Hugging Face's logo

win10
/
EVE-27B-XENO-HAT

Text Generation
Safetensors
Chinese
Russian
English
qwen3_5
Merge
gpt
gpt_oss
262k
conversational
Model card Files
xet
 Community
win10 commited on
Commit
5a56d29
·
verified ·
1 Parent(s): 8e477ec

Add files using upload-large-folder tool

Browse files
Files changed (27) hide show
  1. .gitattributes +1 -0
  2. chat_template.jinja +158 -0
  3. chat_template_stable.jinja +201 -0
  4. config.json +146 -0
  5. generation_config.json +13 -0
  6. model-00001-of-00011.safetensors +3 -0
  7. model-00002-of-00011.safetensors +3 -0
  8. model-00003-of-00011.safetensors +3 -0
  9. model-00004-of-00011.safetensors +3 -0
  10. model-00005-of-00011.safetensors +3 -0
  11. model-00006-of-00011.safetensors +3 -0
  12. model-00007-of-00011.safetensors +3 -0
  13. model-00008-of-00011.safetensors +3 -0
  14. model-00009-of-00011.safetensors +3 -0
  15. model-00010-of-00011.safetensors +3 -0
  16. model-00011-of-00011.safetensors +3 -0
  17. model.safetensors.index.json +0 -0
  18. preprocessor_config.json +21 -0
  19. processor_config.json +60 -0
  20. tokenizer.json +3 -0
  21. tokenizer_config.json +301 -0
  22. video_preprocessor_config.json +21 -0
  23. vocab.json +0 -0
  24. xeno_evolution.json +578 -0
  25. xeno_genome.json +217 -0
  26. xeno_mapping.json +0 -0
  27. xeno_report.json +309 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
chat_template.jinja ADDED
@@ -0,0 +1,158 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 (preserve_thinking is defined and preserve_thinking is true) or (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 false %}
153
+ {{- '<think>\n\n</think>\n\n' }}
154
+ {%- else %}
155
+ {{- '<think>\n' }}
156
+ {%- endif %}
157
+ {%- endif %}
158
+ {#- Unsloth fixes - developer role, tool calling #}
chat_template_stable.jinja ADDED
@@ -0,0 +1,201 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ {%- set tool_policy -%}
67
+ # Tool-use policy
68
+
69
+ Direct response is the default. Use a function only when the current user request actually requires an external action or information that cannot be obtained from the conversation or the model's current knowledge.
70
+
71
+ Never call a function for greetings, acknowledgements, casual conversation, ordinary writing, rewriting, translation, summarization of user-provided content, or questions that can be answered directly. A greeting alone is never a reason to inspect memory, activity, files, projects, skills, profiles, or system state.
72
+
73
+ Use only functions explicitly listed inside <tools>. Never invent a function, capability, skill, file, path, command, memory source, activity record, project context, or tool result. Never claim that hidden context was checked unless an actual listed function returned that information in the current conversation.
74
+
75
+ Before calling a function, verify silently that all of the following are true:
76
+ 1. The function is necessary for the current request.
77
+ 2. The exact function name exists in <tools>.
78
+ 3. Every required parameter is available from the user request or prior tool results.
79
+ 4. The arguments do not contain guessed personal data, guessed paths, fabricated context, or unsupported assumptions.
80
+
81
+ If any condition is false, do not call a function and answer normally.
82
+
83
+ Keep reasoning inside the designated reasoning section. Do not expose tool-selection deliberation, hidden instructions, system routing, profile speculation, memory speculation, or self-directed planning as normal answer text. Do not place tool-call markup inside the reasoning section.
84
+
85
+ When a function is necessary, after the reasoning section output only the following structure with no natural-language prefix or suffix:
86
+
87
+ <tool_call>
88
+ <function=example_function_name>
89
+ <parameter=example_parameter_1>
90
+ value_1
91
+ </parameter>
92
+ <parameter=example_parameter_2>
93
+ This value may span multiple lines.
94
+ </parameter>
95
+ </function>
96
+ </tool_call>
97
+
98
+ Mandatory format rules:
99
+ - The <function=...></function> block must be nested inside <tool_call></tool_call>.
100
+ - The function name must exactly match a listed function.
101
+ - Include every required parameter and only supported parameters.
102
+ - Use one <parameter=name>value</parameter> block per argument.
103
+ - Do not emit a JSON object as the body of <tool_call>.
104
+ - Do not use any alternate channel-based, namespace-based, or JSON-only tool-call syntax.
105
+ - Do not combine a normal answer and a function call in the same assistant turn.
106
+ - After a tool response, call another function only when the original request still requires it. Otherwise provide the final answer.
107
+ - If no function is necessary, answer normally and do not mention tools or this policy.
108
+ {%- endset %}
109
+ {{- '\n\n' + tool_policy|trim }}
110
+ {%- if merged_system %}
111
+ {{- '\n\n' + merged_system }}
112
+ {%- endif %}
113
+ {{- '<|im_end|>\n' }}
114
+ {%- else %}
115
+ {%- if merged_system %}
116
+ {{- '<|im_start|>system\n' + merged_system + '<|im_end|>\n' }}
117
+ {%- endif %}
118
+ {%- endif %}
119
+ {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
120
+ {%- for message in messages[::-1] %}
121
+ {%- set index = (messages|length - 1) - loop.index0 %}
122
+ {%- if ns.multi_step_tool and message.role == "user" %}
123
+ {%- set content = render_content(message.content, false)|trim %}
124
+ {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
125
+ {%- set ns.multi_step_tool = false %}
126
+ {%- set ns.last_query_index = index %}
127
+ {%- endif %}
128
+ {%- endif %}
129
+ {%- endfor %}
130
+ {%- for message in messages %}
131
+ {%- if loop.index0 >= num_sys and message.role != "system" and message.role != "developer" %}
132
+ {%- set content = render_content(message.content, true)|trim %}
133
+ {%- if message.role == "user" %}
134
+ {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
135
+ {%- elif message.role == "assistant" %}
136
+ {%- set reasoning_content = '' %}
137
+ {%- if message.reasoning_content is string %}
138
+ {%- set reasoning_content = message.reasoning_content %}
139
+ {%- else %}
140
+ {%- if '</think>' in content %}
141
+ {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
142
+ {%- set content = content.split('</think>')[-1].lstrip('\n') %}
143
+ {%- endif %}
144
+ {%- endif %}
145
+ {%- set reasoning_content = reasoning_content|trim %}
146
+ {%- if (preserve_thinking is defined and preserve_thinking is true) or (loop.index0 > ns.last_query_index) %}
147
+ {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
148
+ {%- else %}
149
+ {{- '<|im_start|>' + message.role + '\n' + content }}
150
+ {%- endif %}
151
+ {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
152
+ {%- for tool_call in message.tool_calls %}
153
+ {%- if tool_call.function is defined %}
154
+ {%- set tool_call = tool_call.function %}
155
+ {%- endif %}
156
+ {%- if loop.first %}
157
+ {%- if content|trim %}
158
+ {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
159
+ {%- else %}
160
+ {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
161
+ {%- endif %}
162
+ {%- else %}
163
+ {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
164
+ {%- endif %}
165
+ {%- if tool_call.arguments is mapping %}
166
+ {%- for args_name in tool_call.arguments %}
167
+ {%- set args_value = tool_call.arguments[args_name] %}
168
+ {{- '<parameter=' + args_name + '>\n' }}
169
+ {%- 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 %}
170
+ {{- args_value }}
171
+ {{- '\n</parameter>\n' }}
172
+ {%- endfor %}
173
+ {%- endif %}
174
+ {{- '</function>\n</tool_call>' }}
175
+ {%- endfor %}
176
+ {%- endif %}
177
+ {{- '<|im_end|>\n' }}
178
+ {%- elif message.role == "tool" %}
179
+ {%- if loop.previtem and loop.previtem.role != "tool" %}
180
+ {{- '<|im_start|>user' }}
181
+ {%- endif %}
182
+ {{- '\n<tool_response>\n' }}
183
+ {{- content }}
184
+ {{- '\n</tool_response>' }}
185
+ {%- if not loop.last and loop.nextitem.role != "tool" %}
186
+ {{- '<|im_end|>\n' }}
187
+ {%- elif loop.last %}
188
+ {{- '<|im_end|>\n' }}
189
+ {%- endif %}
190
+ {%- endif %}
191
+ {%- endif %}
192
+ {%- endfor %}
193
+ {%- if add_generation_prompt %}
194
+ {{- '<|im_start|>assistant\n' }}
195
+ {%- if enable_thinking is defined and enable_thinking is false %}
196
+ {{- '<think>\n\n</think>\n\n' }}
197
+ {%- else %}
198
+ {{- '<think>\n' }}
199
+ {%- endif %}
200
+ {%- endif %}
201
+ {#- Unsloth fixes - developer role, tool calling #}
config.json ADDED
@@ -0,0 +1,146 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3_5ForConditionalGeneration"
4
+ ],
5
+ "bos_token_id": null,
6
+ "torch_dtype": "bfloat16",
7
+ "eos_token_id": 248046,
8
+ "image_token_id": 248056,
9
+ "language_model_only": false,
10
+ "model_type": "qwen3_5",
11
+ "pad_token_id": 248044,
