Add files using upload-large-folder tool
Browse files- .gitattributes +1 -0
- chat_template.jinja +329 -0
- config.json +439 -0
- generation_config.json +6 -0
- model-00001-of-00003.safetensors +3 -0
- model-00002-of-00003.safetensors +3 -0
- model-00003-of-00003.safetensors +3 -0
- model.safetensors.index.json +896 -0
- processor_config.json +64 -0
- recipe.yaml +9 -0
- tokenizer.json +3 -0
- tokenizer_config.json +33 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,329 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- set template_version = "qwen3.6-froggeric-v21.3" %}
|
| 2 |
+
{%- set _tool_format = tool_call_format if tool_call_format is defined else 'xml' %}
|
| 3 |
+
{%- set image_count = namespace(value=0) %}
|
| 4 |
+
{%- set video_count = namespace(value=0) %}
|
| 5 |
+
{%- set add_vision_id = add_vision_id if add_vision_id is defined else false %}
|
| 6 |
+
{%- set enable_thinking = enable_thinking if enable_thinking is defined else true %}
|
| 7 |
+
{%- set auto_disable_thinking_with_tools = auto_disable_thinking_with_tools if auto_disable_thinking_with_tools is defined else false %}
|
| 8 |
+
{%- set _preserve_thinking = preserve_thinking if preserve_thinking is defined else true %}
|
| 9 |
+
{%- set max_tool_arg_chars = max_tool_arg_chars if max_tool_arg_chars is defined else 0 %}
|
| 10 |
+
{%- set max_tool_response_chars = max_tool_response_chars if max_tool_response_chars is defined else 0 %}
|
| 11 |
+
{%- set _has_tools = (tools is defined and tools and tools is iterable and tools is not mapping) %}
|
| 12 |
+
{%- set ns_state = namespace(thinking=enable_thinking) %}
|
| 13 |
+
{%- if auto_disable_thinking_with_tools and _has_tools %}
|
| 14 |
+
{%- set ns_state.thinking = false %}
|
| 15 |
+
{%- endif %}
|
| 16 |
+
{%- macro render_content(content, do_vision_count, is_system_content=false) %}
|
| 17 |
+
{%- if content is string %}
|
| 18 |
+
{{- content }}
|
| 19 |
+
{%- elif content is iterable and content is not mapping %}
|
| 20 |
+
{%- for item in content %}
|
| 21 |
+
{%- if item is mapping %}
|
| 22 |
+
{%- if item.type == 'image' or 'image' in item or 'image_url' in item %}
|
| 23 |
+
{%- if is_system_content %}
|
| 24 |
+
{{- raise_exception('System message cannot contain images.') }}
|
| 25 |
+
{%- endif %}
|
| 26 |
+
{%- if do_vision_count %}
|
| 27 |
+
{%- set image_count.value = image_count.value + 1 %}
|
| 28 |
+
{%- endif %}
|
| 29 |
+
{%- if add_vision_id %}
|
| 30 |
+
{{- 'Picture ' ~ image_count.value ~ ': ' }}
|
| 31 |
+
{%- endif %}
|
| 32 |
+
{{- '<|vision_start|><|image_pad|><|vision_end|>' }}
|
| 33 |
+
{%- elif item.type == 'video' or 'video' in item %}
|
| 34 |
+
{%- if is_system_content %}
|
| 35 |
+
{{- raise_exception('System message cannot contain videos.') }}
|
| 36 |
+
{%- endif %}
|
| 37 |
+
{%- if do_vision_count %}
|
| 38 |
+
{%- set video_count.value = video_count.value + 1 %}
|
| 39 |
+
{%- endif %}
|
| 40 |
+
{%- if add_vision_id %}
|
| 41 |
+
{{- 'Video ' ~ video_count.value ~ ': ' }}
|
| 42 |
+
{%- endif %}
|
| 43 |
+
{{- '<|vision_start|><|video_pad|><|vision_end|>' }}
|
| 44 |
+
{%- elif 'text' in item %}
|
| 45 |
+
{{- item.text }}
|
| 46 |
+
{%- else %}
|
| 47 |
+
{{- raise_exception('Unexpected item type in content.') }}
|
| 48 |
+
{%- endif %}
|
| 49 |
+
{%- else %}
|
| 50 |
+
{{- item | string }}
|
| 51 |
+
{%- endif %}
|
| 52 |
+
{%- endfor %}
|
| 53 |
+
{%- elif content is none or content is undefined %}
|
| 54 |
+
{{- '' }}
|
| 55 |
+
{%- else %}
|
| 56 |
+
{{- raise_exception('Unexpected content type.') }}
|
| 57 |
+
{%- endif %}
|
| 58 |
+
{%- endmacro %}
|
| 59 |
+
{%- if not messages %}
|
| 60 |
+
{{- raise_exception('No messages provided.') }}
|
| 61 |
+
{%- endif %}
|
| 62 |
+
{%- set _first_role = messages[0].role %}
|
| 63 |
+
{%- if _first_role == 'system' or _first_role == 'developer' %}
|
| 64 |
+
{%- set _sys_msg = messages[0] %}
|
| 65 |
+
{%- set _msgs = messages[1:] %}
|
| 66 |
+
{%- else %}
|
| 67 |
+
{%- set _sys_msg = none %}
|
| 68 |
+
{%- set _msgs = messages %}
|
| 69 |
+
{%- endif %}
|
| 70 |
+
{%- set _sc = '' %}
|
| 71 |
+
{%- if _sys_msg is not none %}
|
| 72 |
+
{%- set _sc = render_content(_sys_msg.content, false, true) | trim %}
|
| 73 |
+
{%- if '<|think_off|>' in _sc %}
|
| 74 |
+
{%- set ns_state.thinking = false %}
|
| 75 |
+
{%- set _sc = _sc.split('<|think_off|>') | join('') | trim %}
|
| 76 |
+
{%- elif '<|think_on|>' in _sc %}
|
| 77 |
+
{%- set ns_state.thinking = true %}
|
| 78 |
+
{%- set _sc = _sc.split('<|think_on|>') | join('') | trim %}
|
| 79 |
+
{%- endif %}
|
| 80 |
+
{%- endif %}
|
| 81 |
+
{%- if _has_tools %}
|
| 82 |
+
{{- '<|im_start|>system\n' }}
|
| 83 |
+
{{- '# Tools\n\nYou have access to the following functions:\n\n<tools>' }}
|
| 84 |
+
{%- for tool in tools %}
|
| 85 |
+
{{- '\n' }}
|
| 86 |
+
{{- tool | tojson }}
|
| 87 |
+
{%- endfor %}
|
| 88 |
+
{{- '\n</tools>' }}
|
| 89 |
+
{%- set tool_instructions %}
|
| 90 |
+
If you choose to call a function ONLY reply in the following format with NO suffix:
|
| 91 |
+
|
| 92 |
+
{%- if _tool_format == 'json' %}
|
| 93 |
+
<think>
|
| 94 |
+
Brief explanation of tool call
|
| 95 |
+
</think>
|
| 96 |
+
<tool_call>
|
| 97 |
+
{"name": "example_function_name", "arguments": {"example_parameter_1": "value_1", "example_parameter_2": "This is the value for the second parameter"}}
|
| 98 |
+
</tool_call>
|
| 99 |
+
{%- else %}
|
| 100 |
+
<think>
|
| 101 |
+
Brief explanation of tool call
|
| 102 |
+
</think>
|
| 103 |
+
<tool_call>
|
| 104 |
+
<function=example_function_name>
|
| 105 |
+
<parameter=example_parameter_1>
|
| 106 |
+
value_1
|
| 107 |
+
</parameter>
|
| 108 |
+
<parameter=example_parameter_2>
|
| 109 |
+
This is the value for the second parameter
|
| 110 |
+
that can span
|
| 111 |
+
multiple lines
|
| 112 |
+
</parameter>
|
| 113 |
+
</function>
|
| 114 |
+
</tool_call>
|
| 115 |
+
{%- endif %}
|
| 116 |
+
|
| 117 |
+
<IMPORTANT>
|
| 118 |
+
Reminder:
|
| 119 |
+
- You can use the <think></think> block to plan your next tool call OR to synthesize data and formulate your final response to the user.
|
| 120 |
+
- ALL explanation and reasoning MUST be placed strictly inside the <think></think> block.
|
| 121 |
+
{%- if _tool_format == 'json' %}
|
| 122 |
+
- Function calls MUST follow the specified format: a single JSON object with "name" and "arguments" keys inside <tool_call></tool_call> XML tags.
|
| 123 |
+
{%- else %}
|
| 124 |
+
- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags.
|
| 125 |
+
{%- endif %}
|
| 126 |
+
- If you choose to call a tool, you MUST output the <tool_call> block IMMEDIATELY after thinking, with NO conversational text before it.
|
| 127 |
+
{%- if _tool_format == 'json' %}
|
| 128 |
+
- The <tool_call> tag MUST be at the very beginning of a new line, with NO spaces or indentation before it.
|
| 129 |
+
{%- else %}
|
| 130 |
+
- The <tool_call> and <function> tags MUST be at the very beginning of a new line, with NO spaces or indentation before them.
|
| 131 |
+
{%- endif %}
|
| 132 |
+
- To call multiple functions, output a separate, completely closed <tool_call></tool_call> block for EACH function. Do NOT nest <tool_call> blocks.
|
| 133 |
+
- If you have all necessary data, provide your final answer directly to the user without any tool call.
|
| 134 |
+
</IMPORTANT>
|
| 135 |
+
{%- endset %}
|
| 136 |
+
{{- '\n\n' ~ tool_instructions | trim }}
|
| 137 |
+
{%- if _sc %}
|
| 138 |
+
{{- '\n\n' + _sc }}
|
| 139 |
+
{%- endif %}
|
| 140 |
+
{{- '<|im_end|>\n' }}
|
| 141 |
+
{%- else %}
|
| 142 |
+
{%- if _sc %}
|
| 143 |
+
{{- '<|im_start|>system\n' + _sc + '<|im_end|>\n' }}
|
| 144 |
+
{%- endif %}
|
| 145 |
+
{%- endif %}
|
| 146 |
+
{%- set _last_idx = _msgs | length - 1 %}
|
| 147 |
+
{%- set ns = namespace(multi_step_tool=true, last_query_index=_last_idx) %}
|
| 148 |
+
{%- for message in _msgs[::-1] %}
|
| 149 |
+
{%- set index = (_msgs | length - 1) - loop.index0 %}
|
| 150 |
+
{%- if ns.multi_step_tool and message.role == 'user' %}
|
| 151 |
+
{%- set _rc = render_content(message.content, false) | trim %}
|
| 152 |
+
{%- if not (_rc.startswith('<tool_response>') and _rc.endswith('</tool_response>')) %}
|
| 153 |
+
{%- set ns.multi_step_tool = false %}
|
| 154 |
+
{%- set ns.last_query_index = index %}
|
| 155 |
+
{%- endif %}
|
| 156 |
+
{%- endif %}
|
| 157 |
+
{%- endfor %}
|
| 158 |
+
{%- if ns.multi_step_tool %}
|
| 159 |
+
{%- if _last_idx > 50 %}
|
| 160 |
+
{%- set ns.last_query_index = _last_idx %}
|
| 161 |
+
{%- else %}
|
| 162 |
+
{%- set ns.last_query_index = 0 %}
|
| 163 |
+
{%- endif %}
|
| 164 |
+
{%- endif %}
|
| 165 |
+
{%- set ns2 = namespace(prev_role='', consecutive_failures=0) %}
|
| 166 |
+
{%- for message in _msgs %}
|
| 167 |
+
{%- set is_system = (message.role == "system" or message.role == "developer") %}
|
| 168 |
+
{%- set content = render_content(message.content, true, is_system) | trim %}
|
| 169 |
+
{%- if is_system or message.role == 'user' %}
|
| 170 |
+
{%- if '<|think_off|>' in content %}
|
| 171 |
+
{%- set ns_state.thinking = false %}
|
| 172 |
+
{%- set content = content.split('<|think_off|>') | join('') | trim %}
|
| 173 |
+
{%- elif '<|think_on|>' in content %}
|
| 174 |
+
{%- set ns_state.thinking = true %}
|
| 175 |
+
{%- set content = content.split('<|think_on|>') | join('') | trim %}
|
| 176 |
+
{%- endif %}
|
| 177 |
+
{%- endif %}
|
| 178 |
+
{%- if is_system %}
|
| 179 |
+
{{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
|
| 180 |
+
{%- elif message.role == 'user' %}
|
| 181 |
+
{%- set ns2.consecutive_failures = 0 %}
|
| 182 |
+
{{- '<|im_start|>user\n' + content + '<|im_end|>\n' }}
|
| 183 |
+
{%- elif message.role == 'assistant' %}
|
| 184 |
+
{%- set reasoning_content = '' %}
|
| 185 |
+
{%- if message.reasoning_content is defined and message.reasoning_content is not none %}
|
| 186 |
+
{%- if message.reasoning_content is string %}
|
| 187 |
+
{%- set reasoning_content = message.reasoning_content %}
|
| 188 |
+
{%- else %}
|
| 189 |
+
{%- set reasoning_content = message.reasoning_content | string %}
|
| 190 |
+
{%- endif %}
|
| 191 |
+
{%- elif message.thinking is defined and message.thinking is not none %}
|
| 192 |
+
{%- if message.thinking is string %}
|
| 193 |
+
{%- set reasoning_content = message.thinking %}
|
| 194 |
+
{%- else %}
|
| 195 |
+
{%- set reasoning_content = message.thinking | string %}
|
| 196 |
+
{%- endif %}
|
| 197 |
+
{%- else %}
|
| 198 |
+
{%- set _think_end = '' %}
|
| 199 |
+
{%- if content.startswith('</think>') %}
|
| 200 |
+
{%- set _think_end = '</think>' %}
|
| 201 |
+
{%- elif content.startswith('</thinking>') %}
|
| 202 |
+
{%- set _think_end = '</thinking>' %}
|
| 203 |
+
{%- elif '\n</think>' in content %}
|
| 204 |
+
{%- set _think_end = '\n</think>' %}
|
| 205 |
+
{%- elif '\n</thinking>' in content %}
|
| 206 |
+
{%- set _think_end = '\n</thinking>' %}
|
| 207 |
+
{%- elif '\n</ think>' in content %}
|
| 208 |
+
{%- set _think_end = '\n</ think>' %}
|
| 209 |
+
{%- elif '\n</think >' in content %}
|
| 210 |
+
{%- set _think_end = '\n</think >' %}
|
| 211 |
+
{%- endif %}
|
| 212 |
+
{%- if _think_end %}
|
| 213 |
+
{%- if 'thinking' in _think_end %}
|
| 214 |
+
{%- set _think_start = '<thinking>' %}
|
| 215 |
+
{%- else %}
|
| 216 |
+
{%- set _think_start = '<think>' %}
|
| 217 |
+
{%- endif %}
|
| 218 |
+
{%- set reasoning_content = content.split(_think_end)[0].rstrip('\n') %}
|
| 219 |
+
{%- if _think_start in reasoning_content %}
|
| 220 |
+
{%- set reasoning_content = reasoning_content.split(_think_start)[-1].lstrip('\n') %}
|
| 221 |
+
{%- endif %}
|
| 222 |
+
{%- set content = content.split(_think_end)[-1].lstrip('\n') %}
|
| 223 |
+
{%- endif %}
|
| 224 |
+
{%- endif %}
|
| 225 |
+
{%- set reasoning_content = reasoning_content | trim %}
|
| 226 |
+
{%- if (_preserve_thinking or loop.index0 > ns.last_query_index) and reasoning_content %}
|
| 227 |
+
{{- '<|im_start|>assistant\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
|
| 228 |
+
{%- else %}
|
| 229 |
+
{{- '<|im_start|>assistant\n' + content }}
|
| 230 |
+
{%- endif %}
|
| 231 |
+
{%- if message.tool_calls is defined and message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
|
| 232 |
+
{%- for tool_call in message.tool_calls %}
|
| 233 |
+
{%- if tool_call.function is defined and tool_call.function is not none %}
|
| 234 |
+
{%- set tc = tool_call.function %}
|
| 235 |
+
{%- else %}
|
| 236 |
+
{%- set tc = tool_call %}
|
| 237 |
+
{%- endif %}
|
| 238 |
+
{%- if _tool_format == 'json' %}
|
| 239 |
+
{%- if not loop.first or content | trim %}
|
| 240 |
+
{{- '\n\n' }}
|
| 241 |
+
{%- endif %}
|
| 242 |
+
{%- set _args = '{}' %}
|
| 243 |
+
{%- if tc.arguments is defined and tc.arguments is not none %}
|
| 244 |
+
{%- if tc.arguments is mapping %}
|
| 245 |
+
{%- set _args = tc.arguments | tojson %}
|
| 246 |
+
{%- elif tc.arguments is string and tc.arguments %}
|
| 247 |
+
{%- set _args = tc.arguments %}
|
| 248 |
+
{%- endif %}
|
| 249 |
+
{%- endif %}
|
| 250 |
+
{{- '<tool_call>\n{"name": ' }}{{- tc.name | tojson }}{{- ', "arguments": ' }}{{- _args }}{{- '}\n</tool_call>' }}
|
| 251 |
+
{%- else %}
|
| 252 |
+
{%- if loop.first %}
|
| 253 |
+
{%- if content | trim %}
|
| 254 |
+
{{- '\n\n<tool_call>\n<function=' + tc.name + '>\n' }}
|
| 255 |
+
{%- else %}
|
| 256 |
+
{{- '<tool_call>\n<function=' + tc.name + '>\n' }}
|
| 257 |
+
{%- endif %}
|
| 258 |
+
{%- else %}
|
| 259 |
+
{{- '\n\n<tool_call>\n<function=' + tc.name + '>\n' }}
|
| 260 |
+
{%- endif %}
|
| 261 |
+
{%- if tc.arguments is defined and tc.arguments is not none %}
|
| 262 |
+
{%- if tc.arguments is mapping %}
|
| 263 |
+
