Hugging Face's logo

infly
/
Infinity-Parser2-Pro

Safetensors
qwen3_5_moe
Eval Results
Model card Files
xet
 Community
zuminghuang commited on
Commit
913e162
·
verified ·
1 Parent(s): a1f46dc

Upload 6 files

Browse files
Files changed (7) hide show
  1. .gitattributes +1 -0
  2. chat_template.jinja +154 -0
  3. config.json +127 -0
  4. model.safetensors.index.json +1 -0
  5. processor_config.json +63 -0
  6. tokenizer.json +3 -0
  7. tokenizer_config.json +32 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
chat_template.jinja ADDED
@@ -0,0 +1,154 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- set image_count = namespace(value=0) %}
2
+ {%- set video_count = namespace(value=0) %}
3
+ {%- macro render_content(content, do_vision_count, is_system_content=false) %}
4
+ {%- if content is string %}
5
+ {{- content }}
6
+ {%- elif content is iterable and content is not mapping %}
7
+ {%- for item in content %}
8
+ {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
9
+ {%- if is_system_content %}
10
+ {{- raise_exception('System message cannot contain images.') }}
11
+ {%- endif %}
12
+ {%- if do_vision_count %}
13
+ {%- set image_count.value = image_count.value + 1 %}
14
+ {%- endif %}
15
+ {%- if add_vision_id %}
16
+ {{- 'Picture ' ~ image_count.value ~ ': ' }}
17
+ {%- endif %}
18
+ {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
19
+ {%- elif 'video' in item or item.type == 'video' %}
20
+ {%- if is_system_content %}
21
+ {{- raise_exception('System message cannot contain videos.') }}
22
+ {%- endif %}
23
+ {%- if do_vision_count %}
24
+ {%- set video_count.value = video_count.value + 1 %}
25
+ {%- endif %}
26
+ {%- if add_vision_id %}
27
+ {{- 'Video ' ~ video_count.value ~ ': ' }}
28
+ {%- endif %}
29
+ {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
30
+ {%- elif 'text' in item %}
31
+ {{- item.text }}
32
+ {%- else %}
33
+ {{- raise_exception('Unexpected item type in content.') }}
34
+ {%- endif %}
35
+ {%- endfor %}
36
+ {%- elif content is none or content is undefined %}
37
+ {{- '' }}
38
+ {%- else %}
39
+ {{- raise_exception('Unexpected content type.') }}
40
+ {%- endif %}
41
+ {%- endmacro %}
42
+ {%- if not messages %}
43
+ {{- raise_exception('No messages provided.') }}
44
+ {%- endif %}
45
+ {%- if tools and tools is iterable and tools is not mapping %}
46
+ {{- '<|im_start|>system\n' }}
47
+ {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
48
+ {%- for tool in tools %}
49
+ {{- "\n" }}
50
+ {{- tool | tojson }}
51
+ {%- endfor %}
52
+ {{- "\n</tools>" }}
53
+ {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
54
+ {%- if messages[0].role == 'system' %}
55
+ {%- set content = render_content(messages[0].content, false, true)|trim %}
56
+ {%- if content %}
57
+ {{- '\n\n' + content }}
58
+ {%- endif %}
59
+ {%- endif %}
60
+ {{- '<|im_end|>\n' }}
61
+ {%- else %}
62
+ {%- if messages[0].role == 'system' %}
63
+ {%- set content = render_content(messages[0].content, false, true)|trim %}
64
+ {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
65
+ {%- endif %}
66
+ {%- endif %}
67
+ {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
68
+ {%- for message in messages[::-1] %}
69
+ {%- set index = (messages|length - 1) - loop.index0 %}
70
+ {%- if ns.multi_step_tool and message.role == "user" %}
71
+ {%- set content = render_content(message.content, false)|trim %}
72
+ {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
73
+ {%- set ns.multi_step_tool = false %}
74
+ {%- set ns.last_query_index = index %}
75
+ {%- endif %}
76
+ {%- endif %}
77
+ {%- endfor %}
78
+ {%- if ns.multi_step_tool %}
79
+ {{- raise_exception('No user query found in messages.') }}
80
+ {%- endif %}
81
+ {%- for message in messages %}
82
+ {%- set content = render_content(message.content, true)|trim %}
83
+ {%- if message.role == "system" %}
84
+ {%- if not loop.first %}
85
+ {{- raise_exception('System message must be at the beginning.') }}
86
+ {%- endif %}
87
+ {%- elif message.role == "user" %}
88
+ {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
89
+ {%- elif message.role == "assistant" %}
90
+ {%- set reasoning_content = '' %}
91
+ {%- if message.reasoning_content is string %}
92
+ {%- set reasoning_content = message.reasoning_content %}
93
+ {%- else %}
94
+ {%- if '</think>' in content %}
95
+ {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
96
+ {%- set content = content.split('</think>')[-1].lstrip('\n') %}
97
+ {%- endif %}
98
+ {%- endif %}
99
+ {%- set reasoning_content = reasoning_content|trim %}
100
+ {%- if loop.index0 > ns.last_query_index %}
101
+ {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
102
+ {%- else %}
103
+ {{- '<|im_start|>' + message.role + '\n' + content }}
104
+ {%- endif %}
105
+ {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
106
+ {%- for tool_call in message.tool_calls %}
107
+ {%- if tool_call.function is defined %}
108
+ {%- set tool_call = tool_call.function %}
109
+ {%- endif %}
110
+ {%- if loop.first %}
111
+ {%- if content|trim %}
112
+ {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
113
+ {%- else %}
114
+ {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
115
+ {%- endif %}
116
+ {%- else %}
117
+ {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
118
+ {%- endif %}
119
+ {%- if tool_call.arguments is defined %}
120
+ {%- for args_name, args_value in tool_call.arguments|items %}
121
+ {{- '<parameter=' + args_name + '>\n' }}
122
+ {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
123
+ {{- args_value }}
124
+ {{- '\n</parameter>\n' }}
125
+ {%- endfor %}
126
+ {%- endif %}
127
+ {{- '</function>\n</tool_call>' }}
128
+ {%- endfor %}
129
+ {%- endif %}
130
+ {{- '<|im_end|>\n' }}
131
+ {%- elif message.role == "tool" %}
132
+ {%- if loop.previtem and loop.previtem.role != "tool" %}
133
+ {{- '<|im_start|>user' }}
134
+ {%- endif %}
135
+ {{- '\n<tool_response>\n' }}
136
+ {{- content }}
137
+ {{- '\n</tool_response>' }}
138
+ {%- if not loop.last and loop.nextitem.role != "tool" %}
139
+ {{- '<|im_end|>\n' }}
140
+ {%- elif loop.last %}
141
+ {{- '<|im_end|>\n' }}
142
+ {%- endif %}
143
+ {%- else %}
144
+ {{- raise_exception('Unexpected message role.') }}
145
+ {%- endif %}
146
+ {%- endfor %}
147
+ {%- if add_generation_prompt %}
148
+ {{- '<|im_start|>assistant\n' }}
149
+ {%- if enable_thinking is defined and enable_thinking is false %}
150
+ {{- '<think>\n\n</think>\n\n' }}
151
+ {%- else %}
152
+ {{- '<think>\n' }}
153
+ {%- endif %}
154
+ {%- endif %}
config.json ADDED
@@ -0,0 +1,127 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3_5MoeForConditionalGeneration"
4
+ ],
5
+ "bos_token_id": null,
6
+ "dtype": "bfloat16",
7
+ "eos_token_id": 248046,
8
+ "hidden_size": 2048,
9
+ "image_token_id": 248056,
10
+ "model_type": "qwen3_5_moe",
11
+ "pad_token_id": 248044,
12
+ "rope_theta": 10000000,
13
+ "text_config": {
14
+ "attention_bias": false,
15
+ "attention_dropout": 0.0,
16
+ "attn_output_gate": true,
17
+ "bos_token_id": null,
18
+ "dtype": "bfloat16",
19
+ "eos_token_id": 248044,
20
+ "full_attention_interval": 4,
21
+ "head_dim": 256,
22
+ "hidden_act": "silu",
23
+ "hidden_size": 2048,
24
+ "initializer_range": 0.02,
25
+ "layer_types": [
26
+ "linear_attention",
27
+ "linear_attention",
28
+ "linear_attention",
29
+ "full_attention",
30
+ "linear_attention",
31
+ "linear_attention",
32
+ "linear_attention",
33
+ "full_attention",
34
+ "linear_attention",
35
+ "linear_attention",
36
+ "linear_attention",
37
+ "full_attention",
38
+ "linear_attention",
39
+ "linear_attention",
40
+ "linear_attention",
41
+ "full_attention",
42
+ "linear_attention",
43
+ "linear_attention",
44
+ "linear_attention",
45
+ "full_attention",
46
+ "linear_attention",
47
+ "linear_attention",
48
+ "linear_attention",
49
+ "full_attention",
50
+ "linear_attention",
51
+ "linear_attention",
52
+ "linear_attention",
53
+ "full_attention",
54
+ "linear_attention",
55
+ "linear_attention",
56
+ "linear_attention",
57
+ "full_attention",
58
+ "linear_attention",
59
+ "linear_attention",
60
+ "linear_attention",
61
+ "full_attention",
62
+ "linear_attention",
63
+ "linear_attention",
64
+ "linear_attention",
65
+ "full_attention"
66
+ ],
67
+ "linear_conv_kernel_dim": 4,
68
+ "linear_key_head_dim": 128,
69
+ "linear_num_key_heads": 16,
70
+ "linear_num_value_heads": 32,
71
+ "linear_value_head_dim": 128,
72
+ "mamba_ssm_dtype": "float32",
73
+ "max_position_embeddings": 262144,
74
+ "mlp_only_layers": [],
75
+ "model_type": "qwen3_5_moe_text",
76
+ "moe_intermediate_size": 512,
77
+ "mtp_num_hidden_layers": 1,
78
+ "mtp_use_dedicated_embeddings": false,
79
+ "num_attention_heads": 16,
80
+ "num_experts": 256,
81
+ "num_experts_per_tok": 8,
82
+ "num_hidden_layers": 40,
83
+ "num_key_value_heads": 2,
84
+ "output_router_logits": false,
85
+ "pad_token_id": null,
86
+ "partial_rotary_factor": 0.25,
87
+ "rms_norm_eps": 1e-06,
88
+ "rope_parameters": {
89
+ "mrope_interleaved": true,
90
+ "mrope_section": [
91
+ 11,
92
+ 11,
93
+ 10
94
+ ],
95
+ "partial_rotary_factor": 0.25,
96
+ "rope_theta": 10000000,
97
+ "rope_type": "default"
98
+ },
99
+ "router_aux_loss_coef": 0.001,
100
+ "shared_expert_intermediate_size": 512,
101
+ "tie_word_embeddings": false,
102
+ "use_cache": true,
103
+ "vocab_size": 248320
104
+ },
105
+ "tie_word_embeddings": false,
106
+ "transformers_version": "5.3.0",
107
+ "video_token_id": 248057,
108
+ "vision_config": {
109
+ "deepstack_visual_indexes": [],
110
+ "depth": 27,
111
+ "dtype": "bfloat16",
112
+ "hidden_act": "gelu_pytorch_tanh",
113
+ "hidden_size": 1152,
114
+ "in_channels": 3,
115
+ "initializer_range": 0.02,
116
+ "intermediate_size": 4304,
117
+ "model_type": "qwen3_5_moe",
118
+ "num_heads": 16,
119
+ "num_position_embeddings": 2304,
120
+ "out_hidden_size": 2048,
121
+ "patch_size": 16,
122
+ "spatial_merge_size": 2,
123
+ "temporal_patch_size": 2
124
+ },
125
+ "vision_end_token_id": 248054,
126
+ "vision_start_token_id": 248053
127
+ }
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"total_size": 70214363872}, "weight_map": {"model.language_model.embed_tokens.weight": "model-00001-of-00015.safetensors", "model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00015.safetensors", "model.language_model.layers.0.linear_attn.A_log": "model-00001-of-00015.safetensors", "model.language_model.layers.0.linear_attn.conv1d.weight": "model-00001-of-00015.safetensors", "model.language_model.layers.0.linear_attn.dt_bias": "model-00001-of-00015.safetensors", "model.language_model.layers.0.linear_attn.in_proj_a.weight": "model-00001-of-00015.safetensors", "model.language_model.layers.0.linear_attn.in_proj_b.weight": "model-00001-of-00015.safetensors", "model.language_model.layers.0.linear_attn.in_proj_qkv.weight": "model-00001-of-00015.safetensors", "model.language_model.layers.0.linear_attn.in_proj_z.weight": "model-00001-of-00015.safetensors", "model.language_model.layers.0.linear_attn.norm.weight": "model-00001-of-00015.safetensors", "model.language_model.layers.0.linear_attn.out_proj.weight": "model-00001-of-00015.safetensors", "model.language_model.layers.0.mlp.gate.weight": "model-00001-of-00015.safetensors", "model.language_model.layers.0.mlp.shared_expert.down_proj.weight": "model-00001-of-00015.safetensors", "model.language_model.layers.0.mlp.shared_expert.gate_proj.weight": "model-00001-of-00015.safetensors", "model.language_model.layers.0.mlp.shared_expert.up_proj.weight": "model-00001-of-00015.safetensors", "model.language_model.layers.0.mlp.shared_expert_gate.weight": "model-00001-of-00015.safetensors", "model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00015.safetensors", "model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00015.safetensors", "model.language_model.layers.1.linear_attn.A_log": "model-00001-of-00015.safetensors", "model.language_model.layers.1.linear_attn.conv1d.weight": "model-00001-of-00015.safetensors", "model.language_model.layers.1.linear_attn.dt_bias": "model-00001-of-00015.safetensors", "model.language_model.layers.1.linear_attn.in_proj_a.weight": "model-00001-of-00015.safetensors", "model.language_model.layers.1.linear_attn.in_proj_b.weight": "model-00001-of-00015.safetensors", "model.language_model.layers.1.linear_attn.in_proj_qkv.weight": "model-00001-of-00015.safetensors", "model.language_model.layers.1.linear_attn.in_proj_z.weight": "model-00001-of-00015.safetensors", "model.language_model.layers.1.linear_attn.norm.weight": "model-00001-of-00015.safetensors", "model.language_model.layers.1.linear_attn.out_proj.weight": "model-00001-of-00015.safetensors", "model.language_model.layers.1.mlp.gate.weight": "model-00001-of-00015.safetensors", "model.language_model.layers.1.mlp.shared_expert.down_proj.weight": "model-00001-of-00015.safetensors", "model.language_model.layers.1.mlp.shared_expert.gate_proj.weight": "model-00001-of-00015.safetensors", "model.language_model.layers.1.mlp.shared_expert.up_proj.weight": "model-00001-of-00015.safetensors", "model.language_model.layers.1.mlp.shared_expert_gate.