision_end_token_id": 151653,
54
- "vision_start_token_id": 151652,
55
- "vision_token_id": 151654,
56
- "vocab_size": 151936
57
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ImageDoctor/generation_config.json DELETED
@@ -1,14 +0,0 @@
1
- {
2
- "attn_implementation": "flash_attention_2",
3
- "bos_token_id": 151643,
4
- "do_sample": true,
5
- "eos_token_id": [
6
- 151645,
7
- 151643
8
- ],
9
- "pad_token_id": 151643,
10
- "repetition_penalty": 1.05,
11
- "temperature": 1e-06,
12
- "transformers_version": "4.49.0",
13
- "use_cache": null
14
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ImageDoctor/model-00001-of-00002.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:1c489da147f447aecc5368d91f63276b6b07e38e04561b98850defe418a1560c
3
- size 4997750760
 
 
 
 
ImageDoctor/model-00002-of-00002.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:6d74334ae04d82ea744b08ef19f542b5dd716b7ce2dd953c9c65a1dce864309f
3
- size 3257990304
 
 
 
 
ImageDoctor/model.safetensors.index.json DELETED
@@ -1,990 +0,0 @@
1
- {
2
- "metadata": {
3
- "total_size": 8255629720
4
- },
5
- "weight_map": {
6
- "heatmap.mask_tokens.weight": "model-00002-of-00002.safetensors",
7
- "heatmap.output_hypernetworks_mlps.0.layers.0.bias": "model-00002-of-00002.safetensors",
8
- "heatmap.output_hypernetworks_mlps.0.layers.0.weight": "model-00002-of-00002.safetensors",
9
- "heatmap.output_hypernetworks_mlps.0.layers.1.bias": "model-00002-of-00002.safetensors",
10
- "heatmap.output_hypernetworks_mlps.0.layers.1.weight": "model-00002-of-00002.safetensors",
11
- "heatmap.output_hypernetworks_mlps.0.layers.2.bias": "model-00002-of-00002.safetensors",
12
- "heatmap.output_hypernetworks_mlps.0.layers.2.weight": "model-00002-of-00002.safetensors",
13
- "heatmap.output_upscaling.conv_layers.0.bias": "model-00002-of-00002.safetensors",
14
- "heatmap.output_upscaling.conv_layers.0.weight": "model-00002-of-00002.safetensors",
15
- "heatmap.output_upscaling.conv_layers.2.scale": "model-00002-of-00002.safetensors",
16
- "heatmap.output_upscaling.conv_layers.3.bias": "model-00002-of-00002.safetensors",
17
- "heatmap.output_upscaling.conv_layers.3.weight": "model-00002-of-00002.safetensors",
18
- "heatmap.output_upscaling.conv_layers.5.scale": "model-00002-of-00002.safetensors",
19
- "heatmap.output_upscaling.conv_layers2.0.0.bias": "model-00002-of-00002.safetensors",
20
- "heatmap.output_upscaling.conv_layers2.0.0.weight": "model-00002-of-00002.safetensors",
21
- "heatmap.output_upscaling.conv_layers2.0.1.scale": "model-00002-of-00002.safetensors",
22
- "heatmap.output_upscaling.conv_layers2.0.3.bias": "model-00002-of-00002.safetensors",
23
- "heatmap.output_upscaling.conv_layers2.0.3.weight": "model-00002-of-00002.safetensors",
24
- "heatmap.output_upscaling.conv_layers2.0.4.scale": "model-00002-of-00002.safetensors",
25
- "heatmap.output_upscaling.conv_layers2.1.0.bias": "model-00002-of-00002.safetensors",
26
- "heatmap.output_upscaling.conv_layers2.1.0.weight": "model-00002-of-00002.safetensors",
27
- "heatmap.output_upscaling.conv_layers2.1.1.scale": "model-00002-of-00002.safetensors",
28
- "heatmap.output_upscaling.conv_layers2.1.3.bias": "model-00002-of-00002.safetensors",
29
- "heatmap.output_upscaling.conv_layers2.1.3.weight": "model-00002-of-00002.safetensors",
30
- "heatmap.output_upscaling.conv_layers2.1.4.scale": "model-00002-of-00002.safetensors",
31
- "heatmap.output_upscaling.conv_layers2.2.0.bias": "model-00002-of-00002.safetensors",
32
- "heatmap.output_upscaling.conv_layers2.2.0.weight": "model-00002-of-00002.safetensors",
33
- "heatmap.output_upscaling.conv_layers2.2.1.scale": "model-00002-of-00002.safetensors",
34
- "heatmap.output_upscaling.conv_layers2.2.3.bias": "model-00002-of-00002.safetensors",
35
- "heatmap.output_upscaling.conv_layers2.2.3.weight": "model-00002-of-00002.safetensors",
36
- "heatmap.output_upscaling.conv_layers2.2.4.scale": "model-00002-of-00002.safetensors",
37
- "heatmap.output_upscaling.conv_layers2.3.0.bias": "model-00002-of-00002.safetensors",
38
- "heatmap.output_upscaling.conv_layers2.3.0.weight": "model-00002-of-00002.safetensors",
39
- "heatmap.output_upscaling.conv_layers2.3.1.scale": "model-00002-of-00002.safetensors",
40
- "heatmap.output_upscaling.conv_layers2.3.3.bias": "model-00002-of-00002.safetensors",
41
- "heatmap.output_upscaling.conv_layers2.3.3.weight": "model-00002-of-00002.safetensors",
42
- "heatmap.output_upscaling.conv_layers2.3.4.scale": "model-00002-of-00002.safetensors",
43
- "heatmap.output_upscaling.deconv_layers.0.0.bias": "model-00002-of-00002.safetensors",
44
- "heatmap.output_upscaling.deconv_layers.0.0.weight": "model-00002-of-00002.safetensors",
45
- "heatmap.output_upscaling.deconv_layers.0.1.scale": "model-00002-of-00002.safetensors",
46
- "heatmap.output_upscaling.deconv_layers.1.0.bias": "model-00002-of-00002.safetensors",
47
- "heatmap.output_upscaling.deconv_layers.1.0.weight": "model-00002-of-00002.safetensors",
48
- "heatmap.output_upscaling.deconv_layers.1.1.scale": "model-00002-of-00002.safetensors",
49
- "heatmap.output_upscaling.deconv_layers.2.0.bias": "model-00002-of-00002.safetensors",
50
- "heatmap.output_upscaling.deconv_layers.2.0.weight": "model-00002-of-00002.safetensors",
51
- "heatmap.output_upscaling.deconv_layers.2.1.scale": "model-00002-of-00002.safetensors",
52
- "heatmap.output_upscaling.deconv_layers.3.0.bias": "model-00002-of-00002.safetensors",
53
- "heatmap.output_upscaling.deconv_layers.3.0.weight": "model-00002-of-00002.safetensors",
54
- "heatmap.output_upscaling.deconv_layers.3.1.scale": "model-00002-of-00002.safetensors",
55
- "heatmap.output_upscaling.last_conv1.bias": "model-00002-of-00002.safetensors",
56
- "heatmap.output_upscaling.last_conv1.weight": "model-00002-of-00002.safetensors",
57
- "heatmap.transformer.final_attn_token_to_image.k_proj.bias": "model-00002-of-00002.safetensors",
58
- "heatmap.transformer.final_attn_token_to_image.k_proj.weight": "model-00002-of-00002.safetensors",
59
- "heatmap.transformer.final_attn_token_to_image.out_proj.bias": "model-00002-of-00002.safetensors",
60
- "heatmap.transformer.final_attn_token_to_image.out_proj.weight": "model-00002-of-00002.safetensors",
61
- "heatmap.transformer.final_attn_token_to_image.q_proj.bias": "model-00002-of-00002.safetensors",
62
- "heatmap.transformer.final_attn_token_to_image.q_proj.weight": "model-00002-of-00002.safetensors",
63
- "heatmap.transformer.final_attn_token_to_image.v_proj.bias": "model-00002-of-00002.safetensors",
64
- "heatmap.transformer.final_attn_token_to_image.v_proj.weight": "model-00002-of-00002.safetensors",
65
- "heatmap.transformer.layers.0.cross_attn_image_to_token.k_proj.bias": "model-00002-of-00002.safetensors",
66
- "heatmap.transformer.layers.0.cross_attn_image_to_token.k_proj.weight": "model-00002-of-00002.safetensors",
67
- "heatmap.transformer.layers.0.cross_attn_image_to_token.out_proj.bias": "model-00002-of-00002.safetensors",
68
- "heatmap.transformer.layers.0.cross_attn_image_to_token.out_proj.weight": "model-00002-of-00002.safetensors",
69
- "heatmap.transformer.layers.0.cross_attn_image_to_token.q_proj.bias": "model-00002-of-00002.safetensors",
70
- "heatmap.transformer.layers.0.cross_attn_image_to_token.q_proj.weight": "model-00002-of-00002.safetensors",
71
- "heatmap.transformer.layers.0.cross_attn_image_to_token.v_proj.bias": "model-00002-of-00002.safetensors",
72
- "heatmap.transformer.layers.0.cross_attn_image_to_token.v_proj.weight": "model-00002-of-00002.safetensors",
73
- "heatmap.transformer.layers.0.cross_attn_token_to_image.k_proj.bias": "model-00002-of-00002.safetensors",
74
- "heatmap.transformer.layers.0.cross_attn_token_to_image.k_proj.weight": "model-00002-of-00002.safetensors",
75
- "heatmap.transformer.layers.0.cross_attn_token_to_image.out_proj.bias": "model-00002-of-00002.safetensors",
76
- "heatmap.transformer.layers.0.cross_attn_token_to_image.out_proj.weight": "model-00002-of-00002.safetensors",
77
- "heatmap.transformer.layers.0.cross_attn_token_to_image.q_proj.bias": "model-00002-of-00002.safetensors",
78
- "heatmap.transformer.layers.0.cross_attn_token_to_image.q_proj.weight": "model-00002-of-00002.safetensors",
79
- "heatmap.transformer.layers.0.cross_attn_token_to_image.v_proj.bias": "model-00002-of-00002.safetensors",
80
- "heatmap.transformer.layers.0.cross_attn_token_to_image.v_proj.weight": "model-00002-of-00002.safetensors",
81
- "heatmap.transformer.layers.0.mlp.lin1.bias": "model-00002-of-00002.safetensors",
82
- "heatmap.transformer.layers.0.mlp.lin1.weight": "model-00002-of-00002.safetensors",
83
- "heatmap.transformer.layers.0.mlp.lin2.bias": "model-00002-of-00002.safetensors",
84
- "heatmap.transformer.layers.0.mlp.lin2.weight": "model-00002-of-00002.safetensors",
85
- "heatmap.transformer.layers.0.norm1.bias": "model-00002-of-00002.safetensors",
86
- "heatmap.transformer.layers.0.norm1.weight": "model-00002-of-00002.safetensors",
87
- "heatmap.transformer.layers.0.norm2.bias": "model-00002-of-00002.safetensors",
88
- "heatmap.transformer.layers.0.norm2.weight": "model-00002-of-00002.safetensors",
89
- "heatmap.transformer.layers.0.norm3.bias": "model-00002-of-00002.safetensors",
90
- "heatmap.transformer.layers.0.norm3.weight": "model-00002-of-00002.safetensors",
91
- "heatmap.transformer.layers.0.norm4.bias": "model-00002-of-00002.safetensors",
92
- "heatmap.transformer.layers.0.norm4.weight": "model-00002-of-00002.safetensors",
93
- "heatmap.transformer.layers.0.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
94
- "heatmap.transformer.layers.0.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
95
- "heatmap.transformer.layers.0.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
96
- "heatmap.transformer.layers.0.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
97
- "heatmap.transformer.layers.0.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
98
- "heatmap.transformer.layers.0.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