{%- for args_name, args_value in tc.arguments.items() %}
|
| 264 |
+
{{- '<parameter=' + args_name + '>\n' }}
|
| 265 |
+
{%- if args_value is mapping or (args_value is sequence and args_value is not string) %}
|
| 266 |
+
{%- set _av = args_value | tojson %}
|
| 267 |
+
{%- else %}
|
| 268 |
+
{%- set _av = args_value | string %}
|
| 269 |
+
{%- endif %}
|
| 270 |
+
{%- if max_tool_arg_chars > 0 and _av | length > max_tool_arg_chars %}
|
| 271 |
+
{{- _av[:max_tool_arg_chars] + '\n[TRUNCATED — original length ' ~ (_av | length | string) ~ ' chars]' }}
|
| 272 |
+
{%- else %}
|
| 273 |
+
{{- _av }}
|
| 274 |
+
{%- endif %}
|
| 275 |
+
{{- '\n</parameter>\n' }}
|
| 276 |
+
{%- endfor %}
|
| 277 |
+
{%- elif tc.arguments is string and tc.arguments %}
|
| 278 |
+
{{- tc.arguments }}
|
| 279 |
+
{%- endif %}
|
| 280 |
+
{%- endif %}
|
| 281 |
+
{{- '</function>\n</tool_call>' }}
|
| 282 |
+
{%- endif %}
|
| 283 |
+
{%- endfor %}
|
| 284 |
+
{%- endif %}
|
| 285 |
+
{{- '<|im_end|>\n' }}
|
| 286 |
+
{%- elif message.role == 'tool' %}
|
| 287 |
+
{%- set _content_lower = content | lower %}
|
| 288 |
+
{%- set _content_head = _content_lower[:80] %}
|
| 289 |
+
{%- if content | length < 500 and '$ ' not in content and 'took ' not in _content_lower and ('"error":' in _content_head or 'error:' in _content_head or 'err!' in _content_head or 'fatal:' in _content_head or 'exception:' in _content_head or 'traceback' in _content_head or 'command not found' in _content_head or 'invalid syntax' in _content_head or 'failed to' in _content_head) %}
|
| 290 |
+
{%- set ns2.consecutive_failures = ns2.consecutive_failures + 1 %}
|
| 291 |
+
{%- else %}
|
| 292 |
+
{%- set ns2.consecutive_failures = 0 %}
|
| 293 |
+
{%- endif %}
|
| 294 |
+
{%- if ns2.prev_role != 'tool' %}
|
| 295 |
+
{{- '<|im_start|>user' }}
|
| 296 |
+
{%- endif %}
|
| 297 |
+
{%- if max_tool_response_chars > 0 and content | length > max_tool_response_chars %}
|
| 298 |
+
{%- set content = content[:max_tool_response_chars] + '\n[TRUNCATED — original length ' ~ (content | length | string) ~ ' chars]' %}
|
| 299 |
+
{%- endif %}
|
| 300 |
+
{{- '\n<tool_response>\n' + content }}
|
| 301 |
+
{%- if ns2.consecutive_failures >= 2 %}
|
| 302 |
+
{{- '\n\n⚠️ SYSTEM WARNING: ' ~ ns2.consecutive_failures ~ ' consecutive tool errors detected. Your previous approach is incorrect. You MUST use a fundamentally different approach or corrected arguments.' }}
|
| 303 |
+
{%- elif ns2.consecutive_failures == 1 %}
|
| 304 |
+
{{- '\n\n⚠️ SYSTEM WARNING: The previous tool call returned an error. Diagnose the failure and retry with completely corrected arguments.' }}
|
| 305 |
+
{%- endif %}
|
| 306 |
+
{{- '\n</tool_response>' }}
|
| 307 |
+
{%- if loop.last %}
|
| 308 |
+
{{- '<|im_end|>\n' }}
|
| 309 |
+
{%- else %}
|
| 310 |
+
{%- set _next_role = _msgs[loop.index0 + 1].role %}
|
| 311 |
+
{%- if _next_role != 'tool' %}
|
| 312 |
+
{{- '<|im_end|>\n' }}
|
| 313 |
+
{%- endif %}
|
| 314 |
+
{%- endif %}
|
| 315 |
+
{%- else %}
|
| 316 |
+
{{- '<|im_start|>user\n[' + message.role + ']: ' + content + '<|im_end|>\n' }}
|
| 317 |
+
{%- endif %}
|
| 318 |
+
{%- set ns2.prev_role = message.role %}
|
| 319 |
+
{%- endfor %}
|
| 320 |
+
{%- if add_generation_prompt %}
|
| 321 |
+
{{- '<|im_start|>assistant\n' }}
|
| 322 |
+
{%- if not ns_state.thinking %}
|
| 323 |
+
{{- '<think>\n\n</think>\n\n' }}
|
| 324 |
+
{%- elif ns2.consecutive_failures >= 2 %}
|
| 325 |
+
{{- '<think>\n\n</think>\n\n' }}
|
| 326 |
+
{%- else %}
|
| 327 |
+
{{- '<think>\n' }}
|
| 328 |
+
{%- endif %}
|
| 329 |
+
{%- endif %}
|
config.json
ADDED
|
@@ -0,0 +1,439 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3_5ForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"dtype": "bfloat16",
|
| 6 |
+
"image_token_id": 248056,
|
| 7 |
+
"model_type": "qwen3_5",
|
| 8 |
+
"pad_token_id": 248055,
|
| 9 |
+
"quantization_config": {
|
| 10 |
+
"config_groups": {
|
| 11 |
+
"group_0": {
|
| 12 |
+
"format": "float-quantized",
|
| 13 |
+
"input_activations": {
|
| 14 |
+
"actorder": null,
|
| 15 |
+
"block_structure": null,
|
| 16 |
+
"dynamic": true,
|
| 17 |
+
"group_size": null,
|
| 18 |
+
"num_bits": 8,
|
| 19 |
+
"observer": null,
|
| 20 |
+
"observer_kwargs": {},
|
| 21 |
+
"scale_dtype": null,
|
| 22 |
+
"strategy": "token",
|
| 23 |
+
"symmetric": true,
|
| 24 |
+
"type": "float",
|
| 25 |
+
"zp_dtype": null
|
| 26 |
+
},
|
| 27 |
+
"output_activations": null,
|
| 28 |
+
"targets": [
|
| 29 |
+
"Linear"
|
| 30 |
+
],
|
| 31 |
+
"weights": {
|
| 32 |
+
"actorder": null,
|
| 33 |
+
"block_structure": null,
|
| 34 |
+
"dynamic": false,
|
| 35 |
+
"group_size": null,
|
| 36 |
+
"num_bits": 8,
|
| 37 |
+
"observer": "memoryless_minmax",
|
| 38 |
+
"observer_kwargs": {},
|
| 39 |
+
"scale_dtype": null,
|
| 40 |
+
"strategy": "channel",
|
| 41 |
+
"symmetric": true,
|
| 42 |
+
"type": "float",
|
| 43 |
+
"zp_dtype": null
|
| 44 |
+
}
|
| 45 |
+
}
|
| 46 |
+
},
|
| 47 |
+
"format": "float-quantized",
|
| 48 |
+
"global_compression_ratio": null,
|
| 49 |
+
"ignore": [
|
| 50 |
+
"model.visual.blocks.0.attn.qkv",
|
| 51 |
+
"model.visual.blocks.0.attn.proj",
|
| 52 |
+
"model.visual.blocks.0.mlp.linear_fc1",
|
| 53 |
+
"model.visual.blocks.0.mlp.linear_fc2",
|
| 54 |
+
"model.visual.blocks.1.attn.qkv",
|
| 55 |
+
"model.visual.blocks.1.attn.proj",
|
| 56 |
+
"model.visual.blocks.1.mlp.linear_fc1",
|
| 57 |
+
"model.visual.blocks.1.mlp.linear_fc2",
|
| 58 |
+
"model.visual.blocks.2.attn.qkv",
|
| 59 |
+
"model.visual.blocks.2.attn.proj",
|
| 60 |
+
"model.visual.blocks.2.mlp.linear_fc1",
|
| 61 |
+
"model.visual.blocks.2.mlp.linear_fc2",
|
| 62 |
+
"model.visual.blocks.3.attn.qkv",
|
| 63 |
+
"model.visual.blocks.3.attn.proj",
|
| 64 |
+
"model.visual.blocks.3.mlp.linear_fc1",
|
| 65 |
+
"model.visual.blocks.3.mlp.linear_fc2",
|
| 66 |
+
"model.visual.blocks.4.attn.qkv",
|
| 67 |
+
"model.visual.blocks.4.attn.proj",
|
| 68 |
+
"model.visual.blocks.4.mlp.linear_fc1",
|
| 69 |
+
"model.visual.blocks.4.mlp.linear_fc2",
|
| 70 |
+
"model.visual.blocks.5.attn.qkv",
|
| 71 |
+
"model.visual.blocks.5.attn.proj",
|
| 72 |
+
"model.visual.blocks.5.mlp.linear_fc1",
|
| 73 |
+
"model.visual.blocks.5.mlp.linear_fc2",
|
| 74 |
+
"model.visual.blocks.6.attn.qkv",
|
| 75 |
+
"model.visual.blocks.6.attn.proj",
|
| 76 |
+
"model.visual.blocks.6.mlp.linear_fc1",
|
| 77 |
+
"model.visual.blocks.6.mlp.linear_fc2",
|
| 78 |
+
"model.visual.blocks.7.attn.qkv",
|
| 79 |
+
"model.visual.blocks.7.attn.proj",
|
| 80 |
+
"model.visual.blocks.7.mlp.linear_fc1",
|
| 81 |
+
"model.visual.blocks.7.mlp.linear_fc2",
|
| 82 |
+
"model.visual.blocks.8.attn.qkv",
|
| 83 |
+
"model.visual.blocks.8.attn.proj",
|
| 84 |
+
"model.visual.blocks.8.mlp.linear_fc1",
|
| 85 |
+
"model.visual.blocks.8.mlp.linear_fc2",
|
| 86 |
+
"model.visual.blocks.9.attn.qkv",
|
| 87 |
+
"model.visual.blocks.9.attn.proj",
|
| 88 |
+
"model.visual.blocks.9.mlp.linear_fc1",
|
| 89 |
+
"model.visual.blocks.9.mlp.linear_fc2",
|
| 90 |
+
"model.visual.blocks.10.attn.qkv",
|
| 91 |
+
"model.visual.blocks.10.attn.proj",
|
| 92 |
+
"model.visual.blocks.10.mlp.linear_fc1",
|
| 93 |
+
"model.visual.blocks.10.mlp.linear_fc2",
|
| 94 |
+
"model.visual.blocks.11.attn.qkv",
|
| 95 |
+
"model.visual.blocks.11.attn.proj",
|
| 96 |
+
"model.visual.blocks.11.mlp.linear_fc1",
|
| 97 |
+
"model.visual.blocks.11.mlp.linear_fc2",
|
| 98 |
+
"model.visual.blocks.12.attn.qkv",
|
| 99 |
+
"model.visual.blocks.12.attn.proj",
|
| 100 |
+
"model.visual.blocks.12.mlp.linear_fc1",
|
| 101 |
+
"model.visual.blocks.12.mlp.linear_fc2",
|
| 102 |
+
"model.visual.blocks.13.attn.qkv",
|
| 103 |
+
"model.visual.blocks.13.attn.proj",
|
| 104 |
+
"model.visual.blocks.13.mlp.linear_fc1",
|
| 105 |
+
"model.visual.blocks.13.mlp.linear_fc2",
|
| 106 |
+
"model.visual.blocks.14.attn.qkv",
|
| 107 |
+
"model.visual.blocks.14.attn.proj",
|
| 108 |
+
"model.visual.blocks.14.mlp.linear_fc1",
|
| 109 |
+
"model.visual.blocks.14.mlp.linear_fc2",
|
| 110 |
+
"model.visual.blocks.15.attn.qkv",
|
| 111 |
+
"model.visual.blocks.15.attn.proj",
|
| 112 |
+
"model.visual.blocks.15.mlp.linear_fc1",
|
| 113 |
+
"model.visual.blocks.15.mlp.linear_fc2",
|
| 114 |
+
"model.visual.blocks.16.attn.qkv",
|
| 115 |
+
"model.visual.blocks.16.attn.proj",
|
| 116 |
+
"model.visual.blocks.16.mlp.linear_fc1",
|
| 117 |
+
"model.visual.blocks.16.mlp.linear_fc2",
|
| 118 |
+
"model.visual.blocks.17.attn.qkv",
|
| 119 |
+
"model.visual.blocks.17.attn.proj",
|
| 120 |
+
"model.visual.blocks.17.mlp.linear_fc1",
|
| 121 |
+
"model.visual.blocks.17.mlp.linear_fc2",
|
| 122 |
+
"model.visual.blocks.18.attn.qkv",
|
| 123 |
+
"model.visual.blocks.18.attn.proj",
|
| 124 |
+
"model.visual.blocks.18.mlp.linear_fc1",
|
| 125 |
+
"model.visual.blocks.18.mlp.linear_fc2",
|
| 126 |
+
"model.visual.blocks.19.attn.qkv",
|
| 127 |
+
"model.visual.blocks.19.attn.proj",
|
| 128 |
+
"model.visual.blocks.19.mlp.linear_fc1",
|
| 129 |
+
"model.visual.blocks.19.mlp.linear_fc2",
|
| 130 |
+
"model.visual.blocks.20.attn.qkv",
|
| 131 |
+
"model.visual.blocks.20.attn.proj",
|
| 132 |
+
"model.visual.blocks.20.mlp.linear_fc1",
|
| 133 |
+
"model.visual.blocks.20.mlp.linear_fc2",
|
| 134 |
+
"model.visual.blocks.21.attn.qkv",
|
| 135 |
+
"model.visual.blocks.21.attn.proj",
|
| 136 |
+
"model.visual.blocks.21.mlp.linear_fc1",
|
| 137 |
+
"model.visual.blocks.21.mlp.linear_fc2",
|
| 138 |
+
"model.visual.blocks.22.attn.qkv",
|
| 139 |
+
"model.visual.blocks.22.attn.proj",
|
| 140 |
+
"model.visual.blocks.22.mlp.linear_fc1",
|
| 141 |
+
"model.visual.blocks.22.mlp.linear_fc2",
|
| 142 |
+
"model.visual.blocks.23.attn.qkv",
|
| 143 |
+
"model.visual.blocks.23.attn.proj",
|
| 144 |
+
"model.visual.blocks.23.mlp.linear_fc1",
|
| 145 |
+
"model.visual.blocks.23.mlp.linear_fc2",
|
| 146 |
+
"model.visual.blocks.24.attn.qkv",
|
| 147 |
+
"model.visual.blocks.24.attn.proj",
|
| 148 |
+
"model.visual.blocks.24.mlp.linear_fc1",
|
| 149 |
+
"model.visual.blocks.24.mlp.linear_fc2",
|
| 150 |
+
"model.visual.blocks.25.attn.qkv",
|
| 151 |
+
"model.visual.blocks.25.attn.proj",
|
| 152 |
+
"model.visual.blocks.25.mlp.linear_fc1",
|
| 153 |
+
"model.visual.blocks.25.mlp.linear_fc2",
|
| 154 |
+
"model.visual.blocks.26.attn.qkv",
|
| 155 |
+
"model.visual.blocks.26.attn.proj",
|
| 156 |
+
"model.visual.blocks.26.mlp.linear_fc1",
|
| 157 |
+
"model.visual.blocks.26.mlp.linear_fc2",
|
| 158 |
+
"model.visual.merger.linear_fc1",
|
| 159 |
+
"model.visual.merger.linear_fc2",
|
| 160 |
+
"model.language_model.layers.0.linear_attn",
|
| 161 |
+
"model.language_model.layers.0.linear_attn.norm",
|
| 162 |
+
"model.language_model.layers.0.linear_attn.out_proj",
|
| 163 |
+
"model.language_model.layers.0.linear_attn.in_proj_qkv",
|
| 164 |
+
"model.language_model.layers.0.linear_attn.in_proj_z",
|
| 165 |
+
"model.language_model.layers.0.linear_attn.in_proj_b",
|
| 166 |
+
"model.language_model.layers.0.linear_attn.in_proj_a",
|
| 167 |
+
"model.language_model.layers.1.linear_attn",
|
| 168 |
+
"model.language_model.layers.1.linear_attn.norm",
|
| 169 |
+
"model.language_model.layers.1.linear_attn.out_proj",
|
| 170 |
+
"model.language_model.layers.1.linear_attn.in_proj_qkv",
|
| 171 |
+
"model.language_model.layers.1.linear_attn.in_proj_z",
|
| 172 |
+
"model.language_model.layers.1.linear_attn.in_proj_b",
|
| 173 |
+
"model.language_model.layers.1.linear_attn.in_proj_a",
|
| 174 |
+
"model.language_model.layers.2.linear_attn",
|
| 175 |
+
"model.language_model.layers.2.linear_attn.norm",
|
| 176 |
+
"model.language_model.layers.2.linear_attn.out_proj",
|
| 177 |
+
"model.language_model.layers.2.linear_attn.in_proj_qkv",
|
| 178 |
+
"model.language_model.layers.2.linear_attn.in_proj_z",
|
| 179 |
+
"model.language_model.layers.2.linear_attn.in_proj_b",
|
| 180 |
+
"model.language_model.layers.2.linear_attn.in_proj_a",
|
| 181 |
+
"model.language_model.layers.4.linear_attn",
|
| 182 |
+
"model.language_model.layers.4.linear_attn.norm",
|
| 183 |
+
"model.language_model.layers.4.linear_attn.out_proj",
|
| 184 |
+
"model.language_model.layers.4.linear_attn.in_proj_qkv",
|
| 185 |
+
"model.language_model.layers.4.linear_attn.in_proj_z",
|
| 186 |
+
"model.language_model.layers.4.linear_attn.in_proj_b",
|
| 187 |
+
"model.language_model.layers.4.linear_attn.in_proj_a",
|
| 188 |
+
"model.language_model.layers.5.linear_attn",
|
| 189 |
+
"model.language_model.layers.5.linear_attn.norm",
|
| 190 |
+
"model.language_model.layers.5.linear_attn.out_proj",
|
| 191 |
+
"model.language_model.layers.5.linear_attn.in_proj_qkv",
|
| 192 |
+
"model.language_model.layers.5.linear_attn.in_proj_z",
|
| 193 |
+
"model.language_model.layers.5.linear_attn.in_proj_b",
|
| 194 |
+
"model.language_model.layers.5.linear_attn.in_proj_a",
|
| 195 |
+
"model.language_model.layers.6.linear_attn",
|
| 196 |
+
"model.language_model.layers.6.linear_attn.norm",
|
| 197 |
+
"model.language_model.layers.6.linear_attn.out_proj",
|
| 198 |
+
"model.language_model.layers.6.linear_attn.in_proj_qkv",
|
| 199 |
+
"model.language_model.layers.6.linear_attn.in_proj_z",
|
| 200 |
+
"model.language_model.layers.6.linear_attn.in_proj_b",
|
| 201 |
+
"model.language_model.layers.6.linear_attn.in_proj_a",
|
| 202 |
+
"model.language_model.layers.8.linear_attn",
|
| 203 |
+
"model.language_model.layers.8.linear_attn.norm",
|
| 204 |
+
"model.language_model.layers.8.linear_attn.out_proj",
|
| 205 |
+
"model.language_model.layers.8.linear_attn.in_proj_qkv",
|
| 206 |
+
"model.language_model.layers.8.linear_attn.in_proj_z",
|
| 207 |
+
"model.language_model.layers.8.linear_attn.in_proj_b",
|
| 208 |
+
"model.language_model.layers.8.linear_attn.in_proj_a",