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.0.attn.proj.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.0.attn.proj.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.0.attn.qkv.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.0.attn.qkv.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.0.norm1.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.0.norm1.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.0.norm2.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.0.norm2.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.1.attn.proj.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.1.attn.proj.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.1.attn.qkv.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.1.attn.qkv.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.1.norm1.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.1.norm1.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.1.norm2.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.1.norm2.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.10.attn.proj.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.10.attn.proj.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.10.attn.qkv.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.10.attn.qkv.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.10.norm1.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.10.norm1.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.10.norm2.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.10.norm2.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.11.attn.proj.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.11.attn.proj.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.11.attn.qkv.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.11.attn.qkv.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.11.norm1.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.11.norm1.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.11.norm2.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.11.norm2.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.12.attn.proj.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.12.attn.proj.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.12.attn.qkv.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.12.attn.qkv.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.12.norm1.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.12.norm1.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.12.norm2.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.12.norm2.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.13.attn.proj.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.13.attn.proj.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.13.attn.qkv.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.13.attn.qkv.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.13.norm1.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.13.norm1.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.13.norm2.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.13.norm2.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.14.attn.proj.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.14.attn.proj.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.14.attn.qkv.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.14.attn.qkv.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.14.norm1.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.14.norm1.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.14.norm2.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.14.norm2.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.15.attn.proj.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.15.attn.proj.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.15.attn.qkv.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.15.attn.qkv.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.15.norm1.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.15.norm1.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.15.norm2.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.15.norm2.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.16.attn.proj.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.16.attn.proj.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.16.attn.qkv.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.16.attn.qkv.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.16.norm1.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.16.norm1.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.16.norm2.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.16.norm2.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.17.attn.proj.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.17.attn.proj.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.17.attn.qkv.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.17.attn.qkv.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.17.norm1.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.17.norm1.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.17.norm2.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.17.norm2.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.18.attn.proj.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.18.attn.proj.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.18.attn.qkv.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.18.attn.qkv.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.18.norm1.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.18.norm1.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.18.norm2.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.18.norm2.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.19.attn.proj.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.19.attn.proj.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.19.attn.qkv.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.19.attn.qkv.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.19.norm1.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.19.norm1.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.19.norm2.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.19.norm2.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.2.attn.proj.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.2.attn.proj.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.2.attn.qkv.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.2.attn.qkv.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.2.norm1.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.2.norm1.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.2.norm2.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.2.norm2.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.20.attn.proj.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.20.attn.proj.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.20.attn.qkv.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.20.attn.qkv.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.20.norm1.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.20.norm1.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.20.norm2.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.20.norm2.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.21.attn.proj.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.21.attn.proj.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.21.attn.qkv.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.21.attn.qkv.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.21.norm1.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.21.norm1.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.21.norm2.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.21.norm2.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.22.attn.proj.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.22.attn.proj.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.22.attn.qkv.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.22.attn.qkv.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.22.norm1.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.22.norm1.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.22.norm2.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.22.norm2.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.23.attn.proj.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.23.attn.proj.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.23.attn.qkv.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.23.attn.qkv.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.23.norm1.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.23.norm1.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.23.norm2.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.23.norm2.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.24.attn.proj.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.24.attn.proj.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.24.attn.qkv.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.24.attn.qkv.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.24.mlp.linear_fc1.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.24.mlp.linear_fc1.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.24.mlp.linear_fc2.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.24.mlp.linear_fc2.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.24.norm1.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.24.norm1.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.24.norm2.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.24.norm2.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.25.attn.proj.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.25.attn.proj.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.25.attn.qkv.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.25.attn.qkv.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.25.mlp.linear_fc1.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.25.mlp.linear_fc1.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.25.mlp.linear_fc2.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.25.mlp.linear_fc2.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.25.norm1.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.25.norm1.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.25.norm2.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.25.norm2.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.26.attn.proj.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.26.attn.proj.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.26.attn.qkv.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.26.attn.qkv.