sabux commited on
Commit
d487fce
·
verified ·
1 Parent(s): 09bef08

Add files using upload-large-folder tool

Browse files
README.md CHANGED
@@ -1,21 +1,8 @@
1
  ---
2
- base_model: unsloth/Qwen3.5-2B
3
  tags:
4
- - text-generation-inference
5
- - transformers
6
  - unsloth
7
- - qwen3_5
8
- license: apache-2.0
9
- language:
10
- - en
11
  ---
12
-
13
- # Uploaded finetuned model
14
-
15
- - **Developed by:** sabux
16
- - **License:** apache-2.0
17
- - **Finetuned from model :** unsloth/Qwen3.5-2B
18
-
19
- This qwen3_5 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
20
-
21
- [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
 
1
  ---
 
2
  tags:
 
 
3
  - unsloth
4
+ - mlx
5
+ base_model: unsloth/Qwen3-0.6B
6
+ library_name: mlx
7
+ pipeline_tag: text-generation
8
  ---
 
 
 
 
 
 
 
 
 
 
added_tokens.json CHANGED
@@ -1,35 +1,28 @@
1
  {
2
- "</think>": 248069,
3
- "</tool_call>": 248059,
4
- "</tool_response>": 248067,
5
- "<think>": 248068,
6
- "<tool_call>": 248058,
7
- "<tool_response>": 248066,
8
- "<tts_pad>": 248072,
9
- "<tts_text_bos>": 248073,
10
- "<tts_text_bos_single>": 248075,
11
- "<tts_text_eod>": 248074,
12
- "<|audio_end|>": 248071,
13
- "<|audio_pad|>": 248076,
14
- "<|audio_start|>": 248070,
15
- "<|box_end|>": 248050,
16
- "<|box_start|>": 248049,
17
- "<|endoftext|>": 248044,
18
- "<|file_sep|>": 248065,
19
- "<|fim_middle|>": 248061,
20
- "<|fim_pad|>": 248063,
21
- "<|fim_prefix|>": 248060,
22
- "<|fim_suffix|>": 248062,
23
- "<|im_end|>": 248046,
24
- "<|im_start|>": 248045,
25
- "<|image_pad|>": 248056,
26
- "<|object_ref_end|>": 248048,
27
- "<|object_ref_start|>": 248047,
28
- "<|quad_end|>": 248052,
29
- "<|quad_start|>": 248051,
30
- "<|repo_name|>": 248064,
31
- "<|video_pad|>": 248057,
32
- "<|vision_end|>": 248054,
33
- "<|vision_pad|>": 248055,
34
- "<|vision_start|>": 248053
35
  }
 
1
  {
2
+ "</think>": 151668,
3
+ "</tool_call>": 151658,
4
+ "</tool_response>": 151666,
5
+ "<think>": 151667,
6
+ "<tool_call>": 151657,
7
+ "<tool_response>": 151665,
8
+ "<|box_end|>": 151649,
9
+ "<|box_start|>": 151648,
10
+ "<|endoftext|>": 151643,
11
+ "<|file_sep|>": 151664,
12
+ "<|fim_middle|>": 151660,
13
+ "<|fim_pad|>": 151662,
14
+ "<|fim_prefix|>": 151659,
15
+ "<|fim_suffix|>": 151661,
16
+ "<|im_end|>": 151645,
17
+ "<|im_start|>": 151644,
18
+ "<|image_pad|>": 151655,
19
+ "<|object_ref_end|>": 151647,
20
+ "<|object_ref_start|>": 151646,
21
+ "<|quad_end|>": 151651,
22
+ "<|quad_start|>": 151650,
23
+ "<|repo_name|>": 151663,
24
+ "<|video_pad|>": 151656,
25
+ "<|vision_end|>": 151653,
26
+ "<|vision_pad|>": 151654,
27
+ "<|vision_start|>": 151652
 
 
 
 
 
 
 
28
  }
chat_template.jinja CHANGED
@@ -1,158 +1,99 @@
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
- {%- set num_sys = 0 %}
46
- {%- set merged_system = '' %}
47
- {%- if messages[0].role == 'system' or messages[0].role == 'developer' %}
48
- {%- set first = render_content(messages[0].content, false, true)|trim %}
49
- {%- if messages|length > 1 and (messages[1].role == 'system' or messages[1].role == 'developer') %}
50
- {%- set second = render_content(messages[1].content, false, true)|trim %}
51
- {%- set merged_system = first + '\n' + second %}
52
- {%- set num_sys = 2 %}
53
- {%- else %}
54
- {%- set merged_system = first %}
55
- {%- set num_sys = 1 %}
56
- {%- endif %}
57
- {%- endif %}
58
- {%- if tools and tools is iterable and tools is not mapping %}
59
  {{- '<|im_start|>system\n' }}
60
- {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
 
 
 
61
  {%- for tool in tools %}
62
  {{- "\n" }}
63
  {{- tool | tojson }}
64
  {%- endfor %}
65
- {{- "\n</tools>" }}
66
- {{- '\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>' }}
67
- {%- if merged_system %}
68
- {{- '\n\n' + merged_system }}
69
- {%- endif %}
70
- {{- '<|im_end|>\n' }}
71
  {%- else %}
72
- {%- if merged_system %}
73
- {{- '<|im_start|>system\n' + merged_system + '<|im_end|>\n' }}
74
  {%- endif %}
75
  {%- endif %}
76
  {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
77
- {%- for message in messages[::-1] %}
78
  {%- set index = (messages|length - 1) - loop.index0 %}
79
- {%- if ns.multi_step_tool and message.role == "user" %}
80
- {%- set content = render_content(message.content, false)|trim %}
81
- {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
82
- {%- set ns.multi_step_tool = false %}
83
- {%- set ns.last_query_index = index %}
84
- {%- endif %}
 
 
 
 
 
 
 
 
 
85
  {%- endif %}
86
  {%- endfor %}
87
  {%- for message in messages %}
88
- {%- if loop.index0 >= num_sys and message.role != "system" and message.role != "developer" %}
89
- {%- set content = render_content(message.content, true)|trim %}
90
- {%- if message.role == "user" %}
91
- {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
92
  {%- elif message.role == "assistant" %}
 
 
93
  {%- set reasoning_content = '' %}
94
- {%- if message.reasoning_content is string %}
95
  {%- set reasoning_content = message.reasoning_content %}
96
  {%- else %}
97
- {%- if '</think>' in content %}
98
- {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
99
- {%- set content = content.split('</think>')[-1].lstrip('\n') %}
 
100
  {%- endif %}
101
  {%- endif %}
102
- {%- set reasoning_content = reasoning_content|trim %}
103
  {%- if loop.index0 > ns.last_query_index %}
104
- {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
 
 
 
 
105
  {%- else %}
106
  {{- '<|im_start|>' + message.role + '\n' + content }}
107
  {%- endif %}
108
- {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
109
  {%- for tool_call in message.tool_calls %}
110
- {%- if tool_call.function is defined %}
 
 
 
111
  {%- set tool_call = tool_call.function %}
112
  {%- endif %}
113
- {%- if loop.first %}
114
- {%- if content|trim %}
115
- {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
116
- {%- else %}
117
- {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
118
- {%- endif %}
119
  {%- else %}
120
- {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
121
- {%- endif %}
122
- {%- if tool_call.arguments is mapping %}
123
- {%- for args_name in tool_call.arguments %}
124
- {%- set args_value = tool_call.arguments[args_name] %}
125
- {{- '<parameter=' + args_name + '>\n' }}
126
- {%- 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 %}
127
- {{- args_value }}
128
- {{- '\n</parameter>\n' }}
129
- {%- endfor %}
130
  {%- endif %}
131
- {{- '</function>\n</tool_call>' }}
132
  {%- endfor %}
133
  {%- endif %}
134
  {{- '<|im_end|>\n' }}
135
  {%- elif message.role == "tool" %}
136
- {%- if loop.previtem and loop.previtem.role != "tool" %}
137
  {{- '<|im_start|>user' }}
138
  {%- endif %}
139
  {{- '\n<tool_response>\n' }}
140
- {{- content }}
141
  {{- '\n</tool_response>' }}
142
- {%- if not loop.last and loop.nextitem.role != "tool" %}
143
- {{- '<|im_end|>\n' }}
144
- {%- elif loop.last %}
145
  {{- '<|im_end|>\n' }}
146
  {%- endif %}
147
  {%- endif %}
148
- {%- endif %}
149
  {%- endfor %}
150
  {%- if add_generation_prompt %}
151
  {{- '<|im_start|>assistant\n' }}
152
- {%- if enable_thinking is defined and enable_thinking is true %}
153
- {{- '<think>\n' }}
154
- {%- else %}
155
  {{- '<think>\n\n</think>\n\n' }}
156
  {%- endif %}
157
- {%- endif %}
158
- {#- Unsloth fixes - developer role, tool calling #}
 
1
+ {%- if tools %}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
  {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0].role == 'system' %}
4
+ {{- messages[0].content + '\n\n' }}
5
+ {%- endif %}
6
+ {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
7
  {%- for tool in tools %}
8
  {{- "\n" }}
9
  {{- tool | tojson }}
10
  {%- endfor %}
11
+ {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
 
 
 
 
 
12
  {%- else %}
13
+ {%- if messages[0].role == 'system' %}
14
+ {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
15
  {%- endif %}
16
  {%- endif %}
17
  {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
18
+ {%- for forward_message in messages %}
19
  {%- set index = (messages|length - 1) - loop.index0 %}
20
+ {%- set message = messages[index] %}
21
+ {%- set current_content = message.content if message.content is defined and message.content is not none else '' %}
22
+ {%- set tool_start = '<tool_response>' %}
23
+ {%- set tool_start_length = tool_start|length %}
24
+ {%- set start_of_message = current_content[:tool_start_length] %}
25
+ {%- set tool_end = '</tool_response>' %}
26
+ {%- set tool_end_length = tool_end|length %}
27
+ {%- set start_pos = (current_content|length) - tool_end_length %}
28
+ {%- if start_pos < 0 %}
29
+ {%- set start_pos = 0 %}
30
+ {%- endif %}
31
+ {%- set end_of_message = current_content[start_pos:] %}
32
+ {%- if ns.multi_step_tool and message.role == "user" and not(start_of_message == tool_start and end_of_message == tool_end) %}
33
+ {%- set ns.multi_step_tool = false %}
34
+ {%- set ns.last_query_index = index %}
35
  {%- endif %}
36
  {%- endfor %}
37
  {%- for message in messages %}
38
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
39
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
 
 
40
  {%- elif message.role == "assistant" %}
41
+ {%- set m_content = message.content if message.content is defined and message.content is not none else '' %}
42
+ {%- set content = m_content %}
43
  {%- set reasoning_content = '' %}
44
+ {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
45
  {%- set reasoning_content = message.reasoning_content %}
46
  {%- else %}
47
+ {%- if '</think>' in m_content %}
48
+ {%- set content = (m_content.split('</think>')|last).lstrip('\n') %}
49
+ {%- set reasoning_content = (m_content.split('</think>')|first).rstrip('\n') %}
50
+ {%- set reasoning_content = (reasoning_content.split('<think>')|last).lstrip('\n') %}
51
  {%- endif %}
52
  {%- endif %}
 
53
  {%- if loop.index0 > ns.last_query_index %}
54
+ {%- if loop.last or (not loop.last and (not reasoning_content.strip() == '')) %}
55
+ {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
56
+ {%- else %}
57
+ {{- '<|im_start|>' + message.role + '\n' + content }}
58
+ {%- endif %}
59
  {%- else %}
60
  {{- '<|im_start|>' + message.role + '\n' + content }}
61
  {%- endif %}
62
+ {%- if message.tool_calls %}
63
  {%- for tool_call in message.tool_calls %}
64
+ {%- if (loop.first and content) or (not loop.first) %}
65
+ {{- '\n' }}
66
+ {%- endif %}
67
+ {%- if tool_call.function %}
68
  {%- set tool_call = tool_call.function %}
69
  {%- endif %}
70
+ {{- '<tool_call>\n{"name": "' }}
71
+ {{- tool_call.name }}
72
+ {{- '", "arguments": ' }}
73
+ {%- if tool_call.arguments is string %}
74
+ {{- tool_call.arguments }}
 