99
- "heatmap.transformer.layers.0.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
100
- "heatmap.transformer.layers.0.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
101
- "heatmap.transformer.layers.1.cross_attn_image_to_token.k_proj.bias": "model-00002-of-00002.safetensors",
102
- "heatmap.transformer.layers.1.cross_attn_image_to_token.k_proj.weight": "model-00002-of-00002.safetensors",
103
- "heatmap.transformer.layers.1.cross_attn_image_to_token.out_proj.bias": "model-00002-of-00002.safetensors",
104
- "heatmap.transformer.layers.1.cross_attn_image_to_token.out_proj.weight": "model-00002-of-00002.safetensors",
105
- "heatmap.transformer.layers.1.cross_attn_image_to_token.q_proj.bias": "model-00002-of-00002.safetensors",
106
- "heatmap.transformer.layers.1.cross_attn_image_to_token.q_proj.weight": "model-00002-of-00002.safetensors",
107
- "heatmap.transformer.layers.1.cross_attn_image_to_token.v_proj.bias": "model-00002-of-00002.safetensors",
108
- "heatmap.transformer.layers.1.cross_attn_image_to_token.v_proj.weight": "model-00002-of-00002.safetensors",
109
- "heatmap.transformer.layers.1.cross_attn_token_to_image.k_proj.bias": "model-00002-of-00002.safetensors",
110
- "heatmap.transformer.layers.1.cross_attn_token_to_image.k_proj.weight": "model-00002-of-00002.safetensors",
111
- "heatmap.transformer.layers.1.cross_attn_token_to_image.out_proj.bias": "model-00002-of-00002.safetensors",
112
- "heatmap.transformer.layers.1.cross_attn_token_to_image.out_proj.weight": "model-00002-of-00002.safetensors",
113
- "heatmap.transformer.layers.1.cross_attn_token_to_image.q_proj.bias": "model-00002-of-00002.safetensors",
114
- "heatmap.transformer.layers.1.cross_attn_token_to_image.q_proj.weight": "model-00002-of-00002.safetensors",
115
- "heatmap.transformer.layers.1.cross_attn_token_to_image.v_proj.bias": "model-00002-of-00002.safetensors",
116
- "heatmap.transformer.layers.1.cross_attn_token_to_image.v_proj.weight": "model-00002-of-00002.safetensors",
117
- "heatmap.transformer.layers.1.mlp.lin1.bias": "model-00002-of-00002.safetensors",
118
- "heatmap.transformer.layers.1.mlp.lin1.weight": "model-00002-of-00002.safetensors",
119
- "heatmap.transformer.layers.1.mlp.lin2.bias": "model-00002-of-00002.safetensors",
120
- "heatmap.transformer.layers.1.mlp.lin2.weight": "model-00002-of-00002.safetensors",
121
- "heatmap.transformer.layers.1.norm1.bias": "model-00002-of-00002.safetensors",
122
- "heatmap.transformer.layers.1.norm1.weight": "model-00002-of-00002.safetensors",
123
- "heatmap.transformer.layers.1.norm2.bias": "model-00002-of-00002.safetensors",
124
- "heatmap.transformer.layers.1.norm2.weight": "model-00002-of-00002.safetensors",
125
- "heatmap.transformer.layers.1.norm3.bias": "model-00002-of-00002.safetensors",
126
- "heatmap.transformer.layers.1.norm3.weight": "model-00002-of-00002.safetensors",
127
- "heatmap.transformer.layers.1.norm4.bias": "model-00002-of-00002.safetensors",
128
- "heatmap.transformer.layers.1.norm4.weight": "model-00002-of-00002.safetensors",
129
- "heatmap.transformer.layers.1.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
130
- "heatmap.transformer.layers.1.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
131
- "heatmap.transformer.layers.1.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
132
- "heatmap.transformer.layers.1.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
133
- "heatmap.transformer.layers.1.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
134
- "heatmap.transformer.layers.1.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
135
- "heatmap.transformer.layers.1.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
136
- "heatmap.transformer.layers.1.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
137
- "heatmap.transformer.norm_final_attn.bias": "model-00002-of-00002.safetensors",
138
- "heatmap.transformer.norm_final_attn.weight": "model-00002-of-00002.safetensors",
139
- "image_hidden_fcs.0.0.bias": "model-00002-of-00002.safetensors",
140
- "image_hidden_fcs.0.0.weight": "model-00002-of-00002.safetensors",
141
- "image_hidden_fcs.0.2.bias": "model-00002-of-00002.safetensors",
142
- "image_hidden_fcs.0.2.weight": "model-00002-of-00002.safetensors",
143
- "lm_head.weight": "model-00002-of-00002.safetensors",
144
- "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
145
- "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
146
- "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
147
- "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
148
- "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
149
- "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
150
- "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
151
- "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
152
- "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
153
- "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
154
- "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
155
- "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
156
- "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
157
- "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
158
- "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
159
- "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
160
- "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
161
- "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
162
- "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
163
- "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
164
- "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
165
- "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
166
- "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
167
- "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
168
- "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
169
- "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
170
- "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
171
- "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
172
- "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
173
- "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
174
- "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
175
- "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
176
- "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
177
- "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
178
- "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
179
- "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
180
- "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
181
- "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
182
- "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
183
- "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
184
- "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
185
- "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
186
- "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
187
- "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
188
- "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
189
- "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
190
- "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
191
- "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
192
- "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
193
- "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
194
- "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
195
- "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
196
- "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
197
- "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
198
- "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
199
- "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
200
- "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
201
- "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
202
- "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
203
- "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
204
- "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
205
- "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
206
- "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
207
- "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
208
- "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
209
- "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
210
- "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
211
- "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
212
- "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
213
- "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
214
- "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
215
- "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
216
- "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
217
- "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
218
- "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
219
- "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
220
- "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
221
- "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
222
- "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
223
- "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
224
- "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
225
- "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
226
- "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
227
- "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
228
- "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
229
- "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
230
- "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
231
- "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
232
- "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
233
- "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
234
- "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
235
- "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
236
- "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
