Hugging Face's logo

runyuanhe
/
qwen35-9b-frontiercs

PyTorch
qwen3_5
Model card Files
xet
 Community
runyuanhe commited on
Commit
96860bf
·
verified ·
1 Parent(s): f25c118

Add files using upload-large-folder tool

Browse files
Files changed (11) hide show
  1. .gitattributes +1 -0
  2. chat_template.jinja +154 -0
  3. config.json +114 -0
  4. processor_config.json +60 -0
  5. pytorch_model-00001.bin +3 -0
  6. pytorch_model-00002.bin +3 -0
  7. pytorch_model-00003.bin +3 -0
  8. pytorch_model-00004.bin +3 -0
  9. pytorch_model.bin.index.json +767 -0
  10. tokenizer.json +3 -0
  11. tokenizer_config.json +33 -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 +1,114 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3_5ForConditionalGeneration"
4
+ ],
5
+ "attn_implementation": "sdpa",
6
+ "bos_token_id": null,
7
+ "dtype": "bfloat16",
8
+ "eos_token_id": 248046,
9
+ "image_token_id": 248056,
10
+ "model_type": "qwen3_5",
11
+ "pad_token_id": 248044,
12
+ "text_config": {
13
+ "attention_bias": false,
14
+ "attention_dropout": 0.0,
15
+ "attn_output_gate": true,
16
+ "bos_token_id": null,
17
+ "dtype": "float32",
18
+ "eos_token_id": 248044,
19
+ "full_attention_interval": 4,
20
+ "head_dim": 256,
21
+ "hidden_act": "silu",
22
+ "hidden_size": 4096,
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 12288,
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
+ ],
59
+ "linear_conv_kernel_dim": 4,
60
+ "linear_key_head_dim": 128,
61
+ "linear_num_key_heads": 16,
62
+ "linear_num_value_heads": 32,
63
+ "linear_value_head_dim": 128,
64
+ "mamba_ssm_dtype": "float32",
65
+ "max_position_embeddings": 262144,
66
+ "mlp_only_layers": [],
67
+ "model_type": "qwen3_5_text",
68
+ "mtp_num_hidden_layers": 1,
69
+ "mtp_use_dedicated_embeddings": false,
70
+ "num_attention_heads": 16,
71
+ "num_hidden_layers": 32,
72
+ "num_key_value_heads": 4,
73
+ "pad_token_id": null,
74
+ "partial_rotary_factor": 0.25,
75
+ "rms_norm_eps": 1e-06,
76
+ "rope_parameters": {
77
+ "mrope_interleaved": true,
78
+ "mrope_section": [
79
+ 11,
80
+ 11,
81
+ 10
82
+ ],
83
+ "partial_rotary_factor": 0.25,
84
+ "rope_theta": 10000000,
85
+ "rope_type": "default"
86
+ },
87
+ "tie_word_embeddings": false,
88
+ "use_cache": true,
89
+ "vocab_size": 248320
90
+ },
91
+ "tie_word_embeddings": false,
92
+ "transformers_version": "5.7.0",
93
+ "video_token_id": 248057,
94
+ "vision_config": {
95
+ "deepstack_visual_indexes": [],
96
+ "depth": 27,
97
+ "dtype": "float32",
98
+ "hidden_act": "gelu_pytorch_tanh",
99
+ "hidden_size": 1152,
100
+ "in_channels": 3,
101
+ "initializer_range": 0.02,
102
+ "intermediate_size": 4304,
103
+ "model_type": "qwen3_5_vision",
104
+ "num_heads": 16,
105
+ "num_position_embeddings": 2304,
106
+ "out_hidden_size": 4096,
107
+ "patch_size": 16,
108
+ "spatial_merge_size": 2,
109
+ "temporal_patch_size": 2
110
+ },
111
+ "vision_end_token_id": 248054,
112
+ "vision_start_token_id": 248053,
113
+ "torch_dtype": "bfloat16"
114
+ }
processor_config.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "image_processor": {
3
+ "do_convert_rgb": true,
4
+ "do_normalize": true,
5
+ "do_rescale": true,
6
+ "do_resize": true,
7
+ "image_mean": [
8
+ 0.5,
9
+ 0.5,
10
+ 0.5
11
+ ],
12
+ "image_processor_type": "Qwen2VLImageProcessor",
13
+ "image_std": [
14
+ 0.5,
15
+ 0.5,
16
+ 0.5
17
+ ],
18
+ "merge_size": 2,
19
+ "patch_size": 16,
20
+ "resample": 3,
21
+ "rescale_factor": 0.00392156862745098,
22
+ "size": {
23
+ "longest_edge": 16777216,
24
+ "shortest_edge": 65536
25
+ },
26
+ "temporal_patch_size": 2
27
+ },
28
+ "processor_class": "Qwen3VLProcessor",
29
+ "video_processor": {
30
+ "do_convert_rgb": true,
31
+ "do_normalize": true,
32
+ "do_rescale": true,
33
+ "do_resize": true,
34
+ "do_sample_frames": true,
35
+ "fps": 2,
36
+ "image_mean": [
37
+ 0.5,
38
+ 0.5,
39
+ 0.5
40
+ ],
41
+ "image_std": [
42
+ 0.5,
43
+ 0.5,
44
+ 0.5
45
+ ],
46
+ "max_frames": 768,
47
+ "merge_size": 2,
48
+ "min_frames": 4,
49
+ "patch_size": 16,
50
+ "resample": 3,
51
+ "rescale_factor": 0.00392156862745098,
52
+ "return_metadata": false,
53
+ "size": {
54
+ "longest_edge": 25165824,
55
+ "shortest_edge": 4096
56
+ },
57
+ "temporal_patch_size": 2,
58
+ "video_processor_type": "Qwen3VLVideoProcessor"
59
+ }
60
+ }
pytorch_model-00001.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be1abdec944e07e474153b430fcf119c4f48fcd9097f6580b515e9bd5d0118ec
3
+ size 5278261409
pytorch_model-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a40de07a80c408c055274f8061231486b6c85b916dda72298492c0f33bebf67
3
+ size 5358108723
pytorch_model-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10cd15a64093e612e04f13b202e150e8cccae72f190557bfb62792b9b8b75317
3
+ size 5340133439
pytorch_model-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5b798d3b791c8532eccba0a2fb0dbda45bd6df8e11472e048e52f6517f765f4
3
+ size 2843382275
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,767 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 18819627488
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00001.bin",
7
+ "model.language_model.embed_tokens.weight": "pytorch_model-00001.bin",
8
+ "model.language_model.layers.0.input_layernorm.weight": "pytorch_model-00001.bin",
9
+ "model.language_model.layers.0.linear_attn.A_log": "pytorch_model-00001.bin",
10
+ "model.language_model.layers.0.linear_attn.conv1d.weight": "pytorch_model-00001.bin",
11
+ "model.language_model.layers.0.linear_attn.dt_bias": "pytorch_model-00001.bin",
12
+ "model.language_model.layers.0.linear_attn.in_proj_a.weight": "pytorch_model-00001.bin",
13
+ "model.language_model.layers.0.linear_attn.in_proj_b.weight": "pytorch_model-00001.bin",
14
+ "model.language_model.layers.0.linear_attn.in_proj_qkv.weight": "pytorch_model-00001.bin",
15
+ "model.language_model.layers.0.linear_attn.in_proj_z.weight": "pytorch_model-00001.bin",
16
+ "model.language_model.layers.0.linear_attn.norm.weight": "pytorch_model-00001.bin",
17
+ "model.language_model.layers.0.linear_attn.out_proj.weight": "pytorch_model-00001.bin",
18
+ "model.language_model.layers.0.mlp.down_proj.weight": "pytorch_model-00001.bin",
19
+ "model.language_model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001.bin",
20
+ "model.language_model.layers.0.mlp.up_proj.weight": "pytorch_model-00001.bin",
21
+ "model.language_model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001.bin",
22
+ "model.language_model.layers.1.input_layernorm.weight": "pytorch_model-00001.bin",
23
+ "model.language_model.layers.1.linear_attn.A_log": "pytorch_model-00001.bin",
24
+ "model.language_model.layers.1.linear_attn.conv1d.weight": "pytorch_model-00001.bin",
25
+ "model.language_model.layers.1.linear_attn.dt_bias": "pytorch_model-00001.bin",
26
+ "model.language_model.layers.1.linear_attn.in_proj_a.weight": "pytorch_model-00001.bin",
27
+ "model.language_model.layers.1.linear_attn.in_proj_b.weight": "pytorch_model-00001.bin",
28
+ "model.language_model.layers.1.linear_attn.in_proj_qkv.weight": "pytorch_model-00001.bin",
29
+ "model.language_model.layers.1.linear_attn.in_proj_z.weight": "pytorch_model-00001.bin",
30
+ "model.language_model.layers.1.linear_attn.norm.weight": "pytorch_model-00001.bin",
31
+ "model.language_model.layers.1.linear_attn.out_proj.weight": "pytorch_model-00001.bin",
32
+ "model.language_model.layers.1.mlp.down_proj.weight": "pytorch_model-00001.bin",
33
+ "model.language_model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001.bin",
34
+ "model.language_model.layers.1.mlp.up_proj.weight": "pytorch_model-00001.bin",
35
+ "model.language_model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001.bin",
36
+ "model.language_model.layers.10.input_layernorm.weight": "pytorch_model-00001.bin",
37
+ "model.language_model.layers.10.linear_attn.A_log": "pytorch_model-00001.bin",
38
+ "model.language_model.layers.10.linear_attn.conv1d.weight": "pytorch_model-00001.bin",
39
+ "model.language_model.layers.10.linear_attn.dt_bias": "pytorch_model-00001.bin",
40
+ "model.language_model.layers.10.linear_attn.in_proj_a.weight": "pytorch_model-00001.bin",
41
+ "model.language_model.layers.10.linear_attn.in_proj_b.weight": "pytorch_model-00001.bin",
42
+ "model.language_model.layers.10.linear_attn.in_proj_qkv.weight": "pytorch_model-00001.bin",
43
+ "model.language_model.layers.10.linear_attn.in_proj_z.weight": "pytorch_model-00001.bin",
44
+ "model.language_model.layers.10.linear_attn.norm.weight": "pytorch_model-00001.bin",
45
+ "model.language_model.layers.10.linear_attn.out_proj.weight": "pytorch_model-00001.bin",
46
+ "model.language_model.layers.10.mlp.down_proj.weight": "pytorch_model-00001.bin",
47