75
  {%- else %}
76
+ {{- tool_call.arguments | tojson }}
 
 
 
 
 
 
 
 
 
77
  {%- endif %}
78
+ {{- '}\n</tool_call>' }}
79
  {%- endfor %}
80
  {%- endif %}
81
  {{- '<|im_end|>\n' }}
82
  {%- elif message.role == "tool" %}
83
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
84
  {{- '<|im_start|>user' }}
85
  {%- endif %}
86
  {{- '\n<tool_response>\n' }}
87
+ {{- message.content }}
88
  {{- '\n</tool_response>' }}
89
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
 
 
90
  {{- '<|im_end|>\n' }}
91
  {%- endif %}
92
  {%- endif %}
 
93
  {%- endfor %}
94
  {%- if add_generation_prompt %}
95
  {{- '<|im_start|>assistant\n' }}
96
+ {%- if enable_thinking is defined and enable_thinking is false %}
 
 
97
  {{- '<think>\n\n</think>\n\n' }}
98
  {%- endif %}
99
+ {%- endif %}
 
config.json CHANGED
@@ -1,105 +1,34 @@
1
  {
2
  "architectures": [
3
- "Qwen3_5ForConditionalGeneration"
4
  ],
5
- "torch_dtype": "bfloat16",
6
- "image_token_id": 248056,
7
- "model_name": "unsloth/Qwen3.5-2B",
8
- "model_type": "qwen3_5",
9
- "mtp_num_hidden_layers": 1,
10
- "pad_token_id": 248055,
11
- "text_config": {
12
- "attention_bias": false,
13
- "attention_dropout": 0.0,
14
- "attn_output_gate": true,
15
- "bos_token_id": null,
16
- "torch_dtype": "bfloat16",
17
- "eos_token_id": 248044,
18
- "full_attention_interval": 4,
19
- "head_dim": 256,
20
- "hidden_act": "silu",
21
- "hidden_size": 2048,
22
- "initializer_range": 0.02,
23
- "intermediate_size": 6144,
24
- "layer_types": [
25
- "linear_attention",
26
- "linear_attention",
27
- "linear_attention",
28
- "full_attention",
29
- "linear_attention",
30
- "linear_attention",
31
- "linear_attention",
32
- "full_attention",
33
- "linear_attention",
34
- "linear_attention",
35
- "linear_attention",
36
- "full_attention",
37
- "linear_attention",
38
- "linear_attention",
39
- "linear_attention",
40
- "full_attention",
41
- "linear_attention",
42
- "linear_attention",
43
- "linear_attention",
44
- "full_attention",
45
- "linear_attention",
46
- "linear_attention",
47
- "linear_attention",
48
- "full_attention"
49
- ],
50
- "linear_conv_kernel_dim": 4,
51
- "linear_key_head_dim": 128,
52
- "linear_num_key_heads": 16,
53
- "linear_num_value_heads": 16,
54
- "linear_value_head_dim": 128,
55
- "mamba_ssm_dtype": "float32",
56
- "max_position_embeddings": 262144,
57
- "mlp_only_layers": [],
58
- "model_type": "qwen3_5_text",
59
- "mtp_num_hidden_layers": 1,
60
- "mtp_use_dedicated_embeddings": false,
61
- "num_attention_heads": 8,
62
- "num_hidden_layers": 24,
63
- "num_key_value_heads": 2,
64
- "pad_token_id": null,
65
- "partial_rotary_factor": 0.25,
66
- "rms_norm_eps": 1e-06,
67
- "rope_parameters": {
68
- "mrope_interleaved": true,
69
- "mrope_section": [
70
- 11,
71
- 11,
72
- 10
73
- ],
74
- "partial_rotary_factor": 0.25,
75
- "rope_theta": 10000000,
76
- "rope_type": "default"
77
- },
78
- "tie_word_embeddings": true,
79
- "use_cache": true,
80
- "vocab_size": 248320
81
- },
82
  "tie_word_embeddings": true,
83
- "unsloth_fixed_mtp": true,
84
- "unsloth_version": "2026.5.9",
85
- "video_token_id": 248057,
86
- "vision_config": {
87
- "deepstack_visual_indexes": [],
88
- "depth": 24,
89
- "torch_dtype": "bfloat16",
90
- "hidden_act": "gelu_pytorch_tanh",
91
- "hidden_size": 1024,
92
- "in_channels": 3,
93
- "initializer_range": 0.02,
94
- "intermediate_size": 4096,
95
- "model_type": "qwen3_5",
96
- "num_heads": 16,
97
- "num_position_embeddings": 2304,
98
- "out_hidden_size": 2048,
99
- "patch_size": 16,
100
- "spatial_merge_size": 2,
101
- "temporal_patch_size": 2
102
- },
103
- "vision_end_token_id": 248054,
104
- "vision_start_token_id": 248053
105
  }
 
1
  {
2
  "architectures": [
3
+ "Qwen3ForCausalLM"
4
  ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "eos_token_id": [
8
+ 151645,
9
+ 151643
10
+ ],
11
+ "head_dim": 128,
12
+ "hidden_act": "silu",
13
+ "hidden_size": 1024,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 3072,
16
+ "max_position_embeddings": 40960,
17
+ "max_window_layers": 28,
18
+ "model_type": "qwen3",
19
+ "num_attention_heads": 16,
20
+ "num_hidden_layers": 28,
21
+ "num_key_value_heads": 8,
22
+ "pad_token_id": 151654,
23
+ "rms_norm_eps": 1e-06,
24
+ "rope_scaling": null,
25
+ "rope_theta": 1000000,
26
+ "sliding_window": null,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
27
  "tie_word_embeddings": true,
28
+ "torch_dtype": "bfloat16",
29
+ "transformers_version": "4.52.4",
30
+ "unsloth_fixed": true,
31
+ "use_cache": true,
32
+ "use_sliding_window": false,
33
+ "vocab_size": 151936
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
34
  }
export_metadata.json CHANGED
@@ -1,3 +1,3 @@
1
  {
2
- "base_model": "unsloth/Qwen3.5-2B"
3
  }
 
1
  {
2
+ "base_model": "unsloth/Qwen3-0.6B"
3
  }
generation_config.json CHANGED
@@ -1,7 +1,14 @@
1
  {
2
- "_from_model_config": true,
3
- "eos_token_id": 248044,
4
- "pad_token_id": 248055,
5
- "transformers_version": "5.3.0",
6
- "use_cache": true
 
 
 
 
 
 
 
7
  }
 
1
  {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "max_length": 40960,
9
+ "pad_token_id": 151654,
10
+ "temperature": 0.6,
11
+ "top_k": 20,
12
+ "top_p": 0.95,
13
+ "transformers_version": "4.52.4"
14
  }
merges.txt CHANGED
The diff for this file is too large to render. See raw diff
 