|
| 209 |
+
"model.language_model.layers.9.linear_attn",
|
| 210 |
+
"model.language_model.layers.9.linear_attn.norm",
|
| 211 |
+
"model.language_model.layers.9.linear_attn.out_proj",
|
| 212 |
+
"model.language_model.layers.9.linear_attn.in_proj_qkv",
|
| 213 |
+
"model.language_model.layers.9.linear_attn.in_proj_z",
|
| 214 |
+
"model.language_model.layers.9.linear_attn.in_proj_b",
|
| 215 |
+
"model.language_model.layers.9.linear_attn.in_proj_a",
|
| 216 |
+
"model.language_model.layers.10.linear_attn",
|
| 217 |
+
"model.language_model.layers.10.linear_attn.norm",
|
| 218 |
+
"model.language_model.layers.10.linear_attn.out_proj",
|
| 219 |
+
"model.language_model.layers.10.linear_attn.in_proj_qkv",
|
| 220 |
+
"model.language_model.layers.10.linear_attn.in_proj_z",
|
| 221 |
+
"model.language_model.layers.10.linear_attn.in_proj_b",
|
| 222 |
+
"model.language_model.layers.10.linear_attn.in_proj_a",
|
| 223 |
+
"model.language_model.layers.12.linear_attn",
|
| 224 |
+
"model.language_model.layers.12.linear_attn.norm",
|
| 225 |
+
"model.language_model.layers.12.linear_attn.out_proj",
|
| 226 |
+
"model.language_model.layers.12.linear_attn.in_proj_qkv",
|
| 227 |
+
"model.language_model.layers.12.linear_attn.in_proj_z",
|
| 228 |
+
"model.language_model.layers.12.linear_attn.in_proj_b",
|
| 229 |
+
"model.language_model.layers.12.linear_attn.in_proj_a",
|
| 230 |
+
"model.language_model.layers.13.linear_attn",
|
| 231 |
+
"model.language_model.layers.13.linear_attn.norm",
|
| 232 |
+
"model.language_model.layers.13.linear_attn.out_proj",
|
| 233 |
+
"model.language_model.layers.13.linear_attn.in_proj_qkv",
|
| 234 |
+
"model.language_model.layers.13.linear_attn.in_proj_z",
|
| 235 |
+
"model.language_model.layers.13.linear_attn.in_proj_b",
|
| 236 |
+
"model.language_model.layers.13.linear_attn.in_proj_a",
|
| 237 |
+
"model.language_model.layers.14.linear_attn",
|
| 238 |
+
"model.language_model.layers.14.linear_attn.norm",
|
| 239 |
+
"model.language_model.layers.14.linear_attn.out_proj",
|
| 240 |
+
"model.language_model.layers.14.linear_attn.in_proj_qkv",
|
| 241 |
+
"model.language_model.layers.14.linear_attn.in_proj_z",
|
| 242 |
+
"model.language_model.layers.14.linear_attn.in_proj_b",
|
| 243 |
+
"model.language_model.layers.14.linear_attn.in_proj_a",
|
| 244 |
+
"model.language_model.layers.16.linear_attn",
|
| 245 |
+
"model.language_model.layers.16.linear_attn.norm",
|
| 246 |
+
"model.language_model.layers.16.linear_attn.out_proj",
|
| 247 |
+
"model.language_model.layers.16.linear_attn.in_proj_qkv",
|
| 248 |
+
"model.language_model.layers.16.linear_attn.in_proj_z",
|
| 249 |
+
"model.language_model.layers.16.linear_attn.in_proj_b",
|
| 250 |
+
"model.language_model.layers.16.linear_attn.in_proj_a",
|
| 251 |
+
"model.language_model.layers.17.linear_attn",
|
| 252 |
+
"model.language_model.layers.17.linear_attn.norm",
|
| 253 |
+
"model.language_model.layers.17.linear_attn.out_proj",
|
| 254 |
+
"model.language_model.layers.17.linear_attn.in_proj_qkv",
|
| 255 |
+
"model.language_model.layers.17.linear_attn.in_proj_z",
|
| 256 |
+
"model.language_model.layers.17.linear_attn.in_proj_b",
|
| 257 |
+
"model.language_model.layers.17.linear_attn.in_proj_a",
|
| 258 |
+
"model.language_model.layers.18.linear_attn",
|
| 259 |
+
"model.language_model.layers.18.linear_attn.norm",
|
| 260 |
+
"model.language_model.layers.18.linear_attn.out_proj",
|
| 261 |
+
"model.language_model.layers.18.linear_attn.in_proj_qkv",
|
| 262 |
+
"model.language_model.layers.18.linear_attn.in_proj_z",
|
| 263 |
+
"model.language_model.layers.18.linear_attn.in_proj_b",
|
| 264 |
+
"model.language_model.layers.18.linear_attn.in_proj_a",
|
| 265 |
+
"model.language_model.layers.20.linear_attn",
|
| 266 |
+
"model.language_model.layers.20.linear_attn.norm",
|
| 267 |
+
"model.language_model.layers.20.linear_attn.out_proj",
|
| 268 |
+
"model.language_model.layers.20.linear_attn.in_proj_qkv",
|
| 269 |
+
"model.language_model.layers.20.linear_attn.in_proj_z",
|
| 270 |
+
"model.language_model.layers.20.linear_attn.in_proj_b",
|
| 271 |
+
"model.language_model.layers.20.linear_attn.in_proj_a",
|
| 272 |
+
"model.language_model.layers.21.linear_attn",
|
| 273 |
+
"model.language_model.layers.21.linear_attn.norm",
|
| 274 |
+
"model.language_model.layers.21.linear_attn.out_proj",
|
| 275 |
+
"model.language_model.layers.21.linear_attn.in_proj_qkv",
|
| 276 |
+
"model.language_model.layers.21.linear_attn.in_proj_z",
|
| 277 |
+
"model.language_model.layers.21.linear_attn.in_proj_b",
|
| 278 |
+
"model.language_model.layers.21.linear_attn.in_proj_a",
|
| 279 |
+
"model.language_model.layers.22.linear_attn",
|
| 280 |
+
"model.language_model.layers.22.linear_attn.norm",
|
| 281 |
+
"model.language_model.layers.22.linear_attn.out_proj",
|
| 282 |
+
"model.language_model.layers.22.linear_attn.in_proj_qkv",
|
| 283 |
+
"model.language_model.layers.22.linear_attn.in_proj_z",
|
| 284 |
+
"model.language_model.layers.22.linear_attn.in_proj_b",
|
| 285 |
+
"model.language_model.layers.22.linear_attn.in_proj_a",
|
| 286 |
+
"model.language_model.layers.24.linear_attn",
|
| 287 |
+
"model.language_model.layers.24.linear_attn.norm",
|
| 288 |
+
"model.language_model.layers.24.linear_attn.out_proj",
|
| 289 |
+
"model.language_model.layers.24.linear_attn.in_proj_qkv",
|
| 290 |
+
"model.language_model.layers.24.linear_attn.in_proj_z",
|
| 291 |
+
"model.language_model.layers.24.linear_attn.in_proj_b",
|
| 292 |
+
"model.language_model.layers.24.linear_attn.in_proj_a",
|
| 293 |
+
"model.language_model.layers.25.linear_attn",
|
| 294 |
+
"model.language_model.layers.25.linear_attn.norm",
|
| 295 |
+
"model.language_model.layers.25.linear_attn.out_proj",
|
| 296 |
+
"model.language_model.layers.25.linear_attn.in_proj_qkv",
|
| 297 |
+
"model.language_model.layers.25.linear_attn.in_proj_z",
|
| 298 |
+
"model.language_model.layers.25.linear_attn.in_proj_b",
|
| 299 |
+
"model.language_model.layers.25.linear_attn.in_proj_a",
|
| 300 |
+
"model.language_model.layers.26.linear_attn",
|
| 301 |
+
"model.language_model.layers.26.linear_attn.norm",
|
| 302 |
+
"model.language_model.layers.26.linear_attn.out_proj",
|
| 303 |
+
"model.language_model.layers.26.linear_attn.in_proj_qkv",
|
| 304 |
+
"model.language_model.layers.26.linear_attn.in_proj_z",
|
| 305 |
+
"model.language_model.layers.26.linear_attn.in_proj_b",
|
| 306 |
+
"model.language_model.layers.26.linear_attn.in_proj_a",
|
| 307 |
+
"model.language_model.layers.28.linear_attn",
|
| 308 |
+
"model.language_model.layers.28.linear_attn.norm",
|
| 309 |
+
"model.language_model.layers.28.linear_attn.out_proj",
|
| 310 |
+
"model.language_model.layers.28.linear_attn.in_proj_qkv",
|
| 311 |
+
"model.language_model.layers.28.linear_attn.in_proj_z",
|
| 312 |
+
"model.language_model.layers.28.linear_attn.in_proj_b",
|
| 313 |
+
"model.language_model.layers.28.linear_attn.in_proj_a",
|
| 314 |
+
"model.language_model.layers.29.linear_attn",
|
| 315 |
+
"model.language_model.layers.29.linear_attn.norm",
|
| 316 |
+
"model.language_model.layers.29.linear_attn.out_proj",
|
| 317 |
+
"model.language_model.layers.29.linear_attn.in_proj_qkv",
|
| 318 |
+
"model.language_model.layers.29.linear_attn.in_proj_z",
|
| 319 |
+
"model.language_model.layers.29.linear_attn.in_proj_b",
|
| 320 |
+
"model.language_model.layers.29.linear_attn.in_proj_a",
|
| 321 |
+
"model.language_model.layers.30.linear_attn",
|
| 322 |
+
"model.language_model.layers.30.linear_attn.norm",
|
| 323 |
+
"model.language_model.layers.30.linear_attn.out_proj",
|
| 324 |
+
"model.language_model.layers.30.linear_attn.in_proj_qkv",
|
| 325 |
+
"model.language_model.layers.30.linear_attn.in_proj_z",
|
| 326 |
+
"model.language_model.layers.30.linear_attn.in_proj_b",
|
| 327 |
+
"model.language_model.layers.30.linear_attn.in_proj_a",
|
| 328 |
+
"lm_head"
|
| 329 |
+
],
|
| 330 |
+
"kv_cache_scheme": null,
|
| 331 |
+
"quant_method": "compressed-tensors",
|
| 332 |
+
"quantization_status": "compressed",
|
| 333 |
+
"sparsity_config": {},
|
| 334 |
+
"transform_config": {},
|
| 335 |
+
"version": "0.18.1.a20260903"
|
| 336 |
+
},
|
| 337 |
+
"text_config": {
|
| 338 |
+
"attention_bias": false,
|
| 339 |
+
"attention_dropout": 0.0,
|
| 340 |
+
"attn_output_gate": true,
|
| 341 |
+
"bos_token_id": null,
|
| 342 |
+
"dtype": "bfloat16",
|
| 343 |
+
"eos_token_id": 248044,
|
| 344 |
+
"full_attention_interval": 4,
|
| 345 |
+
"head_dim": 256,
|
| 346 |
+
"hidden_act": "silu",
|
| 347 |
+
"hidden_size": 4096,
|
| 348 |
+
"initializer_range": 0.02,
|
| 349 |
+
"intermediate_size": 12288,
|
| 350 |
+
"layer_types": [
|
| 351 |
+
"linear_attention",
|
| 352 |
+
"linear_attention",
|
| 353 |
+
"linear_attention",
|
| 354 |
+
"full_attention",
|
| 355 |
+
"linear_attention",
|
| 356 |
+
"linear_attention",
|
| 357 |
+
"linear_attention",
|
| 358 |
+
"full_attention",
|
| 359 |
+
"linear_attention",
|
| 360 |
+
"linear_attention",
|
| 361 |
+
"linear_attention",
|
| 362 |
+
"full_attention",
|
| 363 |
+
"linear_attention",
|
| 364 |
+
"linear_attention",
|
| 365 |
+
"linear_attention",
|
| 366 |
+
"full_attention",
|
| 367 |
+
"linear_attention",
|
| 368 |
+
"linear_attention",
|
| 369 |
+
"linear_attention",
|
| 370 |
+
"full_attention",
|
| 371 |
+
"linear_attention",
|
| 372 |
+
"linear_attention",
|
| 373 |
+
"linear_attention",
|
| 374 |
+
"full_attention",
|
| 375 |
+
"linear_attention",
|
| 376 |
+
"linear_attention",
|
| 377 |
+
"linear_attention",
|
| 378 |
+
"full_attention",
|
| 379 |
+
"linear_attention",
|
| 380 |
+
"linear_attention",
|
| 381 |
+
"linear_attention",
|
| 382 |
+
"full_attention"
|
| 383 |
+
],
|
| 384 |
+
"linear_conv_kernel_dim": 4,
|
| 385 |
+
"linear_key_head_dim": 128,
|
| 386 |
+
"linear_num_key_heads": 16,
|
| 387 |
+
"linear_num_value_heads": 32,
|
| 388 |
+
"linear_value_head_dim": 128,
|
| 389 |
+
"mamba_ssm_dtype": "float32",
|
| 390 |
+
"max_position_embeddings": 262144,
|
| 391 |
+
"mlp_only_layers": [],
|
| 392 |
+
"model_type": "qwen3_5_text",
|
| 393 |
+
"mtp_num_hidden_layers": 0,
|
| 394 |
+
"mtp_use_dedicated_embeddings": false,
|
| 395 |
+
"num_attention_heads": 16,
|
| 396 |
+
"num_hidden_layers": 32,
|
| 397 |
+
"num_key_value_heads": 4,
|
| 398 |
+
"pad_token_id": null,
|
| 399 |
+
"partial_rotary_factor": 0.25,
|
| 400 |
+
"rms_norm_eps": 1e-06,
|
| 401 |
+
"rope_parameters": {
|
| 402 |
+
"mrope_interleaved": true,
|
| 403 |
+
"mrope_section": [
|
| 404 |
+
11,
|
| 405 |
+
11,
|
| 406 |
+
10
|
| 407 |
+
],
|
| 408 |
+
"partial_rotary_factor": 0.25,
|
| 409 |
+
"rope_theta": 10000000,
|
| 410 |
+
"rope_type": "default"
|
| 411 |
+
},
|
| 412 |
+
"tie_word_embeddings": false,
|
| 413 |
+
"use_cache": true,
|
| 414 |
+
"vocab_size": 248320
|
| 415 |
+
},
|
| 416 |
+
"tie_word_embeddings": false,
|
| 417 |
+
"transformers_version": "5.16.1",
|
| 418 |
+
"unsloth_fixed": true,
|
| 419 |
+
"video_token_id": 248057,
|
| 420 |
+
"vision_config": {
|
| 421 |
+
"deepstack_visual_indexes": [],
|
| 422 |
+
"depth": 27,
|
| 423 |
+
"dtype": "bfloat16",
|
| 424 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 425 |
+
"hidden_size": 1152,
|
| 426 |
+
"in_channels": 3,
|
| 427 |
+
"initializer_range": 0.02,
|
| 428 |
+
"intermediate_size": 4304,
|
| 429 |
+
"model_type": "qwen3_5_vision",
|
| 430 |
+
"num_heads": 16,
|
| 431 |
+
"num_position_embeddings": 2304,
|
| 432 |
+
"out_hidden_size": 4096,
|
| 433 |
+
"patch_size": 16,
|
| 434 |
+
"spatial_merge_size": 2,
|
| 435 |
+
"temporal_patch_size": 2
|
| 436 |
+
},
|
| 437 |
+
"vision_end_token_id": 248054,
|
| 438 |
+
"vision_start_token_id": 248053
|
| 439 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"eos_token_id": 248044,
|
| 4 |
+
"transformers_version": "5.16.1",
|
| 5 |
+
"use_cache": true
|
| 6 |
+
}
|
model-00001-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a773ca83d1758d6d4a89a44bdef5099384d899a3edec52fd86d074dfa35faaa4
|
| 3 |
+
size 4980522864
|
model-00002-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:584e868b0cdaf2099836e5e6a44a0577106c51573d4c437d9543ee27fab5fe46
|
| 3 |
+
size 4975897352
|
model-00003-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6845ff7d997c62df20e0fa95c56fbc3355a43956e7b2f9b2ce685aace9836371
|
| 3 |
+
size 3563782368
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,896 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_parameters": 9410845936,
|
| 4 |
+
"total_size": 13520091616
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 7 |
+
"lm_head.weight": "model-00003-of-00003.safetensors",
|
| 8 |
+
"model.language_model.embed_tokens.weight": "model-00001-of-00003.safetensors",
|
| 9 |
+
"model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 10 |
+
"model.language_model.layers.0.linear_attn.A_log": "model-00001-of-00003.safetensors",
|
| 11 |
+
"model.language_model.layers.0.linear_attn.conv1d.weight": "model-00001-of-00003.safetensors",
|
| 12 |
+
"model.language_model.layers.0.linear_attn.dt_bias": "model-00001-of-00003.safetensors",
|
| 13 |
+
"model.language_model.layers.0.linear_attn.in_proj_a.weight": "model-00001-of-00003.safetensors",
|
| 14 |
+
"model.language_model.layers.0.linear_attn.in_proj_b.weight": "model-00001-of-00003.safetensors",
|
| 15 |
+
"model.language_model.layers.0.linear_attn.in_proj_qkv.weight": "model-00001-of-00003.safetensors",
|
| 16 |
+
"model.language_model.layers.0.linear_attn.in_proj_z.weight": "model-00001-of-00003.safetensors",
|
| 17 |
+
"model.language_model.layers.0.linear_attn.norm.weight": "model-00001-of-00003.safetensors",
|
| 18 |
+
"model.language_model.layers.0.linear_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 19 |