+ "model.language_model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001.bin",
48
+ "model.language_model.layers.10.mlp.up_proj.weight": "pytorch_model-00002.bin",
49
+ "model.language_model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002.bin",
50
+ "model.language_model.layers.11.input_layernorm.weight": "pytorch_model-00002.bin",
51
+ "model.language_model.layers.11.mlp.down_proj.weight": "pytorch_model-00002.bin",
52
+ "model.language_model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002.bin",
53
+ "model.language_model.layers.11.mlp.up_proj.weight": "pytorch_model-00002.bin",
54
+ "model.language_model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002.bin",
55
+ "model.language_model.layers.11.self_attn.k_norm.weight": "pytorch_model-00002.bin",
56
+ "model.language_model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002.bin",
57
+ "model.language_model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002.bin",
58
+ "model.language_model.layers.11.self_attn.q_norm.weight": "pytorch_model-00002.bin",
59
+ "model.language_model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002.bin",
60
+ "model.language_model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002.bin",
61
+ "model.language_model.layers.12.input_layernorm.weight": "pytorch_model-00002.bin",
62
+ "model.language_model.layers.12.linear_attn.A_log": "pytorch_model-00002.bin",
63
+ "model.language_model.layers.12.linear_attn.conv1d.weight": "pytorch_model-00002.bin",
64
+ "model.language_model.layers.12.linear_attn.dt_bias": "pytorch_model-00002.bin",
65
+ "model.language_model.layers.12.linear_attn.in_proj_a.weight": "pytorch_model-00002.bin",
66
+ "model.language_model.layers.12.linear_attn.in_proj_b.weight": "pytorch_model-00002.bin",
67
+ "model.language_model.layers.12.linear_attn.in_proj_qkv.weight": "pytorch_model-00002.bin",
68
+ "model.language_model.layers.12.linear_attn.in_proj_z.weight": "pytorch_model-00002.bin",
69
+ "model.language_model.layers.12.linear_attn.norm.weight": "pytorch_model-00002.bin",
70
+ "model.language_model.layers.12.linear_attn.out_proj.weight": "pytorch_model-00002.bin",
71
+ "model.language_model.layers.12.mlp.down_proj.weight": "pytorch_model-00002.bin",
72
+ "model.language_model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002.bin",
73
+ "model.language_model.layers.12.mlp.up_proj.weight": "pytorch_model-00002.bin",
74
+ "model.language_model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002.bin",
75
+ "model.language_model.layers.13.input_layernorm.weight": "pytorch_model-00002.bin",
76
+ "model.language_model.layers.13.linear_attn.A_log": "pytorch_model-00002.bin",
77
+ "model.language_model.layers.13.linear_attn.conv1d.weight": "pytorch_model-00002.bin",
78
+ "model.language_model.layers.13.linear_attn.dt_bias": "pytorch_model-00002.bin",
79
+ "model.language_model.layers.13.linear_attn.in_proj_a.weight": "pytorch_model-00002.bin",
80
+ "model.language_model.layers.13.linear_attn.in_proj_b.weight": "pytorch_model-00002.bin",
81
+ "model.language_model.layers.13.linear_attn.in_proj_qkv.weight": "pytorch_model-00002.bin",
82
+ "model.language_model.layers.13.linear_attn.in_proj_z.weight": "pytorch_model-00002.bin",
83
+ "model.language_model.layers.13.linear_attn.norm.weight": "pytorch_model-00002.bin",
84
+ "model.language_model.layers.13.linear_attn.out_proj.weight": "pytorch_model-00002.bin",
85
+ "model.language_model.layers.13.mlp.down_proj.weight": "pytorch_model-00002.bin",
86
+ "model.language_model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002.bin",
87
+ "model.language_model.layers.13.mlp.up_proj.weight": "pytorch_model-00002.bin",
88
+ "model.language_model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002.bin",
89
+ "model.language_model.layers.14.input_layernorm.weight": "pytorch_model-00002.bin",
90
+ "model.language_model.layers.14.linear_attn.A_log": "pytorch_model-00002.bin",
91
+ "model.language_model.layers.14.linear_attn.conv1d.weight": "pytorch_model-00002.bin",
92
+ "model.language_model.layers.14.linear_attn.dt_bias": "pytorch_model-00002.bin",
93
+ "model.language_model.layers.14.linear_attn.in_proj_a.weight": "pytorch_model-00002.bin",
94
+ "model.language_model.layers.14.linear_attn.in_proj_b.weight": "pytorch_model-00002.bin",
95
+ "model.language_model.layers.14.linear_attn.in_proj_qkv.weight": "pytorch_model-00002.bin",
96
+ "model.language_model.layers.14.linear_attn.in_proj_z.weight": "pytorch_model-00002.bin",
97
+ "model.language_model.layers.14.linear_attn.norm.weight": "pytorch_model-00002.bin",
98
+ "model.language_model.layers.14.linear_attn.out_proj.weight": "pytorch_model-00002.bin",
99
+ "model.language_model.layers.14.mlp.down_proj.weight": "pytorch_model-00002.bin",
100
+ "model.language_model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002.bin",
101
+ "model.language_model.layers.14.mlp.up_proj.weight": "pytorch_model-00002.bin",
102
+ "model.language_model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002.bin",
103
+ "model.language_model.layers.15.input_layernorm.weight": "pytorch_model-00002.bin",
104
+ "model.language_model.layers.15.mlp.down_proj.weight": "pytorch_model-00002.bin",
105
+ "model.language_model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002.bin",
106
+ "model.language_model.layers.15.mlp.up_proj.weight": "pytorch_model-00002.bin",
107
+ "model.language_model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002.bin",
108
+ "model.language_model.layers.15.self_attn.k_norm.weight": "pytorch_model-00002.bin",
109
+ "model.language_model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002.bin",
110
+ "model.language_model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002.bin",
111
+ "model.language_model.layers.15.self_attn.q_norm.weight": "pytorch_model-00002.bin",
112
+ "model.language_model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002.bin",
113
+ "model.language_model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002.bin",
114
+ "model.language_model.layers.16.input_layernorm.weight": "pytorch_model-00002.bin",
115
+ "model.language_model.layers.16.linear_attn.A_log": "pytorch_model-00002.bin",
116
+ "model.language_model.layers.16.linear_attn.conv1d.weight": "pytorch_model-00002.bin",
117
+ "model.language_model.layers.16.linear_attn.dt_bias": "pytorch_model-00002.bin",
118
+ "model.language_model.layers.16.linear_attn.in_proj_a.weight": "pytorch_model-00002.bin",
119
+ "model.language_model.layers.16.linear_attn.in_proj_b.weight": "pytorch_model-00002.bin",
120
+ "model.language_model.layers.16.linear_attn.in_proj_qkv.weight": "pytorch_model-00002.bin",
121
+ "model.language_model.layers.16.linear_attn.in_proj_z.weight": "pytorch_model-00002.bin",
122
+ "model.language_model.layers.16.linear_attn.norm.weight": "pytorch_model-00002.bin",
123
+ "model.language_model.layers.16.linear_attn.out_proj.weight": "pytorch_model-00002.bin",
124
+ "model.language_model.layers.16.mlp.down_proj.weight": "pytorch_model-00002.bin",
125
+ "model.language_model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002.bin",
126
+ "model.language_model.layers.16.mlp.up_proj.weight": "pytorch_model-00002.bin",
127
+ "model.language_model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002.bin",
128
+ "model.language_model.layers.17.input_layernorm.weight": "pytorch_model-00002.bin",
129
+ "model.language_model.layers.17.linear_attn.A_log": "pytorch_model-00002.bin",
130
+ "model.language_model.layers.17.linear_attn.conv1d.weight": "pytorch_model-00002.bin",
131
+ "model.language_model.layers.17.linear_attn.dt_bias": "pytorch_model-00002.bin",
132
+ "model.language_model.layers.17.linear_attn.in_proj_a.weight": "pytorch_model-00002.bin",
133
+ "model.language_model.layers.17.linear_attn.in_proj_b.weight": "pytorch_model-00002.bin",
134
+ "model.language_model.layers.17.linear_attn.in_proj_qkv.weight": "pytorch_model-00002.bin",
135
+ "model.language_model.layers.17.linear_attn.in_proj_z.weight": "pytorch_model-00002.bin",
136
+ "model.language_model.layers.17.linear_attn.norm.weight": "pytorch_model-00002.bin",
137
+ "model.language_model.layers.17.linear_attn.out_proj.weight": "pytorch_model-00002.bin",
138
+ "model.language_model.layers.17.mlp.down_proj.weight": "pytorch_model-00002.bin",
139
+ "model.language_model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002.bin",
140
+ "model.language_model.layers.17.mlp.up_proj.weight": "pytorch_model-00002.bin",
141
+ "model.language_model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002.bin",
142
+ "model.language_model.layers.18.input_layernorm.weight": "pytorch_model-00002.bin",
143
+ "model.language_model.layers.18.linear_attn.A_log": "pytorch_model-00002.bin",