12
+ "text_config": {
13
+ "attention_bias": false,
14
+ "attention_dropout": 0.0,
15
+ "attn_output_gate": true,
16
+ "bos_token_id": 248044,
17
+ "torch_dtype": "bfloat16",
18
+ "eos_token_id": 248044,
19
+ "full_attention_interval": 4,
20
+ "head_dim": 256,
21
+ "hidden_act": "silu",
22
+ "hidden_size": 5120,
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 17408,
25
+ "layer_types": [
26
+ "linear_attention",
27
+ "linear_attention",
28
+ "linear_attention",
29
+ "full_attention",
30
+ "linear_attention",
31
+ "linear_attention",
32
+ "linear_attention",
33
+ "full_attention",
34
+ "linear_attention",
35
+ "linear_attention",
36
+ "linear_attention",
37
+ "full_attention",
38
+ "linear_attention",
39
+ "linear_attention",
40
+ "linear_attention",
41
+ "full_attention",
42
+ "linear_attention",
43
+ "linear_attention",
44
+ "linear_attention",
45
+ "full_attention",
46
+ "linear_attention",
47
+ "linear_attention",
48
+ "linear_attention",
49
+ "full_attention",
50
+ "linear_attention",
51
+ "linear_attention",
52
+ "linear_attention",
53
+ "full_attention",
54
+ "linear_attention",
55
+ "linear_attention",
56
+ "linear_attention",
57
+ "full_attention",
58
+ "linear_attention",
59
+ "linear_attention",
60
+ "linear_attention",
61
+ "full_attention",
62
+ "linear_attention",
63
+ "linear_attention",
64
+ "linear_attention",
65
+ "full_attention",
66
+ "linear_attention",
67
+ "linear_attention",
68
+ "linear_attention",
69
+ "full_attention",
70
+ "linear_attention",
71
+ "linear_attention",
72
+ "linear_attention",
73
+ "full_attention",
74
+ "linear_attention",
75
+ "linear_attention",
76
+ "linear_attention",
77
+ "full_attention",
78
+ "linear_attention",
79
+ "linear_attention",
80
+ "linear_attention",
81
+ "full_attention",
82
+ "linear_attention",
83
+ "linear_attention",
84
+ "linear_attention",
85
+ "full_attention",
86
+ "linear_attention",
87
+ "linear_attention",
88
+ "linear_attention",
89
+ "full_attention"
90
+ ],
91
+ "linear_conv_kernel_dim": 4,
92
+ "linear_key_head_dim": 128,
93
+ "linear_num_key_heads": 16,
94
+ "linear_num_value_heads": 48,
95
+ "linear_value_head_dim": 128,
96
+ "mamba_ssm_dtype": "float32",
97
+ "max_position_embeddings": 262144,
98
+ "model_type": "qwen3_5_text",
99
+ "mtp_num_hidden_layers": 1,
100
+ "mtp_use_dedicated_embeddings": false,
101
+ "num_attention_heads": 24,
102
+ "num_hidden_layers": 64,
103
+ "num_key_value_heads": 4,
104
+ "output_gate_type": "swish",
105
+ "pad_token_id": null,
106
+ "partial_rotary_factor": 0.25,
107
+ "rms_norm_eps": 1e-06,
108
+ "rope_parameters": {
109
+ "mrope_interleaved": true,
110
+ "mrope_section": [
111
+ 11,
112
+ 11,
113
+ 10
114
+ ],
115
+ "partial_rotary_factor": 0.25,
116
+ "rope_theta": 10000000,
117
+ "rope_type": "default"
118
+ },
119
+ "tie_word_embeddings": false,
120
+ "use_cache": true,
121
+ "vocab_size": 248320
122
+ },
123
+ "tie_word_embeddings": false,
124
+ "unsloth_version": "2026.6.7",
125
+ "use_cache": false,
126
+ "video_token_id": 248057,
127
+ "vision_config": {
128
+ "deepstack_visual_indexes": [],
129
+ "depth": 27,
130
+ "torch_dtype": "bfloat16",
131
+ "hidden_act": "gelu_pytorch_tanh",
132
+ "hidden_size": 1152,
133
+ "in_channels": 3,
134
+ "initializer_range": 0.02,
135
+ "intermediate_size": 4304,
136
+ "model_type": "qwen3_5_vision",
137
+ "num_heads": 16,
138
+ "num_position_embeddings": 2304,
139
+ "out_hidden_size": 5120,
140
+ "patch_size": 16,
141
+ "spatial_merge_size": 2,
142
+ "temporal_patch_size": 2
143
+ },
144
+ "vision_end_token_id": 248054,
145
+ "vision_start_token_id": 248053
146
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_sample": true,
3
+ "eos_token_id": [
4
+ 248046,
5
+ 248046,
6
+ 248044
7
+ ],
8
+ "pad_token_id": 248044,
9
+ "temperature": 1.0,
10
+ "top_k": 20,
11
+ "top_p": 0.95,
12
+ "transformers_version": "5.12.1"
13
+ }
model-00001-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9aa41be03ff4da663fb75c4d02d03bae9da8b7129e35ed6e72da8f147a4549ce
3
+ size 5317357528
model-00002-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51e62b80818c78eb1ccbde3f854473262752eaf02908332cb814562376f24c01
3
+ size 5290305904
model-00003-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b697e69797d9fd3b9c28b4022c84fe57f628152062e3d9d0cbbec8738e8567a9
3
+ size 5312345432
model-00004-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:edf42bfc3fb5cdae3fcde07e75f8754bb0143e88329ad5e0d6fb136619cef15e
3
+ size 5321764880
model-00005-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e903ec61f2e92f42e3520c18b01baeae259c512c17775d4813c690b75e9ef094
3
+ size 5321764872
model-00006-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61091b42739e525433785d809d60895e4cf1826e7e56f7026bc94ca23206be51
3
+ size 5321764880
model-00007-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed500e2676fb769f68ee2e73755a7f449e7c36ff7b1e2669ae873f0a621597ad
3
+ size 5353220616
model-00008-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e819ebd0ba8876bcea2a3dbd5c3a362996269e848fd4dbb5e4833d92a606325
3
+ size 5312345432
model-00009-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:581451f1133e2c5c7f710d7fbba33d8a1cef43bc828260e0245e4e0b30313d62
3
+ size 5321764872
model-00010-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0840922d66a81c6002c9521ad9a00e7bbc2e9940e36bfa51993fb43ab25b4cd
3
+ size 5321764840
model-00011-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e4bb0755e168415be02bb5ec76c41d4ec771b8a4338ace7fef23ed9ae6d12a9
3
+ size 2368607632
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
preprocessor_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "size": {
3
+ "longest_edge": 16777216,
4
+ "shortest_edge": 65536
5
+ },
6
+ "patch_size": 16,
7
+ "temporal_patch_size": 2,
8
+ "merge_size": 2,
9
+ "image_mean": [
10
+ 0.5,
11
+ 0.5,
12
+ 0.5
13
+ ],
14
+ "image_std": [
15
+ 0.5,
16
+ 0.5,
17
+ 0.5
18
+ ],
19
+ "processor_class": "Qwen3VLProcessor",
20
+ "image_processor_type": "Qwen2VLImageProcessorFast"
21
+ }
processor_config.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "image_processor": {
3
+ "do_convert_rgb": true,
4
+ "do_normalize": true,
5
+ "do_rescale": true,
6
+ "do_resize": true,
7
+ "image_mean": [
8
+ 0.5,
9
+ 0.5,
10
+ 0.5
11
+ ],
12
+ "image_processor_type": "Qwen2VLImageProcessor",
13
+ "image_std": [
14
+ 0.5,
15
+ 0.5,
16
+ 0.5
17
+ ],
18
+ "merge_size": 2,
19
+ "patch_size": 16,
20
+ "resample": 3,
21
+ "rescale_factor": 0.00392156862745098,
22
+ "size": {
23
+ "longest_edge": 16777216,
24
+ "shortest_edge": 65536
25
+ },
26
+ "temporal_patch_size": 2
27
+ },
28
+ "processor_class": "Qwen3VLProcessor",
29
+ "video_processor": {
30
+ "do_convert_rgb": true,
31
+ "do_normalize": true,
32
+ "do_rescale": true,
33
+ "do_resize": true,
34
+ "do_sample_frames": true,
35
+ "fps": 2,
36
+ "image_mean": [
37
+ 0.5,
38
+ 0.5,
39
+ 0.5
40
+ ],
41
+ "image_std": [
42
+ 0.5,
43
+ 0.5,
44
+ 0.5
45
+ ],
46
+ "max_frames": 768,
47
+ "merge_size": 2,
48
+ "min_frames": 4,
49
+ "patch_size": 16,
50
+ "resample": 3,
51
+ "rescale_factor": 0.00392156862745098,
52
+ "return_metadata": false,
53
+ "size": {
54
+ "longest_edge": 25165824,
55
+ "shortest_edge": 4096
56
+ },
57
+ "temporal_patch_size": 2,
58
+ "video_processor_type": "Qwen3VLVideoProcessor"
59
+ }
60
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
3
+ size 19989325
tokenizer_config.json ADDED
@@ -0,0 +1,301 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "audio_bos_token": "<|audio_start|>",
4
+ "audio_eos_token": "<|audio_end|>",
5
+ "audio_token": "<|audio_pad|>",
6
+ "backend": "tokenizers",
7
+ "bos_token": null,
8
+ "clean_up_tokenization_spaces": false,
9
+ "eos_token": "<|im_end|>",
10
+ "errors": "replace",
11
+ "image_token": "<|image_pad|>",
12
+ "is_local": false,
13
+ "local_files_only": false,
14
+ "model_max_length": 262144,
15
+ "model_specific_special_tokens": {
16
+ "audio_bos_token": "<|audio_start|>",
17
+ "audio_eos_token": "<|audio_end|>",
18
+ "audio_token": "<|audio_pad|>",
19
+ "image_token": "<|image_pad|>",
20
+ "video_token": "<|video_pad|>",
21
+ "vision_bos_token": "<|vision_start|>",
22
+ "vision_eos_token": "<|vision_end|>"
23
+ },
24
+ "pad_token": "<|endoftext|>",
25
+ "padding_side": "right",
26
+ "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+",
27
+ "processor_class": "Qwen3VLProcessor",
28
+ "split_special_tokens": false,
29
+ "tokenizer_class": "Qwen2Tokenizer",
30
+ "unk_token": null,
31
+ "video_token": "<|video_pad|>",
32
+ "vision_bos_token": "<|vision_start|>",
33
+ "vision_eos_token": "<|vision_end|>",
34
+ "added_tokens_decoder": {
35
+ "248044": {
36
+ "content": "<|endoftext|>",
37
+ "single_word": false,
38
+ "lstrip": false,
39
+ "rstrip": false,
40
+ "normalized": false,
41
+ "special": true
42
+ },
43
+ "248045": {
44
+ "content": "<|im_start|>",
45
+ "single_word": false,
46
+ "lstrip": false,
