srmsoumya commited on
Commit
a45ad1f
·
verified ·
1 Parent(s): 374e3d8

remove merged tensors from root

Browse files
chat_template.jinja DELETED
@@ -1,155 +0,0 @@
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 mapping %}
120
- {%- for args_name in tool_call.arguments %}
121
- {%- set args_value = tool_call.arguments[args_name] %}
122
- {{- '<parameter=' + args_name + '>\n' }}
123
- {%- 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 %}
124
- {{- args_value }}
125
- {{- '\n</parameter>\n' }}
126
- {%- endfor %}
127
- {%- endif %}
128
- {{- '</function>\n</tool_call>' }}
129
- {%- endfor %}
130
- {%- endif %}
131
- {{- '<|im_end|>\n' }}
132
- {%- elif message.role == "tool" %}
133
- {%- if loop.previtem and loop.previtem.role != "tool" %}
134
- {{- '<|im_start|>user' }}
135
- {%- endif %}
136
- {{- '\n<tool_response>\n' }}
137
- {{- content }}
138
- {{- '\n</tool_response>' }}
139
- {%- if not loop.last and loop.nextitem.role != "tool" %}
140
- {{- '<|im_end|>\n' }}
141
- {%- elif loop.last %}
142
- {{- '<|im_end|>\n' }}
143
- {%- endif %}
144
- {%- else %}
145
- {{- raise_exception('Unexpected message role.') }}
146
- {%- endif %}
147
- {%- endfor %}
148
- {%- if add_generation_prompt %}
149
- {{- '<|im_start|>assistant\n' }}
150
- {%- if enable_thinking is defined and enable_thinking is true %}
151
- {{- '<think>\n' }}
152
- {%- else %}
153
- {{- '<think>\n\n</think>\n\n' }}
154
- {%- endif %}
155
- {%- endif %}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
model.safetensors-00001-of-00001.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:85a8df6cba15fdbe48981632096b7f580cb831194a050014f4192eade5db8958
3
- size 1746942600
 
 
 
 
model.safetensors.index.json DELETED
@@ -1,495 +0,0 @@
1
- {
2
- "metadata": {
3
- "total_size": 1746882752
4
- },
5
- "weight_map": {
6
- "model.language_model.embed_tokens.weight": "model.safetensors-00001-of-00001.safetensors",
7
- "model.visual.merger.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
8
- "model.language_model.layers.14.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
9
- "model.language_model.layers.12.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
10
- "model.language_model.layers.18.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
11
- "model.language_model.layers.13.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
12
- "model.language_model.layers.2.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
13
- "model.language_model.layers.4.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
14
- "model.language_model.layers.20.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
15
- "model.language_model.layers.1.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
16
- "model.language_model.layers.10.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
17
- "model.language_model.layers.16.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
18
- "model.language_model.layers.17.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
19
- "model.language_model.layers.5.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
20
- "model.language_model.layers.6.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
21
- "model.language_model.layers.8.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
22
- "model.language_model.layers.9.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
23
- "model.language_model.layers.21.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
24
- "model.language_model.layers.22.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
25
- "model.language_model.layers.0.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
26
- "model.language_model.layers.23.self_attn.q_proj.weight": "model.safetensors-00001-of-00001.safetensors",
27
- "model.language_model.layers.15.self_attn.q_proj.weight": "model.safetensors-00001-of-00001.safetensors",
28
- "model.language_model.layers.7.self_attn.q_proj.weight": "model.safetensors-00001-of-00001.safetensors",
29
- "model.language_model.layers.11.self_attn.q_proj.weight": "model.safetensors-00001-of-00001.safetensors",
30
- "mtp.layers.0.self_attn.q_proj.weight": "model.safetensors-00001-of-00001.safetensors",
31
- "model.language_model.layers.19.self_attn.q_proj.weight": "model.safetensors-00001-of-00001.safetensors",
32
- "model.language_model.layers.3.self_attn.q_proj.weight": "model.safetensors-00001-of-00001.safetensors",
33
- "model.language_model.layers.22.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
34
- "model.language_model.layers.22.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
35
- "model.language_model.layers.22.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
36
- "model.language_model.layers.23.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
37
- "model.language_model.layers.23.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
38
- "model.language_model.layers.23.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
39
- "model.language_model.layers.3.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
40
- "model.language_model.layers.3.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
41
- "model.language_model.layers.3.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
42
- "model.language_model.layers.14.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
43
- "model.language_model.layers.14.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
44
- "model.language_model.layers.14.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
45
- "model.language_model.layers.15.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
46
- "model.language_model.layers.15.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
47
- "model.language_model.layers.15.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
48
- "model.language_model.layers.6.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
49
- "model.language_model.layers.6.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
50
- "model.language_model.layers.6.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
51
- "model.language_model.layers.7.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
52
- "model.language_model.layers.7.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
53
- "model.language_model.layers.7.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
54
- "model.language_model.layers.10.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
55
- "model.language_model.layers.11.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
56
- "model.language_model.layers.11.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