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.26.mlp.linear_fc1.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.26.mlp.linear_fc1.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.26.mlp.linear_fc2.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.26.mlp.linear_fc2.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.26.norm1.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.26.norm1.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.26.norm2.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.26.norm2.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.3.attn.proj.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.3.attn.proj.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.3.attn.qkv.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.3.attn.qkv.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.3.norm1.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.3.norm1.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.3.norm2.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.3.norm2.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.4.attn.proj.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.4.attn.proj.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.4.attn.qkv.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.4.attn.qkv.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.4.norm1.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.4.norm1.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.4.norm2.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.4.norm2.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.5.attn.proj.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.5.attn.proj.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.5.attn.qkv.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.5.attn.qkv.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.5.norm1.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.5.norm1.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.5.norm2.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.5.norm2.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.6.attn.proj.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.6.attn.proj.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.6.attn.qkv.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.6.attn.qkv.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.6.norm1.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.6.norm1.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.6.norm2.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.6.norm2.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.7.attn.proj.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.7.attn.proj.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.7.attn.qkv.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.7.attn.qkv.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.7.norm1.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.7.norm1.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.7.norm2.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.7.norm2.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.8.attn.proj.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.8.attn.proj.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.8.attn.qkv.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.8.attn.qkv.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.8.norm1.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.8.norm1.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.8.norm2.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.8.norm2.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.9.attn.proj.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.9.attn.proj.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.9.attn.qkv.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.9.attn.qkv.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.9.norm1.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.9.norm1.weight": "model-00001-of-00015.safetensors", "model.visual.blocks.9.norm2.bias": "model-00001-of-00015.safetensors", "model.visual.blocks.9.norm2.weight": "model-00001-of-00015.safetensors", "model.visual.merger.linear_fc1.bias": "model-00001-of-00015.safetensors", "model.visual.merger.linear_fc1.weight": "model-00001-of-00015.safetensors", "model.visual.merger.linear_fc2.bias": "model-00001-of-00015.safetensors", "model.visual.merger.linear_fc2.weight": "model-00001-of-00015.safetensors", "model.visual.merger.norm.bias": "model-00001-of-00015.safetensors", "model.visual.merger.norm.weight": "model-00001-of-00015.safetensors", "model.visual.patch_embed.proj.bias": "model-00001-of-00015.safetensors", "model.visual.patch_embed.proj.weight": "model-00001-of-00015.safetensors", "model.visual.pos_embed.weight": "model-00001-of-00015.safetensors", "model.language_model.layers.1.post_attention_layernorm.weight": "model-00002-of-00015.safetensors", "model.language_model.layers.2.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.language_model.layers.2.linear_attn.A_log": "model-00002-of-00015.safetensors", "model.language_model.layers.2.linear_attn.conv1d.weight": "model-00002-of-00015.safetensors", "model.language_model.layers.2.linear_attn.dt_bias": "model-00002-of-00015.safetensors", "model.language_model.layers.2.linear_attn.in_proj_a.weight": "model-00002-of-00015.safetensors", "model.language_model.layers.2.linear_attn.in_proj_b.weight": "model-00002-of-00015.safetensors", "model.language_model.layers.2.linear_attn.in_proj_qkv.weight": "model-00002-of-00015.safetensors", "model.language_model.layers.2.linear_attn.in_proj_z.weight": "model-00002-of-00015.safetensors", "model.language_model.layers.2.linear_attn.norm.weight": "model-00002-of-00015.safetensors", "model.language_model.layers.2.linear_attn.out_proj.weight": "model-00002-of-00015.safetensors", "model.language_model.layers.2.mlp.gate.weight": "model-00002-of-00015.safetensors", "model.language_model.layers.2.mlp.shared_expert.down_proj.weight": "model-00002-of-00015.safetensors", "model.language_model.layers.2.mlp.shared_expert.gate_proj.weight": "model-00002-of-00015.safetensors", "model.language_model.layers.2.mlp.shared_expert.up_proj.weight": "model-00002-of-00015.safetensors", "model.language_model.layers.2.mlp.shared_expert_gate.weight": "model-00002-of-00015.safetensors", "model.language_model.layers.2.post_attention_layernorm.weight": "model-00002-of-00015.safetensors", "model.language_model.layers.3.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.language_model.layers.3.mlp.gate.weight": "model-00002-of-00015.safetensors", "model.language_model.layers.3.mlp.shared_expert.down_proj.weight": "model-00002-of-00015.safetensors", "model.language_model.layers.3.mlp.shared_expert.gate_proj.weight": "model-00002-of-00015.safetensors", "model.language_model.layers.3.mlp.shared_expert.up_proj.weight": "model-00002-of-00015.safetensors", "model.language_model.layers.3.mlp.shared_expert_gate.weight": "model-00002-of-00015.safetensors", "model.language_model.layers.3.post_attention_layernorm.weight": "model-00002-of-00015.safetensors", "model.language_model.layers.3.self_attn.k_norm.weight": "model-00002-of-00015.safetensors", "model.language_model.layers.3.self_attn.k_proj.weight": "model-00002-of-00015.safetensors", "model.language_model.layers.3.self_attn.o_proj.weight": "model-00002-of-00015.safetensors", "model.language_model.layers.3.self_attn.q_norm.weight": "model-00002-of-00015.safetensors", "model.language_model.layers.3.self_attn.q_proj.weight": "model-00002-of-00015.safetensors", "model.language_model.layers.3.self_attn.v_proj.weight": "model-00002-of-00015.safetensors", "model.language_model.layers.4.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.language_model.layers.4.linear_attn.A_log": "model-00002-of-00015.safetensors", "model.language_model.layers.4.linear_attn.conv1d.weight": "model-00002-of-00015.safetensors", "model.language_model.layers.4.linear_attn.dt_bias": "model-00002-of-00015.safetensors", "model.language_model.layers.4.linear_attn.in_proj_a.weight": "model-00002-of-00015.safetensors", "model.language_model.layers.4.linear_attn.in_proj_b.weight": "model-00002-of-00015.safetensors", "model.language_model.layers.4.linear_attn.in_proj_qkv.weight": "model-00002-of-00015.safetensors", "model.language_model.layers.4.linear_attn.in_proj_z.weight": "model-00002-of-00015.safetensors", "model.language_model.layers.4.linear_attn.norm.weight": "model-00002-of-00015.safetensors", "model.language_model.layers.4.linear_attn.out_proj.weight": "model-00002-of-00015.safetensors", "model.language_model.layers.4.mlp.gate.weight": "model-00002-of-00015.safetensors", "model.language_model.layers.4.mlp.shared_expert.down_proj.weight": "model-00002-of-00015.safetensors", "model.language_model.layers.4.mlp.shared_expert.gate_proj.weight": "model-00002-of-00015.safetensors", "model.language_model.layers.4.mlp.shared_expert.up_proj.weight": "model-00002-of-00015.safetensors", "model.language_model.layers.4.mlp.shared_expert_gate.weight": "model-00002-of-00015.safetensors", "model.language_model.layers.4.post_attention_layernorm.weight": "model-00003-of-00015.safetensors", "model.language_model.layers.5.input_layernorm.weight": "model-00003-of-00015.safetensors", "model.language_model.layers.5.linear_attn.A_log": "model-00003-of-00015.safetensors", "model.language_model.layers.5.linear_attn.conv1d.weight": "model-00003-of-00015.safetensors", "model.language_model.layers.5.linear_attn.dt_bias": "model-00003-of-00015.safetensors", "model.language_model.layers.5.linear_attn.in_proj_a.weight": "model-00003-of-00015.safetensors", "model.language_model.layers.5.linear_attn.in_proj_b.weight": "model-00003-of-00015.safetensors", "model.language_model.layers.5.linear_attn.in_proj_qkv.weight": "model-00003-of-00015.safetensors", "model.language_model.layers.5.linear_attn.in_proj_z.weight": "model-00003-of-00015.safetensors", "model.language_model.layers.5.linear_attn.norm.weight": "model-00003-of-00015.safetensors", "model.language_model.layers.5.linear_attn.out_proj.weight": "model-00003-of-00015.safetensors", "model.language_model.layers.5.mlp.gate.weight": "model-00003-of-00015.safetensors", "model.language_model.layers.5.mlp.shared_expert.down_proj.weight": "model-00003-of-00015.safetensors", "model.language_model.layers.5.mlp.shared_expert.gate_proj.weight": "model-00003-of-00015.safetensors", "model.language_model.layers.5.mlp.shared_expert.up_proj.weight": "model-00003-of-00015.safetensors", "model.language_model.layers.5.mlp.shared_expert_gate.weight": "model-00003-of-00015.safetensors", "model.language_model.layers.5.post_attention_layernorm.weight": "model-00003-of-00015.safetensors", "model.language_model.layers.6.input_layernorm.weight": "model-00003-of-00015.safetensors", "model.language_model.layers.6.linear_attn.A_log": "model-00003-of-00015.safetensors", "model.language_model.layers.6.linear_attn.conv1d.weight": "model-00003-of-00015.safetensors", "model.language_model.layers.6.linear_attn.dt_bias": "model-00003-of-00015.safetensors", "model.language_model.layers.6.linear_attn.in_proj_a.weight": "model-00003-of-00015.safetensors", "model.language_model.layers.6.linear_attn.in_proj_b.weight": "model-00003-of-00015.safetensors", "model.language_model.layers.6.linear_attn.in_proj_qkv.weight": "model-00003-of-00015.safetensors", "model.language_model.layers.6.linear_attn.in_proj_z.weight": "model-00003-of-00015.safetensors", "model.language_model.layers.6.linear_attn.norm.weight": "model-00003-of-00015.safetensors", "model.language_model.layers.6.linear_attn.out_proj.weight": "model-00003-of-00015.safetensors", "model.language_model.layers.6.mlp.gate.weight": "model-00003-of-00015.safetensors", "model.language_model.layers.6.mlp.shared_expert.down_proj.weight": "model-00003-of-00015.safetensors", "model.language_model.layers.6.mlp.shared_expert.gate_proj.weight": "model-00003-of-00015.safetensors", "model.language_model.layers.6.mlp.shared_expert.up_proj.weight": "model-00003-of-00015.safetensors", "model.language_model.layers.6.mlp.shared_expert_gate.weight": "model-00003-of-00015.safetensors", "model.language_model.layers.6.post_attention_layernorm.weight": "model-00003-of-00015.safetensors", "model.language_model.layers.7.input_layernorm.weight": "model-00003-of-00015.safetensors", "model.language_model.layers.7.mlp.gate.weight": "model-00003-of-00015.safetensors", "model.language_model.layers.7.mlp.shared_expert.down_proj.weight": "model-00003-of-00015.safetensors", "model.language_model.layers.7.mlp.shared_expert.gate_proj.weight": "model-00003-of-00015.safetensors", "model.language_model.layers.7.mlp.shared_expert.up_proj.weight": "model-00003-of-00015.safetensors", "model.language_model.layers.7.mlp.shared_expert_gate.weight": "model-00003-of-00015.safetensors", "model.language_model.layers.7.self_attn.k_norm.weight": "model-00003-of-00015.safetensors", "model.language_model.layers.7.self_attn.k_proj.weight": "model-00003-of-00015.safetensors", "model.language_model.layers.7.self_attn.o_proj.weight": "model-00003-of-00015.safetensors", "model.language_model.layers.7.self_attn.q_norm.weight": "model-00003-of-00015.safetensors", "model.language_model.layers.7.self_attn.q_proj.weight": "model-00003-of-00015.safetensors", "model.language_model.layers.7.self_attn.v_proj.weight": "model-00003-of-00015.safetensors", "model.language_model.layers.10.input_layernorm.weight": "model-00004-of-00015.safetensors", "model.language_model.layers.10.linear_attn.A_log": "model-00004-of-00015.safetensors", "model.language_model.layers.10.linear_attn.conv1d.weight": "model-00004-of-00015.safetensors", "model.language_model.layers.10.linear_attn.dt_bias": "model-00004-of-00015.safetensors", "model.language_model.layers.10.linear_attn.in_proj_a.weight": "model-00004-of-00015.safetensors", "model.language_model.layers.10.linear_attn.in_proj_b.weight": "model-00004-of-00015.safetensors", "model.language_model.layers.10.linear_attn.in_proj_qkv.weight": "model-00004-of-00015.safetensors", "model.language_model.layers.10.linear_attn.in_proj_z.weight": "model-00004-of-00015.safetensors", "model.language_model.layers.10.linear_attn.norm.weight": "model-00004-of-00015.safetensors", "model.language_model.layers.10.linear_attn.out_proj.weight": "model-00004-of-00015.safetensors", "model.language_model.layers.10.mlp.gate.weight": "model-00004-of-00015.safetensors", "model.language_model.layers.10.mlp.shared_expert.down_proj.weight": "model-00004-of-00015.safetensors", "model.language_model.layers.10.mlp.shared_expert.gate_proj.weight": "model-00004-of-00015.safetensors", "model.language_model.layers.10.mlp.shared_expert.up_proj.weight": "model-00004-of-00015.safetensors", "model.language_model.layers.10.mlp.shared_expert_gate.weight": "model-00004-of-00015.safetensors", "model.language_model.layers.7.post_attention_layernorm.weight": "model-00004-of-00015.safetensors", "model.language_model.layers.8.input_layernorm.weight": "model-00004-of-00015.safetensors", "model.language_model.layers.8.linear_attn.A_log": "model-00004-of-00015.safetensors", "model.language_model.layers.8.linear_attn.conv1d.weight": "model-00004-of-00015.safetensors", "model.language_model.layers.8.linear_attn.dt_bias": "model-00004-of-00015.safetensors", "model.language_model.layers.8.linear_attn.in_proj_a.weight": "model-00004-of-00015.safetensors", "model.language_model.layers.8.linear_attn.in_proj_b.weight": "model-00004-of-00015.safetensors", "model.language_model.layers.8.linear_attn.in_proj_qkv.weight": "model-00004-of-00015.safetensors", "model.language_model.layers.8.linear_attn.in_proj_z.weight": "model-00004-of-00015.safetensors", "model.language_model.layers.8.linear_attn.norm.weight": "model-00004-of-00015.safetensors", "model.language_model.layers.8.linear_attn.out_proj.weight": "model-00004-of-00015.safetensors", "model.language_model.layers.8.mlp.gate.weight": "model-00004-of-00015.safetensors", "model.language_model.layers.8.mlp.shared_expert.down_proj.weight": "model-00004-of-00015.safetensors", "model.language_model.layers.8.mlp.shared_expert.gate_proj.weight": "model-00004-of-00015.safetensors", "model.language_model.layers.8.mlp.shared_expert.up_proj.weight": "model-00004-of-00015.safetensors", "model.language_model.layers.8.mlp.shared_expert_gate.weight": "model-00004-of-00015.safetensors", "model.language_model.layers.8.post_attention_layernorm.weight": "model-00004-of-00015.safetensors", "model.language_model.layers.9.input_layernorm.weight": "model-00004-of-00015.safetensors", "model.language_model.layers.9.linear_attn.A_log": "model-00004-of-00015.safetensors", "model.language_model.layers.9.linear_attn.conv1d.weight": "model-00004-of-00015.safetensors", "model.language_model.layers.9.linear_attn.dt_bias": "model-00004-of-00015.safetensors", "model.language_model.layers.9.linear_attn.in_proj_a.weight": "model-00004-of-00015.safetensors", "model.language_model.layers.9.linear_attn.in_proj_b.weight": "model-00004-of-00015.safetensors", "model.language_model.layers.9.linear_attn.in_proj_qkv.weight": "model-00004-of-00015.safetensors", "model.language_model.layers.9.linear_attn.in_proj_z.weight": "model-00004-of-00015.safetensors", "model.language_model.layers.9.linear_attn.norm.weight": "model-00004-of-00015.safetensors", "model.language_model.layers.9.linear_attn.out_proj.weight": "model-00004-of-00015.safetensors", "model.language_model.layers.9.mlp.gate.weight": "model-00004-of-00015.safetensors", "model.language_model.layers.9.mlp.shared_expert.down_proj.weight": "model-00004-of-00015.safetensors", "model.language_model.layers.9.mlp.shared_expert.gate_proj.weight": "model-00004-of-00015.safetensors", "model.language_model.layers.9.mlp.shared_expert.up_proj.weight": "model-00004-of-00015.safetensors", "model.language_model.layers.9.mlp.shared_expert_gate.weight": "model-00004-of-00015.safetensors", "model.language_model.layers.9.post_attention_layernorm.weight": "model-00004-of-00015.safetensors", "model.language_model.layers.10.post_attention_layernorm.weight": "model-00005-of-00015.safetensors", "model.language_model.layers.11.input_layernorm.weight": "model-00005-of-00015.safetensors", "model.language_model.layers.11.mlp.gate.weight": "model-00005-of-00015.safetensors", "model.language_model.layers.11.mlp.shared_expert.down_proj.weight": "model-00005-of-00015.safetensors", "model.language_model.layers.11.mlp.shared_expert.gate_proj.weight": "model-00005-of-00015.safetensors", "model.language_model.layers.11.mlp.shared_expert.up_proj.weight": "model-00005-of-00015.safetensors", "model.language_model.layers.11.mlp.shared_expert_gate.weight": "model-00005-of-00015.safetensors", "model.language_model.layers.11.post_attention_layernorm.weight": "model-00005-of-00015.safetensors", "model.language_model.layers.11.self_attn.k_norm.weight": "model-00005-of-00015.safetensors", "model.language_model.layers.11.self_attn.k_proj.weight": "model-00005-of-00015.safetensors", "model.language_model.layers.11.self_attn.o_proj.weight": "model-00005-of-00015.safetensors", "model.language_model.layers.11.self_attn.q_norm.weight": "model-00005-of-00015.safetensors", "model.language_model.layers.11.self_attn.q_proj.weight": "model-00005-of-00015.safetensors", "model.language_model.layers.11.self_attn.v_proj.weight": "model-00005-of-00015.safetensors", "model.language_model.layers.12.input_layernorm.weight": "model-00005-of-00015.safetensors", "model.language_model.layers.12.linear_attn.A_log": "model-00005-of-00015.safetensors", "model.language_model.layers.12.linear_attn.conv1d.weight": "model-00005-of-00015.safetensors", "model.language_model.layers.12.linear_attn.dt_bias": "model-00005-of-00015.safetensors", "model.language_model.layers.12.linear_attn.in_proj_a.weight": "model-00005-of-00015.safetensors", "model.language_model.layers.12.linear_attn.in_proj_b.weight": "model-00005-of-00015.safetensors", "model.language_model.layers.12.linear_attn.in_proj_qkv.weight": "model-00005-of-00015.safetensors", "model.language_model.layers.12.linear_attn.in_proj_z.weight": "model-00005-of-00015.safetensors", "model.language_model.layers.12.linear_attn.norm.weight": "model-00005-of-00015.safetensors", "model.language_model.layers.12.linear_attn.out_proj.weight": "model-00005-of-00015.safetensors", "model.language_model.layers.12.mlp.gate.weight": "model-00005-of-00015.safetensors", "model.language_model.layers.12.mlp.shared_expert.down_proj.weight": "model-00005-of-00015.safetensors", "model.language_model.layers.12.mlp.shared_expert.gate_proj.weight": "model-00005-of-00015.safetensors", "model.language_model.layers.12.mlp.shared_expert.up_proj.weight": "model-00005-of-00015.safetensors", "model.language_model.layers.12.mlp.shared_expert_gate.weight": "model-00005-of-00015.safetensors", "model.language_model.layers.12.post_attention_layernorm.weight": "model-00005-of-00015.safetensors", "model.language_model.layers.13.input_layernorm.weight": "model-00005-of-00015.safetensors", "model.language_model.layers.13.linear_attn.A_log": "model-00005-of-00015.safetensors", "model.language_model.layers.13.linear_attn.conv1d.weight": "model-00005-of-00015.safetensors", "model.language_model.layers.13.linear_attn.dt_bias": "model-00005-of-00015.safetensors", "model.language_model.layers.13.linear_attn.in_proj_a.weight": "model-00005-of-00015.safetensors", "model.language_model.layers.13.linear_attn.in_proj_b.weight": "model-00005-of-00015.safetensors", "model.language_model.layers.13.linear_attn.in_proj_qkv.weight": "model-00005-of-00015.safetensors", "model.language_model.layers.13.linear_attn.in_proj_z.weight": "model-00005-of-00015.safetensors", "model.language_model.layers.13.linear_attn.norm.weight": "model-00005-of-00015.safetensors", "model.language_model.layers.13.linear_attn.out_proj.weight": "model-00005-of-00015.safetensors", "model.language_model.layers.13.mlp.gate.weight": "model-00005-of-00015.safetensors", "model.language_model.layers.13.mlp.shared_expert.down_proj.weight": "model-00005-of-00015.safetensors", "model.language_model.layers.13.mlp.shared_expert.gate_proj.weight": "model-00005-of-00015.safetensors", "model.language_model.layers.13.mlp.shared_expert.up_proj.weight": "model-00005-of-00015.safetensors", "model.language_model.layers.13.mlp.shared_expert_gate.weight": "model-00005-of-00015.safetensors", "model.language_model.layers.13.post_attention_layernorm.weight": "model-00006-of-00015.safetensors", "model.language_model.layers.14.input_layernorm.weight": "model-00006-of-00015.safetensors", "model.language_model.layers.14.linear_attn.A_log": "model-00006-of-00015.safetensors", "model.language_model.layers.14.linear_attn.conv1d.weight": "model-00006-of-00015.safetensors", "model.language_model.layers.14.linear_attn.dt_bias": "model-00006-of-00015.safetensors", "model.language_model.layers.14.linear_attn.in_proj_a.weight": "model-00006-of-00015.safetensors", "model.language_model.layers.14.linear_attn.in_proj_b.weight": "model-00006-of-00015.safetensors", "model.language_model.layers.14.linear_attn.in_proj_qkv.weight": "model-00006-of-00015.safetensors", "model.language_model.layers.14.linear_attn.in_proj_z.weight": "model-00006-of-00015.safetensors", "model.language_model.layers.14.linear_attn.norm.weight": "model-00006-of-00015.safetensors", "model.language_model.layers.14.linear_attn.out_proj.weight": "model-00006-of-00015.safetensors", "model.language_model.layers.14.mlp.gate.weight": "model-00006-of-00015.safetensors", "model.language_model.layers.14.mlp.shared_expert.down_proj.weight": "model-00006-of-00015.safetensors", "model