144
+ "model.language_model.layers.18.linear_attn.conv1d.weight": "pytorch_model-00002.bin",
145
+ "model.language_model.layers.18.linear_attn.dt_bias": "pytorch_model-00002.bin",
146
+ "model.language_model.layers.18.linear_attn.in_proj_a.weight": "pytorch_model-00002.bin",
147
+ "model.language_model.layers.18.linear_attn.in_proj_b.weight": "pytorch_model-00002.bin",
148
+ "model.language_model.layers.18.linear_attn.in_proj_qkv.weight": "pytorch_model-00002.bin",
149
+ "model.language_model.layers.18.linear_attn.in_proj_z.weight": "pytorch_model-00002.bin",
150
+ "model.language_model.layers.18.linear_attn.norm.weight": "pytorch_model-00002.bin",
151
+ "model.language_model.layers.18.linear_attn.out_proj.weight": "pytorch_model-00002.bin",
152
+ "model.language_model.layers.18.mlp.down_proj.weight": "pytorch_model-00002.bin",
153
+ "model.language_model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002.bin",
154
+ "model.language_model.layers.18.mlp.up_proj.weight": "pytorch_model-00002.bin",
155
+ "model.language_model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002.bin",
156
+ "model.language_model.layers.19.input_layernorm.weight": "pytorch_model-00002.bin",
157
+ "model.language_model.layers.19.mlp.down_proj.weight": "pytorch_model-00002.bin",
158
+ "model.language_model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002.bin",
159
+ "model.language_model.layers.19.mlp.up_proj.weight": "pytorch_model-00002.bin",
160
+ "model.language_model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002.bin",
161
+ "model.language_model.layers.19.self_attn.k_norm.weight": "pytorch_model-00002.bin",
162
+ "model.language_model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002.bin",
163
+ "model.language_model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002.bin",
164
+ "model.language_model.layers.19.self_attn.q_norm.weight": "pytorch_model-00002.bin",
165
+ "model.language_model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002.bin",
166
+ "model.language_model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002.bin",
167
+ "model.language_model.layers.2.input_layernorm.weight": "pytorch_model-00002.bin",
168
+ "model.language_model.layers.2.linear_attn.A_log": "pytorch_model-00002.bin",
169
+ "model.language_model.layers.2.linear_attn.conv1d.weight": "pytorch_model-00002.bin",
170
+ "model.language_model.layers.2.linear_attn.dt_bias": "pytorch_model-00002.bin",
171
+ "model.language_model.layers.2.linear_attn.in_proj_a.weight": "pytorch_model-00002.bin",
172
+ "model.language_model.layers.2.linear_attn.in_proj_b.weight": "pytorch_model-00002.bin",
173
+ "model.language_model.layers.2.linear_attn.in_proj_qkv.weight": "pytorch_model-00002.bin",
174
+ "model.language_model.layers.2.linear_attn.in_proj_z.weight": "pytorch_model-00002.bin",
175
+ "model.language_model.layers.2.linear_attn.norm.weight": "pytorch_model-00002.bin",
176
+ "model.language_model.layers.2.linear_attn.out_proj.weight": "pytorch_model-00002.bin",
177
+ "model.language_model.layers.2.mlp.down_proj.weight": "pytorch_model-00002.bin",
178
+ "model.language_model.layers.2.mlp.gate_proj.weight": "pytorch_model-00002.bin",
179
+ "model.language_model.layers.2.mlp.up_proj.weight": "pytorch_model-00002.bin",
180
+ "model.language_model.layers.2.post_attention_layernorm.weight": "pytorch_model-00002.bin",
181
+ "model.language_model.layers.20.input_layernorm.weight": "pytorch_model-00002.bin",
182
+ "model.language_model.layers.20.linear_attn.A_log": "pytorch_model-00002.bin",
183
+ "model.language_model.layers.20.linear_attn.conv1d.weight": "pytorch_model-00002.bin",
184
+ "model.language_model.layers.20.linear_attn.dt_bias": "pytorch_model-00002.bin",
185
+ "model.language_model.layers.20.linear_attn.in_proj_a.weight": "pytorch_model-00002.bin",
186
+ "model.language_model.layers.20.linear_attn.in_proj_b.weight": "pytorch_model-00002.bin",
187
+ "model.language_model.layers.20.linear_attn.in_proj_qkv.weight": "pytorch_model-00002.bin",
188
+ "model.language_model.layers.20.linear_attn.in_proj_z.weight": "pytorch_model-00002.bin",
189
+ "model.language_model.layers.20.linear_attn.norm.weight": "pytorch_model-00002.bin",
190
+ "model.language_model.layers.20.linear_attn.out_proj.weight": "pytorch_model-00002.bin",
191
+ "model.language_model.layers.20.mlp.down_proj.weight": "pytorch_model-00002.bin",
192
+ "model.language_model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002.bin",
193
+ "model.language_model.layers.20.mlp.up_proj.weight": "pytorch_model-00002.bin",
194
+ "model.language_model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002.bin",
195
+ "model.language_model.layers.21.input_layernorm.weight": "pytorch_model-00002.bin",
196
+ "model.language_model.layers.21.linear_attn.A_log": "pytorch_model-00002.bin",
197
+ "model.language_model.layers.21.linear_attn.conv1d.weight": "pytorch_model-00002.bin",
198
+ "model.language_model.layers.21.linear_attn.dt_bias": "pytorch_model-00002.bin",
199
+ "model.language_model.layers.21.linear_attn.in_proj_a.weight": "pytorch_model-00002.bin",
200
+ "model.language_model.layers.21.linear_attn.in_proj_b.weight": "pytorch_model-00002.bin",
201
+ "model.language_model.layers.21.linear_attn.in_proj_qkv.weight": "pytorch_model-00002.bin",
202
+ "model.language_model.layers.21.linear_attn.in_proj_z.weight": "pytorch_model-00002.bin",
203
+ "model.language_model.layers.21.linear_attn.norm.weight": "pytorch_model-00002.bin",
204
+ "model.language_model.layers.21.linear_attn.out_proj.weight": "pytorch_model-00002.bin",
205
+ "model.language_model.layers.21.mlp.down_proj.weight": "pytorch_model-00002.bin",
206
+ "model.language_model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002.bin",
207
+ "model.language_model.layers.21.mlp.up_proj.weight": "pytorch_model-00002.bin",
208
+ "model.language_model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002.bin",
209
+ "model.language_model.layers.22.input_layernorm.weight": "pytorch_model-00002.bin",
210
+ "model.language_model.layers.22.linear_attn.A_log": "pytorch_model-00002.bin",
211
+ "model.language_model.layers.22.linear_attn.conv1d.weight": "pytorch_model-00002.bin",
212
+ "model.language_model.layers.22.linear_attn.dt_bias": "pytorch_model-00002.bin",
213
+ "model.language_model.layers.22.linear_attn.in_proj_a.weight": "pytorch_model-00002.bin",
214
+ "model.language_model.layers.22.linear_attn.in_proj_b.weight": "pytorch_model-00002.bin",
215
+ "model.language_model.layers.22.linear_attn.in_proj_qkv.weight": "pytorch_model-00002.bin",
216
+ "model.language_model.layers.22.linear_attn.in_proj_z.weight": "pytorch_model-00003.bin",
217
+ "model.language_model.layers.22.linear_attn.norm.weight": "pytorch_model-00003.bin",
218
+ "model.language_model.layers.22.linear_attn.out_proj.weight": "pytorch_model-00003.bin",
219
+ "model.language_model.layers.22.mlp.down_proj.weight": "pytorch_model-00003.bin",
220
+ "model.language_model.layers.22.mlp.gate_proj.weight": "pytorch_model-00003.bin",
221
+ "model.language_model.layers.22.mlp.up_proj.weight": "pytorch_model-00003.bin",
222
+ "model.language_model.layers.22.post_attention_layernorm.weight": "pytorch_model-00003.bin",
223
+ "model.language_model.layers.23.input_layernorm.weight": "pytorch_model-00003.bin",
224
+ "model.language_model.layers.23.mlp.down_proj.weight": "pytorch_model-00003.bin",
225
+ "model.language_model.layers.23.mlp.gate_proj.weight": "pytorch_model-00003.bin",
226
+ "model.language_model.layers.23.mlp.up_proj.weight": "pytorch_model-00003.bin",
227
+ "model.language_model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003.bin",
228
+ "model.language_model.layers.23.self_attn.k_norm.weight": "pytorch_model-00003.bin",
229
+ "model.language_model.layers.23.self_attn.k_proj.weight": "pytorch_model-00003.bin",
230
+ "model.language_model.layers.23.self_attn.o_proj.weight": "pytorch_model-00003.bin",
231
+ "model.language_model.layers.23.self_attn.q_norm.weight": "pytorch_model-00003.bin",
232
+ "model.language_model.layers.23.self_attn.q_proj.weight": "pytorch_model-00003.bin",
233
+ "model.language_model.layers.23.self_attn.v_proj.weight": "pytorch_model-00003.bin",
234
+ "model.language_model.layers.24.input_layernorm.weight": "pytorch_model-00003.bin",
235
+ "model.language_model.layers.24.linear_attn.A_log": "pytorch_model-00003.bin",
236
+ "model.language_model.layers.24.linear_attn.conv1d.weight": "pytorch_model-00003.bin",
237
+ "model.language_model.layers.24.linear_attn.dt_bias": "pytorch_model-00003.bin",
238
+ "model.language_model.layers.24.linear_attn.in_proj_a.weight": "pytorch_model-00003.bin",