57
- "model.language_model.layers.11.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
58
- "model.language_model.layers.9.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
59
- "model.language_model.layers.9.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
60
- "model.language_model.layers.9.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
61
- "mtp.layers.0.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
62
- "mtp.layers.0.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
63
- "mtp.layers.0.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
64
- "model.language_model.layers.17.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
65
- "model.language_model.layers.17.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
66
- "model.language_model.layers.17.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
67
- "model.language_model.layers.18.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
68
- "model.language_model.layers.18.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
69
- "model.language_model.layers.18.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
70
- "model.language_model.layers.12.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
71
- "model.language_model.layers.12.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
72
- "model.language_model.layers.12.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
73
- "model.language_model.layers.13.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
74
- "model.language_model.layers.13.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
75
- "model.language_model.layers.13.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
76
- "model.language_model.layers.19.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
77
- "model.language_model.layers.19.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
78
- "model.language_model.layers.19.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
79
- "model.language_model.layers.4.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
80
- "model.language_model.layers.4.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
81
- "model.language_model.layers.4.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
82
- "model.language_model.layers.2.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
83
- "model.language_model.layers.2.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
84
- "model.language_model.layers.2.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
85
- "model.language_model.layers.20.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
86
- "model.language_model.layers.20.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
87
- "model.language_model.layers.20.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
88
- "model.language_model.layers.1.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
89
- "model.language_model.layers.1.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
90
- "model.language_model.layers.1.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
91
- "model.language_model.layers.10.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
92
- "model.language_model.layers.10.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
93
- "model.language_model.layers.16.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
94
- "model.language_model.layers.16.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
95
- "model.language_model.layers.16.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
96
- "model.language_model.layers.5.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
97
- "model.language_model.layers.5.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
98
- "model.language_model.layers.5.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
99
- "model.language_model.layers.8.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
100
- "model.language_model.layers.8.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
101
- "model.language_model.layers.8.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
102
- "model.language_model.layers.21.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
103
- "model.language_model.layers.21.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
104
- "model.language_model.layers.21.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
105
- "model.language_model.layers.0.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
106
- "model.language_model.layers.0.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
107
- "model.language_model.layers.0.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
108
- "model.visual.merger.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
109
- "model.visual.blocks.0.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
110
- "model.visual.blocks.0.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
111
- "model.visual.blocks.1.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
112
- "model.visual.blocks.1.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
113
- "model.visual.blocks.10.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
114
- "model.visual.blocks.10.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
115
- "model.visual.blocks.11.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
116
- "model.visual.blocks.11.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
117
- "model.visual.blocks.2.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
118
- "model.visual.blocks.2.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
119
- "model.visual.blocks.3.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
120
- "model.visual.blocks.3.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
121
- "model.visual.blocks.4.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
122
- "model.visual.blocks.4.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
123
- "model.visual.blocks.5.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
124
- "model.visual.blocks.5.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
125
- "model.visual.blocks.6.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
126
- "model.visual.blocks.6.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
127
- "model.visual.blocks.7.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
128
- "model.visual.blocks.7.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
129
- "model.visual.blocks.8.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
130
- "model.visual.blocks.8.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
131
- "model.visual.blocks.9.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