47
+ "rstrip": false,
48
+ "normalized": false,
49
+ "special": true
50
+ },
51
+ "248046": {
52
+ "content": "<|im_end|>",
53
+ "single_word": false,
54
+ "lstrip": false,
55
+ "rstrip": false,
56
+ "normalized": false,
57
+ "special": true
58
+ },
59
+ "248047": {
60
+ "content": "<|object_ref_start|>",
61
+ "single_word": false,
62
+ "lstrip": false,
63
+ "rstrip": false,
64
+ "normalized": false,
65
+ "special": true
66
+ },
67
+ "248048": {
68
+ "content": "<|object_ref_end|>",
69
+ "single_word": false,
70
+ "lstrip": false,
71
+ "rstrip": false,
72
+ "normalized": false,
73
+ "special": true
74
+ },
75
+ "248049": {
76
+ "content": "<|box_start|>",
77
+ "single_word": false,
78
+ "lstrip": false,
79
+ "rstrip": false,
80
+ "normalized": false,
81
+ "special": true
82
+ },
83
+ "248050": {
84
+ "content": "<|box_end|>",
85
+ "single_word": false,
86
+ "lstrip": false,
87
+ "rstrip": false,
88
+ "normalized": false,
89
+ "special": true
90
+ },
91
+ "248051": {
92
+ "content": "<|quad_start|>",
93
+ "single_word": false,
94
+ "lstrip": false,
95
+ "rstrip": false,
96
+ "normalized": false,
97
+ "special": true
98
+ },
99
+ "248052": {
100
+ "content": "<|quad_end|>",
101
+ "single_word": false,
102
+ "lstrip": false,
103
+ "rstrip": false,
104
+ "normalized": false,
105
+ "special": true
106
+ },
107
+ "248053": {
108
+ "content": "<|vision_start|>",
109
+ "single_word": false,
110
+ "lstrip": false,
111
+ "rstrip": false,
112
+ "normalized": false,
113
+ "special": true
114
+ },
115
+ "248054": {
116
+ "content": "<|vision_end|>",
117
+ "single_word": false,
118
+ "lstrip": false,
119
+ "rstrip": false,
120
+ "normalized": false,
121
+ "special": true
122
+ },
123
+ "248055": {
124
+ "content": "<|vision_pad|>",
125
+ "single_word": false,
126
+ "lstrip": false,
127
+ "rstrip": false,
128
+ "normalized": false,
129
+ "special": true
130
+ },
131
+ "248056": {
132
+ "content": "<|image_pad|>",
133
+ "single_word": false,
134
+ "lstrip": false,
135
+ "rstrip": false,
136
+ "normalized": false,
137
+ "special": true
138
+ },
139
+ "248057": {
140
+ "content": "<|video_pad|>",
141
+ "single_word": false,
142
+ "lstrip": false,
143
+ "rstrip": false,
144
+ "normalized": false,
145
+ "special": true
146
+ },
147
+ "248058": {
148
+ "content": "<tool_call>",
149
+ "single_word": false,
150
+ "lstrip": false,
151
+ "rstrip": false,
152
+ "normalized": false,
153
+ "special": false
154
+ },
155
+ "248059": {
156
+ "content": "</tool_call>",
157
+ "single_word": false,
158
+ "lstrip": false,
159
+ "rstrip": false,
160
+ "normalized": false,
161
+ "special": false
162
+ },
163
+ "248060": {
164
+ "content": "<|fim_prefix|>",
165
+ "single_word": false,
166
+ "lstrip": false,
167
+ "rstrip": false,
168
+ "normalized": false,
169
+ "special": false
170
+ },
171
+ "248061": {
172
+ "content": "<|fim_middle|>",
173
+ "single_word": false,
174
+ "lstrip": false,
175
+ "rstrip": false,
176
+ "normalized": false,
177
+ "special": false
178
+ },
179
+ "248062": {
180
+ "content": "<|fim_suffix|>",
181
+ "single_word": false,
182
+ "lstrip": false,
183
+ "rstrip": false,
184
+ "normalized": false,
185
+ "special": false
186
+ },
187
+ "248063": {
188
+ "content": "<|fim_pad|>",
189
+ "single_word": false,
190
+ "lstrip": false,
191
+ "rstrip": false,
192
+ "normalized": false,
193
+ "special": false
194
+ },
195
+ "248064": {
196
+ "content": "<|repo_name|>",
197
+ "single_word": false,
198
+ "lstrip": false,
199
+ "rstrip": false,
200
+ "normalized": false,
201
+ "special": false
202
+ },
203
+ "248065": {
204
+ "content": "<|file_sep|>",
205
+ "single_word": false,
206
+ "lstrip": false,
207
+ "rstrip": false,
208
+ "normalized": false,
209
+ "special": false
210
+ },
211
+ "248066": {
212
+ "content": "<tool_response>",
213
+ "single_word": false,
214
+ "lstrip": false,
215
+ "rstrip": false,
216
+ "normalized": false,
217
+ "special": false
218
+ },
219
+ "248067": {
220
+ "content": "</tool_response>",
221
+ "single_word": false,
222
+ "lstrip": false,
223
+ "rstrip": false,
224
+ "normalized": false,
225
+ "special": false
226
+ },
227
+ "248068": {
228
+ "content": "<think>",
229
+ "single_word": false,
230
+ "lstrip": false,
231
+ "rstrip": false,
232
+ "normalized": false,
233
+ "special": false
234
+ },
235
+ "248069": {
236
+ "content": "</think>",
237
+ "single_word": false,
238
+ "lstrip": false,
239
+ "rstrip": false,
240
+ "normalized": false,
241
+ "special": false
242
+ },
243
+ "248070": {
244
+ "content": "<|audio_start|>",
245
+ "single_word": false,
246
+ "lstrip": false,
247
+ "rstrip": false,
248
+ "normalized": false,
249
+ "special": true
250
+ },
251
+ "248071": {
252
+ "content": "<|audio_end|>",
253
+ "single_word": false,
254
+ "lstrip": false,
255
+ "rstrip": false,
256
+ "normalized": false,
257
+ "special": true
258
+ },
259
+ "248072": {
260
+ "content": "<tts_pad>",
261
+ "single_word": false,
262
+ "lstrip": false,
263
+ "rstrip": false,
264
+ "normalized": false,
265
+ "special": true
266
+ },
267
+ "248073": {
268
+ "content": "<tts_text_bos>",
269
+ "single_word": false,
270
+ "lstrip": false,
271
+ "rstrip": false,
272
+ "normalized": false,
273
+ "special": true
274
+ },
275
+ "248074": {
276
+ "content": "<tts_text_eod>",
277
+ "single_word": false,
278
+ "lstrip": false,
279
+ "rstrip": false,
280
+ "normalized": false,
281
+ "special": true
282
+ },
283
+ "248075": {
284
+ "content": "<tts_text_bos_single>",
285
+ "single_word": false,
286
+ "lstrip": false,
287
+ "rstrip": false,
288
+ "normalized": false,
289
+ "special": true
290
+ },
291
+ "248076": {
292
+ "content": "<|audio_pad|>",
293
+ "single_word": false,
294
+ "lstrip": false,
295
+ "rstrip": false,
296
+ "normalized": false,
297
+ "special": true
298
+ }
299
+ },
300
+ "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 (preserve_thinking is defined and preserve_thinking is true) or (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 false %}\n {{- '<think>\\n\\n</think>\\n\\n' }}\n {%- else %}\n {{- '<think>\\n' }}\n {%- endif %}\n{%- endif %}\n{#- Unsloth fixes - developer role, tool calling #}\n"
301
+ }
video_preprocessor_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "size": {
3
+ "longest_edge": 25165824,
4
+ "shortest_edge": 4096
5
+ },
6
+ "patch_size": 16,
7
+ "temporal_patch_size": 2,
8
+ "merge_size": 2,
9
+ "image_mean": [
10
+ 0.5,
11
+ 0.5,
12
+ 0.5
13
+ ],
14
+ "image_std": [
15
+ 0.5,
16
+ 0.5,
17
+ 0.5
18
+ ],
19
+ "processor_class": "Qwen3VLProcessor",
20
+ "video_processor_type": "Qwen3VLVideoProcessor"
21
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
xeno_evolution.json ADDED
@@ -0,0 +1,578 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "algorithm": "XENO-HAT",
3
+ "variant": "intrinsic-viability-standalone",
4
+ "selection_mode": "intrinsic_viability",
5
+ "scientific_status": "intrinsic_structural_evolution",
6
+ "generations_completed": 2000,
7
+ "population": 64,
8
+ "groups": 32,
9
+ "donors": 1,
10
+ "best_intrinsic_viability": 0.49689868092536926,
11
+ "best_components": {
12
+ "assimilation_benefit": 0.7423057556152344,
13
+ "diversity_bonus": 0.0,
14
+ "compatibility_risk": 0.11876931041479111,
15
+ "energy_penalty": 0.1265355944633484,
16
+ "strength_roughness": 0.00010219745308859274,
17
+ "donor_roughness": 0.0,
18
+ "collapse_penalty": 0.0,
19
+ "total": 0.49689868092536926
20
+ },
21
+ "compatibility": [
22
+ [
23
+ 0.7736037969589233
24
+ ],
25
+ [
26
+ 0.7860755324363708
27
+ ],
28
+ [
29
+ 0.7848408222198486
30
+ ],
31
+ [
32
+ 0.7956677079200745
33
+ ],
34
+ [
35
+ 0.801688015460968
36
+ ],
37
+ [
38
+ 0.7957690954208374
39
+ ],
40
+ [
41
+ 0.8060528635978699
42
+ ],
43
+ [
44
+ 0.8099802136421204
45
+ ],
46
+ [
47
+ 0.8204229474067688
48
+ ],
49
+ [
50
+ 0.8158235549926758
51
+ ],
52
+ [
53
+ 0.8195307850837708
54
+ ],
55
+ [
56
+ 0.8203746676445007
57
+ ],
58
+ [
59
+ 0.8259692192077637
60
+ ],
61
+ [
62
+ 0.825683057308197
63
+ ],
64
+ [
65
+ 0.8253080248832703
66
+ ],
67
+ [
68
+ 0.8278267979621887
69
+ ],
70
+ [
71
+ 0.8267802000045776
72
+ ],
73
+ [
74
+ 0.8258090019226074
75
+ ],
76
+ [
77
+ 0.820401668548584
78
+ ],
79
+ [
80
+ 0.8183936476707458
81
+ ],
82
+ [
83
+ 0.8180018067359924
84
+ ],
85
+ [
86
+ 0.8176644444465637
87
+ ],
88
+ [
89
+ 0.8156882524490356
90
+ ],
91
+ [
92
+ 0.814712643623352
93
+ ],
94
+ [
95
+ 0.8127619028091431
96
+ ],
97
+ [
98
+ 0.8118614554405212
99
+ ],
100
+ [
101
+ 0.8101686835289001
102
+ ],
103
+ [
104
+ 0.8081267476081848
105
+ ],
106
+ [
107
+ 0.8020999431610107
108
+ ],
109
+ [
110
+ 0.8031536340713501
111
+ ],
112
+ [
113
+ 0.8024434447288513
114
+ ],
115
+ [
116
+ 0.800318717956543
117
+ ]
118
+ ],
119
+ "history": [
120
+ {
121
+ "generation": 1.0,
122
+ "generation_best": 0.15995393693447113,
123
+ "global_best": 0.15995393693447113,
124
+ "mean_score": 0.12841693812515587,
125