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d74a6ec2ead6ef4bdce7a6767acebc263d9e55a843bb1ae034a2f88def0a35c9
3
- size 4426559145
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e268700f1b4c636c1afe1f45f4f65ffdd7db388776596a4e850661573d3f801
3
+ size 1192134935
model.safetensors.index.json CHANGED
@@ -1,639 +1,318 @@
1
  {
2
- "metadata": {
3
- "total_size": 4548144832
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.22.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
9
- "model.language_model.layers.22.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
10
- "model.language_model.layers.22.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
11
- "model.language_model.layers.23.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
12
- "model.language_model.layers.23.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
13
- "model.language_model.layers.23.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
14
- "model.language_model.layers.3.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
15
- "model.language_model.layers.3.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
16
- "model.language_model.layers.3.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
17
- "model.language_model.layers.6.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
18
- "model.language_model.layers.6.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
19
- "model.language_model.layers.6.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
20
- "model.language_model.layers.7.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
21
- "model.language_model.layers.7.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
22
- "model.language_model.layers.7.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
23
- "model.language_model.layers.9.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
24
- "model.language_model.layers.9.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
25
- "model.language_model.layers.9.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
26
- "mtp.layers.0.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
27
- "mtp.layers.0.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
28
- "mtp.layers.0.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
29
- "model.language_model.layers.10.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
30
- "model.language_model.layers.11.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
31
- "model.language_model.layers.11.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
32
- "model.language_model.layers.11.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
33
- "model.language_model.layers.12.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
34
- "model.language_model.layers.4.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
35
- "model.language_model.layers.4.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
36
- "model.language_model.layers.4.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
37
- "model.language_model.layers.4.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
38
- "model.language_model.layers.14.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
39
- "model.language_model.layers.14.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
40
- "model.language_model.layers.14.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
41
- "model.language_model.layers.14.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
42
- "model.language_model.layers.15.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
43
- "model.language_model.layers.15.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
44
- "model.language_model.layers.15.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
45
- "model.language_model.layers.2.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
46
- "model.language_model.layers.2.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
47
- "model.language_model.layers.2.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
48
- "model.language_model.layers.20.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
49
- "model.language_model.layers.20.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
50
- "model.language_model.layers.20.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
51
- "model.language_model.layers.20.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
52
- "model.language_model.layers.17.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
53
- "model.language_model.layers.17.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
54
- "model.language_model.layers.17.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
55
- "model.language_model.layers.18.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
56
- "model.language_model.layers.18.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
57
- "model.language_model.layers.18.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
58
- "model.language_model.layers.18.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
59
- "model.language_model.layers.12.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
60
- "model.language_model.layers.12.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
61
- "model.language_model.layers.12.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
62
- "model.language_model.layers.13.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
63
- "model.language_model.layers.13.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
64
- "model.language_model.layers.13.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
65
- "model.language_model.layers.13.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
66
- "model.language_model.layers.19.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
67
- "model.language_model.layers.19.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
68
- "model.language_model.layers.19.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
69
- "model.language_model.layers.2.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
70
- "model.language_model.layers.1.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
71
- "model.language_model.layers.1.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
72
- "model.language_model.layers.1.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
73
- "model.language_model.layers.1.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
74
- "model.language_model.layers.10.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
75
- "model.language_model.layers.10.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
76
- "model.language_model.layers.10.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
77
- "model.language_model.layers.16.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
78
- "model.language_model.layers.16.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
79
- "model.language_model.layers.16.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
80
- "model.language_model.layers.16.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
81
- "model.language_model.layers.17.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
82
- "model.language_model.layers.5.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
83
- "model.language_model.layers.5.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
84
- "model.language_model.layers.5.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
85
- "model.language_model.layers.5.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
86
- "model.language_model.layers.6.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
87
- "model.language_model.layers.21.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
88
- "model.language_model.layers.21.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
89
- "model.language_model.layers.21.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
90
- "model.language_model.layers.21.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
91
- "model.language_model.layers.22.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
92
- "model.language_model.layers.8.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
93
- "model.language_model.layers.8.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
94
- "model.language_model.layers.8.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
95
- "model.language_model.layers.8.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
96
- "model.language_model.layers.9.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
97
- "model.language_model.layers.0.linear_attn.in_proj_qkv.weight": "model.safetensors-00001-of-00001.safetensors",
98
- "model.language_model.layers.0.mlp.down_proj.weight": "model.safetensors-00001-of-00001.safetensors",
99
- "model.language_model.layers.0.mlp.gate_proj.weight": "model.safetensors-00001-of-00001.safetensors",
100
- "model.language_model.layers.0.mlp.up_proj.weight": "model.safetensors-00001-of-00001.safetensors",
101
- "model.language_model.layers.23.self_attn.q_proj.weight": "model.safetensors-00001-of-00001.safetensors",
102
- "model.language_model.layers.7.self_attn.q_proj.weight": "model.safetensors-00001-of-00001.safetensors",
103
- "mtp.fc.weight": "model.safetensors-00001-of-00001.safetensors",
104
- "mtp.layers.0.self_attn.q_proj.weight": "model.safetensors-00001-of-00001.safetensors",
105
- "model.language_model.layers.11.self_attn.q_proj.weight": "model.safetensors-00001-of-00001.safetensors",
106
- "model.language_model.layers.3.self_attn.q_proj.weight": "model.safetensors-00001-of-00001.safetensors",
107
- "model.language_model.layers.15.self_attn.q_proj.weight": "model.safetensors-00001-of-00001.safetensors",
108
- "model.language_model.layers.19.self_attn.q_proj.weight": "model.safetensors-00001-of-00001.safetensors",
109
- "model.visual.merger.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
110
- "model.language_model.layers.23.self_attn.o_proj.weight": "model.safetensors-00001-of-00001.safetensors",
111
- "model.language_model.layers.3.self_attn.o_proj.weight": "model.safetensors-00001-of-00001.safetensors",
112
- "model.language_model.layers.6.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
113
- "model.language_model.layers.7.self_attn.o_proj.weight": "model.safetensors-00001-of-00001.safetensors",
114
- "mtp.layers.0.self_attn.o_proj.weight": "model.safetensors-00001-of-00001.safetensors",
115
- "model.language_model.layers.11.self_attn.o_proj.weight": "model.safetensors-00001-of-00001.safetensors",
116
- "model.language_model.layers.12.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
117
- "model.language_model.layers.12.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
118
- "model.language_model.layers.4.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
119
- "model.language_model.layers.4.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
120
- "model.language_model.layers.14.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
121
- "model.language_model.layers.14.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
122
- "model.language_model.layers.15.self_attn.o_proj.weight": "model.safetensors-00001-of-00001.safetensors",
123
- "model.language_model.layers.20.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
124
- "model.language_model.layers.20.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
125
- "model.language_model.layers.17.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
126
- "model.language_model.layers.18.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
127
- "model.language_model.layers.18.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
128
- "model.language_model.layers.13.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
129
- "model.language_model.layers.13.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
130
- "model.language_model.layers.19.self_attn.o_proj.weight": "model.safetensors-00001-of-00001.safetensors",
131
- "model.language_model.layers.2.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
132
- "model.language_model.layers.2.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
133
- "model.language_model.layers.1.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
134
- "model.language_model.layers.1.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
135
- "model.language_model.layers.10.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
136
- "model.language_model.layers.10.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
137
- "model.language_model.layers.16.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
138
- "model.language_model.layers.16.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
139
- "model.language_model.layers.17.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
140
- "model.language_model.layers.5.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
141
- "model.language_model.layers.5.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
142
- "model.language_model.layers.6.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
143
- "model.language_model.layers.21.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
144
- "model.language_model.layers.21.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
145
- "model.language_model.layers.22.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
146
- "model.language_model.layers.22.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
147
- "model.language_model.layers.8.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
148
- "model.language_model.layers.8.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
149
- "model.language_model.layers.9.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
150
- "model.language_model.layers.9.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
151
- "model.language_model.layers.0.linear_attn.in_proj_z.weight": "model.safetensors-00001-of-00001.safetensors",
152
- "model.language_model.layers.0.linear_attn.out_proj.weight": "model.safetensors-00001-of-00001.safetensors",
153
- "model.visual.blocks.0.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
154
- "model.visual.blocks.0.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
155
- "model.visual.blocks.1.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
156
- "model.visual.blocks.1.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
157
- "model.visual.blocks.10.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
158
- "model.visual.blocks.10.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
159
- "model.visual.blocks.11.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
160
- "model.visual.blocks.11.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
161
- "model.visual.blocks.12.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
162
- "model.visual.blocks.12.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
163
- "model.visual.blocks.13.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
164
- "model.visual.blocks.13.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
165
- "model.visual.blocks.14.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
166
- "model.visual.blocks.14.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
167
- "model.visual.blocks.15.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
168
- "model.visual.blocks.15.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
169
- "model.visual.blocks.16.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
170
- "model.visual.blocks.16.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
171
- "model.visual.blocks.17.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
172
- "model.visual.blocks.17.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
173
- "model.visual.blocks.18.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
174
- "model.visual.blocks.18.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
175
- "model.visual.blocks.19.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
176
- "model.visual.blocks.19.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
177
- "model.visual.blocks.2.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
178
- "model.visual.blocks.2.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
179
- "model.visual.blocks.20.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
180
- "model.visual.blocks.20.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
181
- "model.visual.blocks.21.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
182
- "model.visual.blocks.21.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
183
- "model.visual.blocks.22.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
184
- "model.visual.blocks.22.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
185
- "model.visual.blocks.23.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
186
- "model.visual.blocks.23.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
187
- "model.visual.blocks.3.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
188
- "model.visual.blocks.3.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
189
- "model.visual.blocks.4.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
190
- "model.visual.blocks.4.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
191
- "model.visual.blocks.5.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
192
- "model.visual.blocks.5.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
193
- "model.visual.blocks.6.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
194
- "model.visual.blocks.6.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
195
- "model.visual.blocks.7.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
196
- "model.visual.blocks.7.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
197
- "model.visual.blocks.8.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
198
- "model.visual.blocks.8.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
199
- "model.visual.blocks.9.mlp.linear_fc1.weight": "model.safetensors-00001-of-00001.safetensors",
200
- "model.visual.blocks.9.mlp.linear_fc2.weight": "model.safetensors-00001-of-00001.safetensors",
201
- "model.visual.blocks.0.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
202
- "model.visual.blocks.1.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
203
- "model.visual.blocks.10.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
204
- "model.visual.blocks.11.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
205
- "model.visual.blocks.12.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
206
- "model.visual.blocks.13.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
207
- "model.visual.blocks.14.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
208
- "model.visual.blocks.15.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
209
- "model.visual.blocks.16.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
210
- "model.visual.blocks.17.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
211
- "model.visual.blocks.18.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
212
- "model.visual.blocks.19.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
213
- "model.visual.blocks.2.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
214
- "model.visual.blocks.20.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
215
- "model.visual.blocks.21.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
216
- "model.visual.blocks.22.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
217
- "model.visual.blocks.23.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
218
- "model.visual.blocks.3.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
219
- "model.visual.blocks.4.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
220
- "model.visual.blocks.5.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
221
- "model.visual.blocks.6.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
222
- "model.visual.blocks.7.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
223
- "model.visual.blocks.8.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
224
- "model.visual.blocks.9.attn.qkv.weight": "model.safetensors-00001-of-00001.safetensors",
225
- "model.visual.pos_embed.weight": "model.safetensors-00001-of-00001.safetensors",
226
- "model.visual.patch_embed.proj.weight": "model.safetensors-00001-of-00001.safetensors",
227
- "model.language_model.layers.23.self_attn.k_proj.weight": "model.safetensors-00001-of-00001.safetensors",
228
- "model.language_model.layers.23.self_attn.v_proj.weight": "model.safetensors-00001-of-00001.safetensors",
229
- "model.language_model.layers.7.self_attn.k_proj.weight": "model.safetensors-00001-of-00001.safetensors",
230
- "model.language_model.layers.7.self_attn.v_proj.weight": "model.safetensors-00001-of-00001.safetensors",
231
- "mtp.layers.0.self_attn.k_proj.weight": "model.safetensors-00001-of-00001.safetensors",
232
- "mtp.layers.0.self_attn.v_proj.weight": "model.safetensors-00001-of-00001.safetensors",
233
- "model.language_model.layers.11.self_attn.k_proj.weight": "model.safetensors-00001-of-00001.safetensors",
234
- "model.language_model.layers.11.self_attn.v_proj.weight": "model.safetensors-00001-of-00001.safetensors",
235
- "model.language_model.layers.3.self_attn.k_proj.weight": "model.safetensors-00001-of-00001.safetensors",
236
- "model.language_model.layers.3.self_attn.v_proj.weight": "model.safetensors-00001-of-00001.safetensors",
237
- "model.language_model.layers.15.self_attn.k_proj.weight": "model.safetensors-00001-of-00001.safetensors",
238
- "model.language_model.layers.15.self_attn.v_proj.weight": "model.safetensors-00001-of-00001.safetensors",
239
- "model.language_model.layers.19.self_attn.k_proj.weight": "model.safetensors-00001-of-00001.safetensors",
240
- "model.language_model.layers.19.self_attn.v_proj.weight": "model.safetensors-00001-of-00001.safetensors",
241
- "model.visual.blocks.0.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
242
- "model.visual.blocks.1.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
243
- "model.visual.blocks.10.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
244
- "model.visual.blocks.11.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
245
- "model.visual.blocks.12.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
246
- "model.visual.blocks.13.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
247
- "model.visual.blocks.14.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
248
- "model.visual.blocks.15.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
249
- "model.visual.blocks.16.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
250
- "model.visual.blocks.17.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
251
- "model.visual.blocks.18.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
252
- "model.visual.blocks.19.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
253
- "model.visual.blocks.2.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
254
- "model.visual.blocks.20.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
255
- "model.visual.blocks.21.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
256
- "model.visual.blocks.22.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
257
- "model.visual.blocks.23.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
258
- "model.visual.blocks.3.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
259
- "model.visual.blocks.4.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
260
- "model.visual.blocks.5.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
261
- "model.visual.blocks.6.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
262
- "model.visual.blocks.7.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
263
- "model.visual.blocks.8.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
264
- "model.visual.blocks.9.attn.proj.weight": "model.safetensors-00001-of-00001.safetensors",
265
- "model.language_model.layers.12.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
266
- "model.language_model.layers.12.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
267
- "model.language_model.layers.4.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
268
- "model.language_model.layers.4.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
269
- "model.language_model.layers.14.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
270
- "model.language_model.layers.14.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
271
- "model.language_model.layers.20.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
272
- "model.language_model.layers.20.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
273
- "model.language_model.layers.18.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
274
- "model.language_model.layers.18.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
275
- "model.language_model.layers.13.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
276
- "model.language_model.layers.13.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
277
- "model.language_model.layers.2.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
278
- "model.language_model.layers.2.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
279
- "model.language_model.layers.1.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
280
- "model.language_model.layers.1.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
281
- "model.language_model.layers.10.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
282
- "model.language_model.layers.10.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
283
- "model.language_model.layers.16.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
284
- "model.language_model.layers.16.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
285
- "model.language_model.layers.17.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
286
- "model.language_model.layers.17.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
287
- "model.language_model.layers.5.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
288
- "model.language_model.layers.5.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
289
- "model.language_model.layers.6.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
290
- "model.language_model.layers.6.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
291
- "model.language_model.layers.21.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
292
- "model.language_model.layers.21.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
293
- "model.language_model.layers.22.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
294
- "model.language_model.layers.22.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
295
- "model.language_model.layers.8.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
296
- "model.language_model.layers.8.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
297
- "model.language_model.layers.9.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
298
- "model.language_model.layers.9.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
299
- "model.language_model.layers.0.linear_attn.in_proj_b.weight": "model.safetensors-00001-of-00001.safetensors",
300
- "model.language_model.layers.0.linear_attn.in_proj_a.weight": "model.safetensors-00001-of-00001.safetensors",
301
- "model.language_model.layers.8.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
302
- "model.language_model.layers.12.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
303
- "model.language_model.layers.4.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
304
- "model.language_model.layers.5.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
305
- "model.language_model.layers.20.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
306
- "model.language_model.layers.21.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
307
- "model.language_model.layers.18.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
308
- "model.language_model.layers.13.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
309
- "model.language_model.layers.14.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
310
- "model.language_model.layers.2.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
311
- "model.language_model.layers.10.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
312
- "model.language_model.layers.16.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
313
- "model.language_model.layers.17.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
314
- "model.language_model.layers.6.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
315
- "model.language_model.layers.22.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
316