132
- "model.visual.blocks.9.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
133
- "model.language_model.layers.23.self_attn.o_proj.weight": "model.safetensors-00001-of-00001.safetensors",
134
- "model.language_model.layers.3.self_attn.o_proj.weight": "model.safetensors-00001-of-00001.safetensors",
135
- "model.language_model.layers.14.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
136
- "model.language_model.layers.14.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
137
- "model.language_model.layers.15.self_attn.o_proj.weight": "model.safetensors-00001-of-00001.safetensors",
138
- "model.language_model.layers.6.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
139
- "model.language_model.layers.7.self_attn.o_proj.weight": "model.safetensors-00001-of-00001.safetensors",
140
- "model.language_model.layers.11.self_attn.o_proj.weight": "model.safetensors-00001-of-00001.safetensors",
141
- "model.language_model.layers.12.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
142
- "model.language_model.layers.12.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
143
- "mtp.fc.weight": "model.safetensors-00001-of-00001.safetensors",
144
- "mtp.layers.0.self_attn.o_proj.weight": "model.safetensors-00001-of-00001.safetensors",
145
- "model.language_model.layers.17.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
146
- "model.language_model.layers.18.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
147
- "model.language_model.layers.18.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
148
- "model.language_model.layers.13.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
149
- "model.language_model.layers.13.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
150
- "model.language_model.layers.19.self_attn.o_proj.weight": "model.safetensors-00001-of-00001.safetensors",
151
- "model.language_model.layers.2.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
152
- "model.language_model.layers.2.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
153
- "model.language_model.layers.4.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
154
- "model.language_model.layers.4.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
155
- "model.language_model.layers.20.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
156
- "model.language_model.layers.20.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
157
- "model.language_model.layers.1.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
158
- "model.language_model.layers.1.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
159
- "model.language_model.layers.10.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
160
- "model.language_model.layers.10.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
161
- "model.language_model.layers.16.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
162
- "model.language_model.layers.16.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
163
- "model.language_model.layers.17.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
164
- "model.language_model.layers.5.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
165
- "model.language_model.layers.5.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
166
- "model.language_model.layers.6.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
167
- "model.language_model.layers.8.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
168
- "model.language_model.layers.8.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
169
- "model.language_model.layers.9.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
170
- "model.language_model.layers.9.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
171
- "model.language_model.layers.21.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
172
- "model.language_model.layers.21.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
173
- "model.language_model.layers.22.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
174
- "model.language_model.layers.22.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
175
- "model.language_model.layers.0.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
176
- "model.language_model.layers.0.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
177
- "model.visual.blocks.0.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
178
- "model.visual.blocks.1.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
179
- "model.visual.blocks.10.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
180
- "model.visual.blocks.11.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
181
- "model.visual.blocks.2.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
182
- "model.visual.blocks.3.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
183
- "model.visual.blocks.4.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
184
- "model.visual.blocks.5.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
185
- "model.visual.blocks.6.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
186
- "model.visual.blocks.7.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
187
- "model.visual.blocks.8.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
188
- "model.visual.blocks.9.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
189
- "model.visual.pos_embed.weight": "model.safetensors-00001-of-00001.safetensors",
190
- "model.visual.patch_embed.proj.weight": "model.safetensors-00001-of-00001.safetensors",
191
- "model.visual.blocks.0.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
192
- "model.visual.blocks.1.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
193
- "model.visual.blocks.10.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
194
- "model.visual.blocks.11.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
195
- "model.visual.blocks.2.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
196
- "model.visual.blocks.3.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
197
- "model.visual.blocks.4.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
198
- "model.visual.blocks.5.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
199
- "model.visual.blocks.6.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
200
- "model.visual.blocks.7.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
201
- "model.visual.blocks.8.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
202
- "model.visual.blocks.9.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
203
- "model.language_model.layers.23.self_attn.k_proj.weight": "model.safetensors-00001-of-00001.safetensors",
204