+
"model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 20 |
+
"model.language_model.layers.0.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
|
| 21 |
+
"model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 22 |
+
"model.language_model.layers.0.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
|
| 23 |
+
"model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 24 |
+
"model.language_model.layers.0.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
|
| 25 |
+
"model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 26 |
+
"model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 27 |
+
"model.language_model.layers.1.linear_attn.A_log": "model-00001-of-00003.safetensors",
|
| 28 |
+
"model.language_model.layers.1.linear_attn.conv1d.weight": "model-00001-of-00003.safetensors",
|
| 29 |
+
"model.language_model.layers.1.linear_attn.dt_bias": "model-00001-of-00003.safetensors",
|
| 30 |
+
"model.language_model.layers.1.linear_attn.in_proj_a.weight": "model-00001-of-00003.safetensors",
|
| 31 |
+
"model.language_model.layers.1.linear_attn.in_proj_b.weight": "model-00001-of-00003.safetensors",
|
| 32 |
+
"model.language_model.layers.1.linear_attn.in_proj_qkv.weight": "model-00001-of-00003.safetensors",
|
| 33 |
+
"model.language_model.layers.1.linear_attn.in_proj_z.weight": "model-00001-of-00003.safetensors",
|
| 34 |
+
"model.language_model.layers.1.linear_attn.norm.weight": "model-00001-of-00003.safetensors",
|
| 35 |
+
"model.language_model.layers.1.linear_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 36 |
+
"model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 37 |
+
"model.language_model.layers.1.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
|
| 38 |
+
"model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 39 |
+
"model.language_model.layers.1.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
|
| 40 |
+
"model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 41 |
+
"model.language_model.layers.1.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
|
| 42 |
+
"model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 43 |
+
"model.language_model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 44 |
+
"model.language_model.layers.10.linear_attn.A_log": "model-00002-of-00003.safetensors",
|
| 45 |
+
"model.language_model.layers.10.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors",
|
| 46 |
+
"model.language_model.layers.10.linear_attn.dt_bias": "model-00002-of-00003.safetensors",
|
| 47 |
+
"model.language_model.layers.10.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors",
|
| 48 |
+
"model.language_model.layers.10.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors",
|
| 49 |
+
"model.language_model.layers.10.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors",
|
| 50 |
+
"model.language_model.layers.10.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors",
|
| 51 |
+
"model.language_model.layers.10.linear_attn.norm.weight": "model-00002-of-00003.safetensors",
|
| 52 |
+
"model.language_model.layers.10.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 53 |
+
"model.language_model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 54 |
+
"model.language_model.layers.10.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
|
| 55 |
+
"model.language_model.layers.10.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 56 |
+
"model.language_model.layers.10.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
|
| 57 |
+
"model.language_model.layers.10.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 58 |
+
"model.language_model.layers.10.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
|
| 59 |
+
"model.language_model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 60 |
+
"model.language_model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 61 |
+
"model.language_model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 62 |
+
"model.language_model.layers.11.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
|
| 63 |
+
"model.language_model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 64 |
+
"model.language_model.layers.11.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
|
| 65 |
+
"model.language_model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 66 |
+
"model.language_model.layers.11.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
|
| 67 |
+
"model.language_model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 68 |
+
"model.language_model.layers.11.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
|
| 69 |
+
"model.language_model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 70 |
+
"model.language_model.layers.11.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
|
| 71 |
+
"model.language_model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 72 |
+
"model.language_model.layers.11.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
|
| 73 |
+
"model.language_model.layers.11.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
|
| 74 |
+
"model.language_model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 75 |
+
"model.language_model.layers.11.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
|
| 76 |
+
"model.language_model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 77 |
+
"model.language_model.layers.11.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
|
| 78 |
+
"model.language_model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 79 |
+
"model.language_model.layers.12.linear_attn.A_log": "model-00002-of-00003.safetensors",
|
| 80 |
+
"model.language_model.layers.12.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors",
|
| 81 |
+
"model.language_model.layers.12.linear_attn.dt_bias": "model-00002-of-00003.safetensors",
|
| 82 |
+
"model.language_model.layers.12.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors",
|
| 83 |
+
"model.language_model.layers.12.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors",
|
| 84 |
+
"model.language_model.layers.12.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors",
|
| 85 |
+
"model.language_model.layers.12.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors",
|
| 86 |
+
"model.language_model.layers.12.linear_attn.norm.weight": "model-00002-of-00003.safetensors",
|
| 87 |
+
"model.language_model.layers.12.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 88 |
+
"model.language_model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 89 |
+
"model.language_model.layers.12.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
|
| 90 |
+
"model.language_model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 91 |
+
"model.language_model.layers.12.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
|
| 92 |
+
"model.language_model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 93 |
+
"model.language_model.layers.12.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
|
| 94 |
+
"model.language_model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 95 |
+
"model.language_model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 96 |
+
"model.language_model.layers.13.linear_attn.A_log": "model-00002-of-00003.safetensors",
|
| 97 |
+
"model.language_model.layers.13.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors",
|
| 98 |
+
"model.language_model.layers.13.linear_attn.dt_bias": "model-00002-of-00003.safetensors",
|
| 99 |
+
"model.language_model.layers.13.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors",
|
| 100 |
+
"model.language_model.layers.13.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors",
|
| 101 |
+
"model.language_model.layers.13.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors",
|
| 102 |
+
"model.language_model.layers.13.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors",
|
| 103 |
+
"model.language_model.layers.13.linear_attn.norm.weight": "model-00002-of-00003.safetensors",
|
| 104 |
+
"model.language_model.layers.13.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 105 |
+
"model.language_model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 106 |
+
"model.language_model.layers.13.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
|
| 107 |
+
"model.language_model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 108 |
+
"model.language_model.layers.13.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
|
| 109 |
+
"model.language_model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 110 |
+
"model.language_model.layers.13.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
|
| 111 |
+
"model.language_model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 112 |
+
"model.language_model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 113 |
+
"model.language_model.layers.14.linear_attn.A_log": "model-00002-of-00003.safetensors",
|
| 114 |
+
"model.language_model.layers.14.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors",
|
| 115 |
+
"model.language_model.layers.14.linear_attn.dt_bias": "model-00002-of-00003.safetensors",
|
| 116 |
+
"model.language_model.layers.14.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors",
|
| 117 |
+
"model.language_model.layers.14.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors",
|
| 118 |
+
"model.language_model.layers.14.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors",
|
| 119 |
+
"model.language_model.layers.14.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors",
|
| 120 |
+
"model.language_model.layers.14.linear_attn.norm.weight": "model-00002-of-00003.safetensors",
|
| 121 |
+
"model.language_model.layers.14.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 122 |
+
"model.language_model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 123 |
+
"model.language_model.layers.14.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
|
| 124 |
+
"model.language_model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 125 |
+
"model.language_model.layers.14.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
|
| 126 |
+
"model.language_model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 127 |
+
"model.language_model.layers.14.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
|
| 128 |
+
"model.language_model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 129 |
+
"model.language_model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 130 |
+
"model.language_model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 131 |
+
"model.language_model.layers.15.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
|
| 132 |
+
"model.language_model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 133 |
+
"model.language_model.layers.15.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
|
| 134 |
+
"model.language_model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 135 |
+
"model.language_model.layers.15.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
|
| 136 |
+
"model.language_model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 137 |
+
"model.language_model.layers.15.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
|
| 138 |
+
"model.language_model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 139 |
+
"model.language_model.layers.15.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
|
| 140 |
+
"model.language_model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 141 |
+
"model.language_model.layers.15.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
|
| 142 |
+
"model.language_model.layers.15.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
|
| 143 |
+
"model.language_model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 144 |
+
"model.language_model.layers.15.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
|
| 145 |
+
"model.language_model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 146 |
+
"model.language_model.layers.15.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
|
| 147 |
+
"model.language_model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 148 |
+
"model.language_model.layers.16.linear_attn.A_log": "model-00002-of-00003.safetensors",
|
| 149 |
+
"model.language_model.layers.16.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors",
|
| 150 |
+
"model.language_model.layers.16.linear_attn.dt_bias": "model-00002-of-00003.safetensors",
|
| 151 |
+
"model.language_model.layers.16.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors",
|
| 152 |
+
"model.language_model.layers.16.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors",
|
| 153 |
+
"model.language_model.layers.16.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors",
|
| 154 |
+
"model.language_model.layers.16.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors",
|
| 155 |
+
"model.language_model.layers.16.linear_attn.norm.weight": "model-00002-of-00003.safetensors",
|
| 156 |
+
"model.language_model.layers.16.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 157 |
+
"model.language_model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 158 |
+
"model.language_model.layers.16.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
|
| 159 |
+
"model.language_model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 160 |
+
"model.language_model.layers.16.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
|
| 161 |
+
"model.language_model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 162 |
+
"model.language_model.layers.16.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
|
| 163 |
+
"model.language_model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 164 |
+
"model.language_model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 165 |
+
"model.language_model.layers.17.linear_attn.A_log": "model-00002-of-00003.safetensors",
|