237
- "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
238
- "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
239
- "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
240
- "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
241
- "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
242
- "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
243
- "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
244
- "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
245
- "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
246
- "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
247
- "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
248
- "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
249
- "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
250
- "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
251
- "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
252
- "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
253
- "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
254
- "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
255
- "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
256
- "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
257
- "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
258
- "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
259
- "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
260
- "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
261
- "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
262
- "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
263
- "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
264
- "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
265
- "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
266
- "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
267
- "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
268
- "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
269
- "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
270
- "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
271
- "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
272
- "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
273
- "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
274
- "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
275
- "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
276
- "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
277
- "model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
278
- "model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
279
- "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
280
- "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
281
- "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
282
- "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
283
- "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
284
- "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
285
- "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
286
- "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
287
- "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
288
- "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
289
- "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
290
- "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
291
- "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
292
- "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
293
- "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
294
- "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
295
- "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
296
- "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
297
- "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
298
- "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
299
- "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
300
- "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
301
- "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
302
- "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
303
- "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
304
- "model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
305
- "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
306
- "model.layers.20.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
307
- "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
308
- "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
309
- "model.layers.20.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
310
- "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
311
- "model.layers.20.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
312
- "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
313
- "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
314
- "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
315
- "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
316
- "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
317
- "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
318
- "model.layers.21.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
319
- "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
320
- "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
321
- "model.layers.21.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
322
- "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
323
- "model.layers.21.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
324
- "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
325
- "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
326
- "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
327
- "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
328
- "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
329
- "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
330
- "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
331
- "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
332
- "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
333
- "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
334
- "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
335
- "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
336
- "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
337
- "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
338
- "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
339
- "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
340
- "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
341
- "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
342
- "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
343
- "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
344
- "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
345
- "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
346
- "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
347
- "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
348
- "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
349
- "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
350
- "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
351
- "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
352
- "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
353
- "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
354
- "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
355
- "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
356
- "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
357
- "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
358
- "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
359
- "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
360
- "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
361
- "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
362
- "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
363
- "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
364
- "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
365
- "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
366
- "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
367
- "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
368
- "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
369
- "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
370
- "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
371
- "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
372
- "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
373
- "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
374
- "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
375
- "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
376
- "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
377
- "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
378
- "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
379
- "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
380
- "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
381
- "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
382
- "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
383
- "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
384
- "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
385
- "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
386
- "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
387
- "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
388
- "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
389
- "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
390
- "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
391
- "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
392
- "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
393
- "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
394
- "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
395
- "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
396
- "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
397
- "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
398