239
+ "model.language_model.layers.24.linear_attn.in_proj_b.weight": "pytorch_model-00003.bin",
240
+ "model.language_model.layers.24.linear_attn.in_proj_qkv.weight": "pytorch_model-00003.bin",
241
+ "model.language_model.layers.24.linear_attn.in_proj_z.weight": "pytorch_model-00003.bin",
242
+ "model.language_model.layers.24.linear_attn.norm.weight": "pytorch_model-00003.bin",
243
+ "model.language_model.layers.24.linear_attn.out_proj.weight": "pytorch_model-00003.bin",
244
+ "model.language_model.layers.24.mlp.down_proj.weight": "pytorch_model-00003.bin",
245
+ "model.language_model.layers.24.mlp.gate_proj.weight": "pytorch_model-00003.bin",
246
+ "model.language_model.layers.24.mlp.up_proj.weight": "pytorch_model-00003.bin",
247
+ "model.language_model.layers.24.post_attention_layernorm.weight": "pytorch_model-00003.bin",
248
+ "model.language_model.layers.25.input_layernorm.weight": "pytorch_model-00003.bin",
249
+ "model.language_model.layers.25.linear_attn.A_log": "pytorch_model-00003.bin",
250
+ "model.language_model.layers.25.linear_attn.conv1d.weight": "pytorch_model-00003.bin",
251
+ "model.language_model.layers.25.linear_attn.dt_bias": "pytorch_model-00003.bin",
252
+ "model.language_model.layers.25.linear_attn.in_proj_a.weight": "pytorch_model-00003.bin",
253
+ "model.language_model.layers.25.linear_attn.in_proj_b.weight": "pytorch_model-00003.bin",
254
+ "model.language_model.layers.25.linear_attn.in_proj_qkv.weight": "pytorch_model-00003.bin",
255
+ "model.language_model.layers.25.linear_attn.in_proj_z.weight": "pytorch_model-00003.bin",
256
+ "model.language_model.layers.25.linear_attn.norm.weight": "pytorch_model-00003.bin",
257
+ "model.language_model.layers.25.linear_attn.out_proj.weight": "pytorch_model-00003.bin",
258
+ "model.language_model.layers.25.mlp.down_proj.weight": "pytorch_model-00003.bin",
259
+ "model.language_model.layers.25.mlp.gate_proj.weight": "pytorch_model-00003.bin",
260
+ "model.language_model.layers.25.mlp.up_proj.weight": "pytorch_model-00003.bin",
261
+ "model.language_model.layers.25.post_attention_layernorm.weight": "pytorch_model-00003.bin",
262
+ "model.language_model.layers.26.input_layernorm.weight": "pytorch_model-00003.bin",
263
+ "model.language_model.layers.26.linear_attn.A_log": "pytorch_model-00003.bin",
264
+ "model.language_model.layers.26.linear_attn.conv1d.weight": "pytorch_model-00003.bin",
265
+ "model.language_model.layers.26.linear_attn.dt_bias": "pytorch_model-00003.bin",
266
+ "model.language_model.layers.26.linear_attn.in_proj_a.weight": "pytorch_model-00003.bin",
267
+ "model.language_model.layers.26.linear_attn.in_proj_b.weight": "pytorch_model-00003.bin",
268
+ "model.language_model.layers.26.linear_attn.in_proj_qkv.weight": "pytorch_model-00003.bin",
269
+ "model.language_model.layers.26.linear_attn.in_proj_z.weight": "pytorch_model-00003.bin",
270
+ "model.language_model.layers.26.linear_attn.norm.weight": "pytorch_model-00003.bin",
271
+ "model.language_model.layers.26.linear_attn.out_proj.weight": "pytorch_model-00003.bin",
272
+ "model.language_model.layers.26.mlp.down_proj.weight": "pytorch_model-00003.bin",
273
+ "model.language_model.layers.26.mlp.gate_proj.weight": "pytorch_model-00003.bin",
274
+ "model.language_model.layers.26.mlp.up_proj.weight": "pytorch_model-00003.bin",
275
+ "model.language_model.layers.26.post_attention_layernorm.weight": "pytorch_model-00003.bin",
276
+ "model.language_model.layers.27.input_layernorm.weight": "pytorch_model-00003.bin",
277
+ "model.language_model.layers.27.mlp.down_proj.weight": "pytorch_model-00003.bin",
278
+ "model.language_model.layers.27.mlp.gate_proj.weight": "pytorch_model-00003.bin",
279
+ "model.language_model.layers.27.mlp.up_proj.weight": "pytorch_model-00003.bin",
280
+ "model.language_model.layers.27.post_attention_layernorm.weight": "pytorch_model-00003.bin",
281
+ "model.language_model.layers.27.self_attn.k_norm.weight": "pytorch_model-00003.bin",
282
+ "model.language_model.layers.27.self_attn.k_proj.weight": "pytorch_model-00003.bin",
283
+ "model.language_model.layers.27.self_attn.o_proj.weight": "pytorch_model-00003.bin",
284
+ "model.language_model.layers.27.self_attn.q_norm.weight": "pytorch_model-00003.bin",
285
+ "model.language_model.layers.27.self_attn.q_proj.weight": "pytorch_model-00003.bin",
286
+ "model.language_model.layers.27.self_attn.v_proj.weight": "pytorch_model-00003.bin",
287
+ "model.language_model.layers.28.input_layernorm.weight": "pytorch_model-00003.bin",
288
+ "model.language_model.layers.28.linear_attn.A_log": "pytorch_model-00003.bin",
289
+ "model.language_model.layers.28.linear_attn.conv1d.weight": "pytorch_model-00003.bin",
290
+ "model.language_model.layers.28.linear_attn.dt_bias": "pytorch_model-00003.bin",
291
+ "model.language_model.layers.28.linear_attn.in_proj_a.weight": "pytorch_model-00003.bin",
292
+ "model.language_model.layers.28.linear_attn.in_proj_b.weight": "pytorch_model-00003.bin",
293
+ "model.language_model.layers.28.linear_attn.in_proj_qkv.weight": "pytorch_model-00003.bin",
294
+ "model.language_model.layers.28.linear_attn.in_proj_z.weight": "pytorch_model-00003.bin",
295
+ "model.language_model.layers.28.linear_attn.norm.weight": "pytorch_model-00003.bin",
296
+ "model.language_model.layers.28.linear_attn.out_proj.weight": "pytorch_model-00003.bin",
297
+ "model.language_model.layers.28.mlp.down_proj.weight": "pytorch_model-00003.bin",
298
+ "model.language_model.layers.28.mlp.gate_proj.weight": "pytorch_model-00003.bin",
299
+ "model.language_model.layers.28.mlp.up_proj.weight": "pytorch_model-00003.bin",
300
+ "model.language_model.layers.28.post_attention_layernorm.weight": "pytorch_model-00003.bin",
301
+ "model.language_model.layers.29.input_layernorm.weight": "pytorch_model-00003.bin",
302
+ "model.language_model.layers.29.linear_attn.A_log": "pytorch_model-00003.bin",
303
+ "model.language_model.layers.29.linear_attn.conv1d.weight": "pytorch_model-00003.bin",
304
+ "model.language_model.layers.29.linear_attn.dt_bias": "pytorch_model-00003.bin",
305
+ "model.language_model.layers.29.linear_attn.in_proj_a.weight": "pytorch_model-00003.bin",
306
+ "model.language_model.layers.29.linear_attn.in_proj_b.weight": "pytorch_model-00003.bin",
307
+ "model.language_model.layers.29.linear_attn.in_proj_qkv.weight": "pytorch_model-00003.bin",
308
+ "model.language_model.layers.29.linear_attn.in_proj_z.weight": "pytorch_model-00003.bin",
309
+ "model.language_model.layers.29.linear_attn.norm.weight": "pytorch_model-00003.bin",
310
+ "model.language_model.layers.29.linear_attn.out_proj.weight": "pytorch_model-00003.bin",
311
+ "model.language_model.layers.29.mlp.down_proj.weight": "pytorch_model-00003.bin",
312
+ "model.language_model.layers.29.mlp.gate_proj.weight": "pytorch_model-00003.bin",
313
+ "model.language_model.layers.29.mlp.up_proj.weight": "pytorch_model-00003.bin",
314
+ "model.language_model.layers.29.post_attention_layernorm.weight": "pytorch_model-00003.bin",
315
+ "model.language_model.layers.3.input_layernorm.weight": "pytorch_model-00003.bin",
316
+ "model.language_model.layers.3.mlp.down_proj.weight": "pytorch_model-00003.bin",
317
+ "model.language_model.layers.3.mlp.gate_proj.weight": "pytorch_model-00003.bin",
318
+ "model.language_model.layers.3.mlp.up_proj.weight": "pytorch_model-00003.bin",
319
+ "model.language_model.layers.3.post_attention_layernorm.weight": "pytorch_model-00003.bin",
320
+ "model.language_model.layers.3.self_attn.k_norm.weight": "pytorch_model-00003.bin",
321
+ "model.language_model.layers.3.self_attn.k_proj.weight": "pytorch_model-00003.bin",
322
+ "model.language_model.layers.3.self_attn.o_proj.weight": "pytorch_model-00003.bin",
323
+ "model.language_model.layers.3.self_attn.q_norm.weight": "pytorch_model-00003.bin",
324
+ "model.language_model.layers.3.self_attn.q_proj.weight": "pytorch_model-00003.bin",
325
+ "model.language_model.layers.3.self_attn.v_proj.weight": "pytorch_model-00003.bin",
326
+ "model.language_model.layers.30.input_layernorm.weight": "pytorch_model-00003.bin",
327
+ "model.language_model.layers.30.linear_attn.A_log": "pytorch_model-00003.bin",
328
+ "model.language_model.layers.30.linear_attn.conv1d.weight": "pytorch_model-00003.bin",
329
+ "model.language_model.layers.30.linear_attn.dt_bias": "pytorch_model-00003.bin",
330
+ "model.language_model.layers.30.linear_attn.in_proj_a.weight": "pytorch_model-00003.bin",
331
+ "model.language_model.layers.30.linear_attn.in_proj_b.weight": "pytorch_model-00003.bin",
332
+ "model.language_model.layers.30.linear_attn.in_proj_qkv.weight": "pytorch_model-00003.bin",
333
+ "model.language_model.layers.30.linear_attn.in_proj_z.weight": "pytorch_model-00003.bin",