- "model.language_model.layers.23.self_attn.v_proj.weight": "model.safetensors-00001-of-00001.safetensors",
205
- "model.language_model.layers.15.self_attn.k_proj.weight": "model.safetensors-00001-of-00001.safetensors",
206
- "model.language_model.layers.15.self_attn.v_proj.weight": "model.safetensors-00001-of-00001.safetensors",
207
- "model.language_model.layers.7.self_attn.k_proj.weight": "model.safetensors-00001-of-00001.safetensors",
208
- "model.language_model.layers.7.self_attn.v_proj.weight": "model.safetensors-00001-of-00001.safetensors",
209
- "model.language_model.layers.11.self_attn.k_proj.weight": "model.safetensors-00001-of-00001.safetensors",
210
- "model.language_model.layers.11.self_attn.v_proj.weight": "model.safetensors-00001-of-00001.safetensors",
211
- "mtp.layers.0.self_attn.k_proj.weight": "model.safetensors-00001-of-00001.safetensors",
212
- "mtp.layers.0.self_attn.v_proj.weight": "model.safetensors-00001-of-00001.safetensors",
213
- "model.language_model.layers.19.self_attn.k_proj.weight": "model.safetensors-00001-of-00001.safetensors",
214
- "model.language_model.layers.19.self_attn.v_proj.weight": "model.safetensors-00001-of-00001.safetensors",
215
- "model.language_model.layers.3.self_attn.k_proj.weight": "model.safetensors-00001-of-00001.safetensors",
216
- "model.language_model.layers.3.self_attn.v_proj.weight": "model.safetensors-00001-of-00001.safetensors",
217
- "model.language_model.layers.8.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
218
- "model.language_model.layers.12.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
219
- "model.language_model.layers.18.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
220
- "model.language_model.layers.13.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
221
- "model.language_model.layers.14.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
222
- "model.language_model.layers.2.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
223
- "model.language_model.layers.4.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
224
- "model.language_model.layers.5.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
225
- "model.language_model.layers.20.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
226
- "model.language_model.layers.21.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
227
- "model.language_model.layers.10.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
228
- "model.language_model.layers.16.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
229
- "model.language_model.layers.17.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
230
- "model.language_model.layers.6.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
231
- "model.language_model.layers.9.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
232
- "model.language_model.layers.22.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
233
- "model.language_model.layers.0.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
234
- "model.language_model.layers.1.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
235
- "model.language_model.layers.14.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
236
- "model.language_model.layers.14.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
237
- "model.language_model.layers.12.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
238
- "model.language_model.layers.12.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
239
- "model.language_model.layers.18.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
240
- "model.language_model.layers.18.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
241
- "model.language_model.layers.13.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
242
- "model.language_model.layers.13.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
243
- "model.language_model.layers.2.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
244
- "model.language_model.layers.2.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
245
- "model.language_model.layers.4.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
246
- "model.language_model.layers.4.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
247
- "model.language_model.layers.20.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
248
- "model.language_model.layers.20.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
249
- "model.language_model.layers.1.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
250
- "model.language_model.layers.1.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
251
- "model.language_model.layers.10.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
252
- "model.language_model.layers.10.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
253
- "model.language_model.layers.16.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
254
- "model.language_model.layers.16.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
255
- "model.language_model.layers.17.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
256
- "model.language_model.layers.17.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
257
- "model.language_model.layers.5.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
258
- "model.language_model.layers.5.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
259
- "model.language_model.layers.6.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
260
- "model.language_model.layers.6.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
261
- "model.language_model.layers.8.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
262
- "model.language_model.layers.8.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
263
- "model.language_model.layers.9.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
264
- "model.language_model.layers.9.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
265
- "model.language_model.layers.21.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
266
- "model.language_model.layers.21.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
267
- "model.language_model.layers.22.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
268
- "model.language_model.layers.22.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
269
- "model.language_model.layers.0.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
270
- "model.language_model.layers.0.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
271
- "model.visual.blocks.0.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
272
- "model.visual.blocks.1.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
273
- "model.visual.blocks.10.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