- "model.language_model.layers.9.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
317
- "model.language_model.layers.0.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
318
- "model.language_model.layers.1.linear_attn.conv1d.weight": "model.safetensors-00001-of-00001.safetensors",
319
- "model.visual.blocks.0.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
320
- "model.visual.blocks.1.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
321
- "model.visual.blocks.10.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
322
- "model.visual.blocks.11.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
323
- "model.visual.blocks.12.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
324
- "model.visual.blocks.13.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
325
- "model.visual.blocks.14.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
326
- "model.visual.blocks.15.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
327
- "model.visual.blocks.16.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
328
- "model.visual.blocks.17.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
329
- "model.visual.blocks.18.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
330
- "model.visual.blocks.19.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
331
- "model.visual.blocks.2.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
332
- "model.visual.blocks.20.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
333
- "model.visual.blocks.21.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
334
- "model.visual.blocks.22.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
335
- "model.visual.blocks.23.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
336
- "model.visual.blocks.3.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
337
- "model.visual.blocks.4.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
338
- "model.visual.blocks.5.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
339
- "model.visual.blocks.6.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
340
- "model.visual.blocks.7.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
341
- "model.visual.blocks.8.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
342
- "model.visual.blocks.9.mlp.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
343
- "model.visual.merger.linear_fc1.bias": "model.safetensors-00001-of-00001.safetensors",
344
- "model.visual.blocks.0.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
345
- "model.visual.blocks.1.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
346
- "model.visual.blocks.10.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
347
- "model.visual.blocks.11.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
348
- "model.visual.blocks.12.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
349
- "model.visual.blocks.13.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
350
- "model.visual.blocks.14.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
351
- "model.visual.blocks.15.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
352
- "model.visual.blocks.16.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
353
- "model.visual.blocks.17.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
354
- "model.visual.blocks.18.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
355
- "model.visual.blocks.19.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
356
- "model.visual.blocks.2.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
357
- "model.visual.blocks.20.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
358
- "model.visual.blocks.21.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
359
- "model.visual.blocks.22.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
360
- "model.visual.blocks.23.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
361
- "model.visual.blocks.3.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
362
- "model.visual.blocks.4.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
363
- "model.visual.blocks.5.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
364
- "model.visual.blocks.6.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
365
- "model.visual.blocks.7.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
366
- "model.visual.blocks.8.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
367
- "model.visual.blocks.9.attn.qkv.bias": "model.safetensors-00001-of-00001.safetensors",
368
- "model.language_model.layers.22.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
369
- "model.language_model.layers.23.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
370
- "model.language_model.layers.23.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
371
- "model.language_model.layers.3.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
372
- "model.language_model.layers.6.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
373
- "model.language_model.layers.7.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
374
- "model.language_model.layers.7.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
375
- "model.language_model.layers.8.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
376
- "mtp.layers.0.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
377
- "mtp.layers.0.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
378
- "mtp.norm.weight": "model.safetensors-00001-of-00001.safetensors",
379
- "mtp.pre_fc_norm_embedding.weight": "model.safetensors-00001-of-00001.safetensors",
380
- "mtp.pre_fc_norm_hidden.weight": "model.safetensors-00001-of-00001.safetensors",
381
- "model.language_model.layers.11.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
382
- "model.language_model.layers.11.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
383
- "model.language_model.layers.12.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
384
- "model.language_model.layers.3.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
385
- "model.language_model.layers.4.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
386
- "model.language_model.layers.4.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
387
- "model.language_model.layers.14.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
388
- "model.language_model.layers.14.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
389
- "model.language_model.layers.15.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
390
- "model.language_model.layers.15.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
391
- "model.language_model.layers.20.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
392
- "model.language_model.layers.20.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
393
- "model.language_model.layers.17.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
394
- "model.language_model.layers.18.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
395
- "model.language_model.layers.18.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
396
- "model.language_model.layers.19.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
397
- "model.language_model.layers.12.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
398
- "model.language_model.layers.13.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
399
- "model.language_model.layers.13.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
400
- "model.language_model.layers.19.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
401
- "model.language_model.layers.2.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
402
- "model.language_model.layers.2.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
403
- "model.language_model.layers.1.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
404
- "model.language_model.layers.10.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
405
- "model.language_model.layers.10.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
406
- "model.language_model.layers.16.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
407
- "model.language_model.layers.16.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
408
- "model.language_model.layers.17.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
409
- "model.language_model.layers.5.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
410
- "model.language_model.layers.5.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
411
- "model.language_model.layers.6.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
412
- "model.language_model.layers.21.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
413
- "model.language_model.layers.21.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
414
- "model.language_model.layers.22.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
415
- "model.language_model.layers.8.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
416
- "model.language_model.layers.9.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
417
- "model.language_model.layers.9.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
418
- "model.language_model.layers.0.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
419
- "model.language_model.layers.0.post_attention_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
420
- "model.language_model.layers.1.input_layernorm.weight": "model.safetensors-00001-of-00001.safetensors",
421
- "model.language_model.norm.weight": "model.safetensors-00001-of-00001.safetensors",
422
- "model.visual.merger.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
423
- "model.visual.blocks.0.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
424
- "model.visual.blocks.0.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
425
- "model.visual.blocks.0.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
426
- "model.visual.blocks.0.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
427
- "model.visual.blocks.0.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
428
- "model.visual.blocks.0.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
429
- "model.visual.blocks.1.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
430
- "model.visual.blocks.1.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
431
- "model.visual.blocks.1.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
432
- "model.visual.blocks.1.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
433
- "model.visual.blocks.1.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
434
- "model.visual.blocks.1.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
435
- "model.visual.blocks.10.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
436
- "model.visual.blocks.10.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
437
- "model.visual.blocks.10.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
438
- "model.visual.blocks.10.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
439
- "model.visual.blocks.10.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
440
- "model.visual.blocks.10.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
441
- "model.visual.blocks.11.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
442
- "model.visual.blocks.11.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
443
- "model.visual.blocks.11.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
444
- "model.visual.blocks.11.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
445
- "model.visual.blocks.11.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
446
- "model.visual.blocks.11.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
447
- "model.visual.blocks.12.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
448
- "model.visual.blocks.12.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
449
- "model.visual.blocks.12.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
450
- "model.visual.blocks.12.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
451
- "model.visual.blocks.12.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
452
- "model.visual.blocks.12.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
453
- "model.visual.blocks.13.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
454
- "model.visual.blocks.13.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
455
- "model.visual.blocks.13.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
456
- "model.visual.blocks.13.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
457
- "model.visual.blocks.13.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
458
- "model.visual.blocks.13.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
459
- "model.visual.blocks.14.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
460
- "model.visual.blocks.14.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
461
- "model.visual.blocks.14.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
462
- "model.visual.blocks.14.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
463
- "model.visual.blocks.14.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
464
- "model.visual.blocks.14.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
465
- "model.visual.blocks.15.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
466
- "model.visual.blocks.15.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
467
- "model.visual.blocks.15.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
468
- "model.visual.blocks.15.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
469
- "model.visual.blocks.15.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
470
- "model.visual.blocks.15.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
471
- "model.visual.blocks.16.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
472
- "model.visual.blocks.16.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
473
- "model.visual.blocks.16.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
474
- "model.visual.blocks.16.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
475
- "model.visual.blocks.16.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
476
- "model.visual.blocks.16.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
477
- "model.visual.blocks.17.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
478
- "model.visual.blocks.17.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
479
- "model.visual.blocks.17.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
480
- "model.visual.blocks.17.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
481
- "model.visual.blocks.17.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
482
- "model.visual.blocks.17.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
483
- "model.visual.blocks.18.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
484
- "model.visual.blocks.18.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
485
- "model.visual.blocks.18.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
486
- "model.visual.blocks.18.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
487
- "model.visual.blocks.18.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
488
- "model.visual.blocks.18.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
489
- "model.visual.blocks.19.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
490
- "model.visual.blocks.19.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
491
- "model.visual.blocks.19.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
492
- "model.visual.blocks.19.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
493
- "model.visual.blocks.19.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
494
- "model.visual.blocks.19.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
495
- "model.visual.blocks.2.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
496
- "model.visual.blocks.2.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
497
- "model.visual.blocks.2.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
498
- "model.visual.blocks.2.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
499
- "model.visual.blocks.2.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
500
- "model.visual.blocks.2.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
501
- "model.visual.blocks.20.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
502
- "model.visual.blocks.20.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
503
- "model.visual.blocks.20.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
504
- "model.visual.blocks.20.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
505
- "model.visual.blocks.20.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
506
- "model.visual.blocks.20.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
507
- "model.visual.blocks.21.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
508
- "model.visual.blocks.21.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
509
- "model.visual.blocks.21.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
510
- "model.visual.blocks.21.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
511
- "model.visual.blocks.21.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
512
- "model.visual.blocks.21.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
513
- "model.visual.blocks.22.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
514
- "model.visual.blocks.22.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
515
- "model.visual.blocks.22.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
516
- "model.visual.blocks.22.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
517
- "model.visual.blocks.22.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
518
- "model.visual.blocks.22.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
519
- "model.visual.blocks.23.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
520
- "model.visual.blocks.23.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
521
- "model.visual.blocks.23.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
522
- "model.visual.blocks.23.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
523
- "model.visual.blocks.23.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
524
- "model.visual.blocks.23.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
525
- "model.visual.blocks.3.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
526
- "model.visual.blocks.3.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
527
- "model.visual.blocks.3.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
528
- "model.visual.blocks.3.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
529
- "model.visual.blocks.3.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
530
- "model.visual.blocks.3.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
531
- "model.visual.blocks.4.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
532
- "model.visual.blocks.4.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
533
- "model.visual.blocks.4.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
534
- "model.visual.blocks.4.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
535
- "model.visual.blocks.4.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
536
- "model.visual.blocks.4.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
537
- "model.visual.blocks.5.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
538
- "model.visual.blocks.5.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
539
- "model.visual.blocks.5.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
540
- "model.visual.blocks.5.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
541
- "model.visual.blocks.5.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
542
- "model.visual.blocks.5.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
543
- "model.visual.blocks.6.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
544
- "model.visual.blocks.6.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
545
- "model.visual.blocks.6.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
546
- "model.visual.blocks.6.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
547
- "model.visual.blocks.6.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
548
- "model.visual.blocks.6.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
549
- "model.visual.blocks.7.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
550
- "model.visual.blocks.7.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
551
- "model.visual.blocks.7.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
552
- "model.visual.blocks.7.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
553
- "model.visual.blocks.7.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
554
- "model.visual.blocks.7.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
555
- "model.visual.blocks.8.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
556
- "model.visual.blocks.8.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
557
- "model.visual.blocks.8.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
558
- "model.visual.blocks.8.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
559
- "model.visual.blocks.8.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
560
- "model.visual.blocks.8.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
561
- "model.visual.blocks.9.attn.proj.bias": "model.safetensors-00001-of-00001.safetensors",
562
- "model.visual.blocks.9.mlp.linear_fc2.bias": "model.safetensors-00001-of-00001.safetensors",
563
- "model.visual.blocks.9.norm1.bias": "model.safetensors-00001-of-00001.safetensors",
564
- "model.visual.blocks.9.norm1.weight": "model.safetensors-00001-of-00001.safetensors",
565
- "model.visual.blocks.9.norm2.bias": "model.safetensors-00001-of-00001.safetensors",
566
- "model.visual.blocks.9.norm2.weight": "model.safetensors-00001-of-00001.safetensors",
567
- "model.visual.merger.norm.bias": "model.safetensors-00001-of-00001.safetensors",
568
- "model.visual.merger.norm.weight": "model.safetensors-00001-of-00001.safetensors",
569
- "model.visual.patch_embed.proj.bias": "model.safetensors-00001-of-00001.safetensors",
570
- "model.language_model.layers.23.self_attn.k_norm.weight": "model.safetensors-00001-of-00001.safetensors",
571
- "model.language_model.layers.23.self_attn.q_norm.weight": "model.safetensors-00001-of-00001.safetensors",
572
- "model.language_model.layers.3.self_attn.k_norm.weight": "model.safetensors-00001-of-00001.safetensors",
573
- "model.language_model.layers.7.self_attn.k_norm.weight": "model.safetensors-00001-of-00001.safetensors",
574
- "model.language_model.layers.7.self_attn.q_norm.weight": "model.safetensors-00001-of-00001.safetensors",
575
- "mtp.layers.0.self_attn.k_norm.weight": "model.safetensors-00001-of-00001.safetensors",
576
- "mtp.layers.0.self_attn.q_norm.weight": "model.safetensors-00001-of-00001.safetensors",
577
- "model.language_model.layers.11.self_attn.k_norm.weight": "model.safetensors-00001-of-00001.safetensors",
578
- "model.language_model.layers.11.self_attn.q_norm.weight": "model.safetensors-00001-of-00001.safetensors",
579
- "model.language_model.layers.12.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
580
- "model.language_model.layers.3.self_attn.q_norm.weight": "model.safetensors-00001-of-00001.safetensors",
581
- "model.language_model.layers.4.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
582
- "model.language_model.layers.14.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
583
- "model.language_model.layers.15.self_attn.k_norm.weight": "model.safetensors-00001-of-00001.safetensors",
584
- "model.language_model.layers.15.self_attn.q_norm.weight": "model.safetensors-00001-of-00001.safetensors",
585
- "model.language_model.layers.20.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
586
- "model.language_model.layers.18.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
587
- "model.language_model.layers.13.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
588
- "model.language_model.layers.19.self_attn.k_norm.weight": "model.safetensors-00001-of-00001.safetensors",
589
- "model.language_model.layers.19.self_attn.q_norm.weight": "model.safetensors-00001-of-00001.safetensors",
590
- "model.language_model.layers.2.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
591
- "model.language_model.layers.1.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
592
- "model.language_model.layers.10.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
593
- "model.language_model.layers.16.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
594
- "model.language_model.layers.17.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
595
- "model.language_model.layers.5.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
596
- "model.language_model.layers.6.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
597
- "model.language_model.layers.21.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
598
- "model.language_model.layers.22.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
599
- "model.language_model.layers.8.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
600
- "model.language_model.layers.9.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
601
- "model.language_model.layers.0.linear_attn.norm.weight": "model.safetensors-00001-of-00001.safetensors",
602
- "model.language_model.layers.8.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
603
- "model.language_model.layers.12.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
604
- "model.language_model.layers.4.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
605
- "model.language_model.layers.5.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
606
- "model.language_model.layers.16.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
607
- "model.language_model.layers.20.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
608
- "model.language_model.layers.21.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
609
- "model.language_model.layers.18.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
610
- "model.language_model.layers.13.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
611
- "model.language_model.layers.14.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
612
- "model.language_model.layers.2.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
613
- "model.language_model.layers.10.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
614
- "model.language_model.layers.17.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
615
- "model.language_model.layers.6.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
616
- "model.language_model.layers.22.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
617
- "model.language_model.layers.9.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
618
- "model.language_model.layers.0.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
619
- "model.language_model.layers.1.linear_attn.A_log": "model.safetensors-00001-of-00001.safetensors",
620
- "model.language_model.layers.8.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors",
621
- "model.language_model.layers.12.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors",
622
- "model.language_model.layers.4.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors",
623
- "model.language_model.layers.20.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors",
624
- "model.language_model.layers.21.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors",
625
- "model.language_model.layers.18.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors",
626
- "model.language_model.layers.13.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors",
627
- "model.language_model.layers.14.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors",
628
- "model.language_model.layers.2.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors",
629
- "model.language_model.layers.10.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors",
630
- "model.language_model.layers.16.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors",
631
- "model.language_model.layers.17.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors",
632
- "model.language_model.layers.5.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors",
633
- "model.language_model.layers.6.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors",
634
- "model.language_model.layers.22.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors",
635
- "model.language_model.layers.9.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors",
636
- "model.language_model.layers.0.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors",
637
- "model.language_model.layers.1.linear_attn.dt_bias": "model.safetensors-00001-of-00001.safetensors"
638
- }
639
  }
 