334
+ "model.language_model.layers.30.linear_attn.norm.weight": "pytorch_model-00003.bin",
335
+ "model.language_model.layers.30.linear_attn.out_proj.weight": "pytorch_model-00003.bin",
336
+ "model.language_model.layers.30.mlp.down_proj.weight": "pytorch_model-00003.bin",
337
+ "model.language_model.layers.30.mlp.gate_proj.weight": "pytorch_model-00003.bin",
338
+ "model.language_model.layers.30.mlp.up_proj.weight": "pytorch_model-00003.bin",
339
+ "model.language_model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003.bin",
340
+ "model.language_model.layers.31.input_layernorm.weight": "pytorch_model-00003.bin",
341
+ "model.language_model.layers.31.mlp.down_proj.weight": "pytorch_model-00003.bin",
342
+ "model.language_model.layers.31.mlp.gate_proj.weight": "pytorch_model-00003.bin",
343
+ "model.language_model.layers.31.mlp.up_proj.weight": "pytorch_model-00003.bin",
344
+ "model.language_model.layers.31.post_attention_layernorm.weight": "pytorch_model-00003.bin",
345
+ "model.language_model.layers.31.self_attn.k_norm.weight": "pytorch_model-00003.bin",
346
+ "model.language_model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003.bin",
347
+ "model.language_model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003.bin",
348
+ "model.language_model.layers.31.self_attn.q_norm.weight": "pytorch_model-00003.bin",
349
+ "model.language_model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003.bin",
350
+ "model.language_model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003.bin",
351
+ "model.language_model.layers.4.input_layernorm.weight": "pytorch_model-00003.bin",
352
+ "model.language_model.layers.4.linear_attn.A_log": "pytorch_model-00003.bin",
353
+ "model.language_model.layers.4.linear_attn.conv1d.weight": "pytorch_model-00003.bin",
354
+ "model.language_model.layers.4.linear_attn.dt_bias": "pytorch_model-00003.bin",
355
+ "model.language_model.layers.4.linear_attn.in_proj_a.weight": "pytorch_model-00003.bin",
356
+ "model.language_model.layers.4.linear_attn.in_proj_b.weight": "pytorch_model-00003.bin",
357
+ "model.language_model.layers.4.linear_attn.in_proj_qkv.weight": "pytorch_model-00003.bin",
358
+ "model.language_model.layers.4.linear_attn.in_proj_z.weight": "pytorch_model-00003.bin",
359
+ "model.language_model.layers.4.linear_attn.norm.weight": "pytorch_model-00003.bin",
360
+ "model.language_model.layers.4.linear_attn.out_proj.weight": "pytorch_model-00003.bin",
361
+ "model.language_model.layers.4.mlp.down_proj.weight": "pytorch_model-00003.bin",
362
+ "model.language_model.layers.4.mlp.gate_proj.weight": "pytorch_model-00003.bin",
363
+ "model.language_model.layers.4.mlp.up_proj.weight": "pytorch_model-00003.bin",
364
+ "model.language_model.layers.4.post_attention_layernorm.weight": "pytorch_model-00003.bin",
365
+ "model.language_model.layers.5.input_layernorm.weight": "pytorch_model-00003.bin",
366
+ "model.language_model.layers.5.linear_attn.A_log": "pytorch_model-00003.bin",
367
+ "model.language_model.layers.5.linear_attn.conv1d.weight": "pytorch_model-00003.bin",
368
+ "model.language_model.layers.5.linear_attn.dt_bias": "pytorch_model-00003.bin",
369
+ "model.language_model.layers.5.linear_attn.in_proj_a.weight": "pytorch_model-00003.bin",
370
+ "model.language_model.layers.5.linear_attn.in_proj_b.weight": "pytorch_model-00003.bin",
371
+ "model.language_model.layers.5.linear_attn.in_proj_qkv.weight": "pytorch_model-00003.bin",
372
+ "model.language_model.layers.5.linear_attn.in_proj_z.weight": "pytorch_model-00003.bin",
373
+ "model.language_model.layers.5.linear_attn.norm.weight": "pytorch_model-00003.bin",
374
+ "model.language_model.layers.5.linear_attn.out_proj.weight": "pytorch_model-00003.bin",
375
+ "model.language_model.layers.5.mlp.down_proj.weight": "pytorch_model-00003.bin",
376
+ "model.language_model.layers.5.mlp.gate_proj.weight": "pytorch_model-00004.bin",
377
+ "model.language_model.layers.5.mlp.up_proj.weight": "pytorch_model-00004.bin",
378
+ "model.language_model.layers.5.post_attention_layernorm.weight": "pytorch_model-00004.bin",
379
+ "model.language_model.layers.6.input_layernorm.weight": "pytorch_model-00004.bin",
380
+ "model.language_model.layers.6.linear_attn.A_log": "pytorch_model-00004.bin",
381
+ "model.language_model.layers.6.linear_attn.conv1d.weight": "pytorch_model-00004.bin",
382
+ "model.language_model.layers.6.linear_attn.dt_bias": "pytorch_model-00004.bin",
383
+ "model.language_model.layers.6.linear_attn.in_proj_a.weight": "pytorch_model-00004.bin",
384
+ "model.language_model.layers.6.linear_attn.in_proj_b.weight": "pytorch_model-00004.bin",
385
+ "model.language_model.layers.6.linear_attn.in_proj_qkv.weight": "pytorch_model-00004.bin",
386
+ "model.language_model.layers.6.linear_attn.in_proj_z.weight": "pytorch_model-00004.bin",
387
+ "model.language_model.layers.6.linear_attn.norm.weight": "pytorch_model-00004.bin",
388
+ "model.language_model.layers.6.linear_attn.out_proj.weight": "pytorch_model-00004.bin",
389
+ "model.language_model.layers.6.mlp.down_proj.weight": "pytorch_model-00004.bin",
390
+ "model.language_model.layers.6.mlp.gate_proj.weight": "pytorch_model-00004.bin",
391
+ "model.language_model.layers.6.mlp.up_proj.weight": "pytorch_model-00004.bin",
392
+ "model.language_model.layers.6.post_attention_layernorm.weight": "pytorch_model-00004.bin",
393
+ "model.language_model.layers.7.input_layernorm.weight": "pytorch_model-00004.bin",
394
+ "model.language_model.layers.7.mlp.down_proj.weight": "pytorch_model-00004.bin",
395
+ "model.language_model.layers.7.mlp.gate_proj.weight": "pytorch_model-00004.bin",
396
+ "model.language_model.layers.7.mlp.up_proj.weight": "pytorch_model-00004.bin",
397
+ "model.language_model.layers.7.post_attention_layernorm.weight": "pytorch_model-00004.bin",
398
+ "model.language_model.layers.7.self_attn.k_norm.weight": "pytorch_model-00004.bin",
399
+ "model.language_model.layers.7.self_attn.k_proj.weight": "pytorch_model-00004.bin",
400
+ "model.language_model.layers.7.self_attn.o_proj.weight": "pytorch_model-00004.bin",
401
+ "model.language_model.layers.7.self_attn.q_norm.weight": "pytorch_model-00004.bin",
402
+ "model.language_model.layers.7.self_attn.q_proj.weight": "pytorch_model-00004.bin",
403
+ "model.language_model.layers.7.self_attn.v_proj.weight": "pytorch_model-00004.bin",
404
+ "model.language_model.layers.8.input_layernorm.weight": "pytorch_model-00004.bin",
405
+ "model.language_model.layers.8.linear_attn.A_log": "pytorch_model-00004.bin",
406
+ "model.language_model.layers.8.linear_attn.conv1d.weight": "pytorch_model-00004.bin",
407
+ "model.language_model.layers.8.linear_attn.dt_bias": "pytorch_model-00004.bin",
408
+ "model.language_model.layers.8.linear_attn.in_proj_a.weight": "pytorch_model-00004.bin",
409
+ "model.language_model.layers.8.linear_attn.in_proj_b.weight": "pytorch_model-00004.bin",
410
+ "model.language_model.layers.8.linear_attn.in_proj_qkv.weight": "pytorch_model-00004.bin",
411
+ "model.language_model.layers.8.linear_attn.in_proj_z.weight": "pytorch_model-00004.bin",
412
+ "model.language_model.layers.8.linear_attn.norm.weight": "pytorch_model-00004.bin",
413
+ "model.language_model.layers.8.linear_attn.out_proj.weight": "pytorch_model-00004.bin",
414
+ "model.language_model.layers.8.mlp.down_proj.weight": "pytorch_model-00004.bin",
415
+ "model.language_model.layers.8.mlp.gate_proj.weight": "pytorch_model-00004.bin",
416
+ "model.language_model.layers.8.mlp.up_proj.weight": "pytorch_model-00004.bin",
417
+ "model.language_model.layers.8.post_attention_layernorm.weight": "pytorch_model-00004.bin",
418
+ "model.language_model.layers.9.input_layernorm.weight": "pytorch_model-00004.bin",
419
+ "model.language_model.layers.9.linear_attn.A_log": "pytorch_model-00004.bin",
420
+ "model.language_model.layers.9.linear_attn.conv1d.weight": "pytorch_model-00004.bin",
421
+ "model.language_model.layers.9.linear_attn.dt_bias": "pytorch_model-00004.bin",
422
+ "model.language_model.layers.9.linear_attn.in_proj_a.weight": "pytorch_model-00004.bin",
423
+ "model.language_model.layers.9.linear_attn.in_proj_b.weight": "pytorch_model-00004.bin",
424
+ "model.language_model.layers.9.linear_attn.in_proj_qkv.weight": "pytorch_model-00004.bin",
425
+ "model.language_model.layers.9.linear_attn.in_proj_z.weight": "pytorch_model-00004.bin",
426
+ "model.language_model.layers.9.linear_attn.norm.weight": "pytorch_model-00004.bin",
427
+ "model.language_model.layers.9.linear_attn.out_proj.weight": "pytorch_model-00004.bin",
428
+ "model.language_model.layers.9.mlp.down_proj.weight": "pytorch_model-00004.bin",
429
+ "model.language_model.layers.9.mlp.gate_proj.weight": "pytorch_model-00004.bin",