274
- "model.visual.blocks.11.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
275
- "model.visual.blocks.2.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
276
- "model.visual.blocks.3.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
277
- "model.visual.blocks.4.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
278
- "model.visual.blocks.5.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
279
- "model.visual.blocks.6.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
280
- "model.visual.blocks.7.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
281
- "model.visual.blocks.8.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
282
- "model.visual.blocks.9.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
283
- "model.visual.merger.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
284
- "model.visual.blocks.0.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
285
- "model.visual.blocks.1.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
286
- "model.visual.blocks.10.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
287
- "model.visual.blocks.11.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
288
- "model.visual.blocks.2.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
289
- "model.visual.blocks.3.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
290
- "model.visual.blocks.4.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
291
- "model.visual.blocks.5.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
292
- "model.visual.blocks.6.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
293
- "model.visual.blocks.7.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
294
- "model.visual.blocks.8.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
295
- "model.visual.blocks.9.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
296
- "model.language_model.layers.22.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
297
- "model.language_model.layers.23.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
298
- "model.language_model.layers.23.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
299
- "model.language_model.layers.3.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
300
- "model.language_model.layers.14.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
301
- "model.language_model.layers.14.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
302
- "model.language_model.layers.15.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
303
- "model.language_model.layers.15.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
304
- "model.language_model.layers.6.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
305
- "model.language_model.layers.7.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
306
- "model.language_model.layers.7.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
307
- "model.language_model.layers.8.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
308
- "model.language_model.layers.11.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
309
- "model.language_model.layers.11.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
310
- "model.language_model.layers.12.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
311
- "mtp.layers.0.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
312
- "mtp.layers.0.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
313
- "mtp.norm.weight": "model.safetensors-00001-of-00001.safetensors",
314
- "mtp.pre_fc_norm_embedding.weight": "model.safetensors-00001-of-00001.safetensors",
315
- "mtp.pre_fc_norm_hidden.weight": "model.safetensors-00001-of-00001.safetensors",
316
- "model.language_model.layers.17.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
317
- "model.language_model.layers.18.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
318
- "model.language_model.layers.18.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
319
- "model.language_model.layers.19.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
320
- "model.language_model.layers.12.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
321
- "model.language_model.layers.13.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
322
- "model.language_model.layers.13.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
323
- "model.language_model.layers.19.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
324
- "model.language_model.layers.2.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
325
- "model.language_model.layers.2.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
326
- "model.language_model.layers.3.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
327
- "model.language_model.layers.4.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
328
- "model.language_model.layers.4.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
329
- "model.language_model.layers.20.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
330
- "model.language_model.layers.20.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
331
- "model.language_model.layers.1.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
332
- "model.language_model.layers.10.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
333
- "model.language_model.layers.10.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
334
- "model.language_model.layers.16.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
335
- "model.language_model.layers.16.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
336
- "model.language_model.layers.17.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
337
- "model.language_model.layers.5.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
338
- "model.language_model.layers.5.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
339
- "model.language_model.layers.6.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
340
- "model.language_model.layers.8.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
341
- "model.language_model.layers.9.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
342
- "model.language_model.layers.9.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
343
- "model.language_model.layers.21.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
344
- "model.language_model.layers.21.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
345
- "model.language_model.layers.22.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
346
- "model.language_model.layers.0.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
347
- "model.language_model.layers.0.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