1
  {
2
+ "metadata": {
3
+ "total_size": 1192099840,
4
+ "total_parameters": 596049920
5
+ },
6
+ "weight_map": {
7
+ "model.embed_tokens.weight": "model.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model.safetensors",
13
+ "model.layers.0.self_attn.k_norm.weight": "model.safetensors",
14
+ "model.layers.0.self_attn.k_proj.weight": "model.safetensors",
15
+ "model.layers.0.self_attn.o_proj.weight": "model.safetensors",
16
+ "model.layers.0.self_attn.q_norm.weight": "model.safetensors",
17
+ "model.layers.0.self_attn.q_proj.weight": "model.safetensors",
18
+ "model.layers.0.self_attn.v_proj.weight": "model.safetensors",
19
+ "model.layers.1.input_layernorm.weight": "model.safetensors",
20
+ "model.layers.1.mlp.down_proj.weight": "model.safetensors",
21
+ "model.layers.1.mlp.gate_proj.weight": "model.safetensors",
22
+ "model.layers.1.mlp.up_proj.weight": "model.safetensors",
23
+ "model.layers.1.post_attention_layernorm.weight": "model.safetensors",
24
+ "model.layers.1.self_attn.k_norm.weight": "model.safetensors",
25
+ "model.layers.1.self_attn.k_proj.weight": "model.safetensors",
26
+ "model.layers.1.self_attn.o_proj.weight": "model.safetensors",
27
+ "model.layers.1.self_attn.q_norm.weight": "model.safetensors",
28
+ "model.layers.1.self_attn.q_proj.weight": "model.safetensors",
29
+ "model.layers.1.self_attn.v_proj.weight": "model.safetensors",
30
+ "model.layers.10.input_layernorm.weight": "model.safetensors",
31
+ "model.layers.10.mlp.down_proj.weight": "model.safetensors",
32
+ "model.layers.10.mlp.gate_proj.weight": "model.safetensors",
33
+ "model.layers.10.mlp.up_proj.weight": "model.safetensors",
34
+ "model.layers.10.post_attention_layernorm.weight": "model.safetensors",
35
+ "model.layers.10.self_attn.k_norm.weight": "model.safetensors",
36
+ "model.layers.10.self_attn.k_proj.weight": "model.safetensors",
37
+ "model.layers.10.self_attn.o_proj.weight": "model.safetensors",
38
+ "model.layers.10.self_attn.q_norm.weight": "model.safetensors",
39
+ "model.layers.10.self_attn.q_proj.weight": "model.safetensors",
40
+ "model.layers.10.self_attn.v_proj.weight": "model.safetensors",
41
+ "model.layers.11.input_layernorm.weight": "model.safetensors",
42
+ "model.layers.11.mlp.down_proj.weight": "model.safetensors",
43
+ "model.layers.11.mlp.gate_proj.weight": "model.safetensors",
44
+ "model.layers.11.mlp.up_proj.weight": "model.safetensors",
45
+ "model.layers.11.post_attention_layernorm.weight": "model.safetensors",
46
+ "model.layers.11.self_attn.k_norm.weight": "model.safetensors",
47
+ "model.layers.11.self_attn.k_proj.weight": "model.safetensors",
48
+ "model.layers.11.self_attn.o_proj.weight": "model.safetensors",
49
+ "model.layers.11.self_attn.q_norm.weight": "model.safetensors",
50
+ "model.layers.11.self_attn.q_proj.weight": "model.safetensors",
51
+ "model.layers.11.self_attn.v_proj.weight": "model.safetensors",
52
+ "model.layers.12.input_layernorm.weight": "model.safetensors",
53
+ "model.layers.12.mlp.down_proj.weight": "model.safetensors",
54
+ "model.layers.12.mlp.gate_proj.weight": "model.safetensors",
55
+ "model.layers.12.mlp.up_proj.weight": "model.safetensors",
56
+ "model.layers.12.post_attention_layernorm.weight": "model.safetensors",
57
+ "model.layers.12.self_attn.k_norm.weight": "model.safetensors",
58
+ "model.layers.12.self_attn.k_proj.weight": "model.safetensors",
59
+ "model.layers.12.self_attn.o_proj.weight": "model.safetensors",
60
+ "model.layers.12.self_attn.q_norm.weight": "model.safetensors",
61
+ "model.layers.12.self_attn.q_proj.weight": "model.safetensors",
62
+ "model.layers.12.self_attn.v_proj.weight": "model.safetensors",
63
+ "model.layers.13.input_layernorm.weight": "model.safetensors",
64
+ "model.layers.13.mlp.down_proj.weight": "model.safetensors",
65
+ "model.layers.13.mlp.gate_proj.weight": "model.safetensors",
66
+ "model.layers.13.mlp.up_proj.weight": "model.safetensors",
67
+ "model.layers.13.post_attention_layernorm.weight": "model.safetensors",
68
+ "model.layers.13.self_attn.k_norm.weight": "model.safetensors",
69
+ "model.layers.13.self_attn.k_proj.weight": "model.safetensors",
70
+ "model.layers.13.self_attn.o_proj.weight": "model.safetensors",
71
+ "model.layers.13.self_attn.q_norm.weight": "model.safetensors",
72
+ "model.layers.13.self_attn.q_proj.weight": "model.safetensors",
73
+ "model.layers.13.self_attn.v_proj.weight": "model.safetensors",
74
+ "model.layers.14.input_layernorm.weight": "model.safetensors",
75
+ "model.layers.14.mlp.down_proj.weight": "model.safetensors",
76
+ "model.layers.14.mlp.gate_proj.weight": "model.safetensors",
77
+ "model.layers.14.mlp.up_proj.weight": "model.safetensors",
78
+ "model.layers.14.post_attention_layernorm.weight": "model.safetensors",
79
+ "model.layers.14.self_attn.k_norm.weight": "model.safetensors",
80
+ "model.layers.14.self_attn.k_proj.weight": "model.safetensors",
81
+ "model.layers.14.self_attn.o_proj.weight": "model.safetensors",
82
+ "model.layers.14.self_attn.q_norm.weight": "model.safetensors",
83
+ "model.layers.14.self_attn.q_proj.weight": "model.safetensors",
84
+ "model.layers.14.self_attn.v_proj.weight": "model.safetensors",
85
+ "model.layers.15.input_layernorm.weight": "model.safetensors",
86
+ "model.layers.15.mlp.down_proj.weight": "model.safetensors",
87
+ "model.layers.15.mlp.gate_proj.weight": "model.safetensors",
88
+ "model.layers.15.mlp.up_proj.weight": "model.safetensors",
89
+ "model.layers.15.post_attention_layernorm.weight": "model.safetensors",
90
+ "model.layers.15.self_attn.k_norm.weight": "model.safetensors",
91
+ "model.layers.15.self_attn.k_proj.weight": "model.safetensors",
92
+ "model.layers.15.self_attn.o_proj.weight": "model.safetensors",
93
+ "model.layers.15.self_attn.q_norm.weight": "model.safetensors",
94
+ "model.layers.15.self_attn.q_proj.weight": "model.safetensors",
95
+ "model.layers.15.self_attn.v_proj.weight": "model.safetensors",
96
+ "model.layers.16.input_layernorm.weight": "model.safetensors",
97
+ "model.layers.16.mlp.down_proj.weight": "model.safetensors",
98
+ "model.layers.16.mlp.gate_proj.weight": "model.safetensors",
99
+ "model.layers.16.mlp.up_proj.weight": "model.safetensors",
100
+ "model.layers.16.post_attention_layernorm.weight": "model.safetensors",
101
+ "model.layers.16.self_attn.k_norm.weight": "model.safetensors",
102
+ "model.layers.16.self_attn.k_proj.weight": "model.safetensors",
103
+ "model.layers.16.self_attn.o_proj.weight": "model.safetensors",
104
+ "model.layers.16.self_attn.q_norm.weight": "model.safetensors",
105
+ "model.layers.16.self_attn.q_proj.weight": "model.safetensors",
106
+ "model.layers.16.self_attn.v_proj.weight": "model.safetensors",
107
+ "model.layers.17.input_layernorm.weight": "model.safetensors",
108
+ "model.layers.17.mlp.down_proj.weight": "model.safetensors",
109
+ "model.layers.17.mlp.gate_proj.weight": "model.safetensors",
110
+ "model.layers.17.mlp.up_proj.weight": "model.safetensors",
111
+ "model.layers.17.post_attention_layernorm.weight": "model.safetensors",
112
+ "model.layers.17.self_attn.k_norm.weight": "model.safetensors",
113
+ "model.layers.17.self_attn.k_proj.weight": "model.safetensors",
114
+ "model.layers.17.self_attn.o_proj.weight": "model.safetensors",
115
+ "model.layers.17.self_attn.q_norm.weight": "model.safetensors",
116
+ "model.layers.17.self_attn.q_proj.weight": "model.safetensors",
117
+ "model.layers.17.self_attn.v_proj.weight": "model.safetensors",
118
+ "model.layers.18.input_layernorm.weight": "model.safetensors",
119
+ "model.layers.18.mlp.down_proj.weight": "model.safetensors",
120
+ "model.layers.18.mlp.gate_proj.weight": "model.safetensors",
121
+ "model.layers.18.mlp.up_proj.weight": "model.safetensors",
122
+ "model.layers.18.post_attention_layernorm.weight": "model.safetensors",
123
+ "model.layers.18.self_attn.k_norm.weight": "model.safetensors",
124
+ "model.layers.18.self_attn.k_proj.weight": "model.safetensors",
125
+ "model.layers.18.self_attn.o_proj.weight": "model.safetensors",
126
+ "model.layers.18.self_attn.q_norm.weight": "model.safetensors",
127
+ "model.layers.18.self_attn.q_proj.weight": "model.safetensors",
128
+ "model.layers.18.self_attn.v_proj.weight": "model.safetensors",
129
+ "model.layers.19.input_layernorm.weight": "model.safetensors",
130
+ "model.layers.19.mlp.down_proj.weight": "model.safetensors",
131
+ "model.layers.19.mlp.gate_proj.weight": "model.safetensors",
132
+ "model.layers.19.mlp.up_proj.weight": "model.safetensors",
133
+ "model.layers.19.post_attention_layernorm.weight": "model.safetensors",
134
+ "model.layers.19.self_attn.k_norm.weight": "model.safetensors",
135
+ "model.layers.19.self_attn.k_proj.weight": "model.safetensors",
136
+ "model.layers.19.self_attn.o_proj.weight": "model.safetensors",
137
+ "model.layers.19.self_attn.q_norm.weight": "model.safetensors",
138
+ "model.layers.19.self_attn.q_proj.weight": "model.safetensors",
139
+ "model.layers.19.self_attn.v_proj.weight": "model.safetensors",
140
+ "model.layers.2.input_layernorm.weight": "model.safetensors",
141
+ "model.layers.2.mlp.down_proj.weight": "model.safetensors",
142
+ "model.layers.2.mlp.gate_proj.weight": "model.safetensors",
143
+ "model.layers.2.mlp.up_proj.weight": "model.safetensors",
144
+ "model.layers.2.post_attention_layernorm.weight": "model.safetensors",
145
+ "model.layers.2.self_attn.k_norm.weight": "model.safetensors",
146
+ "model.layers.2.self_attn.k_proj.weight": "model.safetensors",
147
+ "model.layers.2.self_attn.o_proj.weight": "model.safetensors",
148
+ "model.layers.2.self_attn.q_norm.weight": "model.safetensors",
149
+ "model.layers.2.self_attn.q_proj.weight": "model.safetensors",
150
+ "model.layers.2.self_attn.v_proj.weight": "model.safetensors",
151
+ "model.layers.20.input_layernorm.weight": "model.safetensors",
152
+ "model.layers.20.mlp.down_proj.weight": "model.safetensors",
153
+ "model.layers.20.mlp.gate_proj.weight": "model.safetensors",
154
+ "model.layers.20.mlp.up_proj.weight": "model.safetensors",
155
+ "model.layers.20.post_attention_layernorm.weight": "model.safetensors",
156
+ "model.layers.20.self_attn.k_norm.weight": "model.safetensors",
157
+ "model.layers.20.self_attn.k_proj.weight": "model.safetensors",
158
+ "model.layers.20.self_attn.o_proj.weight": "model.safetensors",
159
+ "model.layers.20.self_attn.q_norm.weight": "model.safetensors",
160
+ "model.layers.20.self_attn.q_proj.weight": "model.safetensors",
161
+ "model.layers.20.self_attn.v_proj.weight": "model.safetensors",
162
+ "model.layers.21.input_layernorm.weight": "model.safetensors",
163
+ "model.layers.21.mlp.down_proj.weight": "model.safetensors",
164
+ "model.layers.21.mlp.gate_proj.weight": "model.safetensors",
165
+ "model.layers.21.mlp.up_proj.weight": "model.safetensors",
166
+ "model.layers.21.post_attention_layernorm.weight": "model.safetensors",
167
+ "model.layers.21.self_attn.k_norm.weight": "model.safetensors",
168
+ "model.layers.21.self_attn.k_proj.weight": "model.safetensors",