+ "mean_sigma": 0.7847505807876587
126
+ },
127
+ {
128
+ "generation": 100.0,
129
+ "generation_best": 0.427026629447937,
130
+ "global_best": 0.427026629447937,
131
+ "mean_score": 0.4245693371631205,
132
+ "mean_sigma": 0.13201060891151428
133
+ },
134
+ {
135
+ "generation": 200.0,
136
+ "generation_best": 0.44912710785865784,
137
+ "global_best": 0.44912710785865784,
138
+ "mean_score": 0.4480407335795462,
139
+ "mean_sigma": 0.041084542870521545
140
+ },
141
+ {
142
+ "generation": 300.0,
143
+ "generation_best": 0.46552371978759766,
144
+ "global_best": 0.46552371978759766,
145
+ "mean_score": 0.4644366172142327,
146
+ "mean_sigma": 0.03352927044034004
147
+ },
148
+ {
149
+ "generation": 400.0,
150
+ "generation_best": 0.4772692024707794,
151
+ "global_best": 0.4772692024707794,
152
+ "mean_score": 0.4764386098831892,
153
+ "mean_sigma": 0.033223677426576614
154
+ },
155
+ {
156
+ "generation": 500.0,
157
+ "generation_best": 0.4855300784111023,
158
+ "global_best": 0.4855300784111023,
159
+ "mean_score": 0.48506863694638014,
160
+ "mean_sigma": 0.032162439078092575
161
+ },
162
+ {
163
+ "generation": 600.0,
164
+ "generation_best": 0.49077853560447693,
165
+ "global_best": 0.4907899796962738,
166
+ "mean_score": 0.49058493971824646,
167
+ "mean_sigma": 0.03171905502676964
168
+ },
169
+ {
170
+ "generation": 700.0,
171
+ "generation_best": 0.49390125274658203,
172
+ "global_best": 0.49390125274658203,
173
+ "mean_score": 0.49371014442294836,
174
+ "mean_sigma": 0.0317012220621109
175
+ },
176
+ {
177
+ "generation": 800.0,
178
+ "generation_best": 0.4955916702747345,
179
+ "global_best": 0.4955916702747345,
180
+ "mean_score": 0.49545455910265446,
181
+ "mean_sigma": 0.03135889396071434
182
+ },
183
+ {
184
+ "generation": 900.0,
185
+ "generation_best": 0.4964514374732971,
186
+ "global_best": 0.4964514374732971,
187
+ "mean_score": 0.4963453966192901,
188
+ "mean_sigma": 0.03134661167860031
189
+ },
190
+ {
191
+ "generation": 1000.0,
192
+ "generation_best": 0.49676692485809326,
193
+ "global_best": 0.49676692485809326,
194
+ "mean_score": 0.4966689986176789,
195
+ "mean_sigma": 0.03098495490849018
196
+ },
197
+ {
198
+ "generation": 1100.0,
199
+ "generation_best": 0.4968656897544861,
200
+ "global_best": 0.4968656897544861,
201
+ "mean_score": 0.4967864351347089,
202
+ "mean_sigma": 0.031091898679733276
203
+ },
204
+ {
205
+ "generation": 1200.0,
206
+ "generation_best": 0.49688971042633057,
207
+ "global_best": 0.49689149856567383,
208
+ "mean_score": 0.4968199199065566,
209
+ "mean_sigma": 0.031062308698892593
210
+ },
211
+ {
212
+ "generation": 1300.0,
213
+ "generation_best": 0.4968968331813812,
214
+ "global_best": 0.49689704179763794,
215
+ "mean_score": 0.4968256512656808,
216
+ "mean_sigma": 0.03130534663796425
217
+ },
218
+ {
219
+ "generation": 1400.0,
220
+ "generation_best": 0.4968954622745514,
221
+ "global_best": 0.49689850211143494,
222
+ "mean_score": 0.4968294124118984,
223
+ "mean_sigma": 0.031606629490852356
224
+ },
225
+ {
226
+ "generation": 1500.0,
227
+ "generation_best": 0.49689674377441406,
228
+ "global_best": 0.4968985915184021,
229
+ "mean_score": 0.49683248717337847,
230
+ "mean_sigma": 0.031062159687280655
231
+ },
232
+ {
233
+ "generation": 1600.0,
234
+ "generation_best": 0.4968937933444977,
235
+ "global_best": 0.4968985915184021,
236
+ "mean_score": 0.4968359088525176,
237
+ "mean_sigma": 0.03142143785953522
238
+ },
239
+ {
240
+ "generation": 1700.0,
241
+ "generation_best": 0.4968966245651245,
242
+ "global_best": 0.49689868092536926,
243
+ "mean_score": 0.4968287544324994,
244
+ "mean_sigma": 0.03094904124736786
245
+ },
246
+ {
247
+ "generation": 1800.0,
248
+ "generation_best": 0.49689313769340515,
249
+ "global_best": 0.49689868092536926,
250
+ "mean_score": 0.4968287772499025,
251
+ "mean_sigma": 0.03133745118975639
252
+ },
253
+ {
254
+ "generation": 1900.0,
255
+ "generation_best": 0.49689462780952454,
256
+ "global_best": 0.49689868092536926,
257
+ "mean_score": 0.49683063570410013,
258
+ "mean_sigma": 0.03157992660999298
259
+ },
260
+ {
261
+ "generation": 2000.0,
262
+ "generation_best": 0.49689650535583496,
263
+ "global_best": 0.49689868092536926,
264
+ "mean_score": 0.4968306818045676,
265
+ "mean_sigma": 0.03137785941362381
266
+ }
267
+ ],
268
+ "final_report": {
269
+ "algorithm": "XENO-HAT",
270
+ "variant": "intrinsic-viability-standalone",
271
+ "selection_mode": "intrinsic_viability",
272
+ "scientific_status": "intrinsic_structural_evolution",
273
+ "mutated_tensors": 396,
274
+ "protected_or_unmapped_floating_tensors": 537,
275
+ "memory_budget_bytes": 1431655765,
276
+ "memory_skipped_tensors": 266,
277
+ "memory_skipped_tensor_names": [
278
+ "model.language_model.layers.0.linear_attn.in_proj_qkv.weight",
279
+ "model.language_model.layers.0.mlp.down_proj.weight",
280
+ "model.language_model.layers.0.mlp.gate_proj.weight",
281
+ "model.language_model.layers.0.mlp.up_proj.weight",
282
+ "model.language_model.layers.1.linear_attn.in_proj_qkv.weight",
283
+ "model.language_model.layers.1.mlp.down_proj.weight",
284
+ "model.language_model.layers.1.mlp.gate_proj.weight",
285
+ "model.language_model.layers.1.mlp.up_proj.weight",
286
+ "model.language_model.layers.10.linear_attn.in_proj_qkv.weight",
287
+ "model.language_model.layers.10.mlp.down_proj.weight",
288
+ "model.language_model.layers.10.mlp.gate_proj.weight",
289
+ "model.language_model.layers.10.mlp.up_proj.weight",
290
+ "model.language_model.layers.11.mlp.down_proj.weight",
291
+ "model.language_model.layers.11.mlp.gate_proj.weight",
292
+ "model.language_model.layers.11.mlp.up_proj.weight",
293
+ "model.language_model.layers.11.self_attn.q_proj.weight",
294
+ "model.language_model.layers.12.linear_attn.in_proj_qkv.weight",
295
+ "model.language_model.layers.12.mlp.down_proj.weight",
296
+ "model.language_model.layers.12.mlp.gate_proj.weight",
297
+ "model.language_model.layers.12.mlp.up_proj.weight",
298
+ "model.language_model.layers.13.linear_attn.in_proj_qkv.weight",
299
+ "model.language_model.layers.13.mlp.down_proj.weight",
300
+ "model.language_model.layers.13.mlp.gate_proj.weight",
301
+ "model.language_model.layers.13.mlp.up_proj.weight",
302
+ "model.language_model.layers.14.linear_attn.in_proj_qkv.weight",
303
+ "model.language_model.layers.14.mlp.down_proj.weight",
304
+ "model.language_model.layers.14.mlp.gate_proj.weight",
305
+ "model.language_model.layers.14.mlp.up_proj.weight",
306
+ "model.language_model.layers.15.mlp.down_proj.weight",
307
+ "model.language_model.layers.15.mlp.gate_proj.weight",
308
+ "model.language_model.layers.15.mlp.up_proj.weight",
309
+ "model.language_model.layers.15.self_attn.q_proj.weight",
310
+ "model.language_model.layers.16.linear_attn.in_proj_qkv.weight",
311
+ "model.language_model.layers.16.mlp.down_proj.weight",
312
+ "model.language_model.layers.16.mlp.gate_proj.weight",
313
+ "model.language_model.layers.16.mlp.up_proj.weight",
314
+ "model.language_model.layers.17.linear_attn.in_proj_qkv.weight",
315
+ "model.language_model.layers.17.mlp.down_proj.weight",
316
+ "model.language_model.layers.17.mlp.gate_proj.weight",
317
+ "model.language_model.layers.17.mlp.up_proj.weight",
318
+ "model.language_model.layers.18.linear_attn.in_proj_qkv.weight",
319
+ "model.language_model.layers.18.mlp.down_proj.weight",
320
+ "model.language_model.layers.18.mlp.gate_proj.weight",
321
+ "model.language_model.layers.18.mlp.up_proj.weight",
322
+ "model.language_model.layers.19.mlp.down_proj.weight",
323
+ "model.language_model.layers.19.mlp.gate_proj.weight",
324
+ "model.language_model.layers.19.mlp.up_proj.weight",
325
+ "model.language_model.layers.19.self_attn.q_proj.weight",
326
+ "model.language_model.layers.2.linear_attn.in_proj_qkv.weight",
327
+ "model.language_model.layers.2.mlp.down_proj.weight",
328
+ "model.language_model.layers.2.mlp.gate_proj.weight",
329
+ "model.language_model.layers.2.mlp.up_proj.weight",
330
+ "model.language_model.layers.20.linear_attn.in_proj_qkv.weight",
331
+ "model.language_model.layers.20.mlp.down_proj.weight",
332
+ "model.language_model.layers.20.mlp.gate_proj.weight",
333
+ "model.language_model.layers.20.mlp.up_proj.weight",
334
+ "model.language_model.layers.21.linear_attn.in_proj_qkv.weight",
335
+ "model.language_model.layers.21.mlp.down_proj.weight",
336
+ "model.language_model.layers.21.mlp.gate_proj.weight",
337
+ "model.language_model.layers.21.mlp.up_proj.weight",
338
+ "model.language_model.layers.22.linear_attn.in_proj_qkv.weight",
339
+ "model.language_model.layers.22.mlp.down_proj.weight",
340
+ "model.language_model.layers.22.mlp.gate_proj.weight",
341
+ "model.language_model.layers.22.mlp.up_proj.weight",
342
+ "model.language_model.layers.23.mlp.down_proj.weight",
343
+ "model.language_model.layers.23.mlp.gate_proj.weight",
344
+ "model.language_model.layers.23.mlp.up_proj.weight",