- "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
399
- "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
400
- "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
401
- "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
402
- "model.layers.28.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
403
- "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
404
- "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
405
- "model.layers.28.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
406
- "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
407
- "model.layers.28.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
408
- "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
409
- "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
410
- "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
411
- "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
412
- "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
413
- "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
414
- "model.layers.29.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
415
- "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
416
- "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
417
- "model.layers.29.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
418
- "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
419
- "model.layers.29.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
420
- "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
421
- "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
422
- "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
423
- "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
424
- "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
425
- "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
426
- "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
427
- "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
428
- "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
429
- "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
430
- "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
431
- "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
432
- "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
433
- "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
434
- "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
435
- "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
436
- "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
437
- "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
438
- "model.layers.30.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
439
- "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
440
- "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
441
- "model.layers.30.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
442
- "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
443
- "model.layers.30.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
444
- "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
445
- "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
446
- "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
447
- "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
448
- "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
449
- "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
450
- "model.layers.31.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
451
- "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
452
- "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
453
- "model.layers.31.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
454
- "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
455
- "model.layers.31.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
456
- "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
457
- "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
458
- "model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
459
- "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
460
- "model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
461
- "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
462
- "model.layers.32.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
463
- "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
464
- "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
465
- "model.layers.32.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
466
- "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
467
- "model.layers.32.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
468
- "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
469
- "model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
470
- "model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
471
- "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
472
- "model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
473
- "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
474
- "model.layers.33.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
475
- "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
476
- "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
477
- "model.layers.33.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
478
- "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
479
- "model.layers.33.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
480
- "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
481
- "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
482
- "model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
483
- "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
484
- "model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
485
- "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
486
- "model.layers.34.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
487
- "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
488
- "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
489
- "model.layers.34.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
490
- "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
491
- "model.layers.34.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
492
- "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
493
- "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
494
- "model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
495
- "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
496
- "model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
497
- "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
498
- "model.layers.35.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
499
- "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
500
- "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
501
- "model.layers.35.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
502
- "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
503
- "model.layers.35.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
504
- "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
505
- "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
506
- "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
507
- "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
508
- "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
509
- "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
510
- "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
511
- "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
512
- "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
513
- "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
514
- "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
515
- "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
516
- "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
517
- "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
518
- "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
519
- "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
520
- "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
521
- "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
522
- "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
523
- "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
524
- "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
525
- "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
526
- "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
527
- "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
528
- "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
529
- "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
530
- "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
531
- "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
532
- "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
533
- "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
534
- "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
535
- "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
536
- "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
537
- "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
538
- "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
539
- "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
540
- "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
541
- "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
542
- "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
543
- "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
544
- "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
545
- "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
546
- "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
547
- "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
548
- "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
549
- "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
550
- "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
551
- "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
552
- "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
553
- "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
554
- "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