348
- "model.language_model.layers.1.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
349
- "model.language_model.norm.weight": "model.safetensors-00001-of-00001.safetensors",
350
- "model.visual.merger.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
351
- "model.visual.blocks.0.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
352
- "model.visual.blocks.0.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
353
- "model.visual.blocks.0.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
354
- "model.visual.blocks.0.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
355
- "model.visual.blocks.0.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
356
- "model.visual.blocks.0.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
357
- "model.visual.blocks.1.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
358
- "model.visual.blocks.1.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
359
- "model.visual.blocks.1.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
360
- "model.visual.blocks.1.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
361
- "model.visual.blocks.1.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
362
- "model.visual.blocks.1.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
363
- "model.visual.blocks.10.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
364
- "model.visual.blocks.10.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
365
- "model.visual.blocks.10.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
366
- "model.visual.blocks.10.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
367
- "model.visual.blocks.10.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
368
- "model.visual.blocks.10.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
369
- "model.visual.blocks.11.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
370
- "model.visual.blocks.11.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
371
- "model.visual.blocks.11.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
372
- "model.visual.blocks.11.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
373
- "model.visual.blocks.11.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
374
- "model.visual.blocks.11.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
375
- "model.visual.blocks.2.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
376
- "model.visual.blocks.2.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
377
- "model.visual.blocks.2.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
378
- "model.visual.blocks.2.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
379
- "model.visual.blocks.2.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
380
- "model.visual.blocks.2.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
381
- "model.visual.blocks.3.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
382
- "model.visual.blocks.3.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
383
- "model.visual.blocks.3.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
384
- "model.visual.blocks.3.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
385
- "model.visual.blocks.3.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
386
- "model.visual.blocks.3.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
387
- "model.visual.blocks.4.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
388
- "model.visual.blocks.4.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
389
- "model.visual.blocks.4.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
390
- "model.visual.blocks.4.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
391
- "model.visual.blocks.4.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
392
- "model.visual.blocks.4.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
393
- "model.visual.blocks.5.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
394
- "model.visual.blocks.5.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
395
- "model.visual.blocks.5.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
396
- "model.visual.blocks.5.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
397
- "model.visual.blocks.5.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
398
- "model.visual.blocks.5.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
399
- "model.visual.blocks.6.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
400
- "model.visual.blocks.6.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
401
- "model.visual.blocks.6.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
402
- "model.visual.blocks.6.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
403
- "model.visual.blocks.6.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
404
- "model.visual.blocks.6.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
405
- "model.visual.blocks.7.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
406
- "model.visual.blocks.7.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
407
- "model.visual.blocks.7.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
408
- "model.visual.blocks.7.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
409
- "model.visual.blocks.7.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
410
- "model.visual.blocks.7.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
411
- "model.visual.blocks.8.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
412
- "model.visual.blocks.8.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
413
- "model.visual.blocks.8.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
414
- "model.visual.blocks.8.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
415
- "model.visual.blocks.8.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
416
- "model.visual.blocks.8.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
417
- "model.visual.blocks.9.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
418
- "model.visual.blocks.9.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
419
- "model.visual.blocks.9.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
420
- "model.visual.blocks.9.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
421
- "model.visual.blocks.9.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
422
- "model.visual.blocks.9.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
423
- "model.visual.merger.norm.bias": "model.safetensors-00001-of-00001.safetensors",
424
- "model.visual.merger.norm.weight": "model.safetensors-00001-of-00001.safetensors",
425
- "model.visual.patch_embed.proj.bias": "model.safetensors-00001-of-00001.safetensors",
426