.language_model.layers.14.mlp.shared_expert.gate_proj.weight": "model-00006-of-00015.safetensors", "model.language_model.layers.14.mlp.shared_expert.up_proj.weight": "model-00006-of-00015.safetensors", "model.language_model.layers.14.mlp.shared_expert_gate.weight": "model-00006-of-00015.safetensors", "model.language_model.layers.14.post_attention_layernorm.weight": "model-00006-of-00015.safetensors", "model.language_model.layers.15.input_layernorm.weight": "model-00006-of-00015.safetensors", "model.language_model.layers.15.mlp.gate.weight": "model-00006-of-00015.safetensors", "model.language_model.layers.15.mlp.shared_expert.down_proj.weight": "model-00006-of-00015.safetensors", "model.language_model.layers.15.mlp.shared_expert.gate_proj.weight": "model-00006-of-00015.safetensors", "model.language_model.layers.15.mlp.shared_expert.up_proj.weight": "model-00006-of-00015.safetensors", "model.language_model.layers.15.mlp.shared_expert_gate.weight": "model-00006-of-00015.safetensors", "model.language_model.layers.15.post_attention_layernorm.weight": "model-00006-of-00015.safetensors", "model.language_model.layers.15.self_attn.k_norm.weight": "model-00006-of-00015.safetensors", "model.language_model.layers.15.self_attn.k_proj.weight": "model-00006-of-00015.safetensors", "model.language_model.layers.15.self_attn.o_proj.weight": "model-00006-of-00015.safetensors", "model.language_model.layers.15.self_attn.q_norm.weight": "model-00006-of-00015.safetensors", "model.language_model.layers.15.self_attn.q_proj.weight": "model-00006-of-00015.safetensors", "model.language_model.layers.15.self_attn.v_proj.weight": "model-00006-of-00015.safetensors", "model.language_model.layers.16.input_layernorm.weight": "model-00006-of-00015.safetensors", "model.language_model.layers.16.linear_attn.A_log": "model-00006-of-00015.safetensors", "model.language_model.layers.16.linear_attn.conv1d.weight": "model-00006-of-00015.safetensors", "model.language_model.layers.16.linear_attn.dt_bias": "model-00006-of-00015.safetensors", "model.language_model.layers.16.linear_attn.in_proj_a.weight": "model-00006-of-00015.safetensors", "model.language_model.layers.16.linear_attn.in_proj_b.weight": "model-00006-of-00015.safetensors", "model.language_model.layers.16.linear_attn.in_proj_qkv.weight": "model-00006-of-00015.safetensors", "model.language_model.layers.16.linear_attn.in_proj_z.weight": "model-00006-of-00015.safetensors", "model.language_model.layers.16.linear_attn.norm.weight": "model-00006-of-00015.safetensors", "model.language_model.layers.16.linear_attn.out_proj.weight": "model-00006-of-00015.safetensors", "model.language_model.layers.16.mlp.gate.weight": "model-00006-of-00015.safetensors", "model.language_model.layers.16.mlp.shared_expert.down_proj.weight": "model-00006-of-00015.safetensors", "model.language_model.layers.16.mlp.shared_expert.gate_proj.weight": "model-00006-of-00015.safetensors", "model.language_model.layers.16.mlp.shared_expert.up_proj.weight": "model-00006-of-00015.safetensors", "model.language_model.layers.16.mlp.shared_expert_gate.weight": "model-00006-of-00015.safetensors", "model.language_model.layers.0.mlp.experts.gate_up_proj": "model-00006-of-00015.safetensors", "model.language_model.layers.0.mlp.experts.down_proj": "model-00006-of-00015.safetensors", "model.language_model.layers.1.mlp.experts.gate_up_proj": "model-00006-of-00015.safetensors", "model.language_model.layers.1.mlp.experts.down_proj": "model-00006-of-00015.safetensors", "model.language_model.layers.2.mlp.experts.gate_up_proj": "model-00006-of-00015.safetensors", "model.language_model.layers.2.mlp.experts.down_proj": "model-00006-of-00015.safetensors", "model.language_model.layers.3.mlp.experts.gate_up_proj": "model-00006-of-00015.safetensors", "model.language_model.layers.3.mlp.experts.down_proj": "model-00006-of-00015.safetensors", "model.language_model.layers.4.mlp.experts.gate_up_proj": "model-00006-of-00015.safetensors", "model.language_model.layers.4.mlp.experts.down_proj": "model-00006-of-00015.safetensors", "model.language_model.layers.5.mlp.experts.gate_up_proj": "model-00006-of-00015.safetensors", "model.language_model.layers.5.mlp.experts.down_proj": "model-00006-of-00015.safetensors", "model.language_model.layers.6.mlp.experts.gate_up_proj": "model-00006-of-00015.safetensors", "model.language_model.layers.6.mlp.experts.down_proj": "model-00006-of-00015.safetensors", "model.language_model.layers.7.mlp.experts.gate_up_proj": "model-00006-of-00015.safetensors", "model.language_model.layers.7.mlp.experts.down_proj": "model-00006-of-00015.safetensors", "model.language_model.layers.8.mlp.experts.gate_up_proj": "model-00006-of-00015.safetensors", "model.language_model.layers.8.mlp.experts.down_proj": "model-00006-of-00015.safetensors", "model.language_model.layers.9.mlp.experts.gate_up_proj": "model-00006-of-00015.safetensors", "model.language_model.layers.9.mlp.experts.down_proj": "model-00006-of-00015.safetensors", "model.language_model.layers.10.mlp.experts.gate_up_proj": "model-00006-of-00015.safetensors", "model.language_model.layers.10.mlp.experts.down_proj": "model-00006-of-00015.safetensors", "model.language_model.layers.11.mlp.experts.gate_up_proj": "model-00006-of-00015.safetensors", "model.language_model.layers.11.mlp.experts.down_proj": "model-00006-of-00015.safetensors", "model.language_model.layers.12.mlp.experts.gate_up_proj": "model-00006-of-00015.safetensors", "model.language_model.layers.12.mlp.experts.down_proj": "model-00006-of-00015.safetensors", "model.language_model.layers.13.mlp.experts.gate_up_proj": "model-00006-of-00015.safetensors", "model.language_model.layers.13.mlp.experts.down_proj": "model-00006-of-00015.safetensors", "model.language_model.layers.14.mlp.experts.gate_up_proj": "model-00006-of-00015.safetensors", "model.language_model.layers.14.mlp.experts.down_proj": "model-00006-of-00015.safetensors", "model.language_model.layers.15.mlp.experts.gate_up_proj": "model-00006-of-00015.safetensors", "model.language_model.layers.15.mlp.experts.down_proj": "model-00006-of-00015.safetensors", "model.language_model.layers.16.mlp.experts.gate_up_proj": "model-00006-of-00015.safetensors", "model.language_model.layers.16.mlp.experts.down_proj": "model-00006-of-00015.safetensors", "model.language_model.layers.17.mlp.experts.gate_up_proj": "model-00006-of-00015.safetensors", "model.language_model.layers.17.mlp.experts.down_proj": "model-00006-of-00015.safetensors", "model.language_model.layers.18.mlp.experts.gate_up_proj": "model-00006-of-00015.safetensors", "model.language_model.layers.18.mlp.experts.down_proj": "model-00006-of-00015.safetensors", "model.language_model.layers.19.mlp.experts.gate_up_proj": "model-00006-of-00015.safetensors", "model.language_model.layers.19.mlp.experts.down_proj": "model-00006-of-00015.safetensors", "model.language_model.layers.16.post_attention_layernorm.weight": "model-00007-of-00015.safetensors", "model.language_model.layers.17.input_layernorm.weight": "model-00007-of-00015.safetensors", "model.language_model.layers.17.linear_attn.A_log": "model-00007-of-00015.safetensors", "model.language_model.layers.17.linear_attn.conv1d.weight": "model-00007-of-00015.safetensors", "model.language_model.layers.17.linear_attn.dt_bias": "model-00007-of-00015.safetensors", "model.language_model.layers.17.linear_attn.in_proj_a.weight": "model-00007-of-00015.safetensors", "model.language_model.layers.17.linear_attn.in_proj_b.weight": "model-00007-of-00015.safetensors", "model.language_model.layers.17.linear_attn.in_proj_qkv.weight": "model-00007-of-00015.safetensors", "model.language_model.layers.17.linear_attn.in_proj_z.weight": "model-00007-of-00015.safetensors", "model.language_model.layers.17.linear_attn.norm.weight": "model-00007-of-00015.safetensors", "model.language_model.layers.17.linear_attn.out_proj.weight": "model-00007-of-00015.safetensors", "model.language_model.layers.17.mlp.gate.weight": "model-00007-of-00015.safetensors", "model.language_model.layers.17.mlp.shared_expert.down_proj.weight": "model-00007-of-00015.safetensors", "model.language_model.layers.17.mlp.shared_expert.gate_proj.weight": "model-00007-of-00015.safetensors", "model.language_model.layers.17.mlp.shared_expert.up_proj.weight": "model-00007-of-00015.safetensors", "model.language_model.layers.17.mlp.shared_expert_gate.weight": "model-00007-of-00015.safetensors", "model.language_model.layers.17.post_attention_layernorm.weight": "model-00007-of-00015.safetensors", "model.language_model.layers.18.input_layernorm.weight": "model-00007-of-00015.safetensors", "model.language_model.layers.18.linear_attn.A_log": "model-00007-of-00015.safetensors", "model.language_model.layers.18.linear_attn.conv1d.weight": "model-00007-of-00015.safetensors", "model.language_model.layers.18.linear_attn.dt_bias": "model-00007-of-00015.safetensors", "model.language_model.layers.18.linear_attn.in_proj_a.weight": "model-00007-of-00015.safetensors", "model.language_model.layers.18.linear_attn.in_proj_b.weight": "model-00007-of-00015.safetensors", "model.language_model.layers.18.linear_attn.in_proj_qkv.weight": "model-00007-of-00015.safetensors", "model.language_model.layers.18.linear_attn.in_proj_z.weight": "model-00007-of-00015.safetensors", "model.language_model.layers.18.linear_attn.norm.weight": "model-00007-of-00015.safetensors", "model.language_model.layers.18.linear_attn.out_proj.weight": "model-00007-of-00015.safetensors", "model.language_model.layers.18.mlp.gate.weight": "model-00007-of-00015.safetensors", "model.language_model.layers.18.mlp.shared_expert.down_proj.weight": "model-00007-of-00015.safetensors", "model.language_model.layers.18.mlp.shared_expert.gate_proj.weight": "model-00007-of-00015.safetensors", "model.language_model.layers.18.mlp.shared_expert.up_proj.weight": "model-00007-of-00015.safetensors", "model.language_model.layers.18.mlp.shared_expert_gate.weight": "model-00007-of-00015.safetensors", "model.language_model.layers.18.post_attention_layernorm.weight": "model-00007-of-00015.safetensors", "model.language_model.layers.19.input_layernorm.weight": "model-00007-of-00015.safetensors", "model.language_model.layers.19.mlp.gate.weight": "model-00007-of-00015.safetensors", "model.language_model.layers.19.mlp.shared_expert.down_proj.weight": "model-00007-of-00015.safetensors", "model.language_model.layers.19.mlp.shared_expert.gate_proj.weight": "model-00007-of-00015.safetensors", "model.language_model.layers.19.mlp.shared_expert.up_proj.weight": "model-00007-of-00015.safetensors", "model.language_model.layers.19.mlp.shared_expert_gate.weight": "model-00007-of-00015.safetensors", "model.language_model.layers.19.self_attn.k_norm.weight": "model-00007-of-00015.safetensors", "model.language_model.layers.19.self_attn.k_proj.weight": "model-00007-of-00015.safetensors", "model.language_model.layers.19.self_attn.o_proj.weight": "model-00007-of-00015.safetensors", "model.language_model.layers.19.self_attn.q_norm.weight": "model-00007-of-00015.safetensors", "model.language_model.layers.19.self_attn.q_proj.weight": "model-00007-of-00015.safetensors", "model.language_model.layers.19.self_attn.v_proj.weight": "model-00007-of-00015.safetensors", "model.language_model.layers.20.mlp.experts.gate_up_proj": "model-00007-of-00015.safetensors", "model.language_model.layers.20.mlp.experts.down_proj": "model-00007-of-00015.safetensors", "model.language_model.layers.21.mlp.experts.gate_up_proj": "model-00007-of-00015.safetensors", "model.language_model.layers.21.mlp.experts.down_proj": "model-00007-of-00015.safetensors", "model.language_model.layers.22.mlp.experts.gate_up_proj": "model-00007-of-00015.safetensors", "model.language_model.layers.22.mlp.experts.down_proj": "model-00007-of-00015.safetensors", "model.language_model.layers.23.mlp.experts.gate_up_proj": "model-00007-of-00015