555
- "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
556
- "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
557
- "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
558
- "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
559
- "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
560
- "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
561
- "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
562
- "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
563
- "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
564
- "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
565
- "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
566
- "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
567
- "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
568
- "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
569
- "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
570
- "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
571
- "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
572
- "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
573
- "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
574
- "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
575
- "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
576
- "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
577
- "model.norm.weight": "model-00002-of-00002.safetensors",
578
- "prompt_encoder.mask_downscaling.0.bias": "model-00002-of-00002.safetensors",
579
- "prompt_encoder.mask_downscaling.0.weight": "model-00002-of-00002.safetensors",
580
- "prompt_encoder.mask_downscaling.1.bias": "model-00002-of-00002.safetensors",
581
- "prompt_encoder.mask_downscaling.1.weight": "model-00002-of-00002.safetensors",
582
- "prompt_encoder.mask_downscaling.3.bias": "model-00002-of-00002.safetensors",
583
- "prompt_encoder.mask_downscaling.3.weight": "model-00002-of-00002.safetensors",
584
- "prompt_encoder.mask_downscaling.4.bias": "model-00002-of-00002.safetensors",
585
- "prompt_encoder.mask_downscaling.4.weight": "model-00002-of-00002.safetensors",
586
- "prompt_encoder.mask_downscaling.6.bias": "model-00002-of-00002.safetensors",
587
- "prompt_encoder.mask_downscaling.6.weight": "model-00002-of-00002.safetensors",
588
- "prompt_encoder.no_mask_embed.weight": "model-00002-of-00002.safetensors",
589
- "prompt_encoder.not_a_point_embed.weight": "model-00002-of-00002.safetensors",
590
- "prompt_encoder.pe_layer.positional_encoding_gaussian_matrix": "model-00002-of-00002.safetensors",
591
- "prompt_encoder.point_embeddings.0.weight": "model-00002-of-00002.safetensors",
592
- "prompt_encoder.point_embeddings.1.weight": "model-00002-of-00002.safetensors",
593
- "prompt_encoder.point_embeddings.2.weight": "model-00002-of-00002.safetensors",
594
- "prompt_encoder.point_embeddings.3.weight": "model-00002-of-00002.safetensors",
595
- "text_hidden_fcs.0.0.bias": "model-00002-of-00002.safetensors",
596
- "text_hidden_fcs.0.0.weight": "model-00002-of-00002.safetensors",
597
- "text_hidden_fcs.0.2.bias": "model-00002-of-00002.safetensors",
598
- "text_hidden_fcs.0.2.weight": "model-00002-of-00002.safetensors",
599
- "visual.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors",
600
- "visual.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors",
601
- "visual.blocks.0.attn.qkv.bias": "model-00001-of-00002.safetensors",
602
- "visual.blocks.0.attn.qkv.weight": "model-00001-of-00002.safetensors",
603
- "visual.blocks.0.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
604
- "visual.blocks.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
605
- "visual.blocks.0.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
606
- "visual.blocks.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
607
- "visual.blocks.0.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
608
- "visual.blocks.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
609
- "visual.blocks.0.norm1.weight": "model-00001-of-00002.safetensors",
610
- "visual.blocks.0.norm2.weight": "model-00001-of-00002.safetensors",
611
- "visual.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors",
612
- "visual.blocks.1.attn.proj.weight": "model-00001-of-00002.safetensors",
613
- "visual.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors",
614
- "visual.blocks.1.attn.qkv.weight": "model-00001-of-00002.safetensors",
615
- "visual.blocks.1.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
616
- "visual.blocks.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
617
- "visual.blocks.1.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
618
- "visual.blocks.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
619
- "visual.blocks.1.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
620
- "visual.blocks.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
621
- "visual.blocks.1.norm1.weight": "model-00001-of-00002.safetensors",
622
- "visual.blocks.1.norm2.weight": "model-00001-of-00002.safetensors",
623
- "visual.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors",
624
- "visual.blocks.10.attn.proj.weight": "model-00001-of-00002.safetensors",
625
- "visual.blocks.10.attn.qkv.bias": "model-00001-of-00002.safetensors",
626
- "visual.blocks.10.attn.qkv.weight": "model-00001-of-00002.safetensors",
627
- "visual.blocks.10.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
628
- "visual.blocks.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
629
- "visual.blocks.10.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
630
- "visual.blocks.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
631
- "visual.blocks.10.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
632
- "visual.blocks.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
633
- "visual.blocks.10.norm1.weight": "model-00001-of-00002.safetensors",
634
- "visual.blocks.10.norm2.weight": "model-00001-of-00002.safetensors",
635
- "visual.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors",
636
- "visual.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors",
637
- "visual.blocks.11.attn.qkv.bias": "model-00001-of-00002.safetensors",
638
- "visual.blocks.11.attn.qkv.weight": "model-00001-of-00002.safetensors",
639
- "visual.blocks.11.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
640
- "visual.blocks.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
641
- "visual.blocks.11.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
642
- "visual.blocks.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
643
- "visual.blocks.11.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
644
- "visual.blocks.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
645
- "visual.blocks.11.norm1.weight": "model-00001-of-00002.safetensors",
646
- "visual.blocks.11.norm2.weight": "model-00001-of-00002.safetensors",
647
- "visual.blocks.12.attn.proj.bias": "model-00001-of-00002.safetensors",
648
- "visual.blocks.12.attn.proj.weight": "model-00001-of-00002.safetensors",
649
- "visual.blocks.12.attn.qkv.bias": "model-00001-of-00002.safetensors",
650
- "visual.blocks.12.attn.qkv.weight": "model-00001-of-00002.safetensors",
651
- "visual.blocks.12.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
652
- "visual.blocks.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
653
- "visual.blocks.12.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
654
- "visual.blocks.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
655
- "visual.blocks.12.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
656
- "visual.blocks.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
657
- "visual.blocks.12.norm1.weight": "model-00001-of-00002.safetensors",
658
- "visual.blocks.12.norm2.weight": "model-00001-of-00002.safetensors",
659
- "visual.blocks.13.attn.proj.bias": "model-00001-of-00002.safetensors",
660
- "visual.blocks.13.attn.proj.weight": "model-00001-of-00002.safetensors",
661
- "visual.blocks.13.attn.qkv.bias": "model-00001-of-00002.safetensors",
662
- "visual.blocks.13.attn.qkv.weight": "model-00001-of-00002.safetensors",
663
- "visual.blocks.13.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
664
- "visual.blocks.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
665
- "visual.blocks.13.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
666
- "visual.blocks.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
667
- "visual.blocks.13.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
668
- "visual.blocks.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
669
- "visual.blocks.13.norm1.weight": "model-00001-of-00002.safetensors",
670
- "visual.blocks.13.norm2.weight": "model-00001-of-00002.safetensors",
671
- "visual.blocks.14.attn.proj.bias": "model-00001-of-00002.safetensors",
672
- "visual.blocks.14.attn.proj.weight": "model-00001-of-00002.safetensors",
673
- "visual.blocks.14.attn.qkv.bias": "model-00001-of-00002.safetensors",
674
- "visual.blocks.14.attn.qkv.weight": "model-00001-of-00002.safetensors",
675
- "visual.blocks.14.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
676
- "visual.blocks.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
677
- "visual.blocks.14.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
678
- "visual.blocks.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
679
- "visual.blocks.14.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
680
- "visual.blocks.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
681
- "visual.blocks.14.norm1.weight": "model-00001-of-00002.safetensors",
682
- "visual.blocks.14.norm2.weight": "model-00001-of-00002.safetensors",
683
- "visual.blocks.15.attn.proj.bias": "model-00001-of-00002.safetensors",
684
- "visual.blocks.15.attn.proj.weight": "model-00001-of-00002.safetensors",
685
- "visual.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors",
686
- "visual.blocks.15.attn.qkv.weight": "model-00001-of-00002.safetensors",
687
- "visual.blocks.15.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
688