345
+ "model.language_model.layers.23.self_attn.q_proj.weight",
346
+ "model.language_model.layers.24.linear_attn.in_proj_qkv.weight",
347
+ "model.language_model.layers.24.mlp.down_proj.weight",
348
+ "model.language_model.layers.24.mlp.gate_proj.weight",
349
+ "model.language_model.layers.24.mlp.up_proj.weight",
350
+ "model.language_model.layers.25.linear_attn.in_proj_qkv.weight",
351
+ "model.language_model.layers.25.mlp.down_proj.weight",
352
+ "model.language_model.layers.25.mlp.gate_proj.weight",
353
+ "model.language_model.layers.25.mlp.up_proj.weight",
354
+ "model.language_model.layers.26.linear_attn.in_proj_qkv.weight",
355
+ "model.language_model.layers.26.mlp.down_proj.weight",
356
+ "model.language_model.layers.26.mlp.gate_proj.weight",
357
+ "model.language_model.layers.26.mlp.up_proj.weight",
358
+ "model.language_model.layers.27.mlp.down_proj.weight",
359
+ "model.language_model.layers.27.mlp.gate_proj.weight",
360
+ "model.language_model.layers.27.mlp.up_proj.weight",
361
+ "model.language_model.layers.27.self_attn.q_proj.weight",
362
+ "model.language_model.layers.28.linear_attn.in_proj_qkv.weight",
363
+ "model.language_model.layers.28.mlp.down_proj.weight",
364
+ "model.language_model.layers.28.mlp.gate_proj.weight",
365
+ "model.language_model.layers.28.mlp.up_proj.weight",
366
+ "model.language_model.layers.29.linear_attn.in_proj_qkv.weight",
367
+ "model.language_model.layers.29.mlp.down_proj.weight",
368
+ "model.language_model.layers.29.mlp.gate_proj.weight",
369
+ "model.language_model.layers.29.mlp.up_proj.weight",
370
+ "model.language_model.layers.3.mlp.down_proj.weight",
371
+ "model.language_model.layers.3.mlp.gate_proj.weight",
372
+ "model.language_model.layers.3.mlp.up_proj.weight",
373
+ "model.language_model.layers.3.self_attn.q_proj.weight",
374
+ "model.language_model.layers.30.linear_attn.in_proj_qkv.weight",
375
+ "model.language_model.layers.30.mlp.down_proj.weight",
376
+ "model.language_model.layers.30.mlp.gate_proj.weight",
377
+ "model.language_model.layers.30.mlp.up_proj.weight",
378
+ "model.language_model.layers.31.mlp.down_proj.weight",
379
+ "model.language_model.layers.31.mlp.gate_proj.weight",
380
+ "model.language_model.layers.31.mlp.up_proj.weight",
381
+ "model.language_model.layers.31.self_attn.q_proj.weight",
382
+ "model.language_model.layers.32.linear_attn.in_proj_qkv.weight",
383
+ "model.language_model.layers.32.mlp.down_proj.weight",
384
+ "model.language_model.layers.32.mlp.gate_proj.weight",
385
+ "model.language_model.layers.32.mlp.up_proj.weight",
386
+ "model.language_model.layers.33.linear_attn.in_proj_qkv.weight",
387
+ "model.language_model.layers.33.mlp.down_proj.weight",
388
+ "model.language_model.layers.33.mlp.gate_proj.weight",
389
+ "model.language_model.layers.33.mlp.up_proj.weight",
390
+ "model.language_model.layers.34.linear_attn.in_proj_qkv.weight",
391
+ "model.language_model.layers.34.mlp.down_proj.weight",
392
+ "model.language_model.layers.34.mlp.gate_proj.weight",
393
+ "model.language_model.layers.34.mlp.up_proj.weight",
394
+ "model.language_model.layers.35.mlp.down_proj.weight",
395
+ "model.language_model.layers.35.mlp.gate_proj.weight",
396
+ "model.language_model.layers.35.mlp.up_proj.weight",
397
+ "model.language_model.layers.35.self_attn.q_proj.weight",
398
+ "model.language_model.layers.36.linear_attn.in_proj_qkv.weight",
399
+ "model.language_model.layers.36.mlp.down_proj.weight",
400
+ "model.language_model.layers.36.mlp.gate_proj.weight",
401
+ "model.language_model.layers.36.mlp.up_proj.weight",
402
+ "model.language_model.layers.37.linear_attn.in_proj_qkv.weight",
403
+ "model.language_model.layers.37.mlp.down_proj.weight",
404
+ "model.language_model.layers.37.mlp.gate_proj.weight",
405
+ "model.language_model.layers.37.mlp.up_proj.weight",
406
+ "model.language_model.layers.38.linear_attn.in_proj_qkv.weight",
407
+ "model.language_model.layers.38.mlp.down_proj.weight",
408
+ "model.language_model.layers.38.mlp.gate_proj.weight",
409
+ "model.language_model.layers.38.mlp.up_proj.weight",
410
+ "model.language_model.layers.39.mlp.down_proj.weight",
411
+ "model.language_model.layers.39.mlp.gate_proj.weight",
412
+ "model.language_model.layers.39.mlp.up_proj.weight",
413
+ "model.language_model.layers.39.self_attn.q_proj.weight",
414
+ "model.language_model.layers.4.linear_attn.in_proj_qkv.weight",
415
+ "model.language_model.layers.4.mlp.down_proj.weight",
416
+ "model.language_model.layers.4.mlp.gate_proj.weight",
417
+ "model.language_model.layers.4.mlp.up_proj.weight",
418
+ "model.language_model.layers.40.linear_attn.in_proj_qkv.weight",
419
+ "model.language_model.layers.40.mlp.down_proj.weight",
420
+ "model.language_model.layers.40.mlp.gate_proj.weight",
421
+ "model.language_model.layers.40.mlp.up_proj.weight",
422
+ "model.language_model.layers.41.linear_attn.in_proj_qkv.weight",
423
+ "model.language_model.layers.41.mlp.down_proj.weight",
424
+ "model.language_model.layers.41.mlp.gate_proj.weight",
425
+ "model.language_model.layers.41.mlp.up_proj.weight",
426
+ "model.language_model.layers.42.linear_attn.in_proj_qkv.weight",
427
+ "model.language_model.layers.42.mlp.down_proj.weight",
428
+ "model.language_model.layers.42.mlp.gate_proj.weight",
429
+ "model.language_model.layers.42.mlp.up_proj.weight",
430
+ "model.language_model.layers.43.mlp.down_proj.weight",
431
+ "model.language_model.layers.43.mlp.gate_proj.weight",
432
+ "model.language_model.layers.43.mlp.up_proj.weight",
433
+ "model.language_model.layers.43.self_attn.q_proj.weight",
434
+ "model.language_model.layers.44.linear_attn.in_proj_qkv.weight",
435
+ "model.language_model.layers.44.mlp.down_proj.weight",
436
+ "model.language_model.layers.44.mlp.gate_proj.weight",
437
+ "model.language_model.layers.44.mlp.up_proj.weight",
438
+ "model.language_model.layers.45.linear_attn.in_proj_qkv.weight",
439
+ "model.language_model.layers.45.mlp.down_proj.weight",
440
+ "model.language_model.layers.45.mlp.gate_proj.weight",
441
+ "model.language_model.layers.45.mlp.up_proj.weight",
442
+ "model.language_model.layers.46.linear_attn.in_proj_qkv.weight",
443
+ "model.language_model.layers.46.mlp.down_proj.weight",
444
+ "model.language_model.layers.46.mlp.gate_proj.weight",
445
+ "model.language_model.layers.46.mlp.up_proj.weight",
446
+ "model.language_model.layers.47.mlp.down_proj.weight",
447
+ "model.language_model.layers.47.mlp.gate_proj.weight",
448
+ "model.language_model.layers.47.mlp.up_proj.weight",
449
+ "model.language_model.layers.47.self_attn.q_proj.weight",
450
+ "model.language_model.layers.48.linear_attn.in_proj_qkv.weight",
451
+ "model.language_model.layers.48.mlp.down_proj.weight",
452
+ "model.language_model.layers.48.mlp.gate_proj.weight",
453
+ "model.language_model.layers.48.mlp.up_proj.weight",
454
+ "model.language_model.layers.49.linear_attn.in_proj_qkv.weight",
455
+ "model.language_model.layers.49.mlp.down_proj.weight",
456
+ "model.language_model.layers.49.mlp.gate_proj.weight",
457
+ "model.language_model.layers.49.mlp.up_proj.weight",
458
+ "model.language_model.layers.5.linear_attn.in_proj_qkv.weight",
459
+ "model.language_model.layers.5.mlp.down_proj.weight",
460
+ "model.language_model.layers.5.mlp.gate_proj.weight",
461
+ "model.language_model.layers.5.mlp.up_proj.weight",
462
+ "model.language_model.layers.50.linear_attn.in_proj_qkv.weight",
463
+ "model.language_model.layers.50.mlp.down_proj.weight",
464
+ "model.language_model.layers.50.mlp.gate_proj.weight",
465
+ "model.language_model.layers.50.mlp.up_proj.weight",
466
+ "model.language_model.layers.51.mlp.down_proj.weight",
467
+ "model.language_model.layers.51.mlp.gate_proj.weight",
468
+ "model.language_model.layers.51.mlp.up_proj.weight",
469
+ "model.language_model.layers.51.self_attn.q_proj.weight",
470
+ "model.language_model.layers.52.linear_attn.in_proj_qkv.weight",
471
+ "model.language_model.layers.52.mlp.down_proj.weight",
472
+ "model.language_model.layers.52.mlp.gate_proj.weight",
473
+ "model.language_model.layers.52.mlp.up_proj.weight",
474
+ "model.language_model.layers.53.linear_attn.in_proj_qkv.weight",
475
+ "model.language_model.layers.53.mlp.down_proj.weight",
476
+ "model.language_model.layers.53.mlp.gate_proj.weight",
477
+ "model.language_model.layers.53.mlp.up_proj.weight",
478
+ "model.language_model.layers.54.linear_attn.in_proj_qkv.weight",
479
+ "model.language_model.layers.54.mlp.down_proj.weight",
480
+ "model.language_model.layers.54.mlp.gate_proj.weight",
481
+ "model.language_model.layers.54.mlp.up_proj.weight",
482
+ "model.language_model.layers.55.mlp.down_proj.weight",
483
+ "model.language_model.layers.55.mlp.gate_proj.weight",
484
+ "model.language_model.layers.55.mlp.up_proj.weight",
485
+ "model.language_model.layers.55.self_attn.q_proj.weight",
486
+ "model.language_model.layers.56.linear_attn.in_proj_qkv.weight",