430
+ "model.language_model.layers.9.mlp.up_proj.weight": "pytorch_model-00004.bin",
431
+ "model.language_model.layers.9.post_attention_layernorm.weight": "pytorch_model-00004.bin",
432
+ "model.language_model.norm.weight": "pytorch_model-00004.bin",
433
+ "model.visual.blocks.0.attn.proj.bias": "pytorch_model-00004.bin",
434
+ "model.visual.blocks.0.attn.proj.weight": "pytorch_model-00004.bin",
435
+ "model.visual.blocks.0.attn.qkv.bias": "pytorch_model-00004.bin",
436
+ "model.visual.blocks.0.attn.qkv.weight": "pytorch_model-00004.bin",
437
+ "model.visual.blocks.0.mlp.linear_fc1.bias": "pytorch_model-00004.bin",
438
+ "model.visual.blocks.0.mlp.linear_fc1.weight": "pytorch_model-00004.bin",
439
+ "model.visual.blocks.0.mlp.linear_fc2.bias": "pytorch_model-00004.bin",
440
+ "model.visual.blocks.0.mlp.linear_fc2.weight": "pytorch_model-00004.bin",
441
+ "model.visual.blocks.0.norm1.bias": "pytorch_model-00004.bin",
442
+ "model.visual.blocks.0.norm1.weight": "pytorch_model-00004.bin",
443
+ "model.visual.blocks.0.norm2.bias": "pytorch_model-00004.bin",
444
+ "model.visual.blocks.0.norm2.weight": "pytorch_model-00004.bin",
445
+ "model.visual.blocks.1.attn.proj.bias": "pytorch_model-00004.bin",
446
+ "model.visual.blocks.1.attn.proj.weight": "pytorch_model-00004.bin",
447
+ "model.visual.blocks.1.attn.qkv.bias": "pytorch_model-00004.bin",
448
+ "model.visual.blocks.1.attn.qkv.weight": "pytorch_model-00004.bin",
449
+ "model.visual.blocks.1.mlp.linear_fc1.bias": "pytorch_model-00004.bin",
450
+ "model.visual.blocks.1.mlp.linear_fc1.weight": "pytorch_model-00004.bin",
451
+ "model.visual.blocks.1.mlp.linear_fc2.bias": "pytorch_model-00004.bin",
452
+ "model.visual.blocks.1.mlp.linear_fc2.weight": "pytorch_model-00004.bin",
453
+ "model.visual.blocks.1.norm1.bias": "pytorch_model-00004.bin",
454
+ "model.visual.blocks.1.norm1.weight": "pytorch_model-00004.bin",
455
+ "model.visual.blocks.1.norm2.bias": "pytorch_model-00004.bin",
456
+ "model.visual.blocks.1.norm2.weight": "pytorch_model-00004.bin",
457
+ "model.visual.blocks.10.attn.proj.bias": "pytorch_model-00004.bin",
458
+ "model.visual.blocks.10.attn.proj.weight": "pytorch_model-00004.bin",
459
+ "model.visual.blocks.10.attn.qkv.bias": "pytorch_model-00004.bin",
460
+ "model.visual.blocks.10.attn.qkv.weight": "pytorch_model-00004.bin",
461
+ "model.visual.blocks.10.mlp.linear_fc1.bias": "pytorch_model-00004.bin",
462
+ "model.visual.blocks.10.mlp.linear_fc1.weight": "pytorch_model-00004.bin",
463
+ "model.visual.blocks.10.mlp.linear_fc2.bias": "pytorch_model-00004.bin",
464
+ "model.visual.blocks.10.mlp.linear_fc2.weight": "pytorch_model-00004.bin",
465
+ "model.visual.blocks.10.norm1.bias": "pytorch_model-00004.bin",
466
+ "model.visual.blocks.10.norm1.weight": "pytorch_model-00004.bin",
467
+ "model.visual.blocks.10.norm2.bias": "pytorch_model-00004.bin",
468
+ "model.visual.blocks.10.norm2.weight": "pytorch_model-00004.bin",
469
+ "model.visual.blocks.11.attn.proj.bias": "pytorch_model-00004.bin",
470
+ "model.visual.blocks.11.attn.proj.weight": "pytorch_model-00004.bin",
471
+ "model.visual.blocks.11.attn.qkv.bias": "pytorch_model-00004.bin",
472
+ "model.visual.blocks.11.attn.qkv.weight": "pytorch_model-00004.bin",
473
+ "model.visual.blocks.11.mlp.linear_fc1.bias": "pytorch_model-00004.bin",
474
+ "model.visual.blocks.11.mlp.linear_fc1.weight": "pytorch_model-00004.bin",
475
+ "model.visual.blocks.11.mlp.linear_fc2.bias": "pytorch_model-00004.bin",
476
+ "model.visual.blocks.11.mlp.linear_fc2.weight": "pytorch_model-00004.bin",
477
+ "model.visual.blocks.11.norm1.bias": "pytorch_model-00004.bin",
478
+ "model.visual.blocks.11.norm1.weight": "pytorch_model-00004.bin",
479
+ "model.visual.blocks.11.norm2.bias": "pytorch_model-00004.bin",
480
+ "model.visual.blocks.11.norm2.weight": "pytorch_model-00004.bin",
481
+ "model.visual.blocks.12.attn.proj.bias": "pytorch_model-00004.bin",
482
+ "model.visual.blocks.12.attn.proj.weight": "pytorch_model-00004.bin",
483
+ "model.visual.blocks.12.attn.qkv.bias": "pytorch_model-00004.bin",
484
+ "model.visual.blocks.12.attn.qkv.weight": "pytorch_model-00004.bin",
485
+ "model.visual.blocks.12.mlp.linear_fc1.bias": "pytorch_model-00004.bin",
486
+ "model.visual.blocks.12.mlp.linear_fc1.weight": "pytorch_model-00004.bin",
487
+ "model.visual.blocks.12.mlp.linear_fc2.bias": "pytorch_model-00004.bin",
488
+ "model.visual.blocks.12.mlp.linear_fc2.weight": "pytorch_model-00004.bin",
489
+ "model.visual.blocks.12.norm1.bias": "pytorch_model-00004.bin",
490
+ "model.visual.blocks.12.norm1.weight": "pytorch_model-00004.bin",
491
+ "model.visual.blocks.12.norm2.bias": "pytorch_model-00004.bin",
492
+ "model.visual.blocks.12.norm2.weight": "pytorch_model-00004.bin",
493
+ "model.visual.blocks.13.attn.proj.bias": "pytorch_model-00004.bin",
494
+ "model.visual.blocks.13.attn.proj.weight": "pytorch_model-00004.bin",
495
+ "model.visual.blocks.13.attn.qkv.bias": "pytorch_model-00004.bin",
496
+ "model.visual.blocks.13.attn.qkv.weight": "pytorch_model-00004.bin",
497
+ "model.visual.blocks.13.mlp.linear_fc1.bias": "pytorch_model-00004.bin",
498
+ "model.visual.blocks.13.mlp.linear_fc1.weight": "pytorch_model-00004.bin",
499
+ "model.visual.blocks.13.mlp.linear_fc2.bias": "pytorch_model-00004.bin",
500
+ "model.visual.blocks.13.mlp.linear_fc2.weight": "pytorch_model-00004.bin",
501
+ "model.visual.blocks.13.norm1.bias": "pytorch_model-00004.bin",
502
+ "model.visual.blocks.13.norm1.weight": "pytorch_model-00004.bin",
503
+ "model.visual.blocks.13.norm2.bias": "pytorch_model-00004.bin",
504
+ "model.visual.blocks.13.norm2.weight": "pytorch_model-00004.bin",
505
+ "model.visual.blocks.14.attn.proj.bias": "pytorch_model-00004.bin",
506
+ "model.visual.blocks.14.attn.proj.weight": "pytorch_model-00004.bin",
507
+ "model.visual.blocks.14.attn.qkv.bias": "pytorch_model-00004.bin",
508
+ "model.visual.blocks.14.attn.qkv.weight": "pytorch_model-00004.bin",
509
+ "model.visual.blocks.14.mlp.linear_fc1.bias": "pytorch_model-00004.bin",
510
+ "model.visual.blocks.14.mlp.linear_fc1.weight": "pytorch_model-00004.bin",
511
+ "model.visual.blocks.14.mlp.linear_fc2.bias": "pytorch_model-00004.bin",
512
+ "model.visual.blocks.14.mlp.linear_fc2.weight": "pytorch_model-00004.bin",
513
+ "model.visual.blocks.14.norm1.bias": "pytorch_model-00004.bin",
514
+ "model.visual.blocks.14.norm1.weight": "pytorch_model-00004.bin",
515
+ "model.visual.blocks.14.norm2.bias": "pytorch_model-00004.bin",
516
+ "model.visual.blocks.14.norm2.weight": "pytorch_model-00004.bin",
517
+ "model.visual.blocks.15.attn.proj.bias": "pytorch_model-00004.bin",
518
+ "model.visual.blocks.15.attn.proj.weight": "pytorch_model-00004.bin",
519
+ "model.visual.blocks.15.attn.qkv.bias": "pytorch_model-00004.bin",
520
+ "model.visual.blocks.15.attn.qkv.weight": "pytorch_model-00004.bin",
521
+ "model.visual.blocks.15.mlp.linear_fc1.bias": "pytorch_model-00004.bin",
522
+ "model.visual.blocks.15.mlp.linear_fc1.weight": "pytorch_model-00004.bin",
523
+ "model.visual.blocks.15.mlp.linear_fc2.bias": "pytorch_model-00004.bin",
524
+ "model.visual.blocks.15.mlp.linear_fc2.weight": "pytorch_model-00004.bin",
525
+ "model.visual.blocks.15.norm1.bias": "pytorch_model-00004.bin",
526
+ "model.visual.blocks.15.norm1.weight": "pytorch_model-00004.bin",
527
+ "model.visual.blocks.15.norm2.bias": "pytorch_model-00004.bin",
528
+ "model.visual.blocks.15.norm2.weight": "pytorch_model-00004.bin",
529
+ "model.visual.blocks.16.attn.proj.bias": "pytorch_model-00004.bin",
530
+ "model.visual.blocks.16.attn.proj.weight": "pytorch_model-00004.bin",
531
+ "model.visual.blocks.16.attn.qkv.bias": "pytorch_model-00004.bin",
532
+ "model.visual.blocks.16.attn.qkv.weight": "pytorch_model-00004.bin",
533
+ "model.visual.blocks.16.mlp.linear_fc1.bias": "pytorch_model-00004.bin",
534
+ "model.visual.blocks.16.mlp.linear_fc1.weight": "pytorch_model-00004.bin",
535
+ "model.visual.blocks.16.mlp.linear_fc2.bias": "pytorch_model-00004.bin",
536
+ "model.visual.blocks.16.mlp.linear_fc2.weight": "pytorch_model-00004.bin",
537
+ "model.visual.blocks.16.norm1.bias": "pytorch_model-00004.bin",
538
+ "model.visual.blocks.16.norm1.weight": "pytorch_model-00004.bin",
539
+ "model.visual.blocks.16.norm2.bias": "pytorch_model-00004.bin",
540
+ "model.visual.blocks.16.norm2.weight": "pytorch_model-00004.bin",
541
+ "model.visual.blocks.17.attn.proj.bias": "pytorch_model-00004.bin",
542
+ "model.visual.blocks.17.attn.proj.weight": "pytorch_model-00004.bin",
543
+ "model.visual.blocks.17.attn.qkv.bias": "pytorch_model-00004.bin",
544
+ "model.visual.blocks.17.attn.qkv.weight": "pytorch_model-00004.bin",
545