.safetensors", "model.language_model.layers.23.mlp.experts.down_proj": "model-00007-of-00015.safetensors", "model.language_model.layers.24.mlp.experts.gate_up_proj": "model-00007-of-00015.safetensors", "model.language_model.layers.24.mlp.experts.down_proj": "model-00007-of-00015.safetensors", "model.language_model.layers.25.mlp.experts.gate_up_proj": "model-00007-of-00015.safetensors", "model.language_model.layers.25.mlp.experts.down_proj": "model-00007-of-00015.safetensors", "model.language_model.layers.26.mlp.experts.gate_up_proj": "model-00007-of-00015.safetensors", "model.language_model.layers.26.mlp.experts.down_proj": "model-00007-of-00015.safetensors", "model.language_model.layers.27.mlp.experts.gate_up_proj": "model-00007-of-00015.safetensors", "model.language_model.layers.27.mlp.experts.down_proj": "model-00007-of-00015.safetensors", "model.language_model.layers.28.mlp.experts.gate_up_proj": "model-00007-of-00015.safetensors", "model.language_model.layers.28.mlp.experts.down_proj": "model-00007-of-00015.safetensors", "model.language_model.layers.29.mlp.experts.gate_up_proj": "model-00007-of-00015.safetensors", "model.language_model.layers.29.mlp.experts.down_proj": "model-00007-of-00015.safetensors", "model.language_model.layers.30.mlp.experts.gate_up_proj": "model-00007-of-00015.safetensors", "model.language_model.layers.30.mlp.experts.down_proj": "model-00007-of-00015.safetensors", "model.language_model.layers.31.mlp.experts.gate_up_proj": "model-00007-of-00015.safetensors", "model.language_model.layers.31.mlp.experts.down_proj": "model-00007-of-00015.safetensors", "model.language_model.layers.32.mlp.experts.gate_up_proj": "model-00007-of-00015.safetensors", "model.language_model.layers.32.mlp.experts.down_proj": "model-00007-of-00015.safetensors", "model.language_model.layers.33.mlp.experts.gate_up_proj": "model-00007-of-00015.safetensors", "model.language_model.layers.33.mlp.experts.down_proj": "model-00007-of-00015.safetensors", "model.language_model.layers.34.mlp.experts.gate_up_proj": "model-00007-of-00015.safetensors", "model.language_model.layers.34.mlp.experts.down_proj": "model-00007-of-00015.safetensors", "model.language_model.layers.35.mlp.experts.gate_up_proj": "model-00007-of-00015.safetensors", "model.language_model.layers.35.mlp.experts.down_proj": "model-00007-of-00015.safetensors", "model.language_model.layers.36.mlp.experts.gate_up_proj": "model-00007-of-00015.safetensors", "model.language_model.layers.36.mlp.experts.down_proj": "model-00007-of-00015.safetensors", "model.language_model.layers.37.mlp.experts.gate_up_proj": "model-00007-of-00015.safetensors", "model.language_model.layers.37.mlp.experts.down_proj": "model-00007-of-00015.safetensors", "model.language_model.layers.38.mlp.experts.gate_up_proj": "model-00007-of-00015.safetensors", "model.language_model.layers.38.mlp.experts.down_proj": "model-00007-of-00015.safetensors", "model.language_model.layers.39.mlp.experts.gate_up_proj": "model-00007-of-00015.safetensors", "model.language_model.layers.39.mlp.experts.down_proj": "model-00007-of-00015.safetensors", "model.language_model.layers.19.post_attention_layernorm.weight": "model-00008-of-00015.safetensors", "model.language_model.layers.20.input_layernorm.weight": "model-00008-of-00015.safetensors", "model.language_model.layers.20.linear_attn.A_log": "model-00008-of-00015.safetensors", "model.language_model.layers.20.linear_attn.conv1d.weight": "model-00008-of-00015.safetensors", "model.language_model.layers.20.linear_attn.dt_bias": "model-00008-of-00015.safetensors", "model.language_model.layers.20.linear_attn.in_proj_a.weight": "model-00008-of-00015.safetensors", "model.language_model.layers.20.linear_attn.in_proj_b.weight": "model-00008-of-00015.safetensors", "model.language_model.layers.20.linear_attn.in_proj_qkv.weight": "model-00008-of-00015.safetensors", "model.language_model.layers.20.linear_attn.in_proj_z.weight": "model-00008-of-00015.safetensors", "model.language_model.layers.20.linear_attn.norm.weight": "model-00008-of-00015.safetensors", "model.language_model.layers.20.linear_attn.out_proj.weight": "model-00008-of-00015.safetensors", "model.language_model.layers.20.mlp.gate.weight": "model-00008-of-00015.safetensors", "model.language_model.layers.20.mlp.shared_expert.down_proj.weight": "model-00008-of-00015.safetensors", "model.language_model.layers.20.mlp.shared_expert.gate_proj.weight": "model-00008-of-00015.safetensors", "model.language_model.layers.20.mlp.shared_expert.up_proj.weight": "model-00008-of-00015.safetensors", "model.language_model.layers.20.mlp.shared_expert_gate.weight": "model-00008-of-00015.safetensors", "model.language_model.layers.20.post_attention_layernorm.weight": "model-00008-of-00015.safetensors", "model.language_model.layers.21.input_layernorm.weight": "model-00008-of-00015.safetensors", "model.language_model.layers.21.linear_attn.A_log": "model-00008-of-00015.safetensors", "model.language_model.layers.21.linear_attn.conv1d.weight": "model-00008-of-00015.safetensors", "model.language_model.layers.21.linear_attn.dt_bias": "model-00008-of-00015.safetensors", "model.language_model.layers.21.linear_attn.in_proj_a.weight": "model-00008-of-00015.safetensors", "model.language_model.layers.21.linear_attn.in_proj_b.weight": "model-00008-of-00015.safetensors", "model.language_model.layers.21.linear_attn.in_proj_qkv.weight": "model-00008-of-00015.safetensors", "model.language_model.layers.21.linear_attn.in_proj_z.weight": "model-00008-of-00015.safetensors", "model.language_model.layers.21.linear_attn.norm.weight": "model-00008-of-00015.safetensors", "model.language_model.layers.21.linear_attn.out_proj.weight": "model-00008-of-00015.safetensors", "model.language_model.layers.21.mlp.gate.weight": "model-00008-of-00015.safetensors", "model.language_model.layers.21.mlp.shared_expert.down_proj.weight": "model-00008-of-00015.safetensors", "model.language_model.layers.21.mlp.shared_expert.gate_proj.weight": "model-00008-of-00015.safetensors", "model.language_model.layers.21.mlp.shared_expert.up_proj.weight": "model-00008-of-00015.safetensors", "model.language_model.layers.21.mlp.shared_expert_gate.weight": "model-00008-of-00015.safetensors", "model.language_model.layers.21.post_attention_layernorm.weight": "model-00008-of-00015.safetensors", "model.language_model.layers.22.input_layernorm.weight": "model-00008-of-00015.safetensors", "model.language_model.layers.22.linear_attn.A_log": "model-00008-of-00015.safetensors", "model.language_model.layers.22.linear_attn.conv1d.weight": "model-00008-of-00015.safetensors", "model.language_model.layers.22.linear_attn.dt_bias": "model-00008-of-00015.safetensors", "model.language_model.layers.22.linear_attn.in_proj_a.weight": "model-00008-of-00015.safetensors", "model.language_model.layers.22.linear_attn.in_proj_b.weight": "model-00008-of-00015.safetensors", "model.language_model.layers.22.linear_attn.in_proj_qkv.weight": "model-00008-of-00015.safetensors", "model.language_model.layers.22.linear_attn.in_proj_z.weight": "model-00008-of-00015.safetensors", "model.language_model.layers.22.linear_attn.norm.weight": "model-00008-of-00015.safetensors", "model.language_model.layers.22.linear_attn.out_proj.weight": "model-00008-of-00015.safetensors", "model.language_model.layers.22.mlp.gate.weight": "model-00008-of-00015.safetensors", "model.language_model.layers.22.mlp.shared_expert.down_proj.weight": "model-00008-of-00015.safetensors", "model.language_model.layers.22.mlp.shared_expert.gate_proj.weight": "model-00008-of-00015.safetensors", "model.language_model.layers.22.mlp.shared_expert.up_proj.weight": "model-00008-of-00015.safetensors", "model.language_model.layers.22.mlp.shared_expert_gate.weight": "model-00008-of-00015.safetensors", "model.language_model.layers.22.post_attention_layernorm.weight": "model-00009-of-00015.safetensors", "model.language_model.layers.23.input_layernorm.weight": "model-00009-of-00015.safetensors", "model.language_model.layers.23.mlp.gate.weight": "model-00009-of-00015.safetensors", "model.language_model.layers.23.mlp.shared_expert.down_proj.weight": "model-00009-of-00015.safetensors", "model.language_model.layers.23.mlp.shared_expert.gate_proj.weight": "model-00009-of-00015.safetensors", "model.language_model.layers.23.mlp.shared_expert.up_proj.weight": "model-00009-of-00015.safetensors", "model.language_model.layers.23.mlp.shared_expert_gate.weight": "model-00009-of-00015.safetensors", "model.language_model.layers.23.post_attention_layernorm.weight": "model-00009-of-00015.safetensors", "model.language_model.layers.23.self_attn.k_norm.weight": "model-00009-of-00015.safetensors", "model.language_model.layers.23.self_attn.k_proj.weight": "model-00009-of-00015.safetensors", "model.language_model.layers.23.self_attn.o_proj.weight": "model-00009-of-00015.safetensors", "model.language_model.layers.23.self_attn.q_norm.weight": "model-00009-of-00015.safetensors", "model.language_model.layers.23.self_attn.q_proj.weight": "model-00009-of-00015.safetensors", "model.language_model.layers.23.self_attn.v_proj.weight": "model-00009-of-00015.safetensors", "model.language_model.layers.24.input_layernorm.weight": "model-00009-of-00015.safetensors", "model.language_model.layers.24.linear_attn.A_log": "model-00009-of-00015.safetensors", "model.language_model.layers.24.linear_attn.conv1d.weight": "model-00009-of-00015.safetensors", "model.language_model.layers.24.linear_attn.dt_bias": "model-00009-of-00015.safetensors", "model.language_model.layers.24.linear_attn.in_proj_a.weight": "model-00009-of-00015.safetensors", "model.language_model.layers.24.linear_attn.in_proj_b.weight": "model-00009-of-00015.safetensors", "model.language_model.layers.24.linear_attn.in_proj_qkv.weight": "model-00009-of-00015.safetensors", "model.language_model.layers.24.linear_attn.in_proj_z.weight": "model-00009-of-00015.safetensors", "model.language_model.layers.24.linear_attn.norm.weight": "model-00009-of-00015.safetensors", "model.language_model.layers.24.linear_attn.out_proj.weight": "model-00009-of-00015.safetensors", "model.language_model.layers.24.mlp.gate.weight": "model-00009-of-00015.safetensors", "model.language_model.layers.24.mlp.shared_expert.down_proj.weight": "model-00009-of-00015.safetensors", "model.language_model.layers.24.mlp.shared_expert.gate_proj.weight": "model-00009-of-00015.safetensors", "model.language_model.layers.24.mlp.shared_expert.up_proj.weight": "model-00009-of-00015.safetensors", "model.language_model.layers.24.mlp.shared_expert_gate.weight": "model-00009-of-00015.safetensors", "model.language_model.layers.24.post_attention_layernorm.weight": "model-00009-of-00015.safetensors", "model.language_model.layers.25.input_layernorm.weight": "model-00009-of-00015.safetensors", "model.language_model.layers.25.linear_attn.A_log": "model-00009-of-00015.safetensors", "model.language_model.layers.25.linear_attn.conv1d.weight": "model-00009-of-00015.safetensors", "model.language_model.layers.25.linear_attn.dt_bias": "model-00009-of-00015.safetensors", "model.language_model.layers.25.linear_attn.in_proj_a.weight": "model-00009-of-00015.safetensors", "model.language_model.layers.25.linear_attn.in_proj_b.weight": "model-00009-of-00015.safetensors", "model.language_model.layers.25.linear_attn.in_proj_qkv.weight": "model-00009-of-00015.safetensors", "model.language_model.layers.25.linear_attn.in_proj_z.weight": "model-00009-of-00015.safetensors", "model.language_model.layers.25.linear_attn.norm.weight": "model-00009-of-00015.safetensors", "model.language_model.layers.25.linear_attn.out_proj.weight": "model-00009-of-00015.safetensors", "model.language_model.layers.25.mlp.gate.weight": "model-00009-of-00015.safetensors", "model.language_model.layers.25.mlp.shared_expert.down_proj.weight": "model-00009-of-00015.safetensors", "model.language_