| 166 |
+
"model.language_model.layers.17.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors",
|
| 167 |
+
"model.language_model.layers.17.linear_attn.dt_bias": "model-00002-of-00003.safetensors",
|
| 168 |
+
"model.language_model.layers.17.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors",
|
| 169 |
+
"model.language_model.layers.17.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors",
|
| 170 |
+
"model.language_model.layers.17.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors",
|
| 171 |
+
"model.language_model.layers.17.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors",
|
| 172 |
+
"model.language_model.layers.17.linear_attn.norm.weight": "model-00002-of-00003.safetensors",
|
| 173 |
+
"model.language_model.layers.17.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 174 |
+
"model.language_model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 175 |
+
"model.language_model.layers.17.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
|
| 176 |
+
"model.language_model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 177 |
+
"model.language_model.layers.17.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
|
| 178 |
+
"model.language_model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 179 |
+
"model.language_model.layers.17.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
|
| 180 |
+
"model.language_model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 181 |
+
"model.language_model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 182 |
+
"model.language_model.layers.18.linear_attn.A_log": "model-00002-of-00003.safetensors",
|
| 183 |
+
"model.language_model.layers.18.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors",
|
| 184 |
+
"model.language_model.layers.18.linear_attn.dt_bias": "model-00002-of-00003.safetensors",
|
| 185 |
+
"model.language_model.layers.18.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors",
|
| 186 |
+
"model.language_model.layers.18.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors",
|
| 187 |
+
"model.language_model.layers.18.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors",
|
| 188 |
+
"model.language_model.layers.18.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors",
|
| 189 |
+
"model.language_model.layers.18.linear_attn.norm.weight": "model-00002-of-00003.safetensors",
|
| 190 |
+
"model.language_model.layers.18.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 191 |
+
"model.language_model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 192 |
+
"model.language_model.layers.18.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
|
| 193 |
+
"model.language_model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 194 |
+
"model.language_model.layers.18.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
|
| 195 |
+
"model.language_model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 196 |
+
"model.language_model.layers.18.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
|
| 197 |
+
"model.language_model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 198 |
+
"model.language_model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 199 |
+
"model.language_model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 200 |
+
"model.language_model.layers.19.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
|
| 201 |
+
"model.language_model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 202 |
+
"model.language_model.layers.19.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
|
| 203 |
+
"model.language_model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 204 |
+
"model.language_model.layers.19.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
|
| 205 |
+
"model.language_model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 206 |
+
"model.language_model.layers.19.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
|
| 207 |
+
"model.language_model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 208 |
+
"model.language_model.layers.19.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
|
| 209 |
+
"model.language_model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 210 |
+
"model.language_model.layers.19.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
|
| 211 |
+
"model.language_model.layers.19.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
|
| 212 |
+
"model.language_model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 213 |
+
"model.language_model.layers.19.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
|
| 214 |
+
"model.language_model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 215 |
+
"model.language_model.layers.19.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
|
| 216 |
+
"model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 217 |
+
"model.language_model.layers.2.linear_attn.A_log": "model-00001-of-00003.safetensors",
|
| 218 |
+
"model.language_model.layers.2.linear_attn.conv1d.weight": "model-00001-of-00003.safetensors",
|
| 219 |
+
"model.language_model.layers.2.linear_attn.dt_bias": "model-00001-of-00003.safetensors",
|
| 220 |
+
"model.language_model.layers.2.linear_attn.in_proj_a.weight": "model-00001-of-00003.safetensors",
|
| 221 |
+
"model.language_model.layers.2.linear_attn.in_proj_b.weight": "model-00001-of-00003.safetensors",
|
| 222 |
+
"model.language_model.layers.2.linear_attn.in_proj_qkv.weight": "model-00001-of-00003.safetensors",
|
| 223 |
+
"model.language_model.layers.2.linear_attn.in_proj_z.weight": "model-00001-of-00003.safetensors",
|
| 224 |
+
"model.language_model.layers.2.linear_attn.norm.weight": "model-00001-of-00003.safetensors",
|
| 225 |
+
"model.language_model.layers.2.linear_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 226 |
+
"model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 227 |
+
"model.language_model.layers.2.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
|
| 228 |
+
"model.language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 229 |
+
"model.language_model.layers.2.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
|
| 230 |
+
"model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 231 |
+
"model.language_model.layers.2.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
|
| 232 |
+
"model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 233 |
+
"model.language_model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 234 |
+
"model.language_model.layers.20.linear_attn.A_log": "model-00002-of-00003.safetensors",
|
| 235 |
+
"model.language_model.layers.20.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors",
|
| 236 |
+
"model.language_model.layers.20.linear_attn.dt_bias": "model-00002-of-00003.safetensors",
|
| 237 |
+
"model.language_model.layers.20.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors",
|
| 238 |
+
"model.language_model.layers.20.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors",
|
| 239 |
+
"model.language_model.layers.20.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors",
|
| 240 |
+
"model.language_model.layers.20.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors",
|
| 241 |
+
"model.language_model.layers.20.linear_attn.norm.weight": "model-00002-of-00003.safetensors",
|
| 242 |
+
"model.language_model.layers.20.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 243 |
+
"model.language_model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 244 |
+
"model.language_model.layers.20.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
|
| 245 |
+
"model.language_model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 246 |
+
"model.language_model.layers.20.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
|
| 247 |
+
"model.language_model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 248 |
+
"model.language_model.layers.20.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
|
| 249 |
+
"model.language_model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 250 |
+
"model.language_model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 251 |
+
"model.language_model.layers.21.linear_attn.A_log": "model-00002-of-00003.safetensors",
|
| 252 |
+
"model.language_model.layers.21.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors",
|
| 253 |
+
"model.language_model.layers.21.linear_attn.dt_bias": "model-00002-of-00003.safetensors",
|
| 254 |
+
"model.language_model.layers.21.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors",
|
| 255 |
+
"model.language_model.layers.21.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors",
|
| 256 |
+
"model.language_model.layers.21.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors",
|
| 257 |
+
"model.language_model.layers.21.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors",
|
| 258 |
+
"model.language_model.layers.21.linear_attn.norm.weight": "model-00002-of-00003.safetensors",
|
| 259 |
+
"model.language_model.layers.21.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 260 |
+
"model.language_model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 261 |
+
"model.language_model.layers.21.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
|
| 262 |
+
"model.language_model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 263 |
+
"model.language_model.layers.21.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
|
| 264 |
+
"model.language_model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 265 |
+
"model.language_model.layers.21.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
|
| 266 |
+
"model.language_model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 267 |
+
"model.language_model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 268 |
+
"model.language_model.layers.22.linear_attn.A_log": "model-00002-of-00003.safetensors",
|
| 269 |
+
"model.language_model.layers.22.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors",
|
| 270 |
+
"model.language_model.layers.22.linear_attn.dt_bias": "model-00002-of-00003.safetensors",
|
| 271 |
+
"model.language_model.layers.22.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors",
|
| 272 |
+
"model.language_model.layers.22.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors",
|
| 273 |
+
"model.language_model.layers.22.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors",
|
| 274 |
+
"model.language_model.layers.22.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors",
|
| 275 |
+
"model.language_model.layers.22.linear_attn.norm.weight": "model-00002-of-00003.safetensors",
|
| 276 |
+
"model.language_model.layers.22.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 277 |
+
"model.language_model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 278 |
+
"model.language_model.layers.22.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
|
| 279 |
+
"model.language_model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 280 |
+
"model.language_model.layers.22.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
|
| 281 |
+
"model.language_model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 282 |
+
"model.language_model.layers.22.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
|
| 283 |
+
"model.language_model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 284 |
+
"model.language_model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 285 |
+
"model.language_model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 286 |
+
"model.language_model.layers.23.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
|
| 287 |
+
"model.language_model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 288 |
+
"model.language_model.layers.23.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
|
| 289 |
+
"model.language_model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 290 |
+
"model.language_model.layers.23.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
|
| 291 |
+
"model.language_model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 292 |
+
"model.language_model.layers.23.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
|
| 293 |
+
"model.language_model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 294 |
+
"model.language_model.layers.23.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
|
| 295 |
+
"model.language_model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 296 |
+
"model.language_model.layers.23.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
|
| 297 |
+
"model.language_model.layers.23.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
|
| 298 |
+
"model.language_model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 299 |
+
"model.language_model.layers.23.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
|
| 300 |
+
"model.language_model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 301 |
+
"model.language_model.layers.23.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
|
| 302 |
+
"model.language_model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 303 |
+
"model.language_model.layers.24.linear_attn.A_log": "model-00002-of-00003.safetensors",
|
| 304 |
+
"model.language_model.layers.24.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors",
|
| 305 |
+
"model.language_model.layers.24.linear_attn.dt_bias": "model-00002-of-00003.safetensors",
|
| 306 |
+
"model.language_model.layers.24.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors",
|
| 307 |
+
"model.language_model.layers.24.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors",
|
| 308 |
+
"model.language_model.layers.24.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors",
|
| 309 |
+
"model.language_model.layers.24.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors",
|
| 310 |
+
"model.language_model.layers.24.linear_attn.norm.weight": "model-00002-of-00003.safetensors",