- "visual.blocks.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
689
- "visual.blocks.15.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
690
- "visual.blocks.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
691
- "visual.blocks.15.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
692
- "visual.blocks.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
693
- "visual.blocks.15.norm1.weight": "model-00001-of-00002.safetensors",
694
- "visual.blocks.15.norm2.weight": "model-00001-of-00002.safetensors",
695
- "visual.blocks.16.attn.proj.bias": "model-00001-of-00002.safetensors",
696
- "visual.blocks.16.attn.proj.weight": "model-00001-of-00002.safetensors",
697
- "visual.blocks.16.attn.qkv.bias": "model-00001-of-00002.safetensors",
698
- "visual.blocks.16.attn.qkv.weight": "model-00001-of-00002.safetensors",
699
- "visual.blocks.16.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
700
- "visual.blocks.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
701
- "visual.blocks.16.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
702
- "visual.blocks.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
703
- "visual.blocks.16.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
704
- "visual.blocks.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
705
- "visual.blocks.16.norm1.weight": "model-00001-of-00002.safetensors",
706
- "visual.blocks.16.norm2.weight": "model-00001-of-00002.safetensors",
707
- "visual.blocks.17.attn.proj.bias": "model-00001-of-00002.safetensors",
708
- "visual.blocks.17.attn.proj.weight": "model-00001-of-00002.safetensors",
709
- "visual.blocks.17.attn.qkv.bias": "model-00001-of-00002.safetensors",
710
- "visual.blocks.17.attn.qkv.weight": "model-00001-of-00002.safetensors",
711
- "visual.blocks.17.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
712
- "visual.blocks.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
713
- "visual.blocks.17.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
714
- "visual.blocks.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
715
- "visual.blocks.17.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
716
- "visual.blocks.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
717
- "visual.blocks.17.norm1.weight": "model-00001-of-00002.safetensors",
718
- "visual.blocks.17.norm2.weight": "model-00001-of-00002.safetensors",
719
- "visual.blocks.18.attn.proj.bias": "model-00001-of-00002.safetensors",
720
- "visual.blocks.18.attn.proj.weight": "model-00001-of-00002.safetensors",
721
- "visual.blocks.18.attn.qkv.bias": "model-00001-of-00002.safetensors",
722
- "visual.blocks.18.attn.qkv.weight": "model-00001-of-00002.safetensors",
723
- "visual.blocks.18.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
724
- "visual.blocks.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
725
- "visual.blocks.18.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
726
- "visual.blocks.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
727
- "visual.blocks.18.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
728
- "visual.blocks.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
729
- "visual.blocks.18.norm1.weight": "model-00001-of-00002.safetensors",
730
- "visual.blocks.18.norm2.weight": "model-00001-of-00002.safetensors",
731
- "visual.blocks.19.attn.proj.bias": "model-00001-of-00002.safetensors",
732
- "visual.blocks.19.attn.proj.weight": "model-00001-of-00002.safetensors",
733
- "visual.blocks.19.attn.qkv.bias": "model-00001-of-00002.safetensors",
734
- "visual.blocks.19.attn.qkv.weight": "model-00001-of-00002.safetensors",
735
- "visual.blocks.19.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
736
- "visual.blocks.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
737
- "visual.blocks.19.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
738
- "visual.blocks.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
739
- "visual.blocks.19.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
740
- "visual.blocks.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
741
- "visual.blocks.19.norm1.weight": "model-00001-of-00002.safetensors",
742
- "visual.blocks.19.norm2.weight": "model-00001-of-00002.safetensors",
743
- "visual.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors",
744
- "visual.blocks.2.attn.proj.weight": "model-00001-of-00002.safetensors",
745
- "visual.blocks.2.attn.qkv.bias": "model-00001-of-00002.safetensors",
746
- "visual.blocks.2.attn.qkv.weight": "model-00001-of-00002.safetensors",
747
- "visual.blocks.2.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
748
- "visual.blocks.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
749
- "visual.blocks.2.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
750
- "visual.blocks.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
751
- "visual.blocks.2.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
752
- "visual.blocks.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
753
- "visual.blocks.2.norm1.weight": "model-00001-of-00002.safetensors",
754
- "visual.blocks.2.norm2.weight": "model-00001-of-00002.safetensors",
755
- "visual.blocks.20.attn.proj.bias": "model-00001-of-00002.safetensors",
756
- "visual.blocks.20.attn.proj.weight": "model-00001-of-00002.safetensors",
757
- "visual.blocks.20.attn.qkv.bias": "model-00001-of-00002.safetensors",
758
- "visual.blocks.20.attn.qkv.weight": "model-00001-of-00002.safetensors",
759
- "visual.blocks.20.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
760
- "visual.blocks.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
761
- "visual.blocks.20.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
762
- "visual.blocks.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
763
- "visual.blocks.20.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
764
- "visual.blocks.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
765
- "visual.blocks.20.norm1.weight": "model-00001-of-00002.safetensors",
766
- "visual.blocks.20.norm2.weight": "model-00001-of-00002.safetensors",
767
- "visual.blocks.21.attn.proj.bias": "model-00001-of-00002.safetensors",
768
- "visual.blocks.21.attn.proj.weight": "model-00001-of-00002.safetensors",
769
- "visual.blocks.21.attn.qkv.bias": "model-00001-of-00002.safetensors",
770
- "visual.blocks.21.attn.qkv.weight": "model-00001-of-00002.safetensors",
771
- "visual.blocks.21.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
772
- "visual.blocks.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
773
- "visual.blocks.21.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
774
- "visual.blocks.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
775
- "visual.blocks.21.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
776
- "visual.blocks.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
777
- "visual.blocks.21.norm1.weight": "model-00001-of-00002.safetensors",
778
- "visual.blocks.21.norm2.weight": "model-00001-of-00002.safetensors",
779
- "visual.blocks.22.attn.proj.bias": "model-00001-of-00002.safetensors",
780
- "visual.blocks.22.attn.proj.weight": "model-00001-of-00002.safetensors",
781
- "visual.blocks.22.attn.qkv.bias": "model-00001-of-00002.safetensors",
782
- "visual.blocks.22.attn.qkv.weight": "model-00001-of-00002.safetensors",
783
- "visual.blocks.22.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
784
- "visual.blocks.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
785
- "visual.blocks.22.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
786
- "visual.blocks.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
787
- "visual.blocks.22.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
788
- "visual.blocks.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
789
- "visual.blocks.22.norm1.weight": "model-00001-of-00002.safetensors",
790
- "visual.blocks.22.norm2.weight": "model-00001-of-00002.safetensors",
791
- "visual.blocks.23.attn.proj.bias": "model-00001-of-00002.safetensors",
792
- "visual.blocks.23.attn.proj.weight": "model-00001-of-00002.safetensors",
793
- "visual.blocks.23.attn.qkv.bias": "model-00001-of-00002.safetensors",
794
- "visual.blocks.23.attn.qkv.weight": "model-00001-of-00002.safetensors",
795
- "visual.blocks.23.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
796
- "visual.blocks.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
797
- "visual.blocks.23.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
798
- "visual.blocks.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
799
- "visual.blocks.23.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
800
- "visual.blocks.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
801
- "visual.blocks.23.norm1.weight": "model-00001-of-00002.safetensors",
802
- "visual.blocks.23.norm2.weight": "model-00001-of-00002.safetensors",
803
- "visual.blocks.24.attn.proj.bias": "model-00001-of-00002.safetensors",
804
- "visual.blocks.24.attn.proj.weight": "model-00001-of-00002.safetensors",
805
- "visual.blocks.24.attn.qkv.bias": "model-00001-of-00002.safetensors",
806
- "visual.blocks.24.attn.qkv.weight": "model-00001-of-00002.safetensors",
807
- "visual.blocks.24.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
808
- "visual.blocks.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
809
- "visual.blocks.24.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
810
- "visual.blocks.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
811
- "visual.blocks.24.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
812
- "visual.blocks.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
813
- "visual.blocks.24.norm1.weight": "model-00001-of-00002.safetensors",
814
- "visual.blocks.24.norm2.weight": "model-00001-of-00002.safetensors",
815
- "visual.blocks.25.attn.proj.bias": "model-00001-of-00002.safetensors",
816
- "visual.blocks.25.attn.proj.weight": "model-00001-of-00002.safetensors",
817
- "visual.blocks.25.attn.qkv.bias": "model-00001-of-00002.safetensors",
818
- "visual.blocks.25.attn.qkv.weight": "model-00001-of-00002.safetensors",