+ "model.visual.blocks.17.mlp.linear_fc1.bias": "pytorch_model-00004.bin",
546
+ "model.visual.blocks.17.mlp.linear_fc1.weight": "pytorch_model-00004.bin",
547
+ "model.visual.blocks.17.mlp.linear_fc2.bias": "pytorch_model-00004.bin",
548
+ "model.visual.blocks.17.mlp.linear_fc2.weight": "pytorch_model-00004.bin",
549
+ "model.visual.blocks.17.norm1.bias": "pytorch_model-00004.bin",
550
+ "model.visual.blocks.17.norm1.weight": "pytorch_model-00004.bin",
551
+ "model.visual.blocks.17.norm2.bias": "pytorch_model-00004.bin",
552
+ "model.visual.blocks.17.norm2.weight": "pytorch_model-00004.bin",
553
+ "model.visual.blocks.18.attn.proj.bias": "pytorch_model-00004.bin",
554
+ "model.visual.blocks.18.attn.proj.weight": "pytorch_model-00004.bin",
555
+ "model.visual.blocks.18.attn.qkv.bias": "pytorch_model-00004.bin",
556
+ "model.visual.blocks.18.attn.qkv.weight": "pytorch_model-00004.bin",
557
+ "model.visual.blocks.18.mlp.linear_fc1.bias": "pytorch_model-00004.bin",
558
+ "model.visual.blocks.18.mlp.linear_fc1.weight": "pytorch_model-00004.bin",
559
+ "model.visual.blocks.18.mlp.linear_fc2.bias": "pytorch_model-00004.bin",
560
+ "model.visual.blocks.18.mlp.linear_fc2.weight": "pytorch_model-00004.bin",
561
+ "model.visual.blocks.18.norm1.bias": "pytorch_model-00004.bin",
562
+ "model.visual.blocks.18.norm1.weight": "pytorch_model-00004.bin",
563
+ "model.visual.blocks.18.norm2.bias": "pytorch_model-00004.bin",
564
+ "model.visual.blocks.18.norm2.weight": "pytorch_model-00004.bin",
565
+ "model.visual.blocks.19.attn.proj.bias": "pytorch_model-00004.bin",
566
+ "model.visual.blocks.19.attn.proj.weight": "pytorch_model-00004.bin",
567
+ "model.visual.blocks.19.attn.qkv.bias": "pytorch_model-00004.bin",
568
+ "model.visual.blocks.19.attn.qkv.weight": "pytorch_model-00004.bin",
569
+ "model.visual.blocks.19.mlp.linear_fc1.bias": "pytorch_model-00004.bin",
570
+ "model.visual.blocks.19.mlp.linear_fc1.weight": "pytorch_model-00004.bin",
571
+ "model.visual.blocks.19.mlp.linear_fc2.bias": "pytorch_model-00004.bin",
572
+ "model.visual.blocks.19.mlp.linear_fc2.weight": "pytorch_model-00004.bin",
573
+ "model.visual.blocks.19.norm1.bias": "pytorch_model-00004.bin",
574
+ "model.visual.blocks.19.norm1.weight": "pytorch_model-00004.bin",
575
+ "model.visual.blocks.19.norm2.bias": "pytorch_model-00004.bin",
576
+ "model.visual.blocks.19.norm2.weight": "pytorch_model-00004.bin",
577
+ "model.visual.blocks.2.attn.proj.bias": "pytorch_model-00004.bin",
578
+ "model.visual.blocks.2.attn.proj.weight": "pytorch_model-00004.bin",
579
+ "model.visual.blocks.2.attn.qkv.bias": "pytorch_model-00004.bin",
580
+ "model.visual.blocks.2.attn.qkv.weight": "pytorch_model-00004.bin",
581
+ "model.visual.blocks.2.mlp.linear_fc1.bias": "pytorch_model-00004.bin",
582
+ "model.visual.blocks.2.mlp.linear_fc1.weight": "pytorch_model-00004.bin",
583
+ "model.visual.blocks.2.mlp.linear_fc2.bias": "pytorch_model-00004.bin",
584
+ "model.visual.blocks.2.mlp.linear_fc2.weight": "pytorch_model-00004.bin",
585
+ "model.visual.blocks.2.norm1.bias": "pytorch_model-00004.bin",
586
+ "model.visual.blocks.2.norm1.weight": "pytorch_model-00004.bin",
587
+ "model.visual.blocks.2.norm2.bias": "pytorch_model-00004.bin",
588
+ "model.visual.blocks.2.norm2.weight": "pytorch_model-00004.bin",
589
+ "model.visual.blocks.20.attn.proj.bias": "pytorch_model-00004.bin",
590
+ "model.visual.blocks.20.attn.proj.weight": "pytorch_model-00004.bin",
591
+ "model.visual.blocks.20.attn.qkv.bias": "pytorch_model-00004.bin",
592
+ "model.visual.blocks.20.attn.qkv.weight": "pytorch_model-00004.bin",
593
+ "model.visual.blocks.20.mlp.linear_fc1.bias": "pytorch_model-00004.bin",
594
+ "model.visual.blocks.20.mlp.linear_fc1.weight": "pytorch_model-00004.bin",
595
+ "model.visual.blocks.20.mlp.linear_fc2.bias": "pytorch_model-00004.bin",
596
+ "model.visual.blocks.20.mlp.linear_fc2.weight": "pytorch_model-00004.bin",
597
+ "model.visual.blocks.20.norm1.bias": "pytorch_model-00004.bin",
598
+ "model.visual.blocks.20.norm1.weight": "pytorch_model-00004.bin",
599
+ "model.visual.blocks.20.norm2.bias": "pytorch_model-00004.bin",
600
+ "model.visual.blocks.20.norm2.weight": "pytorch_model-00004.bin",
601
+ "model.visual.blocks.21.attn.proj.bias": "pytorch_model-00004.bin",
602
+ "model.visual.blocks.21.attn.proj.weight": "pytorch_model-00004.bin",
603
+ "model.visual.blocks.21.attn.qkv.bias": "pytorch_model-00004.bin",
604
+ "model.visual.blocks.21.attn.qkv.weight": "pytorch_model-00004.bin",
605
+ "model.visual.blocks.21.mlp.linear_fc1.bias": "pytorch_model-00004.bin",
606
+ "model.visual.blocks.21.mlp.linear_fc1.weight": "pytorch_model-00004.bin",
607
+ "model.visual.blocks.21.mlp.linear_fc2.bias": "pytorch_model-00004.bin",
608
+ "model.visual.blocks.21.mlp.linear_fc2.weight": "pytorch_model-00004.bin",
609
+ "model.visual.blocks.21.norm1.bias": "pytorch_model-00004.bin",
610
+ "model.visual.blocks.21.norm1.weight": "pytorch_model-00004.bin",
611
+ "model.visual.blocks.21.norm2.bias": "pytorch_model-00004.bin",
612
+ "model.visual.blocks.21.norm2.weight": "pytorch_model-00004.bin",
613
+ "model.visual.blocks.22.attn.proj.bias": "pytorch_model-00004.bin",
614
+ "model.visual.blocks.22.attn.proj.weight": "pytorch_model-00004.bin",
615
+ "model.visual.blocks.22.attn.qkv.bias": "pytorch_model-00004.bin",
616
+ "model.visual.blocks.22.attn.qkv.weight": "pytorch_model-00004.bin",
617
+ "model.visual.blocks.22.mlp.linear_fc1.bias": "pytorch_model-00004.bin",
618
+ "model.visual.blocks.22.mlp.linear_fc1.weight": "pytorch_model-00004.bin",
619
+ "model.visual.blocks.22.mlp.linear_fc2.bias": "pytorch_model-00004.bin",
620
+ "model.visual.blocks.22.mlp.linear_fc2.weight": "pytorch_model-00004.bin",
621
+ "model.visual.blocks.22.norm1.bias": "pytorch_model-00004.bin",
622
+ "model.visual.blocks.22.norm1.weight": "pytorch_model-00004.bin",
623
+ "model.visual.blocks.22.norm2.bias": "pytorch_model-00004.bin",
624
+ "model.visual.blocks.22.norm2.weight": "pytorch_model-00004.bin",
625
+ "model.visual.blocks.23.attn.proj.bias": "pytorch_model-00004.bin",
626
+ "model.visual.blocks.23.attn.proj.weight": "pytorch_model-00004.bin",
627
+ "model.visual.blocks.23.attn.qkv.bias": "pytorch_model-00004.bin",
628
+ "model.visual.blocks.23.attn.qkv.weight": "pytorch_model-00004.bin",
629
+ "model.visual.blocks.23.mlp.linear_fc1.bias": "pytorch_model-00004.bin",
630
+ "model.visual.blocks.23.mlp.linear_fc1.weight": "pytorch_model-00004.bin",
631
+ "model.visual.blocks.23.mlp.linear_fc2.bias": "pytorch_model-00004.bin",
632
+ "model.visual.blocks.23.mlp.linear_fc2.weight": "pytorch_model-00004.bin",
633
+ "model.visual.blocks.23.norm1.bias": "pytorch_model-00004.bin",
634
+ "model.visual.blocks.23.norm1.weight": "pytorch_model-00004.bin",
635
+ "model.visual.blocks.23.norm2.bias": "pytorch_model-00004.bin",
636
+ "model.visual.blocks.23.norm2.weight": "pytorch_model-00004.bin",
637
+ "model.visual.blocks.24.attn.proj.bias": "pytorch_model-00004.bin",
638
+ "model.visual.blocks.24.attn.proj.weight": "pytorch_model-00004.bin",
639
+ "model.visual.blocks.24.attn.qkv.bias": "pytorch_model-00004.bin",
640
+ "model.visual.blocks.24.attn.qkv.weight": "pytorch_model-00004.bin",
641
+ "model.visual.blocks.24.mlp.linear_fc1.bias": "pytorch_model-00004.bin",
642
+ "model.visual.blocks.24.mlp.linear_fc1.weight": "pytorch_model-00004.bin",
643
+ "model.visual.blocks.24.mlp.linear_fc2.bias": "pytorch_model-00004.bin",
644
+ "model.visual.blocks.24.mlp.linear_fc2.weight": "pytorch_model-00004.bin",
645
+ "model.visual.blocks.24.norm1.bias": "pytorch_model-00004.bin",
646
+ "model.visual.blocks.24.norm1.weight": "pytorch_model-00004.bin",
647
+ "model.visual.blocks.24.norm2.bias": "pytorch_model-00004.bin",
648
+ "model.visual.blocks.24.norm2.weight": "pytorch_model-00004.bin",
649
+ "model.visual.blocks.25.attn.proj.bias": "pytorch_model-00004.bin",
650
+ "model.visual.blocks.25.attn.proj.weight": "pytorch_model-00004.bin",
651
+ "model.visual.blocks.25.attn.qkv.bias": "pytorch_model-00004.bin",
652
+ "model.visual.blocks.25.attn.qkv.weight": "pytorch_model-00004.bin",
653
+ "model.visual.blocks.25.mlp.linear_fc1.bias": "pytorch_model-00004.bin",
654
+ "model.visual.blocks.25.mlp.linear_fc1.weight": "pytorch_model-00004.bin",
655
+ "model.visual.blocks.25.mlp.linear_fc2.bias": "pytorch_model-00004.bin",
656
+ "model.visual.blocks.25.mlp.linear_fc2.weight": "pytorch_model-00004.bin",
657
+ "model.visual.blocks.25.norm1.bias": "pytorch_model-00004.bin",
658
+ "model.visual.blocks.25.norm1.weight": "pytorch_model-00004.bin",
659
+ "model.visual.blocks.25.norm2.bias": "pytorch_model-00004.bin",
660
+ "model.visual.blocks.25.norm2.weight": "pytorch_model-00004.bin",
661