169
+ "model.layers.21.self_attn.o_proj.weight": "model.safetensors",
170
+ "model.layers.21.self_attn.q_norm.weight": "model.safetensors",
171
+ "model.layers.21.self_attn.q_proj.weight": "model.safetensors",
172
+ "model.layers.21.self_attn.v_proj.weight": "model.safetensors",
173
+ "model.layers.22.input_layernorm.weight": "model.safetensors",
174
+ "model.layers.22.mlp.down_proj.weight": "model.safetensors",
175
+ "model.layers.22.mlp.gate_proj.weight": "model.safetensors",
176
+ "model.layers.22.mlp.up_proj.weight": "model.safetensors",
177
+ "model.layers.22.post_attention_layernorm.weight": "model.safetensors",
178
+ "model.layers.22.self_attn.k_norm.weight": "model.safetensors",
179
+ "model.layers.22.self_attn.k_proj.weight": "model.safetensors",
180
+ "model.layers.22.self_attn.o_proj.weight": "model.safetensors",
181
+ "model.layers.22.self_attn.q_norm.weight": "model.safetensors",
182
+ "model.layers.22.self_attn.q_proj.weight": "model.safetensors",
183
+ "model.layers.22.self_attn.v_proj.weight": "model.safetensors",
184
+ "model.layers.23.input_layernorm.weight": "model.safetensors",
185
+ "model.layers.23.mlp.down_proj.weight": "model.safetensors",
186
+ "model.layers.23.mlp.gate_proj.weight": "model.safetensors",
187
+ "model.layers.23.mlp.up_proj.weight": "model.safetensors",
188
+ "model.layers.23.post_attention_layernorm.weight": "model.safetensors",
189
+ "model.layers.23.self_attn.k_norm.weight": "model.safetensors",
190
+ "model.layers.23.self_attn.k_proj.weight": "model.safetensors",
191
+ "model.layers.23.self_attn.o_proj.weight": "model.safetensors",
192
+ "model.layers.23.self_attn.q_norm.weight": "model.safetensors",
193
+ "model.layers.23.self_attn.q_proj.weight": "model.safetensors",
194
+ "model.layers.23.self_attn.v_proj.weight": "model.safetensors",
195
+ "model.layers.24.input_layernorm.weight": "model.safetensors",
196
+ "model.layers.24.mlp.down_proj.weight": "model.safetensors",
197
+ "model.layers.24.mlp.gate_proj.weight": "model.safetensors",
198
+ "model.layers.24.mlp.up_proj.weight": "model.safetensors",
199
+ "model.layers.24.post_attention_layernorm.weight": "model.safetensors",
200
+ "model.layers.24.self_attn.k_norm.weight": "model.safetensors",
201
+ "model.layers.24.self_attn.k_proj.weight": "model.safetensors",
202
+ "model.layers.24.self_attn.o_proj.weight": "model.safetensors",
203
+ "model.layers.24.self_attn.q_norm.weight": "model.safetensors",
204
+ "model.layers.24.self_attn.q_proj.weight": "model.safetensors",
205
+ "model.layers.24.self_attn.v_proj.weight": "model.safetensors",
206
+ "model.layers.25.input_layernorm.weight": "model.safetensors",
207
+ "model.layers.25.mlp.down_proj.weight": "model.safetensors",
208
+ "model.layers.25.mlp.gate_proj.weight": "model.safetensors",
209
+ "model.layers.25.mlp.up_proj.weight": "model.safetensors",
210
+ "model.layers.25.post_attention_layernorm.weight": "model.safetensors",
211
+ "model.layers.25.self_attn.k_norm.weight": "model.safetensors",
212
+ "model.layers.25.self_attn.k_proj.weight": "model.safetensors",
213
+ "model.layers.25.self_attn.o_proj.weight": "model.safetensors",
214
+ "model.layers.25.self_attn.q_norm.weight": "model.safetensors",
215
+ "model.layers.25.self_attn.q_proj.weight": "model.safetensors",
216
+ "model.layers.25.self_attn.v_proj.weight": "model.safetensors",
217
+ "model.layers.26.input_layernorm.weight": "model.safetensors",
218
+ "model.layers.26.mlp.down_proj.weight": "model.safetensors",
219
+ "model.layers.26.mlp.gate_proj.weight": "model.safetensors",
220
+ "model.layers.26.mlp.up_proj.weight": "model.safetensors",
221
+ "model.layers.26.post_attention_layernorm.weight": "model.safetensors",
222
+ "model.layers.26.self_attn.k_norm.weight": "model.safetensors",
223
+ "model.layers.26.self_attn.k_proj.weight": "model.safetensors",
224
+ "model.layers.26.self_attn.o_proj.weight": "model.safetensors",
225
+ "model.layers.26.self_attn.q_norm.weight": "model.safetensors",
226
+ "model.layers.26.self_attn.q_proj.weight": "model.safetensors",
227
+ "model.layers.26.self_attn.v_proj.weight": "model.safetensors",
228
+ "model.layers.27.input_layernorm.weight": "model.safetensors",
229
+ "model.layers.27.mlp.down_proj.weight": "model.safetensors",
230
+ "model.layers.27.mlp.gate_proj.weight": "model.safetensors",
231
+ "model.layers.27.mlp.up_proj.weight": "model.safetensors",
232
+ "model.layers.27.post_attention_layernorm.weight": "model.safetensors",
233
+ "model.layers.27.self_attn.k_norm.weight": "model.safetensors",
234
+ "model.layers.27.self_attn.k_proj.weight": "model.safetensors",
235
+ "model.layers.27.self_attn.o_proj.weight": "model.safetensors",
236
+ "model.layers.27.self_attn.q_norm.weight": "model.safetensors",
237
+ "model.layers.27.self_attn.q_proj.weight": "model.safetensors",
238
+ "model.layers.27.self_attn.v_proj.weight": "model.safetensors",
239
+ "model.layers.3.input_layernorm.weight": "model.safetensors",
240
+ "model.layers.3.mlp.down_proj.weight": "model.safetensors",
241
+ "model.layers.3.mlp.gate_proj.weight": "model.safetensors",
242
+ "model.layers.3.mlp.up_proj.weight": "model.safetensors",
243
+ "model.layers.3.post_attention_layernorm.weight": "model.safetensors",
244
+ "model.layers.3.self_attn.k_norm.weight": "model.safetensors",
245
+ "model.layers.3.self_attn.k_proj.weight": "model.safetensors",
246
+ "model.layers.3.self_attn.o_proj.weight": "model.safetensors",
247
+ "model.layers.3.self_attn.q_norm.weight": "model.safetensors",
248
+ "model.layers.3.self_attn.q_proj.weight": "model.safetensors",
249
+ "model.layers.3.self_attn.v_proj.weight": "model.safetensors",
250
+ "model.layers.4.input_layernorm.weight": "model.safetensors",
251
+ "model.layers.4.mlp.down_proj.weight": "model.safetensors",
252
+ "model.layers.4.mlp.gate_proj.weight": "model.safetensors",
253
+ "model.layers.4.mlp.up_proj.weight": "model.safetensors",
254
+ "model.layers.4.post_attention_layernorm.weight": "model.safetensors",
255
+ "model.layers.4.self_attn.k_norm.weight": "model.safetensors",
256
+ "model.layers.4.self_attn.k_proj.weight": "model.safetensors",
257
+ "model.layers.4.self_attn.o_proj.weight": "model.safetensors",
258
+ "model.layers.4.self_attn.q_norm.weight": "model.safetensors",
259
+ "model.layers.4.self_attn.q_proj.weight": "model.safetensors",
260
+ "model.layers.4.self_attn.v_proj.weight": "model.safetensors",
261
+ "model.layers.5.input_layernorm.weight": "model.safetensors",
262
+ "model.layers.5.mlp.down_proj.weight": "model.safetensors",
263
+ "model.layers.5.mlp.gate_proj.weight": "model.safetensors",
264
+ "model.layers.5.mlp.up_proj.weight": "model.safetensors",
265
+ "model.layers.5.post_attention_layernorm.weight": "model.safetensors",
266
+ "model.layers.5.self_attn.k_norm.weight": "model.safetensors",
267
+ "model.layers.5.self_attn.k_proj.weight": "model.safetensors",
268
+ "model.layers.5.self_attn.o_proj.weight": "model.safetensors",
269
+ "model.layers.5.self_attn.q_norm.weight": "model.safetensors",
270
+ "model.layers.5.self_attn.q_proj.weight": "model.safetensors",
271
+ "model.layers.5.self_attn.v_proj.weight": "model.safetensors",
272
+ "model.layers.6.input_layernorm.weight": "model.safetensors",
273
+ "model.layers.6.mlp.down_proj.weight": "model.safetensors",
274
+ "model.layers.6.mlp.gate_proj.weight": "model.safetensors",
275
+ "model.layers.6.mlp.up_proj.weight": "model.safetensors",
276
+ "model.layers.6.post_attention_layernorm.weight": "model.safetensors",
277
+ "model.layers.6.self_attn.k_norm.weight": "model.safetensors",
278
+ "model.layers.6.self_attn.k_proj.weight": "model.safetensors",
279
+ "model.layers.6.self_attn.o_proj.weight": "model.safetensors",
280
+ "model.layers.6.self_attn.q_norm.weight": "model.safetensors",
281
+ "model.layers.6.self_attn.q_proj.weight": "model.safetensors",
282
+ "model.layers.6.self_attn.v_proj.weight": "model.safetensors",
283
+ "model.layers.7.input_layernorm.weight": "model.safetensors",
284
+ "model.layers.7.mlp.down_proj.weight": "model.safetensors",
285
+ "model.layers.7.mlp.gate_proj.weight": "model.safetensors",
286
+ "model.layers.7.mlp.up_proj.weight": "model.safetensors",
287
+ "model.layers.7.post_attention_layernorm.weight": "model.safetensors",
288
+ "model.layers.7.self_attn.k_norm.weight": "model.safetensors",
289
+ "model.layers.7.self_attn.k_proj.weight": "model.safetensors",
290
+ "model.layers.7.self_attn.o_proj.weight": "model.safetensors",
291
+ "model.layers.7.self_attn.q_norm.weight": "model.safetensors",
292
+ "model.layers.7.self_attn.q_proj.weight": "model.safetensors",
293
+ "model.layers.7.self_attn.v_proj.weight": "model.safetensors",
294
+ "model.layers.8.input_layernorm.weight": "model.safetensors",
295
+ "model.layers.8.mlp.down_proj.weight": "model.safetensors",
296
+ "model.layers.8.mlp.gate_proj.weight": "model.safetensors",
297
+ "model.layers.8.mlp.up_proj.weight": "model.safetensors",
298
+ "model.layers.8.post_attention_layernorm.weight": "model.safetensors",
299
+ "model.layers.8.self_attn.k_norm.weight": "model.safetensors",
300
+ "model.layers.8.self_attn.k_proj.weight": "model.safetensors",
301
+ "model.layers.8.self_attn.o_proj.weight": "model.safetensors",
302
+ "model.layers.8.self_attn.q_norm.weight": "model.safetensors",
303
+ "model.layers.8.self_attn.q_proj.weight": "model.safetensors",
304
+ "model.layers.8.self_attn.v_proj.weight": "model.safetensors",
305
+ "model.layers.9.input_layernorm.weight": "model.safetensors",
306
+ "model.layers.9.mlp.down_proj.weight": "model.safetensors",
307
+ "model.layers.9.mlp.gate_proj.weight": "model.safetensors",
308
+ "model.layers.9.mlp.up_proj.weight": "model.safetensors",
309
+ "model.layers.9.post_attention_layernorm.weight": "model.safetensors",
310
+ "model.layers.9.self_attn.k_norm.weight": "model.safetensors",
311
+ "model.layers.9.self_attn.k_proj.weight": "model.safetensors",
312
+ "model.layers.9.self_attn.o_proj.weight": "model.safetensors",
313
+ "model.layers.9.self_attn.q_norm.weight": "model.safetensors",
314
+ "model.layers.9.self_attn.q_proj.weight": "model.safetensors",
315
+ "model.layers.9.self_attn.v_proj.weight": "model.safetensors",
316
+ "model.norm.weight": "model.safetensors"
317
+ }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
318
  }
special_tokens_map.json CHANGED
@@ -14,9 +14,6 @@
14
  "<|image_pad|>",
15
  "<|video_pad|>"
16
  ],
17
- "audio_bos_token": "<|audio_start|>",
18
- "audio_eos_token": "<|audio_end|>",
19
- "audio_token": "<|audio_pad|>",
20
  "eos_token": {
21
  "content": "<|im_end|>",
22
  "lstrip": false,
@@ -24,15 +21,11 @@
24
  "rstrip": false,
25
  "single_word": false
26
  },
27
- "image_token": "<|image_pad|>",
28
  "pad_token": {
29
  "content": "<|vision_pad|>",
30
  "lstrip": false,
31
  "normalized": false,
32
  "rstrip": false,
33
  "single_word": false
34
- },
35
- "video_token": "<|video_pad|>",
36
- "vision_bos_token": "<|vision_start|>",
37
- "vision_eos_token": "<|vision_end|>"
38
  }
 