- "model.language_model.layers.23.self_attn.k_norm.weight": "model.safetensors-00001-of-00001.safetensors",
427
- "model.language_model.layers.23.self_attn.q_norm.weight": "model.safetensors-00001-of-00001.safetensors",
428
- "model.language_model.layers.3.self_attn.k_norm.weight": "model.safetensors-00001-of-00001.safetensors",
429
- "model.language_model.layers.14.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
430
- "model.language_model.layers.15.self_attn.k_norm.weight": "model.safetensors-00001-of-00001.safetensors",
431
- "model.language_model.layers.15.self_attn.q_norm.weight": "model.safetensors-00001-of-00001.safetensors",
432
- "model.language_model.layers.7.self_attn.k_norm.weight": "model.safetensors-00001-of-00001.safetensors",
433
- "model.language_model.layers.7.self_attn.q_norm.weight": "model.safetensors-00001-of-00001.safetensors",
434
- "model.language_model.layers.11.self_attn.k_norm.weight": "model.safetensors-00001-of-00001.safetensors",
435
- "model.language_model.layers.11.self_attn.q_norm.weight": "model.safetensors-00001-of-00001.safetensors",
436
- "model.language_model.layers.12.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
437
- "mtp.layers.0.self_attn.k_norm.weight": "model.safetensors-00001-of-00001.safetensors",
438
- "mtp.layers.0.self_attn.q_norm.weight": "model.safetensors-00001-of-00001.safetensors",
439
- "model.language_model.layers.18.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
440
- "model.language_model.layers.13.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
441
- "model.language_model.layers.19.self_attn.k_norm.weight": "model.safetensors-00001-of-00001.safetensors",
442
- "model.language_model.layers.19.self_attn.q_norm.weight": "model.safetensors-00001-of-00001.safetensors",
443
- "model.language_model.layers.2.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
444
- "model.language_model.layers.3.self_attn.q_norm.weight": "model.safetensors-00001-of-00001.safetensors",
445
- "model.language_model.layers.4.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
446
- "model.language_model.layers.20.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
447
- "model.language_model.layers.1.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
448
- "model.language_model.layers.10.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
449
- "model.language_model.layers.16.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
450
- "model.language_model.layers.17.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
451
- "model.language_model.layers.5.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
452
- "model.language_model.layers.6.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
453
- "model.language_model.layers.8.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
454
- "model.language_model.layers.9.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
455
- "model.language_model.layers.21.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
456
- "model.language_model.layers.22.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
457
- "model.language_model.layers.0.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
458
- "model.language_model.layers.16.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
459
- "model.language_model.layers.8.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
460
- "model.language_model.layers.12.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
461
- "model.language_model.layers.18.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
462
- "model.language_model.layers.13.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
463
- "model.language_model.layers.14.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
464
- "model.language_model.layers.2.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
465
- "model.language_model.layers.4.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
466
- "model.language_model.layers.5.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
467
- "model.language_model.layers.20.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
468
- "model.language_model.layers.21.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
469
- "model.language_model.layers.10.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
470
- "model.language_model.layers.17.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
471
- "model.language_model.layers.6.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
472
- "model.language_model.layers.9.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
473
- "model.language_model.layers.22.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
474
- "model.language_model.layers.0.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
475
- "model.language_model.layers.1.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
476
- "model.language_model.layers.8.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors",
477
- "model.language_model.layers.12.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors",
478
- "model.language_model.layers.18.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors",
479
- "model.language_model.layers.13.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors",
480
- "model.language_model.layers.14.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors",
481
- "model.language_model.layers.2.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors",
482
- "model.language_model.layers.4.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors",
483
- "model.language_model.layers.20.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors",
484
- "model.language_model.layers.21.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors",
485
- "model.language_model.layers.10.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors",
486
- "model.language_model.layers.16.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors",
487
- "model.language_model.layers.17.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors",
488
- "model.language_model.layers.5.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors",
489
- "model.language_model.layers.6.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors",
490
- "model.language_model.layers.9.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors",
491
- "model.language_model.layers.22.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors",
492
- "model.language_model.layers.0.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors",
493
- "model.language_model.layers.1.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors"
494
- }
495
- }