487
+ "model.language_model.layers.56.mlp.down_proj.weight",
488
+ "model.language_model.layers.56.mlp.gate_proj.weight",
489
+ "model.language_model.layers.56.mlp.up_proj.weight",
490
+ "model.language_model.layers.57.linear_attn.in_proj_qkv.weight",
491
+ "model.language_model.layers.57.mlp.down_proj.weight",
492
+ "model.language_model.layers.57.mlp.gate_proj.weight",
493
+ "model.language_model.layers.57.mlp.up_proj.weight",
494
+ "model.language_model.layers.58.linear_attn.in_proj_qkv.weight",
495
+ "model.language_model.layers.58.mlp.down_proj.weight",
496
+ "model.language_model.layers.58.mlp.gate_proj.weight",
497
+ "model.language_model.layers.58.mlp.up_proj.weight",
498
+ "model.language_model.layers.59.mlp.down_proj.weight",
499
+ "model.language_model.layers.59.mlp.gate_proj.weight",
500
+ "model.language_model.layers.59.mlp.up_proj.weight",
501
+ "model.language_model.layers.59.self_attn.q_proj.weight",
502
+ "model.language_model.layers.6.linear_attn.in_proj_qkv.weight",
503
+ "model.language_model.layers.6.mlp.down_proj.weight",
504
+ "model.language_model.layers.6.mlp.gate_proj.weight",
505
+ "model.language_model.layers.6.mlp.up_proj.weight",
506
+ "model.language_model.layers.60.linear_attn.in_proj_qkv.weight",
507
+ "model.language_model.layers.60.mlp.down_proj.weight",
508
+ "model.language_model.layers.60.mlp.gate_proj.weight",
509
+ "model.language_model.layers.60.mlp.up_proj.weight",
510
+ "model.language_model.layers.61.linear_attn.in_proj_qkv.weight",
511
+ "model.language_model.layers.61.mlp.down_proj.weight",
512
+ "model.language_model.layers.61.mlp.gate_proj.weight",
513
+ "model.language_model.layers.61.mlp.up_proj.weight",
514
+ "model.language_model.layers.62.linear_attn.in_proj_qkv.weight",
515
+ "model.language_model.layers.62.mlp.down_proj.weight",
516
+ "model.language_model.layers.62.mlp.gate_proj.weight",
517
+ "model.language_model.layers.62.mlp.up_proj.weight",
518
+ "model.language_model.layers.63.mlp.down_proj.weight",
519
+ "model.language_model.layers.63.mlp.gate_proj.weight",
520
+ "model.language_model.layers.63.mlp.up_proj.weight",
521
+ "model.language_model.layers.63.self_attn.q_proj.weight",
522
+ "model.language_model.layers.7.mlp.down_proj.weight",
523
+ "model.language_model.layers.7.mlp.gate_proj.weight",
524
+ "model.language_model.layers.7.mlp.up_proj.weight",
525
+ "model.language_model.layers.7.self_attn.q_proj.weight",
526
+ "model.language_model.layers.8.linear_attn.in_proj_qkv.weight",
527
+ "model.language_model.layers.8.mlp.down_proj.weight",
528
+ "model.language_model.layers.8.mlp.gate_proj.weight",
529
+ "model.language_model.layers.8.mlp.up_proj.weight",
530
+ "model.language_model.layers.9.linear_attn.in_proj_qkv.weight",
531
+ "model.language_model.layers.9.mlp.down_proj.weight",
532
+ "model.language_model.layers.9.mlp.gate_proj.weight",
533
+ "model.language_model.layers.9.mlp.up_proj.weight",
534
+ "model.visual.blocks.4.mlp.linear_fc1.weight",
535
+ "model.visual.blocks.5.mlp.linear_fc1.weight",
536
+ "model.visual.blocks.7.mlp.linear_fc1.weight",
537
+ "model.visual.blocks.8.mlp.linear_fc1.weight",
538
+ "model.visual.blocks.9.mlp.linear_fc1.weight",
539
+ "mtp.fc.weight",
540
+ "mtp.layers.0.mlp.down_proj.weight",
541
+ "mtp.layers.0.mlp.gate_proj.weight",
542
+ "mtp.layers.0.mlp.up_proj.weight",
543
+ "mtp.layers.0.self_attn.q_proj.weight"
544
+ ],
545
+ "io_chunk_elements": 262144,
546
+ "nonfinite_tensors": 0,
547
+ "input_tensors": 1199,
548
+ "total_tensors": 1199,
549
+ "output_contract": "host",
550
+ "fp8": {
551
+ "host_fp8_weights": 0,
552
+ "donor_fp8_tensor_uses": 0,
553
+ "native_fp8_weights": 0,
554
+ "requantized_weights": 0,
555
+ "updated_scale_tensors": 0,
556
+ "dequantized_output_weights": 0,
557
+ "removed_scale_tensors": 0,
558
+ "quantization_limited_weights": 0,
559
+ "lost_mutations": 0,
560
+ "independent_scale_mutations": 0
561
+ },
562
+ "relative_delta_l2": 0.024734919742108584,
563
+ "intrinsic_viability": {
564
+ "assimilation_benefit": 0.7423057556152344,
565
+ "diversity_bonus": 0.0,
566
+ "compatibility_risk": 0.11876931041479111,
567
+ "energy_penalty": 0.1265355944633484,
568
+ "strength_roughness": 0.00010219745308859274,
569
+ "donor_roughness": 0.0,
570
+ "collapse_penalty": 0.0,
571
+ "total": 0.49689868092536926
572
+ },
573
+ "shards": 11,
574
+ "total_size": 55563006888,
575
+ "output": "E:\\text-generation-webui-1.14\\user_data\\models\\EVE-27B-XENO-HAT-gpt-oss"
576
+ },
577
+ "elapsed_seconds": 4223.817697763443
578
+ }
xeno_genome.json ADDED
@@ -0,0 +1,217 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "algorithm": "XENO-HAT",
3
+ "variant": "intrinsic-viability-standalone",
4
+ "selection_mode": "intrinsic_viability",
5
+ "raw_genome": [
6
+ 2.06084942817688,
7
+ 0.3256472945213318,
8
+ 2.0781283378601074,
9
+ 0.16558592021465302,
10
+ 2.1115078926086426,
11
+ 0.1995798945426941,
12
+ 2.1564748287200928,
13
+ -0.25499361753463745,
14
+ 2.2038941383361816,
15
+ -0.636002779006958,
16
+ 2.237774610519409,
17
+ -0.6026392579078674,
18
+ 2.309107780456543,
19
+ 0.22862574458122253,
20
+ 2.3816049098968506,
21
+ -0.5035353302955627,
22
+ 2.4245028495788574,
23
+ 0.008394641801714897,
24
+ 2.4586424827575684,
25
+ -0.08441460132598877,
26
+ 2.496774673461914,
27
+ 0.19497986137866974,
28
+ 2.5286083221435547,
29
+ 0.10306008905172348,
30
+ 2.559535503387451,
31
+ 0.3059891164302826,
32
+ 2.5708017349243164,
33
+ -0.09388812631368637,
34
+ 2.577117919921875,
35
+ -0.09997903555631638,
36
+ 2.583726406097412,
37
+ 0.3281572461128235,
38
+ 2.581967830657959,
39
+ -0.4778151512145996,
40
+ 2.5668323040008545,
41
+ -0.04591358080506325,
42
+ 2.541919231414795,
43
+ -0.44974327087402344,
44
+ 2.5125622749328613,
45
+ -0.0038277513813227415,
46
+ 2.495992660522461,
47
+ 0.38734304904937744,
48
+ 2.473592519760132,
49
+ 0.4455373287200928,
50
+ 2.4574499130249023,
51
+ 0.22669440507888794,
52
+ 2.436908721923828,
53
+ 0.4334656298160553,
54
+ 2.41078519821167,
55
+ -0.06585805863142014,
56
+ 2.3858985900878906,
57
+ 0.3048376142978668,
58
+ 2.358673095703125,
59
+ -0.34457725286483765,
60
+ 2.3312244415283203,
61
+ -0.22693422436714172,
62
+ 2.3152670860290527,
63
+ -0.47636234760284424,
64
+ 2.3073549270629883,
65
+ -0.31545987725257874,
66
+ 2.3056745529174805,
67
+ -0.3262193500995636,
68
+ 2.3040518760681152,
69
+ 0.0969403088092804
70
+ ],
71
+ "groups": 32,
72
+ "donors": 1,
73
+ "max_strength": 0.03,
74
+ "strengths": [
75
+ 0.026611177250742912,
76
+ 0.02666277438402176,
77
+ 0.02676049992442131,
78
+ 0.02688816748559475,
79
+ 0.027017958462238312,
80
+ 0.02710772305727005,
81
+ 0.027288854122161865,
82
+ 0.027462411671876907,
83
+ 0.02756030298769474,
84
+ 0.027635734528303146,
85
+ 0.027717463672161102,
86
+ 0.027783695608377457,
87
+ 0.02784634567797184,
88
+ 0.027868758887052536,
89
+ 0.027881229296326637,
90
+ 0.02789420634508133,
91
+ 0.027890758588910103,
92
+ 0.027860883623361588,
93
+ 0.02781086042523384,
94
+ 0.02775053307414055,
95
+ 0.027715809643268585,
96
+ 0.027668088674545288,
97
+ 0.02763313613831997,
98
+ 0.02758796326816082,
99
+ 0.027529381215572357,
100
+ 0.027472371235489845,
101
+ 0.02740863338112831,
102
+ 0.0273429062217474,
103
+ 0.02730400487780571,
104
+ 0.02728452906012535,
105
+ 0.027280377224087715,
106
+ 0.027276363223791122
107
+ ],
108
+ "donor_weights": [
109
+ [
110
+ 1.0
111
+ ],
112
+ [
113
+ 1.0
114
+ ],
115
+ [
116
+ 1.0
117
+ ],
118
+ [
119
+ 1.0
120
+ ],
121
+ [
122
+ 1.0
123
+ ],
124
+ [
125
+ 1.0
126
+ ],
127
+ [
128
+ 1.0
129
+ ],
130
+ [
131
+ 1.0
132
+ ],
133
+ [
134
+ 1.0
135
+ ],
136
+ [
137
+ 1.0
138
+ ],
139
+ [
140
+ 1.0
141
+ ],
142
+ [
143
+ 1.0
144
+ ],
145
+ [
146
+ 1.0
147
+ ],
148
+ [
149
+ 1.0
150
+ ],
151
+ [
152
+ 1.0
153
+ ],
154
+ [
155
+ 1.0
156
+ ],
157
+ [
158
+ 1.0
159
+ ],
160
+ [
161
+ 1.0
162
+ ],
163
+ [
164
+ 1.0
165
+ ],
166
+ [
167
+ 1.0
168
+ ],
169
+ [
170
+ 1.0
171
+ ],
172
+ [
173
+ 1.0
174
+ ],
175
+ [
176
+ 1.0
177
+ ],
178
+ [
179
+ 1.0
180
+ ],
181
+ [
182
+ 1.0
183
+ ],
184
+ [
185
+ 1.0
186
+ ],
187
+ [
188
+ 1.0
189
+ ],
190
+ [
191
+ 1.0
192
+ ],
193
+ [
194
+ 1.0
195
+ ],
196
+ [
197
+ 1.0
198
+ ],
199
+ [
200
+ 1.0
201
+ ],
202
+ [
203
+ 1.0
204
+ ]
205
+ ],
206
+ "intrinsic_viability": {
207
+ "assimilation_benefit": 0.7423057556152344,
208
+ "diversity_bonus": 0.0,
209
+ "compatibility_risk": 0.11876931041479111,
210
+ "energy_penalty": 0.1265355944633484,
211
+ "strength_roughness": 0.00010219745308859274,
212
+ "donor_roughness": 0.0,
213
+ "collapse_penalty": 0.0,
214
+ "total": 0.49689868092536926
215
+ },
216
+ "seed": 42
217
+ }
xeno_mapping.json ADDED
The diff for this file is too large to render. See raw diff
 
xeno_report.json ADDED
@@ -0,0 +1,309 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "algorithm": "XENO-HAT",
3
+ "variant": "intrinsic-viability-standalone",