819
- "visual.blocks.25.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
820
- "visual.blocks.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
821
- "visual.blocks.25.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
822
- "visual.blocks.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
823
- "visual.blocks.25.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
824
- "visual.blocks.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
825
- "visual.blocks.25.norm1.weight": "model-00001-of-00002.safetensors",
826
- "visual.blocks.25.norm2.weight": "model-00001-of-00002.safetensors",
827
- "visual.blocks.26.attn.proj.bias": "model-00001-of-00002.safetensors",
828
- "visual.blocks.26.attn.proj.weight": "model-00001-of-00002.safetensors",
829
- "visual.blocks.26.attn.qkv.bias": "model-00001-of-00002.safetensors",
830
- "visual.blocks.26.attn.qkv.weight": "model-00001-of-00002.safetensors",
831
- "visual.blocks.26.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
832
- "visual.blocks.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
833
- "visual.blocks.26.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
834
- "visual.blocks.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
835
- "visual.blocks.26.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
836
- "visual.blocks.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
837
- "visual.blocks.26.norm1.weight": "model-00001-of-00002.safetensors",
838
- "visual.blocks.26.norm2.weight": "model-00001-of-00002.safetensors",
839
- "visual.blocks.27.attn.proj.bias": "model-00001-of-00002.safetensors",
840
- "visual.blocks.27.attn.proj.weight": "model-00001-of-00002.safetensors",
841
- "visual.blocks.27.attn.qkv.bias": "model-00001-of-00002.safetensors",
842
- "visual.blocks.27.attn.qkv.weight": "model-00001-of-00002.safetensors",
843
- "visual.blocks.27.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
844
- "visual.blocks.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
845
- "visual.blocks.27.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
846
- "visual.blocks.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
847
- "visual.blocks.27.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
848
- "visual.blocks.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
849
- "visual.blocks.27.norm1.weight": "model-00001-of-00002.safetensors",
850
- "visual.blocks.27.norm2.weight": "model-00001-of-00002.safetensors",
851
- "visual.blocks.28.attn.proj.bias": "model-00001-of-00002.safetensors",
852
- "visual.blocks.28.attn.proj.weight": "model-00001-of-00002.safetensors",
853
- "visual.blocks.28.attn.qkv.bias": "model-00001-of-00002.safetensors",
854
- "visual.blocks.28.attn.qkv.weight": "model-00001-of-00002.safetensors",
855
- "visual.blocks.28.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
856
- "visual.blocks.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
857
- "visual.blocks.28.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
858
- "visual.blocks.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
859
- "visual.blocks.28.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
860
- "visual.blocks.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
861
- "visual.blocks.28.norm1.weight": "model-00001-of-00002.safetensors",
862
- "visual.blocks.28.norm2.weight": "model-00001-of-00002.safetensors",
863
- "visual.blocks.29.attn.proj.bias": "model-00001-of-00002.safetensors",
864
- "visual.blocks.29.attn.proj.weight": "model-00001-of-00002.safetensors",
865
- "visual.blocks.29.attn.qkv.bias": "model-00001-of-00002.safetensors",
866
- "visual.blocks.29.attn.qkv.weight": "model-00001-of-00002.safetensors",
867
- "visual.blocks.29.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
868
- "visual.blocks.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
869
- "visual.blocks.29.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
870
- "visual.blocks.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
871
- "visual.blocks.29.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
872
- "visual.blocks.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
873
- "visual.blocks.29.norm1.weight": "model-00001-of-00002.safetensors",
874
- "visual.blocks.29.norm2.weight": "model-00001-of-00002.safetensors",
875
- "visual.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors",
876
- "visual.blocks.3.attn.proj.weight": "model-00001-of-00002.safetensors",
877
- "visual.blocks.3.attn.qkv.bias": "model-00001-of-00002.safetensors",
878
- "visual.blocks.3.attn.qkv.weight": "model-00001-of-00002.safetensors",
879
- "visual.blocks.3.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
880
- "visual.blocks.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
881
- "visual.blocks.3.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
882
- "visual.blocks.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
883
- "visual.blocks.3.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
884
- "visual.blocks.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
885
- "visual.blocks.3.norm1.weight": "model-00001-of-00002.safetensors",
886
- "visual.blocks.3.norm2.weight": "model-00001-of-00002.safetensors",
887
- "visual.blocks.30.attn.proj.bias": "model-00001-of-00002.safetensors",
888
- "visual.blocks.30.attn.proj.weight": "model-00001-of-00002.safetensors",
889
- "visual.blocks.30.attn.qkv.bias": "model-00001-of-00002.safetensors",
890
- "visual.blocks.30.attn.qkv.weight": "model-00001-of-00002.safetensors",
891
- "visual.blocks.30.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
892
- "visual.blocks.30.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
893
- "visual.blocks.30.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
894
- "visual.blocks.30.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
895
- "visual.blocks.30.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
896
- "visual.blocks.30.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
897
- "visual.blocks.30.norm1.weight": "model-00001-of-00002.safetensors",
898
- "visual.blocks.30.norm2.weight": "model-00001-of-00002.safetensors",
899
- "visual.blocks.31.attn.proj.bias": "model-00001-of-00002.safetensors",
900
- "visual.blocks.31.attn.proj.weight": "model-00001-of-00002.safetensors",
901
- "visual.blocks.31.attn.qkv.bias": "model-00001-of-00002.safetensors",
902
- "visual.blocks.31.attn.qkv.weight": "model-00001-of-00002.safetensors",
903
- "visual.blocks.31.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
904
- "visual.blocks.31.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
905
- "visual.blocks.31.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
906
- "visual.blocks.31.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
907
- "visual.blocks.31.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
908
- "visual.blocks.31.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
909
- "visual.blocks.31.norm1.weight": "model-00001-of-00002.safetensors",
910
- "visual.blocks.31.norm2.weight": "model-00001-of-00002.safetensors",
911
- "visual.blocks.4.attn.proj.bias": "model-00001-of-00002.safetensors",
912
- "visual.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors",
913
- "visual.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors",
914
- "visual.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors",
915
- "visual.blocks.4.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
916
- "visual.blocks.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
917
- "visual.blocks.4.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
918
- "visual.blocks.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
919
- "visual.blocks.4.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
920
- "visual.blocks.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
921
- "visual.blocks.4.norm1.weight": "model-00001-of-00002.safetensors",
922
- "visual.blocks.4.norm2.weight": "model-00001-of-00002.safetensors",
923
- "visual.blocks.5.attn.proj.bias": "model-00001-of-00002.safetensors",
924
- "visual.blocks.5.attn.proj.weight": "model-00001-of-00002.safetensors",
925
- "visual.blocks.5.attn.qkv.bias": "model-00001-of-00002.safetensors",
926
- "visual.blocks.5.attn.qkv.weight": "model-00001-of-00002.safetensors",
927
- "visual.blocks.5.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
928
- "visual.blocks.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
929
- "visual.blocks.5.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
930
- "visual.blocks.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
931
- "visual.blocks.5.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
932
- "visual.blocks.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
933
- "visual.blocks.5.norm1.weight": "model-00001-of-00002.safetensors",
934
- "visual.blocks.5.norm2.weight": "model-00001-of-00002.safetensors",
935
- "visual.blocks.6.attn.proj.bias": "model-00001-of-00002.safetensors",
936
- "visual.blocks.6.attn.proj.weight": "model-00001-of-00002.safetensors",
937
- "visual.blocks.6.attn.qkv.bias": "model-00001-of-00002.safetensors",
938
- "visual.blocks.6.attn.qkv.weight": "model-00001-of-00002.safetensors",
939
- "visual.blocks.6.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
940
- "visual.blocks.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
941
- "visual.blocks.6.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
942
- "visual.blocks.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
943
- "visual.blocks.6.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
944
- "visual.blocks.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
945
- "visual.blocks.6.norm1.weight": "model-00001-of-00002.safetensors",
946
- "visual.blocks.6.norm2.weight": "model-00001-of-00002.safetensors",
947
- "visual.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors",
948
- "visual.blocks.7.attn.proj.weight": "model-00001-of-00002.safetensors",
949