14
  "<|image_pad|>",
15
  "<|video_pad|>"
16
  ],
 
 
 
17
  "eos_token": {
18
  "content": "<|im_end|>",
19
  "lstrip": false,
 
21
  "rstrip": false,
22
  "single_word": false
23
  },
 
24
  "pad_token": {
25
  "content": "<|vision_pad|>",
26
  "lstrip": false,
27
  "normalized": false,
28
  "rstrip": false,
29
  "single_word": false
30
+ }
 
 
 
31
  }
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
3
- size 19989343
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
+ size 11422654
tokenizer_config.json CHANGED
@@ -1,300 +1,241 @@
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
- "model_max_length": 262144,
14
- "model_specific_special_tokens": {
15
- "audio_bos_token": "<|audio_start|>",
16
- "audio_eos_token": "<|audio_end|>",
17
- "audio_token": "<|audio_pad|>",
18
- "image_token": "<|image_pad|>",
19
- "video_token": "<|video_pad|>",
20
- "vision_bos_token": "<|vision_start|>",
21
- "vision_eos_token": "<|vision_end|>"
22
- },
23
- "pad_token": "<|vision_pad|>",
24
- "padding_side": "left",
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": "TokenizersBackend",
29
- "unk_token": null,
30
- "video_token": "<|video_pad|>",
31
- "vision_bos_token": "<|vision_start|>",
32
- "vision_eos_token": "<|vision_end|>",
33
  "added_tokens_decoder": {
34
- "248044": {
35
  "content": "<|endoftext|>",
36
- "single_word": false,
37
  "lstrip": false,
38
- "rstrip": false,
39
  "normalized": false,
 
 
40
  "special": true
41
  },
42
- "248045": {
43
  "content": "<|im_start|>",
44
- "single_word": false,
45
  "lstrip": false,
46
- "rstrip": false,
47
  "normalized": false,
 
 
48
  "special": true
49
  },
50
- "248046": {
51
  "content": "<|im_end|>",
52
- "single_word": false,
53
  "lstrip": false,
54
- "rstrip": false,
55
  "normalized": false,
 
 
56
  "special": true
57
  },
58
- "248047": {
59
  "content": "<|object_ref_start|>",
60
- "single_word": false,
61
  "lstrip": false,
62
- "rstrip": false,
63
  "normalized": false,
 
 
64
  "special": true
65
  },
66
- "248048": {
67
  "content": "<|object_ref_end|>",
68
- "single_word": false,
69
  "lstrip": false,
70
- "rstrip": false,
71
  "normalized": false,
 
 
72
  "special": true
73
  },
74
- "248049": {
75
  "content": "<|box_start|>",
76
- "single_word": false,
77
  "lstrip": false,
78
- "rstrip": false,
79
  "normalized": false,
 
 
80
  "special": true
81
  },
82
- "248050": {
83
  "content": "<|box_end|>",
84
- "single_word": false,
85
  "lstrip": false,
86
- "rstrip": false,
87
  "normalized": false,
 
 
88
  "special": true
89
  },
90
- "248051": {
91
  "content": "<|quad_start|>",
92
- "single_word": false,
93
  "lstrip": false,
94
- "rstrip": false,
95
  "normalized": false,
 
 
96
  "special": true
97
  },
98
- "248052": {
99
  "content": "<|quad_end|>",
100
- "single_word": false,
101
  "lstrip": false,
102
- "rstrip": false,
103
  "normalized": false,
 
 
104
  "special": true
105
  },
106
- "248053": {
107
  "content": "<|vision_start|>",
108
- "single_word": false,
109
  "lstrip": false,
110
- "rstrip": false,
111
  "normalized": false,
 
 
112
  "special": true
113
  },
114
- "248054": {
115
  "content": "<|vision_end|>",
116
- "single_word": false,
117
  "lstrip": false,
118
- "rstrip": false,
119
  "normalized": false,
 
 
120
  "special": true
121
  },
122
- "248055": {
123
  "content": "<|vision_pad|>",
124
- "single_word": false,
125
  "lstrip": false,
126
- "rstrip": false,
127
  "normalized": false,
 
 
128
  "special": true
129
  },
130
- "248056": {
131
  "content": "<|image_pad|>",
132
- "single_word": false,
133
  "lstrip": false,
134
- "rstrip": false,
135
  "normalized": false,
 
 
136
  "special": true
137
  },
138
- "248057": {
139
  "content": "<|video_pad|>",
140
- "single_word": false,
141
  "lstrip": false,
142
- "rstrip": false,
143
  "normalized": false,
 
 
144
  "special": true
145
  },
146
- "248058": {
147
  "content": "<tool_call>",
148
- "single_word": false,
149
  "lstrip": false,
150
- "rstrip": false,
151
  "normalized": false,
 
 
152
  "special": false
153
  },
154
- "248059": {
155
  "content": "</tool_call>",
156
- "single_word": false,
157
  "lstrip": false,
158
- "rstrip": false,
159
  "normalized": false,
 
 
160
  "special": false
161
  },
162
- "248060": {
163
  "content": "<|fim_prefix|>",
164
- "single_word": false,
165
  "lstrip": false,
166
- "rstrip": false,
167
  "normalized": false,
 
 
168
  "special": false
169
  },
170
- "248061": {
171
  "content": "<|fim_middle|>",
172
- "single_word": false,
173
  "lstrip": false,
174
- "rstrip": false,
175
  "normalized": false,
 
 
176
  "special": false
177
  },
178
- "248062": {
179
  "content": "<|fim_suffix|>",
180
- "single_word": false,
181
  "lstrip": false,
182
- "rstrip": false,
183
  "normalized": false,
 
 
184
  "special": false
185
  },
186
- "248063": {
187
  "content": "<|fim_pad|>",
188
- "single_word": false,
189
  "lstrip": false,
190
- "rstrip": false,
191
  "normalized": false,
 
 
192
  "special": false
193
  },
194
- "248064": {
195
  "content": "<|repo_name|>",
196
- "single_word": false,
197
  "lstrip": false,
198
- "rstrip": false,
199
  "normalized": false,
 
 
200
  "special": false
201
  },
202
- "248065": {
203
  "content": "<|file_sep|>",
204
- "single_word": false,
205
  "lstrip": false,
206
- "rstrip": false,
207
  "normalized": false,
 