4
+ "selection_mode": "intrinsic_viability",
5
+ "scientific_status": "intrinsic_structural_evolution",
6
+ "mutated_tensors": 396,
7
+ "protected_or_unmapped_floating_tensors": 537,
8
+ "memory_budget_bytes": 1431655765,
9
+ "memory_skipped_tensors": 266,
10
+ "memory_skipped_tensor_names": [
11
+ "model.language_model.layers.0.linear_attn.in_proj_qkv.weight",
12
+ "model.language_model.layers.0.mlp.down_proj.weight",
13
+ "model.language_model.layers.0.mlp.gate_proj.weight",
14
+ "model.language_model.layers.0.mlp.up_proj.weight",
15
+ "model.language_model.layers.1.linear_attn.in_proj_qkv.weight",
16
+ "model.language_model.layers.1.mlp.down_proj.weight",
17
+ "model.language_model.layers.1.mlp.gate_proj.weight",
18
+ "model.language_model.layers.1.mlp.up_proj.weight",
19
+ "model.language_model.layers.10.linear_attn.in_proj_qkv.weight",
20
+ "model.language_model.layers.10.mlp.down_proj.weight",
21
+ "model.language_model.layers.10.mlp.gate_proj.weight",
22
+ "model.language_model.layers.10.mlp.up_proj.weight",
23
+ "model.language_model.layers.11.mlp.down_proj.weight",
24
+ "model.language_model.layers.11.mlp.gate_proj.weight",
25
+ "model.language_model.layers.11.mlp.up_proj.weight",
26
+ "model.language_model.layers.11.self_attn.q_proj.weight",
27
+ "model.language_model.layers.12.linear_attn.in_proj_qkv.weight",
28
+ "model.language_model.layers.12.mlp.down_proj.weight",
29
+ "model.language_model.layers.12.mlp.gate_proj.weight",
30
+ "model.language_model.layers.12.mlp.up_proj.weight",
31
+ "model.language_model.layers.13.linear_attn.in_proj_qkv.weight",
32
+ "model.language_model.layers.13.mlp.down_proj.weight",
33
+ "model.language_model.layers.13.mlp.gate_proj.weight",
34
+ "model.language_model.layers.13.mlp.up_proj.weight",
35
+ "model.language_model.layers.14.linear_attn.in_proj_qkv.weight",
36
+ "model.language_model.layers.14.mlp.down_proj.weight",
37
+ "model.language_model.layers.14.mlp.gate_proj.weight",
38
+ "model.language_model.layers.14.mlp.up_proj.weight",
39
+ "model.language_model.layers.15.mlp.down_proj.weight",
40
+ "model.language_model.layers.15.mlp.gate_proj.weight",
41
+ "model.language_model.layers.15.mlp.up_proj.weight",
42
+ "model.language_model.layers.15.self_attn.q_proj.weight",
43
+ "model.language_model.layers.16.linear_attn.in_proj_qkv.weight",
44
+ "model.language_model.layers.16.mlp.down_proj.weight",
45
+ "model.language_model.layers.16.mlp.gate_proj.weight",
46
+ "model.language_model.layers.16.mlp.up_proj.weight",
47
+ "model.language_model.layers.17.linear_attn.in_proj_qkv.weight",
48
+ "model.language_model.layers.17.mlp.down_proj.weight",
49
+ "model.language_model.layers.17.mlp.gate_proj.weight",
50
+ "model.language_model.layers.17.mlp.up_proj.weight",
51
+ "model.language_model.layers.18.linear_attn.in_proj_qkv.weight",
52
+ "model.language_model.layers.18.mlp.down_proj.weight",
53
+ "model.language_model.layers.18.mlp.gate_proj.weight",
54
+ "model.language_model.layers.18.mlp.up_proj.weight",
55
+ "model.language_model.layers.19.mlp.down_proj.weight",
56
+ "model.language_model.layers.19.mlp.gate_proj.weight",
57
+ "model.language_model.layers.19.mlp.up_proj.weight",
58
+ "model.language_model.layers.19.self_attn.q_proj.weight",
59
+ "model.language_model.layers.2.linear_attn.in_proj_qkv.weight",
60
+ "model.language_model.layers.2.mlp.down_proj.weight",
61
+ "model.language_model.layers.2.mlp.gate_proj.weight",
62
+ "model.language_model.layers.2.mlp.up_proj.weight",
63
+ "model.language_model.layers.20.linear_attn.in_proj_qkv.weight",
64
+ "model.language_model.layers.20.mlp.down_proj.weight",
65
+ "model.language_model.layers.20.mlp.gate_proj.weight",
66
+ "model.language_model.layers.20.mlp.up_proj.weight",
67
+ "model.language_model.layers.21.linear_attn.in_proj_qkv.weight",
68
+ "model.language_model.layers.21.mlp.down_proj.weight",
69
+ "model.language_model.layers.21.mlp.gate_proj.weight",
70
+ "model.language_model.layers.21.mlp.up_proj.weight",
71
+ "model.language_model.layers.22.linear_attn.in_proj_qkv.weight",
72
+ "model.language_model.layers.22.mlp.down_proj.weight",
73
+ "model.language_model.layers.22.mlp.gate_proj.weight",
74
+ "model.language_model.layers.22.mlp.up_proj.weight",
75
+ "model.language_model.layers.23.mlp.down_proj.weight",
76
+ "model.language_model.layers.23.mlp.gate_proj.weight",
77
+ "model.language_model.layers.23.mlp.up_proj.weight",
78
+ "model.language_model.layers.23.self_attn.q_proj.weight",
79
+ "model.language_model.layers.24.linear_attn.in_proj_qkv.weight",
80
+ "model.language_model.layers.24.mlp.down_proj.weight",
81
+ "model.language_model.layers.24.mlp.gate_proj.weight",
82
+ "model.language_model.layers.24.mlp.up_proj.weight",
83
+ "model.language_model.layers.25.linear_attn.in_proj_qkv.weight",
84
+ "model.language_model.layers.25.mlp.down_proj.weight",
85
+ "model.language_model.layers.25.mlp.gate_proj.weight",
86
+ "model.language_model.layers.25.mlp.up_proj.weight",
87
+ "model.language_model.layers.26.linear_attn.in_proj_qkv.weight",
88
+ "model.language_model.layers.26.mlp.down_proj.weight",
89
+ "model.language_model.layers.26.mlp.gate_proj.weight",
90
+ "model.language_model.layers.26.mlp.up_proj.weight",
91
+ "model.language_model.layers.27.mlp.down_proj.weight",
92
+ "model.language_model.layers.27.mlp.gate_proj.weight",
93
+ "model.language_model.layers.27.mlp.up_proj.weight",
94
+ "model.language_model.layers.27.self_attn.q_proj.weight",
95
+ "model.language_model.layers.28.linear_attn.in_proj_qkv.weight",
96
+ "model.language_model.layers.28.mlp.down_proj.weight",
97
+ "model.language_model.layers.28.mlp.gate_proj.weight",
98
+ "model.language_model.layers.28.mlp.up_proj.weight",
99
+ "model.language_model.layers.29.linear_attn.in_proj_qkv.weight",
100
+ "model.language_model.layers.29.mlp.down_proj.weight",
101
+ "model.language_model.layers.29.mlp.gate_proj.weight",
102
+ "model.language_model.layers.29.mlp.up_proj.weight",
103
+ "model.language_model.layers.3.mlp.down_proj.weight",
104
+ "model.language_model.layers.3.mlp.gate_proj.weight",
105
+ "model.language_model.layers.3.mlp.up_proj.weight",
106
+ "model.language_model.layers.3.self_attn.q_proj.weight",
107
+ "model.language_model.layers.30.linear_attn.in_proj_qkv.weight",
108
+ "model.language_model.layers.30.mlp.down_proj.weight",
109
+ "model.language_model.layers.30.mlp.gate_proj.weight",
110
+ "model.language_model.layers.30.mlp.up_proj.weight",
111
+ "model.language_model.layers.31.mlp.down_proj.weight",
112
+ "model.language_model.layers.31.mlp.gate_proj.weight",
113
+ "model.language_model.layers.31.mlp.up_proj.weight",
114
+ "model.language_model.layers.31.self_attn.q_proj.weight",
115
+ "model.language_model.layers.32.linear_attn.in_proj_qkv.weight",
116
+ "model.language_model.layers.32.mlp.down_proj.weight",
117
+ "model.language_model.layers.32.mlp.gate_proj.weight",
118
+ "model.language_model.layers.32.mlp.up_proj.weight",
119
+ "model.language_model.layers.33.linear_attn.in_proj_qkv.weight",
120
+ "model.language_model.layers.33.mlp.down_proj.weight",
121
+ "model.language_model.layers.33.mlp.gate_proj.weight",
122
+ "model.language_model.layers.33.mlp.up_proj.weight",
123
+ "model.language_model.layers.34.linear_attn.in_proj_qkv.weight",
124
+ "model.language_model.layers.34.mlp.down_proj.weight",
125
+ "model.language_model.layers.34.mlp.gate_proj.weight",
126
+ "model.language_model.layers.34.mlp.up_proj.weight",
127
+ "model.language_model.layers.35.mlp.down_proj.weight",
128
+ "model.language_model.layers.35.mlp.gate_proj.weight",
129
+ "model.language_model.layers.35.mlp.up_proj.weight",
130
+ "model.language_model.layers.35.self_attn.q_proj.weight",
131
+ "model.language_model.layers.36.linear_attn.in_proj_qkv.weight",
132
+ "model.language_model.layers.36.mlp.down_proj.weight",
133
+ "model.language_model.layers.36.mlp.gate_proj.weight",
134
+ "model.language_model.layers.36.mlp.up_proj.weight",
135
+ "model.language_model.layers.37.linear_attn.in_proj_qkv.weight",
136
+ "model.language_model.layers.37.mlp.down_proj.weight",
137
+ "model.language_model.layers.37.mlp.gate_proj.weight",
138
+ "model.language_model.layers.37.mlp.up_proj.weight",
139
+ "model.language_model.layers.38.linear_attn.in_proj_qkv.weight",
140
+ "model.language_model.layers.38.mlp.down_proj.weight",
141
+ "model.language_model.layers.38.mlp.gate_proj.weight",
142
+ "model.language_model.layers.38.mlp.up_proj.weight",
143
+ "model.language_model.layers.39.mlp.down_proj.weight",
144
+ "model.language_model.layers.39.mlp.gate_proj.weight",
145
+ "model.language_model.layers.39.mlp.up_proj.weight",
146
+ "model.language_model.layers.39.self_attn.q_proj.weight",
147
+ "model.language_model.layers.4.linear_attn.in_proj_qkv.weight",
148
+ "model.language_model.layers.4.mlp.down_proj.weight",
149
+ "model.language_model.layers.4.mlp.gate_proj.weight",