|
| 311 |
+
"model.language_model.layers.24.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 312 |
+
"model.language_model.layers.24.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 313 |
+
"model.language_model.layers.24.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
|
| 314 |
+
"model.language_model.layers.24.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 315 |
+
"model.language_model.layers.24.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
|
| 316 |
+
"model.language_model.layers.24.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 317 |
+
"model.language_model.layers.24.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
|
| 318 |
+
"model.language_model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 319 |
+
"model.language_model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 320 |
+
"model.language_model.layers.25.linear_attn.A_log": "model-00002-of-00003.safetensors",
|
| 321 |
+
"model.language_model.layers.25.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors",
|
| 322 |
+
"model.language_model.layers.25.linear_attn.dt_bias": "model-00002-of-00003.safetensors",
|
| 323 |
+
"model.language_model.layers.25.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors",
|
| 324 |
+
"model.language_model.layers.25.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors",
|
| 325 |
+
"model.language_model.layers.25.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors",
|
| 326 |
+
"model.language_model.layers.25.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors",
|
| 327 |
+
"model.language_model.layers.25.linear_attn.norm.weight": "model-00002-of-00003.safetensors",
|
| 328 |
+
"model.language_model.layers.25.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 329 |
+
"model.language_model.layers.25.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 330 |
+
"model.language_model.layers.25.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
|
| 331 |
+
"model.language_model.layers.25.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 332 |
+
"model.language_model.layers.25.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
|
| 333 |
+
"model.language_model.layers.25.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 334 |
+
"model.language_model.layers.25.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
|
| 335 |
+
"model.language_model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 336 |
+
"model.language_model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 337 |
+
"model.language_model.layers.26.linear_attn.A_log": "model-00002-of-00003.safetensors",
|
| 338 |
+
"model.language_model.layers.26.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors",
|
| 339 |
+
"model.language_model.layers.26.linear_attn.dt_bias": "model-00002-of-00003.safetensors",
|
| 340 |
+
"model.language_model.layers.26.linear_attn.in_proj_a.weight": "model-00003-of-00003.safetensors",
|
| 341 |
+
"model.language_model.layers.26.linear_attn.in_proj_b.weight": "model-00003-of-00003.safetensors",
|
| 342 |
+
"model.language_model.layers.26.linear_attn.in_proj_qkv.weight": "model-00003-of-00003.safetensors",
|
| 343 |
+
"model.language_model.layers.26.linear_attn.in_proj_z.weight": "model-00003-of-00003.safetensors",
|
| 344 |
+
"model.language_model.layers.26.linear_attn.norm.weight": "model-00002-of-00003.safetensors",
|
| 345 |
+
"model.language_model.layers.26.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 346 |
+
"model.language_model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 347 |
+
"model.language_model.layers.26.mlp.down_proj.weight_scale": "model-00003-of-00003.safetensors",
|
| 348 |
+
"model.language_model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 349 |
+
"model.language_model.layers.26.mlp.gate_proj.weight_scale": "model-00003-of-00003.safetensors",
|
| 350 |
+
"model.language_model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 351 |
+
"model.language_model.layers.26.mlp.up_proj.weight_scale": "model-00003-of-00003.safetensors",
|
| 352 |
+
"model.language_model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 353 |
+
"model.language_model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 354 |
+
"model.language_model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 355 |
+
"model.language_model.layers.27.mlp.down_proj.weight_scale": "model-00003-of-00003.safetensors",
|
| 356 |
+
"model.language_model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 357 |
+
"model.language_model.layers.27.mlp.gate_proj.weight_scale": "model-00003-of-00003.safetensors",
|
| 358 |
+
"model.language_model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 359 |
+
"model.language_model.layers.27.mlp.up_proj.weight_scale": "model-00003-of-00003.safetensors",
|
| 360 |
+
"model.language_model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 361 |
+
"model.language_model.layers.27.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
|
| 362 |
+
"model.language_model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 363 |
+
"model.language_model.layers.27.self_attn.k_proj.weight_scale": "model-00003-of-00003.safetensors",
|
| 364 |
+
"model.language_model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 365 |
+
"model.language_model.layers.27.self_attn.o_proj.weight_scale": "model-00003-of-00003.safetensors",
|
| 366 |
+
"model.language_model.layers.27.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
|
| 367 |
+
"model.language_model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 368 |
+
"model.language_model.layers.27.self_attn.q_proj.weight_scale": "model-00003-of-00003.safetensors",
|
| 369 |
+
"model.language_model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 370 |
+
"model.language_model.layers.27.self_attn.v_proj.weight_scale": "model-00003-of-00003.safetensors",
|
| 371 |
+
"model.language_model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 372 |
+
"model.language_model.layers.28.linear_attn.A_log": "model-00003-of-00003.safetensors",
|
| 373 |
+
"model.language_model.layers.28.linear_attn.conv1d.weight": "model-00003-of-00003.safetensors",
|
| 374 |
+
"model.language_model.layers.28.linear_attn.dt_bias": "model-00003-of-00003.safetensors",
|
| 375 |
+
"model.language_model.layers.28.linear_attn.in_proj_a.weight": "model-00003-of-00003.safetensors",
|
| 376 |
+
"model.language_model.layers.28.linear_attn.in_proj_b.weight": "model-00003-of-00003.safetensors",
|
| 377 |
+
"model.language_model.layers.28.linear_attn.in_proj_qkv.weight": "model-00003-of-00003.safetensors",
|
| 378 |
+
"model.language_model.layers.28.linear_attn.in_proj_z.weight": "model-00003-of-00003.safetensors",
|
| 379 |
+
"model.language_model.layers.28.linear_attn.norm.weight": "model-00003-of-00003.safetensors",
|
| 380 |
+
"model.language_model.layers.28.linear_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 381 |
+
"model.language_model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 382 |
+
"model.language_model.layers.28.mlp.down_proj.weight_scale": "model-00003-of-00003.safetensors",
|
| 383 |
+
"model.language_model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 384 |
+
"model.language_model.layers.28.mlp.gate_proj.weight_scale": "model-00003-of-00003.safetensors",
|
| 385 |
+
"model.language_model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 386 |
+
"model.language_model.layers.28.mlp.up_proj.weight_scale": "model-00003-of-00003.safetensors",
|
| 387 |
+
"model.language_model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 388 |
+
"model.language_model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 389 |
+
"model.language_model.layers.29.linear_attn.A_log": "model-00003-of-00003.safetensors",
|
| 390 |
+
"model.language_model.layers.29.linear_attn.conv1d.weight": "model-00003-of-00003.safetensors",
|
| 391 |
+
"model.language_model.layers.29.linear_attn.dt_bias": "model-00003-of-00003.safetensors",
|
| 392 |
+
"model.language_model.layers.29.linear_attn.in_proj_a.weight": "model-00003-of-00003.safetensors",
|
| 393 |
+
"model.language_model.layers.29.linear_attn.in_proj_b.weight": "model-00003-of-00003.safetensors",
|
| 394 |
+
"model.language_model.layers.29.linear_attn.in_proj_qkv.weight": "model-00003-of-00003.safetensors",
|
| 395 |
+
"model.language_model.layers.29.linear_attn.in_proj_z.weight": "model-00003-of-00003.safetensors",
|
| 396 |
+
"model.language_model.layers.29.linear_attn.norm.weight": "model-00003-of-00003.safetensors",
|
| 397 |
+
"model.language_model.layers.29.linear_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 398 |
+
"model.language_model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 399 |
+
"model.language_model.layers.29.mlp.down_proj.weight_scale": "model-00003-of-00003.safetensors",
|
| 400 |
+
"model.language_model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 401 |
+
"model.language_model.layers.29.mlp.gate_proj.weight_scale": "model-00003-of-00003.safetensors",
|
| 402 |
+
"model.language_model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 403 |
+
"model.language_model.layers.29.mlp.up_proj.weight_scale": "model-00003-of-00003.safetensors",
|
| 404 |
+
"model.language_model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 405 |
+
"model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 406 |
+
"model.language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 407 |
+
"model.language_model.layers.3.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
|
| 408 |
+
"model.language_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 409 |
+
"model.language_model.layers.3.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
|
| 410 |
+
"model.language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 411 |
+
"model.language_model.layers.3.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
|
| 412 |
+
"model.language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 413 |
+
"model.language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
|
| 414 |
+
"model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 415 |
+
"model.language_model.layers.3.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
|
| 416 |
+
"model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 417 |
+
"model.language_model.layers.3.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
|
| 418 |
+
"model.language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
|
| 419 |
+
"model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 420 |
+
"model.language_model.layers.3.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
|
| 421 |
+
"model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 422 |
+
"model.language_model.layers.3.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
|
| 423 |
+
"model.language_model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 424 |
+
"model.language_model.layers.30.linear_attn.A_log": "model-00003-of-00003.safetensors",
|
| 425 |
+
"model.language_model.layers.30.linear_attn.conv1d.weight": "model-00003-of-00003.safetensors",
|
| 426 |
+
"model.language_model.layers.30.linear_attn.dt_bias": "model-00003-of-00003.safetensors",
|
| 427 |
+
"model.language_model.layers.30.linear_attn.in_proj_a.weight": "model-00003-of-00003.safetensors",
|
| 428 |
+
"model.language_model.layers.30.linear_attn.in_proj_b.weight": "model-00003-of-00003.safetensors",
|
| 429 |
+
"model.language_model.layers.30.linear_attn.in_proj_qkv.weight": "model-00003-of-00003.safetensors",
|
| 430 |
+
"model.language_model.layers.30.linear_attn.in_proj_z.weight": "model-00003-of-00003.safetensors",
|
| 431 |
+
"model.language_model.layers.30.linear_attn.norm.weight": "model-00003-of-00003.safetensors",
|
| 432 |
+
"model.language_model.layers.30.linear_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 433 |
+
"model.language_model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 434 |
+
"model.language_model.layers.30.mlp.down_proj.weight_scale": "model-00003-of-00003.safetensors",
|
| 435 |
+
"model.language_model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 436 |
+
"model.language_model.layers.30.mlp.gate_proj.weight_scale": "model-00003-of-00003.safetensors",
|
| 437 |
+
"model.language_model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 438 |
+
"model.language_model.layers.30.mlp.up_proj.weight_scale": "model-00003-of-00003.safetensors",
|
| 439 |
+
"model.language_model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 440 |
+
"model.language_model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 441 |
+
"model.language_model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 442 |
+
"model.language_model.layers.31.mlp.down_proj.weight_scale": "model-00003-of-00003.safetensors",
|
| 443 |
+
"model.language_model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 444 |
+
"model.language_model.layers.31.mlp.gate_proj.weight_scale": "model-00003-of-00003.safetensors",
|
| 445 |
+
"model.language_model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 446 |
+
"model.language_model.layers.31.mlp.up_proj.weight_scale": "model-00003-of-00003.safetensors",
|
| 447 |
+
"model.language_model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 448 |
+
"model.language_model.layers.31.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
|
| 449 |
+
"model.language_model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 450 |
+
"model.language_model.layers.31.self_attn.k_proj.weight_scale": "model-00003-of-00003.safetensors",
|
| 451 |
+
"model.language_model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 452 |
+
"model.language_model.layers.31.self_attn.o_proj.weight_scale": "model-00003-of-00003.safetensors",