+ "model.visual.blocks.26.attn.proj.bias": "pytorch_model-00004.bin",
662
+ "model.visual.blocks.26.attn.proj.weight": "pytorch_model-00004.bin",
663
+ "model.visual.blocks.26.attn.qkv.bias": "pytorch_model-00004.bin",
664
+ "model.visual.blocks.26.attn.qkv.weight": "pytorch_model-00004.bin",
665
+ "model.visual.blocks.26.mlp.linear_fc1.bias": "pytorch_model-00004.bin",
666
+ "model.visual.blocks.26.mlp.linear_fc1.weight": "pytorch_model-00004.bin",
667
+ "model.visual.blocks.26.mlp.linear_fc2.bias": "pytorch_model-00004.bin",
668
+ "model.visual.blocks.26.mlp.linear_fc2.weight": "pytorch_model-00004.bin",
669
+ "model.visual.blocks.26.norm1.bias": "pytorch_model-00004.bin",
670
+ "model.visual.blocks.26.norm1.weight": "pytorch_model-00004.bin",
671
+ "model.visual.blocks.26.norm2.bias": "pytorch_model-00004.bin",
672
+ "model.visual.blocks.26.norm2.weight": "pytorch_model-00004.bin",
673
+ "model.visual.blocks.3.attn.proj.bias": "pytorch_model-00004.bin",
674
+ "model.visual.blocks.3.attn.proj.weight": "pytorch_model-00004.bin",
675
+ "model.visual.blocks.3.attn.qkv.bias": "pytorch_model-00004.bin",
676
+ "model.visual.blocks.3.attn.qkv.weight": "pytorch_model-00004.bin",
677
+ "model.visual.blocks.3.mlp.linear_fc1.bias": "pytorch_model-00004.bin",
678
+ "model.visual.blocks.3.mlp.linear_fc1.weight": "pytorch_model-00004.bin",
679
+ "model.visual.blocks.3.mlp.linear_fc2.bias": "pytorch_model-00004.bin",
680
+ "model.visual.blocks.3.mlp.linear_fc2.weight": "pytorch_model-00004.bin",
681
+ "model.visual.blocks.3.norm1.bias": "pytorch_model-00004.bin",
682
+ "model.visual.blocks.3.norm1.weight": "pytorch_model-00004.bin",
683
+ "model.visual.blocks.3.norm2.bias": "pytorch_model-00004.bin",
684
+ "model.visual.blocks.3.norm2.weight": "pytorch_model-00004.bin",
685
+ "model.visual.blocks.4.attn.proj.bias": "pytorch_model-00004.bin",
686
+ "model.visual.blocks.4.attn.proj.weight": "pytorch_model-00004.bin",
687
+ "model.visual.blocks.4.attn.qkv.bias": "pytorch_model-00004.bin",
688
+ "model.visual.blocks.4.attn.qkv.weight": "pytorch_model-00004.bin",
689
+ "model.visual.blocks.4.mlp.linear_fc1.bias": "pytorch_model-00004.bin",
690
+ "model.visual.blocks.4.mlp.linear_fc1.weight": "pytorch_model-00004.bin",
691
+ "model.visual.blocks.4.mlp.linear_fc2.bias": "pytorch_model-00004.bin",
692
+ "model.visual.blocks.4.mlp.linear_fc2.weight": "pytorch_model-00004.bin",
693
+ "model.visual.blocks.4.norm1.bias": "pytorch_model-00004.bin",
694
+ "model.visual.blocks.4.norm1.weight": "pytorch_model-00004.bin",
695
+ "model.visual.blocks.4.norm2.bias": "pytorch_model-00004.bin",
696
+ "model.visual.blocks.4.norm2.weight": "pytorch_model-00004.bin",
697
+ "model.visual.blocks.5.attn.proj.bias": "pytorch_model-00004.bin",
698
+ "model.visual.blocks.5.attn.proj.weight": "pytorch_model-00004.bin",
699
+ "model.visual.blocks.5.attn.qkv.bias": "pytorch_model-00004.bin",
700
+ "model.visual.blocks.5.attn.qkv.weight": "pytorch_model-00004.bin",
701
+ "model.visual.blocks.5.mlp.linear_fc1.bias": "pytorch_model-00004.bin",
702
+ "model.visual.blocks.5.mlp.linear_fc1.weight": "pytorch_model-00004.bin",
703
+ "model.visual.blocks.5.mlp.linear_fc2.bias": "pytorch_model-00004.bin",
704
+ "model.visual.blocks.5.mlp.linear_fc2.weight": "pytorch_model-00004.bin",
705
+ "model.visual.blocks.5.norm1.bias": "pytorch_model-00004.bin",
706
+ "model.visual.blocks.5.norm1.weight": "pytorch_model-00004.bin",
707
+ "model.visual.blocks.5.norm2.bias": "pytorch_model-00004.bin",
708
+ "model.visual.blocks.5.norm2.weight": "pytorch_model-00004.bin",
709
+ "model.visual.blocks.6.attn.proj.bias": "pytorch_model-00004.bin",
710
+ "model.visual.blocks.6.attn.proj.weight": "pytorch_model-00004.bin",
711
+ "model.visual.blocks.6.attn.qkv.bias": "pytorch_model-00004.bin",
712
+ "model.visual.blocks.6.attn.qkv.weight": "pytorch_model-00004.bin",
713
+ "model.visual.blocks.6.mlp.linear_fc1.bias": "pytorch_model-00004.bin",
714
+ "model.visual.blocks.6.mlp.linear_fc1.weight": "pytorch_model-00004.bin",
715
+ "model.visual.blocks.6.mlp.linear_fc2.bias": "pytorch_model-00004.bin",
716
+ "model.visual.blocks.6.mlp.linear_fc2.weight": "pytorch_model-00004.bin",
717
+ "model.visual.blocks.6.norm1.bias": "pytorch_model-00004.bin",
718
+ "model.visual.blocks.6.norm1.weight": "pytorch_model-00004.bin",
719
+ "model.visual.blocks.6.norm2.bias": "pytorch_model-00004.bin",
720
+ "model.visual.blocks.6.norm2.weight": "pytorch_model-00004.bin",
721
+ "model.visual.blocks.7.attn.proj.bias": "pytorch_model-00004.bin",
722
+ "model.visual.blocks.7.attn.proj.weight": "pytorch_model-00004.bin",
723
+ "model.visual.blocks.7.attn.qkv.bias": "pytorch_model-00004.bin",
724
+ "model.visual.blocks.7.attn.qkv.weight": "pytorch_model-00004.bin",
725
+ "model.visual.blocks.7.mlp.linear_fc1.bias": "pytorch_model-00004.bin",
726
+ "model.visual.blocks.7.mlp.linear_fc1.weight": "pytorch_model-00004.bin",
727
+ "model.visual.blocks.7.mlp.linear_fc2.bias": "pytorch_model-00004.bin",
728
+ "model.visual.blocks.7.mlp.linear_fc2.weight": "pytorch_model-00004.bin",
729
+ "model.visual.blocks.7.norm1.bias": "pytorch_model-00004.bin",
730
+ "model.visual.blocks.7.norm1.weight": "pytorch_model-00004.bin",
731
+ "model.visual.blocks.7.norm2.bias": "pytorch_model-00004.bin",
732
+ "model.visual.blocks.7.norm2.weight": "pytorch_model-00004.bin",
733
+ "model.visual.blocks.8.attn.proj.bias": "pytorch_model-00004.bin",
734
+ "model.visual.blocks.8.attn.proj.weight": "pytorch_model-00004.bin",
735
+ "model.visual.blocks.8.attn.qkv.bias": "pytorch_model-00004.bin",
736
+ "model.visual.blocks.8.attn.qkv.weight": "pytorch_model-00004.bin",
737
+ "model.visual.blocks.8.mlp.linear_fc1.bias": "pytorch_model-00004.bin",
738
+ "model.visual.blocks.8.mlp.linear_fc1.weight": "pytorch_model-00004.bin",
739
+ "model.visual.blocks.8.mlp.linear_fc2.bias": "pytorch_model-00004.bin",
740
+ "model.visual.blocks.8.mlp.linear_fc2.weight": "pytorch_model-00004.bin",
741
+ "model.visual.blocks.8.norm1.bias": "pytorch_model-00004.bin",
742
+ "model.visual.blocks.8.norm1.weight": "pytorch_model-00004.bin",
743
+ "model.visual.blocks.8.norm2.bias": "pytorch_model-00004.bin",
744
+ "model.visual.blocks.8.norm2.weight": "pytorch_model-00004.bin",
745
+ "model.visual.blocks.9.attn.proj.bias": "pytorch_model-00004.bin",
746
+ "model.visual.blocks.9.attn.proj.weight": "pytorch_model-00004.bin",
747
+ "model.visual.blocks.9.attn.qkv.bias": "pytorch_model-00004.bin",
748
+ "model.visual.blocks.9.attn.qkv.weight": "pytorch_model-00004.bin",
749
+ "model.visual.blocks.9.mlp.linear_fc1.bias": "pytorch_model-00004.bin",
750
+ "model.visual.blocks.9.mlp.linear_fc1.weight": "pytorch_model-00004.bin",
751
+ "model.visual.blocks.9.mlp.linear_fc2.bias": "pytorch_model-00004.bin",
752
+ "model.visual.blocks.9.mlp.linear_fc2.weight": "pytorch_model-00004.bin",
753
+ "model.visual.blocks.9.norm1.bias": "pytorch_model-00004.bin",
754
+ "model.visual.blocks.9.norm1.weight": "pytorch_model-00004.bin",
755
+ "model.visual.blocks.9.norm2.bias": "pytorch_model-00004.bin",
756
+ "model.visual.blocks.9.norm2.weight": "pytorch_model-00004.bin",
757
+ "model.visual.merger.linear_fc1.bias": "pytorch_model-00004.bin",
758
+ "model.visual.merger.linear_fc1.weight": "pytorch_model-00004.bin",
759
+ "model.visual.merger.linear_fc2.bias": "pytorch_model-00004.bin",
760
+ "model.visual.merger.linear_fc2.weight": "pytorch_model-00004.bin",
761
+ "model.visual.merger.norm.bias": "pytorch_model-00004.bin",
762
+ "model.visual.merger.norm.weight": "pytorch_model-00004.bin",
763
+ "model.visual.patch_embed.proj.bias": "pytorch_model-00004.bin",
764
+ "model.visual.patch_embed.proj.weight": "pytorch_model-00004.bin",
765
+ "model.visual.pos_embed.weight": "pytorch_model-00004.bin"
766
+ }
767
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
3
+ size 19989325
tokenizer_config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false,
13
+ "local_files_only": false,
14
+ "model_max_length": 262144,
15
+ "model_specific_special_tokens": {
16
+ "audio_bos_token": "<|audio_start|>",
17
+ "audio_eos_token": "<|audio_end|>",
18
+ "audio_token": "<|audio_pad|>",
19
+ "image_token": "<|image_pad|>",
20
+ "video_token": "<|video_pad|>",
21
+ "vision_bos_token": "<|vision_start|>",
22
+ "vision_eos_token": "<|vision_end|>"
23
+ },
24
+ "pad_token": "<|endoftext|>",
25
+ "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+",
26
+ "processor_class": "Qwen3VLProcessor",
27
+ "split_special_tokens": false,
28
+ "tokenizer_class": "Qwen2Tokenizer",
29
+ "unk_token": null,
30
+ "video_token": "<|video_pad|>",
31
+ "vision_bos_token": "<|vision_start|>",
32
+ "vision_eos_token": "<|vision_end|>"
33
+ }