- "visual.blocks.7.attn.qkv.bias": "model-00001-of-00002.safetensors",
950
- "visual.blocks.7.attn.qkv.weight": "model-00001-of-00002.safetensors",
951
- "visual.blocks.7.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
952
- "visual.blocks.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
953
- "visual.blocks.7.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
954
- "visual.blocks.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
955
- "visual.blocks.7.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
956
- "visual.blocks.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
957
- "visual.blocks.7.norm1.weight": "model-00001-of-00002.safetensors",
958
- "visual.blocks.7.norm2.weight": "model-00001-of-00002.safetensors",
959
- "visual.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors",
960
- "visual.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors",
961
- "visual.blocks.8.attn.qkv.bias": "model-00001-of-00002.safetensors",
962
- "visual.blocks.8.attn.qkv.weight": "model-00001-of-00002.safetensors",
963
- "visual.blocks.8.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
964
- "visual.blocks.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
965
- "visual.blocks.8.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
966
- "visual.blocks.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
967
- "visual.blocks.8.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
968
- "visual.blocks.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
969
- "visual.blocks.8.norm1.weight": "model-00001-of-00002.safetensors",
970
- "visual.blocks.8.norm2.weight": "model-00001-of-00002.safetensors",
971
- "visual.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors",
972
- "visual.blocks.9.attn.proj.weight": "model-00001-of-00002.safetensors",
973
- "visual.blocks.9.attn.qkv.bias": "model-00001-of-00002.safetensors",
974
- "visual.blocks.9.attn.qkv.weight": "model-00001-of-00002.safetensors",
975
- "visual.blocks.9.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
976
- "visual.blocks.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
977
- "visual.blocks.9.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
978
- "visual.blocks.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
979
- "visual.blocks.9.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
980
- "visual.blocks.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
981
- "visual.blocks.9.norm1.weight": "model-00001-of-00002.safetensors",
982
- "visual.blocks.9.norm2.weight": "model-00001-of-00002.safetensors",
983
- "visual.merger.ln_q.weight": "model-00001-of-00002.safetensors",
984
- "visual.merger.mlp.0.bias": "model-00001-of-00002.safetensors",
985
- "visual.merger.mlp.0.weight": "model-00001-of-00002.safetensors",
986
- "visual.merger.mlp.2.bias": "model-00001-of-00002.safetensors",
987
- "visual.merger.mlp.2.weight": "model-00001-of-00002.safetensors",
988
- "visual.patch_embed.proj.weight": "model-00001-of-00002.safetensors"
989
- }
990
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ImageDoctor/modeling_ImageDoctor.py DELETED
The diff for this file is too large to render. See raw diff
 
ImageDoctor/preprocessor_config.json DELETED
@@ -1,36 +0,0 @@
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_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": "Qwen2VLImageProcessorFast",
17
- "image_std": [
18
- 0.26862954,
19
- 0.26130258,
20
- 0.27577711
21
- ],
22
- "input_data_format": null,
23
- "max_pixels": 12845056,
24
- "merge_size": 2,
25
- "min_pixels": 3136,
26
- "patch_size": 14,
27
- "processor_class": "Qwen2_5_VLProcessor",
28
- "resample": 3,
29
- "rescale_factor": 0.00392156862745098,
30
- "return_tensors": null,
31
- "size": {
32
- "longest_edge": 12845056,
33
- "shortest_edge": 3136
34
- },
35
- "temporal_patch_size": 2
36
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ImageDoctor/special_tokens_map.json DELETED
@@ -1,33 +0,0 @@
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
- "<|misalignment|>",
17
- "<|artifact|>"
18
- ],
19
- "eos_token": {
20
- "content": "<|im_end|>",
21
- "lstrip": false,
22
- "normalized": false,
23
- "rstrip": false,
24
- "single_word": false
25
- },
26
- "pad_token": {
27
- "content": "<|endoftext|>",
28
- "lstrip": false,
29
- "normalized": false,
30
- "rstrip": false,
31
- "single_word": false
32
- }
33
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ImageDoctor/tokenizer.json DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:3f0a390600f1225d4752ef13378287db66fde45e725007b1fa5f3396a0be0109
3
- size 11422445
 
 
 
 
ImageDoctor/tokenizer_config.json DELETED
@@ -1,228 +0,0 @@
1
- {
2
- "add_bos_token": false,
3
- "add_prefix_space": false,
4
- "added_tokens_decoder": {
5
- "151643": {
6
- "content": "<|endoftext|>",
7
- "lstrip": false,
8
- "normalized": false,
9
- "rstrip": false,
10
- "single_word": false,
11
- "special": true
12
- },
13
- "151644": {
14
- "content": "<|im_start|>",
15
- "lstrip": false,
16
- "normalized": false,
17
- "rstrip": false,
18
- "single_word": false,
19
- "special": true
20
- },
21
- "151645": {
22
- "content": "<|im_end|>",
23
- "lstrip": false,
24
- "normalized": false,
25
- "rstrip": false,
26
- "single_word": false,
27
- "special": true
28
- },
29
- "151646": {
30
- "content": "<|object_ref_start|>",
31
- "lstrip": false,
32
- "normalized": false,
33
- "rstrip": false,
34
- "single_word": false,
35
- "special": true
36
- },
37
- "151647": {
38
- "content": "<|object_ref_end|>",
39
- "lstrip": false,
40
- "normalized": false,
41
- "rstrip": false,
42
- "single_word": false,
43
- "special": true
44
- },
45
- "151648": {
46
- "content": "<|box_start|>",
47
- "lstrip": false,
48
- "normalized": false,
49
- "rstrip": false,
50
- "single_word": false,
51
- "special": true
52
- },
53
- "151649": {
54
- "content": "<|box_end|>",
55
- "lstrip": false,
56
- "normalized": false,
57
- "rstrip": false,
58
- "single_word": false,
59
- "special": true
60
- },
61
- "151650": {
62
- "content": "<|quad_start|>",
63
- "lstrip": false,
64
- "normalized": false,
65
- "rstrip": false,
66
- "single_word": false,
67
- "special": true
68
- },
69
- "151651": {
70
- "content": "<|quad_end|>",
71
- "lstrip": false,
72
- "normalized": false,
73
- "rstrip": false,
74
- "single_word": false,
75
- "special": true
76
- },
77
- "151652": {
78
- "content": "<|vision_start|>",
79
- "lstrip": false,
80
- "normalized": false,
81
- "rstrip": false,
82
- "single_word": false,
83
- "special": true
84
- },
85
- "151653": {
86
- "content": "<|vision_end|>",
87
- "lstrip": false,
88
- "normalized": false,
89
- "rstrip": false,
90
- "single_word": false,
91
- "special": true
92
- },
93
- "151654": {
94
- "content": "<|vision_pad|>",
95
- "lstrip": false,
96
- "normalized": false,
97
- "rstrip": false,
98
- "single_word": false,
99
- "special": true
100
- },
101
- "151655": {
102
- "content": "<|image_pad|>",
103
- "lstrip": false,
104
- "normalized": false,
105
- "rstrip": false,
106
- "single_word": false,
107
- "special": true
108
- },
109
- "151656": {
110
- "content": "<|video_pad|>",
111
- "lstrip": false,
112
- "normalized": false,
113
- "rstrip": false,
114
- "single_word": false,
115
- "special": true
116
- },
117
- "151657": {
118
- "content": "<tool_call>",
119
- "lstrip": false,
120
- "normalized": false,
121
- "rstrip": false,
122
- "single_word": false,
123
- "special": false
124
- },
125
- "151658": {
126
- "content": "</tool_call>",
127
- "lstrip": false,
128
- "normalized": false,
129
- "rstrip": false,
130
- "single_word": false,
131
- "special": false
132
- },
133
- "151659": {
134
- "content": "<|fim_prefix|>",
135
- "lstrip": false,
136
- "normalized": false,
137
- "rstrip": false,
138
- "single_word": false,
139
- "special": false
140
- },
141
- "151660": {
142
- "content": "<|fim_middle|>",
143
- "lstrip": false,
144
- "normalized": false,
145
- "rstrip": false,
146
- "single_word": false,
147
- "special": false
148
- },
149
- "151661": {
150
- "content": "<|fim_suffix|>",
151
- "lstrip": false,
152
- "normalized": false,
153
- "rstrip": false,
154
- "single_word": false,
155
- "special": false
156
- },
157
- "151662": {
158
- "content": "<|fim_pad|>",
159
- "lstrip": false,
160
- "normalized": false,
161
- "rstrip": false,
162
- "single_word": false,
163
- "special": false
164
- },
165
- "151663": {
166
- "content": "<|repo_name|>",
167
- "lstrip": false,
168
- "normalized": false,
169
- "rstrip": false,
170
- "single_word": false,
171
- "special": false
172
- },
173
- "151664": {
174
- "content": "<|file_sep|>",
175
- "lstrip": false,
176
- "normalized": false,
177
- "rstrip": false,
178
- "single_word": false,
179
- "special": false
180
- },
181
- "151665": {
182
- "content": "<|misalignment|>",
183
- "lstrip": false,
184
- "normalized": false,
185
- "rstrip": false,
186
- "single_word": false,
187
- "special": true
188
- },
189
- "151666": {
190
- "content": "<|artifact|>",
191
- "lstrip": false,
192
- "normalized": false,
193
- "rstrip": false,
194
- "single_word": false,
195
- "special": true
196
- }
197
- },
198
- "additional_special_tokens": [
199
- "<|im_start|>",
200
- "<|im_end|>",
201
- "<|object_ref_start|>",
202
- "<|object_ref_end|>",
203
- "<|box_start|>",
204
- "<|box_end|>",
205
- "<|quad_start|>",
206
- "<|quad_end|>",
207
- "<|vision_start|>",
208
- "<|vision_end|>",
209
- "<|vision_pad|>",
210
- "<|image_pad|>",
211
- "<|video_pad|>",
212
- "<|misalignment|>",
213
- "<|artifact|>"
214
- ],
215
- "bos_token": null,
216
- "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
217
- "clean_up_tokenization_spaces": false,
218
- "eos_token": "<|im_end|>",
219
- "errors": "replace",
220
- "extra_special_tokens": {},
221
- "model_max_length": 131072,
222
- "pad_token": "<|endoftext|>",
223
- "padding_side": "right",
224
- "processor_class": "Qwen2_5_VLProcessor",
225
- "split_special_tokens": false,
226
- "tokenizer_class": "Qwen2Tokenizer",
227
- "unk_token": null
228
- }