model.layers.25.mlp.shared_expert.gate_proj.weight": "model-00009-of-00015.safetensors", "model.language_model.layers.25.mlp.shared_expert.up_proj.weight": "model-00009-of-00015.safetensors", "model.language_model.layers.25.mlp.shared_expert_gate.weight": "model-00009-of-00015.safetensors", "model.language_model.layers.25.post_attention_layernorm.weight": "model-00010-of-00015.safetensors", "model.language_model.layers.26.input_layernorm.weight": "model-00010-of-00015.safetensors", "model.language_model.layers.26.linear_attn.A_log": "model-00010-of-00015.safetensors", "model.language_model.layers.26.linear_attn.conv1d.weight": "model-00010-of-00015.safetensors", "model.language_model.layers.26.linear_attn.dt_bias": "model-00010-of-00015.safetensors", "model.language_model.layers.26.linear_attn.in_proj_a.weight": "model-00010-of-00015.safetensors", "model.language_model.layers.26.linear_attn.in_proj_b.weight": "model-00010-of-00015.safetensors", "model.language_model.layers.26.linear_attn.in_proj_qkv.weight": "model-00010-of-00015.safetensors", "model.language_model.layers.26.linear_attn.in_proj_z.weight": "model-00010-of-00015.safetensors", "model.language_model.layers.26.linear_attn.norm.weight": "model-00010-of-00015.safetensors", "model.language_model.layers.26.linear_attn.out_proj.weight": "model-00010-of-00015.safetensors", "model.language_model.layers.26.mlp.gate.weight": "model-00010-of-00015.safetensors", "model.language_model.layers.26.mlp.shared_expert.down_proj.weight": "model-00010-of-00015.safetensors", "model.language_model.layers.26.mlp.shared_expert.gate_proj.weight": "model-00010-of-00015.safetensors", "model.language_model.layers.26.mlp.shared_expert.up_proj.weight": "model-00010-of-00015.safetensors", "model.language_model.layers.26.mlp.shared_expert_gate.weight": "model-00010-of-00015.safetensors", "model.language_model.layers.26.post_attention_layernorm.weight": "model-00010-of-00015.safetensors", "model.language_model.layers.27.input_layernorm.weight": "model-00010-of-00015.safetensors", "model.language_model.layers.27.mlp.gate.weight": "model-00010-of-00015.safetensors", "model.language_model.layers.27.mlp.shared_expert.down_proj.weight": "model-00010-of-00015.safetensors", "model.language_model.layers.27.mlp.shared_expert.gate_proj.weight": "model-00010-of-00015.safetensors", "model.language_model.layers.27.mlp.shared_expert.up_proj.weight": "model-00010-of-00015.safetensors", "model.language_model.layers.27.mlp.shared_expert_gate.weight": "model-00010-of-00015.safetensors", "model.language_model.layers.27.post_attention_layernorm.weight": "model-00010-of-00015.safetensors", "model.language_model.layers.27.self_attn.k_norm.weight": "model-00010-of-00015.safetensors", "model.language_model.layers.27.self_attn.k_proj.weight": "model-00010-of-00015.safetensors", "model.language_model.layers.27.self_attn.o_proj.weight": "model-00010-of-00015.safetensors", "model.language_model.layers.27.self_attn.q_norm.weight": "model-00010-of-00015.safetensors", "model.language_model.layers.27.self_attn.q_proj.weight": "model-00010-of-00015.safetensors", "model.language_model.layers.27.self_attn.v_proj.weight": "model-00010-of-00015.safetensors", "model.language_model.layers.28.input_layernorm.weight": "model-00010-of-00015.safetensors", "model.language_model.layers.28.linear_attn.A_log": "model-00010-of-00015.safetensors", "model.language_model.layers.28.linear_attn.conv1d.weight": "model-00010-of-00015.safetensors", "model.language_model.layers.28.linear_attn.dt_bias": "model-00010-of-00015.safetensors", "model.language_model.layers.28.linear_attn.in_proj_a.weight": "model-00010-of-00015.safetensors", "model.language_model.layers.28.linear_attn.in_proj_b.weight": "model-00010-of-00015.safetensors", "model.language_model.layers.28.linear_attn.in_proj_qkv.weight": "model-00010-of-00015.safetensors", "model.language_model.layers.28.linear_attn.in_proj_z.weight": "model-00010-of-00015.safetensors", "model.language_model.layers.28.linear_attn.norm.weight": "model-00010-of-00015.safetensors", "model.language_model.layers.28.linear_attn.out_proj.weight": "model-00010-of-00015.safetensors", "model.language_model.layers.28.mlp.gate.weight": "model-00010-of-00015.safetensors", "model.language_model.layers.28.mlp.shared_expert.down_proj.weight": "model-00010-of-00015.safetensors", "model.language_model.layers.28.mlp.shared_expert.gate_proj.weight": "model-00010-of-00015.safetensors", "model.language_model.layers.28.mlp.shared_expert.up_proj.weight": "model-00010-of-00015.safetensors", "model.language_model.layers.28.mlp.shared_expert_gate.weight": "model-00010-of-00015.safetensors", "model.language_model.layers.28.post_attention_layernorm.weight": "model-00011-of-00015.safetensors", "model.language_model.layers.29.input_layernorm.weight": "model-00011-of-00015.safetensors", "model.language_model.layers.29.linear_attn.A_log": "model-00011-of-00015.safetensors", "model.language_model.layers.29.linear_attn.conv1d.weight": "model-00011-of-00015.safetensors", "model.language_model.layers.29.linear_attn.dt_bias": "model-00011-of-00015.safetensors", "model.language_model.layers.29.linear_attn.in_proj_a.weight": "model-00011-of-00015.safetensors", "model.language_model.layers.29.linear_attn.in_proj_b.weight": "model-00011-of-00015.safetensors", "model.language_model.layers.29.linear_attn.in_proj_qkv.weight": "model-00011-of-00015.safetensors", "model.language_model.layers.29.linear_attn.in_proj_z.weight": "model-00011-of-00015.safetensors", "model.language_model.layers.29.linear_attn.norm.weight": "model-00011-of-00015.safetensors", "model.language_model.layers.29.linear_attn.out_proj.weight": "model-00011-of-00015.safetensors", "model.language_model.layers.29.mlp.gate.weight": "model-00011-of-00015.safetensors", "model.language_model.layers.29.mlp.shared_expert.down_proj.weight": "model-00011-of-00015.safetensors", "model.language_model.layers.29.mlp.shared_expert.gate_proj.weight": "model-00011-of-00015.safetensors", "model.language_model.layers.29.mlp.shared_expert.up_proj.weight": "model-00011-of-00015.safetensors", "model.language_model.layers.29.mlp.shared_expert_gate.weight": "model-00011-of-00015.safetensors", "model.language_model.layers.29.post_attention_layernorm.weight": "model-00011-of-00015.safetensors", "model.language_model.layers.30.input_layernorm.weight": "model-00011-of-00015.safetensors", "model.language_model.layers.30.linear_attn.A_log": "model-00011-of-00015.safetensors", "model.language_model.layers.30.linear_attn.conv1d.weight": "model-00011-of-00015.safetensors", "model.language_model.layers.30.linear_attn.dt_bias": "model-00011-of-00015.safetensors", "model.language_model.layers.30.linear_attn.in_proj_a.weight": "model-00011-of-00015.safetensors", "model.language_model.layers.30.linear_attn.in_proj_b.weight": "model-00011-of-00015.safetensors", "model.language_model.layers.30.linear_attn.in_proj_qkv.weight": "model-00011-of-00015.safetensors", "model.language_model.layers.30.linear_attn.in_proj_z.weight": "model-00011-of-00015.safetensors", "model.language_model.layers.30.linear_attn.norm.weight": "model-00011-of-00015.safetensors", "model.language_model.layers.30.linear_attn.out_proj.weight": "model-00011-of-00015.safetensors", "model.language_model.layers.30.mlp.gate.weight": "model-00011-of-00015.safetensors", "model.language_model.layers.30.mlp.shared_expert.down_proj.weight": "model-00011-of-00015.safetensors", "model.language_model.layers.30.mlp.shared_expert.gate_proj.weight": "model-00011-of-00015.safetensors", "model.language_model.layers.30.mlp.shared_expert.up_proj.weight": "model-00011-of-00015.safetensors", "model.language_model.layers.30.mlp.shared_expert_gate.weight": "model-00011-of-00015.safetensors", "model.language_model.layers.30.post_attention_layernorm.weight": "model-00011-of-00015.safetensors", "model.language_model.layers.31.input_layernorm.weight": "model-00011-of-00015.safetensors", "model.language_model.layers.31.mlp.gate.weight": "model-00011-of-00015.safetensors", "model.language_model.layers.31.mlp.shared_expert.down_proj.weight": "model-00011-of-00015.safetensors", "model.language_model.layers.31.mlp.shared_expert.gate_proj.weight": "model-00011-of-00015.safetensors", "model.language_model.layers.31.mlp.shared_expert.up_proj.weight": "model-00011-of-00015.safetensors", "model.language_model.layers.31.mlp.shared_expert_gate.weight": "model-00011-of-00015.safetensors", "model.language_model.layers.31.self_attn.k_norm.weight": "model-00011-of-00015.safetensors", "model.language_model.layers.31.self_attn.k_proj.weight": "model-00011-of-00015.safetensors", "model.language_model.layers.31.self_attn.o_proj.weight": "model-00011-of-00015.safetensors", "model.language_model.layers.31.self_attn.q_norm.weight": "model-00011-of-00015.safetensors", "model.language_model.layers.31.self_attn.q_proj.weight": "model-00011-of-00015.safetensors", "model.language_model.layers.31.self_attn.v_proj.weight": "model-00011-of-00015.safetensors", "model.language_model.layers.31.post_attention_layernorm.weight": "model-00012-of-00015.safetensors", "model.language_model.layers.32.input_layernorm.weight": "model-00012-of-00015.safetensors", "model.language_model.layers.32.linear_attn.A_log": "model-00012-of-00015.safetensors", "model.language_model.layers.32.linear_attn.conv1d.weight": "model-00012-of-00015.safetensors", "model.language_model.layers.32.linear_attn.dt_bias": "model-00012-of-00015.safetensors", "model.language_model.layers.32.linear_attn.in_proj_a.weight": "model-00012-of-00015.safetensors", "model.language_model.layers.32.linear_attn.in_proj_b.weight": "model-00012-of-00015.safetensors", "model.language_model.layers.32.linear_attn.in_proj_qkv.weight": "model-00012-of-00015.safetensors", "model.language_model.layers.32.linear_attn.in_proj_z.weight": "model-00012-of-00015.safetensors", "model.language_model.layers.32.linear_attn.norm.weight": "model-00012-of-00015.safetensors", "model.language_model.layers.32.linear_attn.out_proj.weight": "model-00012-of-00015.safetensors", "model.language_model.layers.32.mlp.gate.weight": "model-00012-of-00015.safetensors", "model.language_model.layers.32.mlp.shared_expert.down_proj.weight": "model-00012-of-00015.safetensors", "model.language_model.layers.32.mlp.shared_expert.gate_proj.weight": "model-00012-of-00015.safetensors", "model.language_model.layers.32.mlp.shared_expert.up_proj.weight": "model-00012-of-00015.safetensors", "model.language_model.layers.32.mlp.shared_expert_gate.weight": "model-00012-of-00015.safetensors", "model.language_model.layers.32.post_attention_layernorm.weight": "model-00012-of-00015.safetensors", "model.language_model.layers.33.input_layernorm.weight": "model-00012-of-00015.safetensors", "model.language_model.layers.33.linear_attn.A_log": "model-00012-of-00015.safetensors", "model.language_model.layers.33.linear_attn.conv1d.weight": "model-00012-of-00015.safetensors", "model.language_model.layers.33.linear_attn.dt_bias": "model-00012-of-00015.safetensors", "model.language_model.layers.33.linear_attn.in_proj_a.weight": "model-00012-of-00015.safetensors", "model.language_model.layers.33.linear_attn.in_proj_b.weight": "model-00012-of-00015.safetensors", "model.language_model.layers.33.linear_attn.in_proj_qkv.weight": "model-00012-of-00015.safetensors", "model.language_model.layers.33.linear_attn.in_proj_z.weight": "model-00012-of-00015.safetensors", "model.language_model.layers.33.linear_attn.norm.weight": "model-00012-of-00015.safetensors", "model.language_model.layers.33.linear_attn.out_proj.weight": "model-00012-of-00015.safetensors", "model.language_model.layers.33.mlp.gate.weight": "model-00012-of-00015.safetensors", "model.language_model.layers.33.mlp.shared_expert.down_proj.weight": "model-00012-of-00015.safetensors", "model.language