|
| 453 |
+
"model.language_model.layers.31.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
|
| 454 |
+
"model.language_model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 455 |
+
"model.language_model.layers.31.self_attn.q_proj.weight_scale": "model-00003-of-00003.safetensors",
|
| 456 |
+
"model.language_model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 457 |
+
"model.language_model.layers.31.self_attn.v_proj.weight_scale": "model-00003-of-00003.safetensors",
|
| 458 |
+
"model.language_model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 459 |
+
"model.language_model.layers.4.linear_attn.A_log": "model-00001-of-00003.safetensors",
|
| 460 |
+
"model.language_model.layers.4.linear_attn.conv1d.weight": "model-00001-of-00003.safetensors",
|
| 461 |
+
"model.language_model.layers.4.linear_attn.dt_bias": "model-00001-of-00003.safetensors",
|
| 462 |
+
"model.language_model.layers.4.linear_attn.in_proj_a.weight": "model-00001-of-00003.safetensors",
|
| 463 |
+
"model.language_model.layers.4.linear_attn.in_proj_b.weight": "model-00001-of-00003.safetensors",
|
| 464 |
+
"model.language_model.layers.4.linear_attn.in_proj_qkv.weight": "model-00001-of-00003.safetensors",
|
| 465 |
+
"model.language_model.layers.4.linear_attn.in_proj_z.weight": "model-00001-of-00003.safetensors",
|
| 466 |
+
"model.language_model.layers.4.linear_attn.norm.weight": "model-00001-of-00003.safetensors",
|
| 467 |
+
"model.language_model.layers.4.linear_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 468 |
+
"model.language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 469 |
+
"model.language_model.layers.4.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
|
| 470 |
+
"model.language_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 471 |
+
"model.language_model.layers.4.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
|
| 472 |
+
"model.language_model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 473 |
+
"model.language_model.layers.4.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
|
| 474 |
+
"model.language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 475 |
+
"model.language_model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 476 |
+
"model.language_model.layers.5.linear_attn.A_log": "model-00001-of-00003.safetensors",
|
| 477 |
+
"model.language_model.layers.5.linear_attn.conv1d.weight": "model-00001-of-00003.safetensors",
|
| 478 |
+
"model.language_model.layers.5.linear_attn.dt_bias": "model-00001-of-00003.safetensors",
|
| 479 |
+
"model.language_model.layers.5.linear_attn.in_proj_a.weight": "model-00001-of-00003.safetensors",
|
| 480 |
+
"model.language_model.layers.5.linear_attn.in_proj_b.weight": "model-00001-of-00003.safetensors",
|
| 481 |
+
"model.language_model.layers.5.linear_attn.in_proj_qkv.weight": "model-00001-of-00003.safetensors",
|
| 482 |
+
"model.language_model.layers.5.linear_attn.in_proj_z.weight": "model-00001-of-00003.safetensors",
|
| 483 |
+
"model.language_model.layers.5.linear_attn.norm.weight": "model-00001-of-00003.safetensors",
|
| 484 |
+
"model.language_model.layers.5.linear_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 485 |
+
"model.language_model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 486 |
+
"model.language_model.layers.5.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
|
| 487 |
+
"model.language_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 488 |
+
"model.language_model.layers.5.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
|
| 489 |
+
"model.language_model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 490 |
+
"model.language_model.layers.5.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
|
| 491 |
+
"model.language_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 492 |
+
"model.language_model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 493 |
+
"model.language_model.layers.6.linear_attn.A_log": "model-00001-of-00003.safetensors",
|
| 494 |
+
"model.language_model.layers.6.linear_attn.conv1d.weight": "model-00001-of-00003.safetensors",
|
| 495 |
+
"model.language_model.layers.6.linear_attn.dt_bias": "model-00001-of-00003.safetensors",
|
| 496 |
+
"model.language_model.layers.6.linear_attn.in_proj_a.weight": "model-00001-of-00003.safetensors",
|
| 497 |
+
"model.language_model.layers.6.linear_attn.in_proj_b.weight": "model-00001-of-00003.safetensors",
|
| 498 |
+
"model.language_model.layers.6.linear_attn.in_proj_qkv.weight": "model-00001-of-00003.safetensors",
|
| 499 |
+
"model.language_model.layers.6.linear_attn.in_proj_z.weight": "model-00001-of-00003.safetensors",
|
| 500 |
+
"model.language_model.layers.6.linear_attn.norm.weight": "model-00001-of-00003.safetensors",
|
| 501 |
+
"model.language_model.layers.6.linear_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 502 |
+
"model.language_model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 503 |
+
"model.language_model.layers.6.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
|
| 504 |
+
"model.language_model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 505 |
+
"model.language_model.layers.6.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
|
| 506 |
+
"model.language_model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 507 |
+
"model.language_model.layers.6.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
|
| 508 |
+
"model.language_model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 509 |
+
"model.language_model.layers.7.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 510 |
+
"model.language_model.layers.7.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 511 |
+
"model.language_model.layers.7.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
|
| 512 |
+
"model.language_model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 513 |
+
"model.language_model.layers.7.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
|
| 514 |
+
"model.language_model.layers.7.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 515 |
+
"model.language_model.layers.7.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
|
| 516 |
+
"model.language_model.layers.7.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 517 |
+
"model.language_model.layers.7.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
|
| 518 |
+
"model.language_model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 519 |
+
"model.language_model.layers.7.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
|
| 520 |
+
"model.language_model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 521 |
+
"model.language_model.layers.7.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
|
| 522 |
+
"model.language_model.layers.7.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
|
| 523 |
+
"model.language_model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 524 |
+
"model.language_model.layers.7.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
|
| 525 |
+
"model.language_model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 526 |
+
"model.language_model.layers.7.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
|
| 527 |
+
"model.language_model.layers.8.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 528 |
+
"model.language_model.layers.8.linear_attn.A_log": "model-00002-of-00003.safetensors",
|
| 529 |
+
"model.language_model.layers.8.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors",
|
| 530 |
+
"model.language_model.layers.8.linear_attn.dt_bias": "model-00002-of-00003.safetensors",
|
| 531 |
+
"model.language_model.layers.8.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors",
|
| 532 |
+
"model.language_model.layers.8.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors",
|
| 533 |
+
"model.language_model.layers.8.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors",
|
| 534 |
+
"model.language_model.layers.8.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors",
|
| 535 |
+
"model.language_model.layers.8.linear_attn.norm.weight": "model-00002-of-00003.safetensors",
|
| 536 |
+
"model.language_model.layers.8.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 537 |
+
"model.language_model.layers.8.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 538 |
+
"model.language_model.layers.8.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
|
| 539 |
+
"model.language_model.layers.8.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 540 |
+
"model.language_model.layers.8.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
|
| 541 |
+
"model.language_model.layers.8.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 542 |
+
"model.language_model.layers.8.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
|
| 543 |
+
"model.language_model.layers.8.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 544 |
+
"model.language_model.layers.9.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 545 |
+
"model.language_model.layers.9.linear_attn.A_log": "model-00002-of-00003.safetensors",
|
| 546 |
+
"model.language_model.layers.9.linear_attn.conv1d.weight": "model-00002-of-00003.safetensors",
|
| 547 |
+
"model.language_model.layers.9.linear_attn.dt_bias": "model-00002-of-00003.safetensors",
|
| 548 |
+
"model.language_model.layers.9.linear_attn.in_proj_a.weight": "model-00002-of-00003.safetensors",
|
| 549 |
+
"model.language_model.layers.9.linear_attn.in_proj_b.weight": "model-00002-of-00003.safetensors",
|
| 550 |
+
"model.language_model.layers.9.linear_attn.in_proj_qkv.weight": "model-00002-of-00003.safetensors",
|
| 551 |
+
"model.language_model.layers.9.linear_attn.in_proj_z.weight": "model-00002-of-00003.safetensors",
|
| 552 |
+
"model.language_model.layers.9.linear_attn.norm.weight": "model-00002-of-00003.safetensors",
|
| 553 |
+
"model.language_model.layers.9.linear_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 554 |
+
"model.language_model.layers.9.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 555 |
+
"model.language_model.layers.9.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
|
| 556 |
+
"model.language_model.layers.9.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 557 |
+
"model.language_model.layers.9.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
|
| 558 |
+
"model.language_model.layers.9.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 559 |
+
"model.language_model.layers.9.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
|
| 560 |
+
"model.language_model.layers.9.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 561 |
+
"model.language_model.norm.weight": "model-00003-of-00003.safetensors",
|
| 562 |
+
"model.visual.blocks.0.attn.proj.bias": "model-00001-of-00003.safetensors",
|
| 563 |
+
"model.visual.blocks.0.attn.proj.weight": "model-00001-of-00003.safetensors",
|
| 564 |
+
"model.visual.blocks.0.attn.qkv.bias": "model-00001-of-00003.safetensors",
|
| 565 |
+
"model.visual.blocks.0.attn.qkv.weight": "model-00001-of-00003.safetensors",
|
| 566 |
+
"model.visual.blocks.0.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
|
| 567 |
+
"model.visual.blocks.0.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
|
| 568 |
+
"model.visual.blocks.0.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
|
| 569 |
+
"model.visual.blocks.0.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
|
| 570 |
+
"model.visual.blocks.0.norm1.bias": "model-00001-of-00003.safetensors",
|
| 571 |
+
"model.visual.blocks.0.norm1.weight": "model-00001-of-00003.safetensors",
|
| 572 |
+
"model.visual.blocks.0.norm2.bias": "model-00001-of-00003.safetensors",
|
| 573 |
+
"model.visual.blocks.0.norm2.weight": "model-00001-of-00003.safetensors",
|
| 574 |
+
"model.visual.blocks.1.attn.proj.bias": "model-00001-of-00003.safetensors",
|
| 575 |
+
"model.visual.blocks.1.attn.proj.weight": "model-00001-of-00003.safetensors",
|
| 576 |
+
"model.visual.blocks.1.attn.qkv.bias": "model-00001-of-00003.safetensors",
|
| 577 |
+
"model.visual.blocks.1.attn.qkv.weight": "model-00001-of-00003.safetensors",
|
| 578 |
+
"model.visual.blocks.1.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
|
| 579 |
+
"model.visual.blocks.1.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
|
| 580 |
+
"model.visual.blocks.1.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
|
| 581 |
+
"model.visual.blocks.1.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
|
| 582 |
+
"model.visual.blocks.1.norm1.bias": "model-00001-of-00003.safetensors",
|
| 583 |
+
"model.visual.blocks.1.norm1.weight": "model-00001-of-00003.safetensors",
|
| 584 |
+
"model.visual.blocks.1.norm2.bias": "model-00001-of-00003.safetensors",
|
| 585 |
+
"model.visual.blocks.1.norm2.weight": "model-00001-of-00003.safetensors",
|
| 586 |
+
"model.visual.blocks.10.attn.proj.bias": "model-00001-of-00003.safetensors",
|
| 587 |
+
"model.visual.blocks.10.attn.proj.weight": "model-00001-of-00003.safetensors",
|
| 588 |
+
"model.visual.blocks.10.attn.qkv.bias": "model-00001-of-00003.safetensors",
|
| 589 |
+
"model.visual.blocks.10.attn.qkv.weight": "model-00001-of-00003.safetensors",
|
| 590 |
+
"model.visual.blocks.10.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
|
| 591 |
+
"model.visual.blocks.10.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
|
| 592 |
+
"model.visual.blocks.10.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
|
| 593 |
+
"model.visual.blocks.10.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
|
| 594 |
+
"model.visual.blocks.10.norm1.bias": "model-00001-of-00003.safetensors",
|
| 595 |
+
"model.visual.blocks.10.norm1.weight": "model-00001-of-00003.safetensors",
|
| 596 |
+
"model.visual.blocks.10.norm2.bias": "model-00001-of-00003.safetensors",