150
+ "model.language_model.layers.4.mlp.up_proj.weight",
151
+ "model.language_model.layers.40.linear_attn.in_proj_qkv.weight",
152
+ "model.language_model.layers.40.mlp.down_proj.weight",
153
+ "model.language_model.layers.40.mlp.gate_proj.weight",
154
+ "model.language_model.layers.40.mlp.up_proj.weight",
155
+ "model.language_model.layers.41.linear_attn.in_proj_qkv.weight",
156
+ "model.language_model.layers.41.mlp.down_proj.weight",
157
+ "model.language_model.layers.41.mlp.gate_proj.weight",
158
+ "model.language_model.layers.41.mlp.up_proj.weight",
159
+ "model.language_model.layers.42.linear_attn.in_proj_qkv.weight",
160
+ "model.language_model.layers.42.mlp.down_proj.weight",
161
+ "model.language_model.layers.42.mlp.gate_proj.weight",
162
+ "model.language_model.layers.42.mlp.up_proj.weight",
163
+ "model.language_model.layers.43.mlp.down_proj.weight",
164
+ "model.language_model.layers.43.mlp.gate_proj.weight",
165
+ "model.language_model.layers.43.mlp.up_proj.weight",
166
+ "model.language_model.layers.43.self_attn.q_proj.weight",
167
+ "model.language_model.layers.44.linear_attn.in_proj_qkv.weight",
168
+ "model.language_model.layers.44.mlp.down_proj.weight",
169
+ "model.language_model.layers.44.mlp.gate_proj.weight",
170
+ "model.language_model.layers.44.mlp.up_proj.weight",
171
+ "model.language_model.layers.45.linear_attn.in_proj_qkv.weight",
172
+ "model.language_model.layers.45.mlp.down_proj.weight",
173
+ "model.language_model.layers.45.mlp.gate_proj.weight",
174
+ "model.language_model.layers.45.mlp.up_proj.weight",
175
+ "model.language_model.layers.46.linear_attn.in_proj_qkv.weight",
176
+ "model.language_model.layers.46.mlp.down_proj.weight",
177
+ "model.language_model.layers.46.mlp.gate_proj.weight",
178
+ "model.language_model.layers.46.mlp.up_proj.weight",
179
+ "model.language_model.layers.47.mlp.down_proj.weight",
180
+ "model.language_model.layers.47.mlp.gate_proj.weight",
181
+ "model.language_model.layers.47.mlp.up_proj.weight",
182
+ "model.language_model.layers.47.self_attn.q_proj.weight",
183
+ "model.language_model.layers.48.linear_attn.in_proj_qkv.weight",
184
+ "model.language_model.layers.48.mlp.down_proj.weight",
185
+ "model.language_model.layers.48.mlp.gate_proj.weight",
186
+ "model.language_model.layers.48.mlp.up_proj.weight",
187
+ "model.language_model.layers.49.linear_attn.in_proj_qkv.weight",
188
+ "model.language_model.layers.49.mlp.down_proj.weight",
189
+ "model.language_model.layers.49.mlp.gate_proj.weight",
190
+ "model.language_model.layers.49.mlp.up_proj.weight",
191
+ "model.language_model.layers.5.linear_attn.in_proj_qkv.weight",
192
+ "model.language_model.layers.5.mlp.down_proj.weight",
193
+ "model.language_model.layers.5.mlp.gate_proj.weight",
194
+ "model.language_model.layers.5.mlp.up_proj.weight",
195
+ "model.language_model.layers.50.linear_attn.in_proj_qkv.weight",
196
+ "model.language_model.layers.50.mlp.down_proj.weight",
197
+ "model.language_model.layers.50.mlp.gate_proj.weight",
198
+ "model.language_model.layers.50.mlp.up_proj.weight",
199
+ "model.language_model.layers.51.mlp.down_proj.weight",
200
+ "model.language_model.layers.51.mlp.gate_proj.weight",
201
+ "model.language_model.layers.51.mlp.up_proj.weight",
202
+ "model.language_model.layers.51.self_attn.q_proj.weight",
203
+ "model.language_model.layers.52.linear_attn.in_proj_qkv.weight",
204
+ "model.language_model.layers.52.mlp.down_proj.weight",
205
+ "model.language_model.layers.52.mlp.gate_proj.weight",
206
+ "model.language_model.layers.52.mlp.up_proj.weight",
207
+ "model.language_model.layers.53.linear_attn.in_proj_qkv.weight",
208
+ "model.language_model.layers.53.mlp.down_proj.weight",
209
+ "model.language_model.layers.53.mlp.gate_proj.weight",
210
+ "model.language_model.layers.53.mlp.up_proj.weight",
211
+ "model.language_model.layers.54.linear_attn.in_proj_qkv.weight",
212
+ "model.language_model.layers.54.mlp.down_proj.weight",
213
+ "model.language_model.layers.54.mlp.gate_proj.weight",
214
+ "model.language_model.layers.54.mlp.up_proj.weight",
215
+ "model.language_model.layers.55.mlp.down_proj.weight",
216
+ "model.language_model.layers.55.mlp.gate_proj.weight",
217
+ "model.language_model.layers.55.mlp.up_proj.weight",
218
+ "model.language_model.layers.55.self_attn.q_proj.weight",
219
+ "model.language_model.layers.56.linear_attn.in_proj_qkv.weight",
220
+ "model.language_model.layers.56.mlp.down_proj.weight",
221
+ "model.language_model.layers.56.mlp.gate_proj.weight",
222
+ "model.language_model.layers.56.mlp.up_proj.weight",
223
+ "model.language_model.layers.57.linear_attn.in_proj_qkv.weight",
224
+ "model.language_model.layers.57.mlp.down_proj.weight",
225
+ "model.language_model.layers.57.mlp.gate_proj.weight",
226
+ "model.language_model.layers.57.mlp.up_proj.weight",
227
+ "model.language_model.layers.58.linear_attn.in_proj_qkv.weight",
228
+ "model.language_model.layers.58.mlp.down_proj.weight",
229
+ "model.language_model.layers.58.mlp.gate_proj.weight",
230
+ "model.language_model.layers.58.mlp.up_proj.weight",
231
+ "model.language_model.layers.59.mlp.down_proj.weight",
232
+ "model.language_model.layers.59.mlp.gate_proj.weight",
233
+ "model.language_model.layers.59.mlp.up_proj.weight",
234
+ "model.language_model.layers.59.self_attn.q_proj.weight",
235
+ "model.language_model.layers.6.linear_attn.in_proj_qkv.weight",
236
+ "model.language_model.layers.6.mlp.down_proj.weight",
237
+ "model.language_model.layers.6.mlp.gate_proj.weight",
238
+ "model.language_model.layers.6.mlp.up_proj.weight",
239
+ "model.language_model.layers.60.linear_attn.in_proj_qkv.weight",
240
+ "model.language_model.layers.60.mlp.down_proj.weight",
241
+ "model.language_model.layers.60.mlp.gate_proj.weight",
242
+ "model.language_model.layers.60.mlp.up_proj.weight",
243
+ "model.language_model.layers.61.linear_attn.in_proj_qkv.weight",
244
+ "model.language_model.layers.61.mlp.down_proj.weight",
245
+ "model.language_model.layers.61.mlp.gate_proj.weight",
246
+ "model.language_model.layers.61.mlp.up_proj.weight",
247
+ "model.language_model.layers.62.linear_attn.in_proj_qkv.weight",
248
+ "model.language_model.layers.62.mlp.down_proj.weight",
249
+ "model.language_model.layers.62.mlp.gate_proj.weight",
250
+ "model.language_model.layers.62.mlp.up_proj.weight",
251
+ "model.language_model.layers.63.mlp.down_proj.weight",
252
+ "model.language_model.layers.63.mlp.gate_proj.weight",
253
+ "model.language_model.layers.63.mlp.up_proj.weight",
254
+ "model.language_model.layers.63.self_attn.q_proj.weight",
255
+ "model.language_model.layers.7.mlp.down_proj.weight",
256
+ "model.language_model.layers.7.mlp.gate_proj.weight",
257
+ "model.language_model.layers.7.mlp.up_proj.weight",
258
+ "model.language_model.layers.7.self_attn.q_proj.weight",
259
+ "model.language_model.layers.8.linear_attn.in_proj_qkv.weight",
260
+ "model.language_model.layers.8.mlp.down_proj.weight",
261
+ "model.language_model.layers.8.mlp.gate_proj.weight",
262
+ "model.language_model.layers.8.mlp.up_proj.weight",
263
+ "model.language_model.layers.9.linear_attn.in_proj_qkv.weight",
264
+ "model.language_model.layers.9.mlp.down_proj.weight",
265
+ "model.language_model.layers.9.mlp.gate_proj.weight",
266
+ "model.language_model.layers.9.mlp.up_proj.weight",
267
+ "model.visual.blocks.4.mlp.linear_fc1.weight",
268
+ "model.visual.blocks.5.mlp.linear_fc1.weight",
269
+ "model.visual.blocks.7.mlp.linear_fc1.weight",
270
+ "model.visual.blocks.8.mlp.linear_fc1.weight",
271
+ "model.visual.blocks.9.mlp.linear_fc1.weight",
272
+ "mtp.fc.weight",
273
+ "mtp.layers.0.mlp.down_proj.weight",
274
+ "mtp.layers.0.mlp.gate_proj.weight",
275
+ "mtp.layers.0.mlp.up_proj.weight",
276
+ "mtp.layers.0.self_attn.q_proj.weight"
277
+ ],
278
+ "io_chunk_elements": 262144,
279
+ "nonfinite_tensors": 0,
280
+ "input_tensors": 1199,
281
+ "total_tensors": 1199,
282
+ "output_contract": "host",
283
+ "fp8": {
284
+ "host_fp8_weights": 0,
285
+ "donor_fp8_tensor_uses": 0,
286
+ "native_fp8_weights": 0,
287
+ "requantized_weights": 0,
288
+ "updated_scale_tensors": 0,
289
+ "dequantized_output_weights": 0,
290
+ "removed_scale_tensors": 0,
291
+ "quantization_limited_weights": 0,
292
+ "lost_mutations": 0,
293
+ "independent_scale_mutations": 0
294
+ },
295
+ "relative_delta_l2": 0.024734919742108584,
296
+ "intrinsic_viability": {
297
+ "assimilation_benefit": 0.7423057556152344,
298
+ "diversity_bonus": 0.0,
299
+ "compatibility_risk": 0.11876931041479111,
300
+ "energy_penalty": 0.1265355944633484,
301
+ "strength_roughness": 0.00010219745308859274,
302
+ "donor_roughness": 0.0,
303
+ "collapse_penalty": 0.0,
304
+ "total": 0.49689868092536926
305
+ },
306
+ "shards": 11,
307
+ "total_size": 55563006888,
308
+ "output": "E:\\text-generation-webui-1.14\\user_data\\models\\EVE-27B-XENO-HAT-gpt-oss"
309
+ }