_model.layers.33.mlp.shared_expert.gate_proj.weight": "model-00012-of-00015.safetensors", "model.language_model.layers.33.mlp.shared_expert.up_proj.weight": "model-00012-of-00015.safetensors", "model.language_model.layers.33.mlp.shared_expert_gate.weight": "model-00012-of-00015.safetensors", "model.language_model.layers.33.post_attention_layernorm.weight": "model-00012-of-00015.safetensors", "model.language_model.layers.34.input_layernorm.weight": "model-00012-of-00015.safetensors", "model.language_model.layers.34.linear_attn.A_log": "model-00012-of-00015.safetensors", "model.language_model.layers.34.linear_attn.conv1d.weight": "model-00012-of-00015.safetensors", "model.language_model.layers.34.linear_attn.dt_bias": "model-00012-of-00015.safetensors", "model.language_model.layers.34.linear_attn.in_proj_a.weight": "model-00012-of-00015.safetensors", "model.language_model.layers.34.linear_attn.in_proj_b.weight": "model-00012-of-00015.safetensors", "model.language_model.layers.34.linear_attn.in_proj_qkv.weight": "model-00012-of-00015.safetensors", "model.language_model.layers.34.linear_attn.in_proj_z.weight": "model-00012-of-00015.safetensors", "model.language_model.layers.34.linear_attn.norm.weight": "model-00012-of-00015.safetensors", "model.language_model.layers.34.linear_attn.out_proj.weight": "model-00012-of-00015.safetensors", "model.language_model.layers.34.mlp.gate.weight": "model-00012-of-00015.safetensors", "model.language_model.layers.34.mlp.shared_expert.down_proj.weight": "model-00012-of-00015.safetensors", "model.language_model.layers.34.mlp.shared_expert.gate_proj.weight": "model-00012-of-00015.safetensors", "model.language_model.layers.34.mlp.shared_expert.up_proj.weight": "model-00012-of-00015.safetensors", "model.language_model.layers.34.mlp.shared_expert_gate.weight": "model-00012-of-00015.safetensors", "model.language_model.layers.34.post_attention_layernorm.weight": "model-00013-of-00015.safetensors", "model.language_model.layers.35.input_layernorm.weight": "model-00013-of-00015.safetensors", "model.language_model.layers.35.mlp.gate.weight": "model-00013-of-00015.safetensors", "model.language_model.layers.35.mlp.shared_expert.down_proj.weight": "model-00013-of-00015.safetensors", "model.language_model.layers.35.mlp.shared_expert.gate_proj.weight": "model-00013-of-00015.safetensors", "model.language_model.layers.35.mlp.shared_expert.up_proj.weight": "model-00013-of-00015.safetensors", "model.language_model.layers.35.mlp.shared_expert_gate.weight": "model-00013-of-00015.safetensors", "model.language_model.layers.35.post_attention_layernorm.weight": "model-00013-of-00015.safetensors", "model.language_model.layers.35.self_attn.k_norm.weight": "model-00013-of-00015.safetensors", "model.language_model.layers.35.self_attn.k_proj.weight": "model-00013-of-00015.safetensors", "model.language_model.layers.35.self_attn.o_proj.weight": "model-00013-of-00015.safetensors", "model.language_model.layers.35.self_attn.q_norm.weight": "model-00013-of-00015.safetensors", "model.language_model.layers.35.self_attn.q_proj.weight": "model-00013-of-00015.safetensors", "model.language_model.layers.35.self_attn.v_proj.weight": "model-00013-of-00015.safetensors", "model.language_model.layers.36.input_layernorm.weight": "model-00013-of-00015.safetensors", "model.language_model.layers.36.linear_attn.A_log": "model-00013-of-00015.safetensors", "model.language_model.layers.36.linear_attn.conv1d.weight": "model-00013-of-00015.safetensors", "model.language_model.layers.36.linear_attn.dt_bias": "model-00013-of-00015.safetensors", "model.language_model.layers.36.linear_attn.in_proj_a.weight": "model-00013-of-00015.safetensors", "model.language_model.layers.36.linear_attn.in_proj_b.weight": "model-00013-of-00015.safetensors", "model.language_model.layers.36.linear_attn.in_proj_qkv.weight": "model-00013-of-00015.safetensors", "model.language_model.layers.36.linear_attn.in_proj_z.weight": "model-00013-of-00015.safetensors", "model.language_model.layers.36.linear_attn.norm.weight": "model-00013-of-00015.safetensors", "model.language_model.layers.36.linear_attn.out_proj.weight": "model-00013-of-00015.safetensors", "model.language_model.layers.36.mlp.gate.weight": "model-00013-of-00015.safetensors", "model.language_model.layers.36.mlp.shared_expert.down_proj.weight": "model-00013-of-00015.safetensors", "model.language_model.layers.36.mlp.shared_expert.gate_proj.weight": "model-00013-of-00015.safetensors", "model.language_model.layers.36.mlp.shared_expert.up_proj.weight": "model-00013-of-00015.safetensors", "model.language_model.layers.36.mlp.shared_expert_gate.weight": "model-00013-of-00015.safetensors", "model.language_model.layers.36.post_attention_layernorm.weight": "model-00013-of-00015.safetensors", "model.language_model.layers.37.input_layernorm.weight": "model-00013-of-00015.safetensors", "model.language_model.layers.37.linear_attn.A_log": "model-00013-of-00015.safetensors", "model.language_model.layers.37.linear_attn.conv1d.weight": "model-00013-of-00015.safetensors", "model.language_model.layers.37.linear_attn.dt_bias": "model-00013-of-00015.safetensors", "model.language_model.layers.37.linear_attn.in_proj_a.weight": "model-00013-of-00015.safetensors", "model.language_model.layers.37.linear_attn.in_proj_b.weight": "model-00013-of-00015.safetensors", "model.language_model.layers.37.linear_attn.in_proj_qkv.weight": "model-00013-of-00015.safetensors", "model.language_model.layers.37.linear_attn.in_proj_z.weight": "model-00013-of-00015.safetensors", "model.language_model.layers.37.linear_attn.norm.weight": "model-00013-of-00015.safetensors", "model.language_model.layers.37.linear_attn.out_proj.weight": "model-00013-of-00015.safetensors", "model.language_model.layers.37.mlp.gate.weight": "model-00013-of-00015.safetensors", "model.language_model.layers.37.mlp.shared_expert.down_proj.weight": "model-00013-of-00015.safetensors", "model.language_model.layers.37.mlp.shared_expert.gate_proj.weight": "model-00013-of-00015.safetensors", "model.language_model.layers.37.mlp.shared_expert.up_proj.weight": "model-00013-of-00015.safetensors", "model.language_model.layers.37.mlp.shared_expert_gate.weight": "model-00013-of-00015.safetensors", "model.language_model.layers.37.post_attention_layernorm.weight": "model-00014-of-00015.safetensors", "model.language_model.layers.38.input_layernorm.weight": "model-00014-of-00015.safetensors", "model.language_model.layers.38.linear_attn.A_log": "model-00014-of-00015.safetensors", "model.language_model.layers.38.linear_attn.conv1d.weight": "model-00014-of-00015.safetensors", "model.language_model.layers.38.linear_attn.dt_bias": "model-00014-of-00015.safetensors", "model.language_model.layers.38.linear_attn.in_proj_a.weight": "model-00014-of-00015.safetensors", "model.language_model.layers.38.linear_attn.in_proj_b.weight": "model-00014-of-00015.safetensors", "model.language_model.layers.38.linear_attn.in_proj_qkv.weight": "model-00014-of-00015.safetensors", "model.language_model.layers.38.linear_attn.in_proj_z.weight": "model-00014-of-00015.safetensors", "model.language_model.layers.38.linear_attn.norm.weight": "model-00014-of-00015.safetensors", "model.language_model.layers.38.linear_attn.out_proj.weight": "model-00014-of-00015.safetensors", "model.language_model.layers.38.mlp.gate.weight": "model-00014-of-00015.safetensors", "model.language_model.layers.38.mlp.shared_expert.down_proj.weight": "model-00014-of-00015.safetensors", "model.language_model.layers.38.mlp.shared_expert.gate_proj.weight": "model-00014-of-00015.safetensors", "model.language_model.layers.38.mlp.shared_expert.up_proj.weight": "model-00014-of-00015.safetensors", "model.language_model.layers.38.mlp.shared_expert_gate.weight": "model-00014-of-00015.safetensors", "model.language_model.layers.38.post_attention_layernorm.weight": "model-00014-of-00015.safetensors", "model.language_model.layers.39.input_layernorm.weight": "model-00014-of-00015.safetensors", "model.language_model.layers.39.mlp.gate.weight": "model-00014-of-00015.safetensors", "model.language_model.layers.39.mlp.shared_expert.down_proj.weight": "model-00014-of-00015.safetensors", "model.language_model.layers.39.mlp.shared_expert.gate_proj.weight": "model-00014-of-00015.safetensors", "model.language_model.layers.39.mlp.shared_expert.up_proj.weight": "model-00014-of-00015.safetensors", "model.language_model.layers.39.mlp.shared_expert_gate.weight": "model-00014-of-00015.safetensors", "model.language_model.layers.39.post_attention_layernorm.weight": "model-00014-of-00015.safetensors", "model.language_model.layers.39.self_attn.k_norm.weight": "model-00014-of-00015.safetensors", "model.language_model.layers.39.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.language_model.layers.39.self_attn.o_proj.weight": "model-00014-of-00015.safetensors", "model.language_model.layers.39.self_attn.q_norm.weight": "model-00014-of-00015.safetensors", "model.language_model.layers.39.self_attn.q_proj.weight": "model-00014-of-00015.safetensors", "model.language_model.layers.39.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", "lm_head.weight": "model-00015-of-00015.safetensors", "model.language_model.norm.weight": "model-00015-of-00015.safetensors"}}
processor_config.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "image_processor": {
3
+ "data_format": "channels_first",
4
+ "do_convert_rgb": true,
5
+ "do_normalize": true,
6
+ "do_rescale": true,
7
+ "do_resize": true,
8
+ "image_mean": [
9
+ 0.5,
10
+ 0.5,
11
+ 0.5
12
+ ],
13
+ "image_processor_type": "Qwen2VLImageProcessorFast",
14
+ "image_std": [
15
+ 0.5,
16
+ 0.5,
17
+ 0.5
18
+ ],
19
+ "merge_size": 2,
20
+ "patch_size": 16,
21
+ "resample": 3,
22
+ "rescale_factor": 0.00392156862745098,
23
+ "size": {
24
+ "longest_edge": 16777216,
25
+ "shortest_edge": 65536
26
+ },
27
+ "temporal_patch_size": 2
28
+ },
29
+ "processor_class": "Qwen3VLProcessor",
30
+ "video_processor": {
31
+ "data_format": "channels_first",
32
+ "default_to_square": true,
33
+ "do_convert_rgb": true,
34
+ "do_normalize": true,
35
+ "do_rescale": true,
36
+ "do_resize": true,
37
+ "do_sample_frames": true,
38
+ "fps": 2,
39
+ "image_mean": [
40
+ 0.5,
41
+ 0.5,
42
+ 0.5
43
+ ],
44
+ "image_std": [
45
+ 0.5,
46
+ 0.5,
47
+ 0.5
48
+ ],
49
+ "max_frames": 768,
50
+ "merge_size": 2,
51
+ "min_frames": 4,
52
+ "patch_size": 16,
53
+ "resample": 3,
54
+ "rescale_factor": 0.00392156862745098,
55
+ "return_metadata": false,
56
+ "size": {
57
+ "longest_edge": 25165824,
58
+ "shortest_edge": 4096
59
+ },
60
+ "temporal_patch_size": 2,
61
+ "video_processor_type": "Qwen3VLVideoProcessor"
62
+ }
63
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
3
+ size 19989343
tokenizer_config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "audio_bos_token": "<|audio_start|>",
4
+ "audio_eos_token": "<|audio_end|>",
5
+ "audio_token": "<|audio_pad|>",
6
+ "backend": "tokenizers",
7
+ "bos_token": null,
8
+ "clean_up_tokenization_spaces": false,
9
+ "eos_token": "<|im_end|>",
10
+ "errors": "replace",
11
+ "image_token": "<|image_pad|>",
12
+ "is_local": true,
13
+ "model_max_length": 262144,
14
+ "model_specific_special_tokens": {
15
+ "audio_bos_token": "<|audio_start|>",
16
+ "audio_eos_token": "<|audio_end|>",
17
+ "audio_token": "<|audio_pad|>",
18
+ "image_token": "<|image_pad|>",
19
+ "video_token": "<|video_pad|>",
20
+ "vision_bos_token": "<|vision_start|>",
21
+ "vision_eos_token": "<|vision_end|>"
22
+ },
23
+ "pad_token": "<|endoftext|>",
24
+ "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
25
+ "processor_class": "Qwen3VLProcessor",
26
+ "split_special_tokens": false,
27
+ "tokenizer_class": "TokenizersBackend",
28
+ "unk_token": null,
29
+ "video_token": "<|video_pad|>",
30
+ "vision_bos_token": "<|vision_start|>",
31
+ "vision_eos_token": "<|vision_end|>"
32
+ }