 
208
  "special": false
209
  },
210
- "248066": {
211
  "content": "<tool_response>",
212
- "single_word": false,
213
  "lstrip": false,
214
- "rstrip": false,
215
  "normalized": false,
 
 
216
  "special": false
217
  },
218
- "248067": {
219
  "content": "</tool_response>",
220
- "single_word": false,
221
  "lstrip": false,
222
- "rstrip": false,
223
  "normalized": false,
224
- "special": false
225
- },
226
- "248068": {
227
- "content": "<think>",
228
- "single_word": false,
229
- "lstrip": false,
230
  "rstrip": false,
231
- "normalized": false,
232
- "special": false
233
- },
234
- "248069": {
235
- "content": "</think>",
236
  "single_word": false,
237
- "lstrip": false,
238
- "rstrip": false,
239
- "normalized": false,
240
  "special": false
241
  },
242
- "248070": {
243
- "content": "<|audio_start|>",
244
- "single_word": false,
245
- "lstrip": false,
246
- "rstrip": false,
247
- "normalized": false,
248
- "special": true
249
- },
250
- "248071": {
251
- "content": "<|audio_end|>",
252
- "single_word": false,
253
  "lstrip": false,
254
- "rstrip": false,
255
  "normalized": false,
256
- "special": true
257
- },
258
- "248072": {
259
- "content": "<tts_pad>",
260
- "single_word": false,
261
- "lstrip": false,
262
  "rstrip": false,
263
- "normalized": false,
264
- "special": true
265
- },
266
- "248073": {
267
- "content": "<tts_text_bos>",
268
  "single_word": false,
269
- "lstrip": false,
270
- "rstrip": false,
271
- "normalized": false,
272
- "special": true
273
  },
274
- "248074": {
275
- "content": "<tts_text_eod>",
276
- "single_word": false,
277
  "lstrip": false,
278
- "rstrip": false,
279
  "normalized": false,
280
- "special": true
281
- },
282
- "248075": {
283
- "content": "<tts_text_bos_single>",
284
- "single_word": false,
285
- "lstrip": false,
286
  "rstrip": false,
287
- "normalized": false,
288
- "special": true
289
- },
290
- "248076": {
291
- "content": "<|audio_pad|>",
292
  "single_word": false,
293
- "lstrip": false,
294
- "rstrip": false,
295
- "normalized": false,
296
- "special": true
297
  }
298
  },
299
- "chat_template": "{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- macro render_content(content, do_vision_count, is_system_content=false) %}\n {%- if content is string %}\n {{- content }}\n {%- elif content is iterable and content is not mapping %}\n {%- for item in content %}\n {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}\n {%- if is_system_content %}\n {{- raise_exception('System message cannot contain images.') }}\n {%- endif %}\n {%- if do_vision_count %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- endif %}\n {%- if add_vision_id %}\n {{- 'Picture ' ~ image_count.value ~ ': ' }}\n {%- endif %}\n {{- '<|vision_start|><|image_pad|><|vision_end|>' }}\n {%- elif 'video' in item or item.type == 'video' %}\n {%- if is_system_content %}\n {{- raise_exception('System message cannot contain videos.') }}\n {%- endif %}\n {%- if do_vision_count %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- endif %}\n {%- if add_vision_id %}\n {{- 'Video ' ~ video_count.value ~ ': ' }}\n {%- endif %}\n {{- '<|vision_start|><|video_pad|><|vision_end|>' }}\n {%- elif 'text' in item %}\n {{- item.text }}\n {%- else %}\n {{- raise_exception('Unexpected item type in content.') }}\n {%- endif %}\n {%- endfor %}\n {%- elif content is none or content is undefined %}\n {{- '' }}\n {%- else %}\n {{- raise_exception('Unexpected content type.') }}\n {%- endif %}\n{%- endmacro %}\n{%- if not messages %}\n {{- raise_exception('No messages provided.') }}\n{%- endif %}\n{%- set num_sys = 0 %}\n{%- set merged_system = '' %}\n{%- if messages[0].role == 'system' or messages[0].role == 'developer' %}\n {%- set first = render_content(messages[0].content, false, true)|trim %}\n {%- if messages|length > 1 and (messages[1].role == 'system' or messages[1].role == 'developer') %}\n {%- set second = render_content(messages[1].content, false, true)|trim %}\n {%- set merged_system = first + '\\n' + second %}\n {%- set num_sys = 2 %}\n {%- else %}\n {%- set merged_system = first %}\n {%- set num_sys = 1 %}\n {%- endif %}\n{%- endif %}\n{%- if tools and tools is iterable and tools is not mapping %}\n {{- '<|im_start|>system\\n' }}\n {{- \"# Tools\\n\\nYou have access to the following functions:\\n\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\" }}\n {{- '\\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>' }}\n {%- if merged_system %}\n {{- '\\n\\n' + merged_system }}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n{%- else %}\n {%- if merged_system %}\n {{- '<|im_start|>system\\n' + merged_system + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" %}\n {%- set content = render_content(message.content, false)|trim %}\n {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n {%- if loop.index0 >= num_sys and message.role != \"system\" and message.role != \"developer\" %}\n {%- set content = render_content(message.content, true)|trim %}\n {%- if message.role == \"user\" %}\n {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is string %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in content %}\n {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- set reasoning_content = reasoning_content|trim %}\n {%- if loop.index0 > ns.last_query_index %}\n {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content + '\\n</think>\\n\\n' + content }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {%- if loop.first %}\n {%- if content|trim %}\n {{- '\\n\\n<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n {%- else %}\n {{- '<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n {%- endif %}\n {%- else %}\n {{- '\\n<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n {%- endif %}\n {%- if tool_call.arguments is mapping %}\n {%- for args_name in tool_call.arguments %}\n {%- set args_value = tool_call.arguments[args_name] %}\n {{- '<parameter=' + args_name + '>\\n' }}\n {%- 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 %}\n {{- args_value }}\n {{- '\\n</parameter>\\n' }}\n {%- endfor %}\n {%- endif %}\n {{- '</function>\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.previtem and loop.previtem.role != \"tool\" %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- content }}\n {{- '\\n</tool_response>' }}\n {%- if not loop.last and loop.nextitem.role != \"tool\" %}\n {{- '<|im_end|>\\n' }}\n {%- elif loop.last %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n {%- if enable_thinking is defined and enable_thinking is true %}\n {{- '<think>\\n' }}\n {%- else %}\n {{- '<think>\\n\\n</think>\\n\\n' }}\n {%- endif %}\n{%- endif %}\n{#- Unsloth fixes - developer role, tool calling #}\n"
300
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  {
2
+ "add_bos_token": false,
3
  "add_prefix_space": false,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4
  "added_tokens_decoder": {
5
+ "151643": {
6
  "content": "<|endoftext|>",
 
7
  "lstrip": false,
 
8
  "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
  "special": true
12
  },
13
+ "151644": {
14
  "content": "<|im_start|>",
 
15
  "lstrip": false,
 
16
  "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
  "special": true
20
  },
21
+ "151645": {
22
  "content": "<|im_end|>",
 
23
  "lstrip": false,
 
24
  "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
  "special": true
28
  },
29
+ "151646": {
30
  "content": "<|object_ref_start|>",
 
31
  "lstrip": false,
 
32
  "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
  "special": true
36
  },
37
+ "151647": {
38
  "content": "<|object_ref_end|>",
 
39
  "lstrip": false,
 
40
  "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
  "special": true
44
  },
45
+ "151648": {
46
  "content": "<|box_start|>",
 
47
  "lstrip": false,
 
48
  "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
  "special": true
52
  },
53
+ "151649": {
54
  "content": "<|box_end|>",
 
55
  "lstrip": false,
 
56
  "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
  "special": true
60
  },
61
+ "151650": {
62
  "content": "<|quad_start|>",
 
63
  "lstrip": false,
 
64
  "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
  "special": true
68
  },
69
+ "151651": {
70
  "content": "<|quad_end|>",
 
71
  "lstrip": false,
 
72
  "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
  "special": true
76
  },
77
+ "151652": {
78
  "content": "<|vision_start|>",
 
79
  "lstrip": false,
 
80
  "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
  "special": true
84
  },
85
+ "151653": {
86
  "content": "<|vision_end|>",
 
87
  "lstrip": false,
 
88
  "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
  "special": true
92
  },
93
+ "151654": {
94
  "content": "<|vision_pad|>",
 
95
  "lstrip": false,
 
96
  "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
  "special": true
100
  },
101
+ "151655": {
102
  "content": "<|image_pad|>",
 
103
  "lstrip": false,
 
104
  "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
  "special": true
108
  },
109
+ "151656": {
110
  "content": "<|video_pad|>",
 
111
  "lstrip": false,
 
112
  "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
  "special": true
116
  },
117
+ "151657": {
118
  "content": "<tool_call>",
 
119
  "lstrip": false,
 
120
  "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
  "special": false
124
  },
125
+ "151658": {
126
  "content": "</tool_call>",
 
127
  "lstrip": false,
 
128
  "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
  "special": false
132
  },
133
+ "151659": {
134
  "content": "<|fim_prefix|>",
 
135
  "lstrip": false,
 
136
  "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
  "special": false
140
  },
141
+ "151660": {
142
  "content": "<|fim_middle|>",
 
143
  "lstrip": false,
 
144
  "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
  "special": false
148
  },
149
+ "151661": {
150
  "content": "<|fim_suffix|>",
 
151
  "lstrip": false,
 
152
  "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
  "special": false
156
  },
157
+ "151662": {
158
  "content": "<|fim_pad|>",
 
159
  "lstrip": false,
 
160
  "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
  "special": false
164
  },
165
+ "151663": {
166
  "content": "<|repo_name|>",
 
167
  "lstrip": false,
 
168
  "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
  "special": false
172
  },
173
+ "151664": {
174
  "content": "<|file_sep|>",
 
175
  "lstrip": false,
 
176
  "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
  "special": false
180
  },
181
+ "151665": {
182
  "content": "<tool_response>",
 
183
  "lstrip": false,
 
184
  "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
  "special": false
188
  },
189
+ "151666": {
190
  "content": "</tool_response>",
 
191
  "lstrip": false,
 
192
  "normalized": false,
 
 
 
 
 
 
193
  "rstrip": false,
 
 
 
 
 
194
  "single_word": false,
 
 
 
195
  "special": false
196
  },
197
+ "151667": {
198
+ "content": "<think>",
 
 
 
 
 
 
 
 
 
199
  "lstrip": false,
 
200
  "normalized": false,
 
 
 
 
 
 
201
  "rstrip": false,
 
 
 
 
 
202
  "single_word": false,
203
+ "special": false
 
 
 
204
  },
205
+ "151668": {
206
+ "content": "</think>",
 
207
  "lstrip": false,
 
208
  "normalized": false,
 
 
 
 
 
 
209
  "rstrip": false,
 
 
 
 
 
210
  "single_word": false,
211
+ "special": false
 
 
 
212
  }
213
  },
214
+ "additional_special_tokens": [
215
+ "<|im_start|>",
216
+ "<|im_end|>",
217
+ "<|object_ref_start|>",
218
+ "<|object_ref_end|>",
219
+ "<|box_start|>",
220
+ "<|box_end|>",
221
+ "<|quad_start|>",
222
+ "<|quad_end|>",
223
+ "<|vision_start|>",
224
+ "<|vision_end|>",
225
+ "<|vision_pad|>",
226
+ "<|image_pad|>",
227
+ "<|video_pad|>"
228
+ ],
229
+ "bos_token": null,
230
+ "clean_up_tokenization_spaces": false,
231
+ "eos_token": "<|im_end|>",
232
+ "errors": "replace",
233
+ "extra_special_tokens": {},
234
+ "model_max_length": 40960,
235
+ "pad_token": "<|vision_pad|>",
236
+ "padding_side": "left",
237
+ "split_special_tokens": false,
238
+ "tokenizer_class": "Qwen2Tokenizer",
239
+ "tool_parser_type": "json_tools",
240
+ "unk_token": null
241
+ }
vocab.json CHANGED
The diff for this file is too large to render. See raw diff