|
| 597 |
+
"model.visual.blocks.10.norm2.weight": "model-00001-of-00003.safetensors",
|
| 598 |
+
"model.visual.blocks.11.attn.proj.bias": "model-00001-of-00003.safetensors",
|
| 599 |
+
"model.visual.blocks.11.attn.proj.weight": "model-00001-of-00003.safetensors",
|
| 600 |
+
"model.visual.blocks.11.attn.qkv.bias": "model-00001-of-00003.safetensors",
|
| 601 |
+
"model.visual.blocks.11.attn.qkv.weight": "model-00001-of-00003.safetensors",
|
| 602 |
+
"model.visual.blocks.11.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
|
| 603 |
+
"model.visual.blocks.11.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
|
| 604 |
+
"model.visual.blocks.11.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
|
| 605 |
+
"model.visual.blocks.11.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
|
| 606 |
+
"model.visual.blocks.11.norm1.bias": "model-00001-of-00003.safetensors",
|
| 607 |
+
"model.visual.blocks.11.norm1.weight": "model-00001-of-00003.safetensors",
|
| 608 |
+
"model.visual.blocks.11.norm2.bias": "model-00001-of-00003.safetensors",
|
| 609 |
+
"model.visual.blocks.11.norm2.weight": "model-00001-of-00003.safetensors",
|
| 610 |
+
"model.visual.blocks.12.attn.proj.bias": "model-00001-of-00003.safetensors",
|
| 611 |
+
"model.visual.blocks.12.attn.proj.weight": "model-00001-of-00003.safetensors",
|
| 612 |
+
"model.visual.blocks.12.attn.qkv.bias": "model-00001-of-00003.safetensors",
|
| 613 |
+
"model.visual.blocks.12.attn.qkv.weight": "model-00001-of-00003.safetensors",
|
| 614 |
+
"model.visual.blocks.12.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
|
| 615 |
+
"model.visual.blocks.12.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
|
| 616 |
+
"model.visual.blocks.12.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
|
| 617 |
+
"model.visual.blocks.12.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
|
| 618 |
+
"model.visual.blocks.12.norm1.bias": "model-00001-of-00003.safetensors",
|
| 619 |
+
"model.visual.blocks.12.norm1.weight": "model-00001-of-00003.safetensors",
|
| 620 |
+
"model.visual.blocks.12.norm2.bias": "model-00001-of-00003.safetensors",
|
| 621 |
+
"model.visual.blocks.12.norm2.weight": "model-00001-of-00003.safetensors",
|
| 622 |
+
"model.visual.blocks.13.attn.proj.bias": "model-00001-of-00003.safetensors",
|
| 623 |
+
"model.visual.blocks.13.attn.proj.weight": "model-00001-of-00003.safetensors",
|
| 624 |
+
"model.visual.blocks.13.attn.qkv.bias": "model-00001-of-00003.safetensors",
|
| 625 |
+
"model.visual.blocks.13.attn.qkv.weight": "model-00001-of-00003.safetensors",
|
| 626 |
+
"model.visual.blocks.13.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
|
| 627 |
+
"model.visual.blocks.13.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
|
| 628 |
+
"model.visual.blocks.13.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
|
| 629 |
+
"model.visual.blocks.13.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
|
| 630 |
+
"model.visual.blocks.13.norm1.bias": "model-00001-of-00003.safetensors",
|
| 631 |
+
"model.visual.blocks.13.norm1.weight": "model-00001-of-00003.safetensors",
|
| 632 |
+
"model.visual.blocks.13.norm2.bias": "model-00001-of-00003.safetensors",
|
| 633 |
+
"model.visual.blocks.13.norm2.weight": "model-00001-of-00003.safetensors",
|
| 634 |
+
"model.visual.blocks.14.attn.proj.bias": "model-00001-of-00003.safetensors",
|
| 635 |
+
"model.visual.blocks.14.attn.proj.weight": "model-00001-of-00003.safetensors",
|
| 636 |
+
"model.visual.blocks.14.attn.qkv.bias": "model-00001-of-00003.safetensors",
|
| 637 |
+
"model.visual.blocks.14.attn.qkv.weight": "model-00001-of-00003.safetensors",
|
| 638 |
+
"model.visual.blocks.14.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
|
| 639 |
+
"model.visual.blocks.14.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
|
| 640 |
+
"model.visual.blocks.14.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
|
| 641 |
+
"model.visual.blocks.14.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
|
| 642 |
+
"model.visual.blocks.14.norm1.bias": "model-00001-of-00003.safetensors",
|
| 643 |
+
"model.visual.blocks.14.norm1.weight": "model-00001-of-00003.safetensors",
|
| 644 |
+
"model.visual.blocks.14.norm2.bias": "model-00001-of-00003.safetensors",
|
| 645 |
+
"model.visual.blocks.14.norm2.weight": "model-00001-of-00003.safetensors",
|
| 646 |
+
"model.visual.blocks.15.attn.proj.bias": "model-00001-of-00003.safetensors",
|
| 647 |
+
"model.visual.blocks.15.attn.proj.weight": "model-00001-of-00003.safetensors",
|
| 648 |
+
"model.visual.blocks.15.attn.qkv.bias": "model-00001-of-00003.safetensors",
|
| 649 |
+
"model.visual.blocks.15.attn.qkv.weight": "model-00001-of-00003.safetensors",
|
| 650 |
+
"model.visual.blocks.15.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
|
| 651 |
+
"model.visual.blocks.15.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
|
| 652 |
+
"model.visual.blocks.15.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
|
| 653 |
+
"model.visual.blocks.15.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
|
| 654 |
+
"model.visual.blocks.15.norm1.bias": "model-00001-of-00003.safetensors",
|
| 655 |
+
"model.visual.blocks.15.norm1.weight": "model-00001-of-00003.safetensors",
|
| 656 |
+
"model.visual.blocks.15.norm2.bias": "model-00001-of-00003.safetensors",
|
| 657 |
+
"model.visual.blocks.15.norm2.weight": "model-00001-of-00003.safetensors",
|
| 658 |
+
"model.visual.blocks.16.attn.proj.bias": "model-00001-of-00003.safetensors",
|
| 659 |
+
"model.visual.blocks.16.attn.proj.weight": "model-00001-of-00003.safetensors",
|
| 660 |
+
"model.visual.blocks.16.attn.qkv.bias": "model-00001-of-00003.safetensors",
|
| 661 |
+
"model.visual.blocks.16.attn.qkv.weight": "model-00001-of-00003.safetensors",
|
| 662 |
+
"model.visual.blocks.16.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
|
| 663 |
+
"model.visual.blocks.16.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
|
| 664 |
+
"model.visual.blocks.16.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
|
| 665 |
+
"model.visual.blocks.16.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
|
| 666 |
+
"model.visual.blocks.16.norm1.bias": "model-00001-of-00003.safetensors",
|
| 667 |
+
"model.visual.blocks.16.norm1.weight": "model-00001-of-00003.safetensors",
|
| 668 |
+
"model.visual.blocks.16.norm2.bias": "model-00001-of-00003.safetensors",
|
| 669 |
+
"model.visual.blocks.16.norm2.weight": "model-00001-of-00003.safetensors",
|
| 670 |
+
"model.visual.blocks.17.attn.proj.bias": "model-00001-of-00003.safetensors",
|
| 671 |
+
"model.visual.blocks.17.attn.proj.weight": "model-00001-of-00003.safetensors",
|
| 672 |
+
"model.visual.blocks.17.attn.qkv.bias": "model-00001-of-00003.safetensors",
|
| 673 |
+
"model.visual.blocks.17.attn.qkv.weight": "model-00001-of-00003.safetensors",
|
| 674 |
+
"model.visual.blocks.17.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
|
| 675 |
+
"model.visual.blocks.17.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
|
| 676 |
+
"model.visual.blocks.17.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
|
| 677 |
+
"model.visual.blocks.17.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
|
| 678 |
+
"model.visual.blocks.17.norm1.bias": "model-00001-of-00003.safetensors",
|
| 679 |
+
"model.visual.blocks.17.norm1.weight": "model-00001-of-00003.safetensors",
|
| 680 |
+
"model.visual.blocks.17.norm2.bias": "model-00001-of-00003.safetensors",
|
| 681 |
+
"model.visual.blocks.17.norm2.weight": "model-00001-of-00003.safetensors",
|
| 682 |
+
"model.visual.blocks.18.attn.proj.bias": "model-00001-of-00003.safetensors",
|
| 683 |
+
"model.visual.blocks.18.attn.proj.weight": "model-00001-of-00003.safetensors",
|
| 684 |
+
"model.visual.blocks.18.attn.qkv.bias": "model-00001-of-00003.safetensors",
|
| 685 |
+
"model.visual.blocks.18.attn.qkv.weight": "model-00001-of-00003.safetensors",
|
| 686 |
+
"model.visual.blocks.18.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
|
| 687 |
+
"model.visual.blocks.18.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
|
| 688 |
+
"model.visual.blocks.18.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
|
| 689 |
+
"model.visual.blocks.18.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
|
| 690 |
+
"model.visual.blocks.18.norm1.bias": "model-00001-of-00003.safetensors",
|
| 691 |
+
"model.visual.blocks.18.norm1.weight": "model-00001-of-00003.safetensors",
|
| 692 |
+
"model.visual.blocks.18.norm2.bias": "model-00001-of-00003.safetensors",
|
| 693 |
+
"model.visual.blocks.18.norm2.weight": "model-00001-of-00003.safetensors",
|
| 694 |
+
"model.visual.blocks.19.attn.proj.bias": "model-00001-of-00003.safetensors",
|
| 695 |
+
"model.visual.blocks.19.attn.proj.weight": "model-00001-of-00003.safetensors",
|
| 696 |
+
"model.visual.blocks.19.attn.qkv.bias": "model-00001-of-00003.safetensors",
|
| 697 |
+
"model.visual.blocks.19.attn.qkv.weight": "model-00001-of-00003.safetensors",
|
| 698 |
+
"model.visual.blocks.19.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
|
| 699 |
+
"model.visual.blocks.19.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
|
| 700 |
+
"model.visual.blocks.19.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
|
| 701 |
+
"model.visual.blocks.19.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
|
| 702 |
+
"model.visual.blocks.19.norm1.bias": "model-00001-of-00003.safetensors",
|
| 703 |
+
"model.visual.blocks.19.norm1.weight": "model-00001-of-00003.safetensors",
|
| 704 |
+
"model.visual.blocks.19.norm2.bias": "model-00001-of-00003.safetensors",
|
| 705 |
+
"model.visual.blocks.19.norm2.weight": "model-00001-of-00003.safetensors",
|
| 706 |
+
"model.visual.blocks.2.attn.proj.bias": "model-00001-of-00003.safetensors",
|
| 707 |
+
"model.visual.blocks.2.attn.proj.weight": "model-00001-of-00003.safetensors",
|
| 708 |
+
"model.visual.blocks.2.attn.qkv.bias": "model-00001-of-00003.safetensors",
|
| 709 |
+
"model.visual.blocks.2.attn.qkv.weight": "model-00001-of-00003.safetensors",
|
| 710 |
+
"model.visual.blocks.2.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
|
| 711 |
+
"model.visual.blocks.2.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
|
| 712 |
+
"model.visual.blocks.2.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
|
| 713 |
+
"model.visual.blocks.2.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
|
| 714 |
+
"model.visual.blocks.2.norm1.bias": "model-00001-of-00003.safetensors",
|
| 715 |
+
"model.visual.blocks.2.norm1.weight": "model-00001-of-00003.safetensors",
|
| 716 |
+
"model.visual.blocks.2.norm2.bias": "model-00001-of-00003.safetensors",
|
| 717 |
+
"model.visual.blocks.2.norm2.weight": "model-00001-of-00003.safetensors",
|
| 718 |
+
"model.visual.blocks.20.attn.proj.bias": "model-00001-of-00003.safetensors",
|
| 719 |
+
"model.visual.blocks.20.attn.proj.weight": "model-00001-of-00003.safetensors",
|
| 720 |
+
"model.visual.blocks.20.attn.qkv.bias": "model-00001-of-00003.safetensors",
|
| 721 |
+
"model.visual.blocks.20.attn.qkv.weight": "model-00001-of-00003.safetensors",
|
| 722 |
+
"model.visual.blocks.20.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
|
| 723 |
+
"model.visual.blocks.20.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
|
| 724 |
+
"model.visual.blocks.20.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
|
| 725 |
+
"model.visual.blocks.20.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
|
| 726 |
+
"model.visual.blocks.20.norm1.bias": "model-00001-of-00003.safetensors",
|
| 727 |
+
"model.visual.blocks.20.norm1.weight": "model-00001-of-00003.safetensors",
|
| 728 |
+
"model.visual.blocks.20.norm2.bias": "model-00001-of-00003.safetensors",
|
| 729 |
+
"model.visual.blocks.20.norm2.weight": "model-00001-of-00003.safetensors",
|
| 730 |
+
"model.visual.blocks.21.attn.proj.bias": "model-00001-of-00003.safetensors",
|
| 731 |
+
"model.visual.blocks.21.attn.proj.weight": "model-00001-of-00003.safetensors",
|
| 732 |
+
"model.visual.blocks.21.attn.qkv.bias": "model-00001-of-00003.safetensors",
|
| 733 |
+
"model.visual.blocks.21.attn.qkv.weight": "model-00001-of-00003.safetensors",
|
| 734 |
+
"model.visual.blocks.21.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
|
| 735 |
+
"model.visual.blocks.21.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
|
| 736 |
+
"model.visual.blocks.21.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
|
| 737 |
+
"model.visual.blocks.21.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
|
| 738 |
+
"model.visual.blocks.21.norm1.bias": "model-00001-of-00003.safetensors",
|
| 739 |
+
"model.visual.blocks.21.norm1.weight": "model-00001-of-00003.safetensors",
|
| 740 |
+
"model.visual.blocks.21.norm2.bias": "model-00001-of-00003.safetensors",
|
| 741 |
+
"model.visual.blocks.21.norm2.weight": "model-00001-of-00003.safetensors",
|
| 742 |
+
"model.visual.blocks.22.attn.proj.bias": "model-00001-of-00003.safetensors",
|
| 743 |
+
"model.visual.blocks.22.attn.proj.weight": "model-00001-of-00003.safetensors",
|
| 744 |
+
"model.visual.blocks.22.attn.qkv.bias": "model-00001-of-00003.safetensors",
|
| 745 |
+
"model.visual.blocks.22.attn.qkv.weight": "model-00001-of-00003.safetensors",
|
| 746 |
+
"model.visual.blocks.22.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
|
| 747 |
+
"model.visual.blocks.22.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
|
| 748 |
+
"model.visual.blocks.22.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
|
| 749 |
+
"model.visual.blocks.22.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
|
| 750 |
+
"model.visual.blocks.22.norm1.bias": "model-00001-of-00003.safetensors",
|
| 751 |
+
"model.visual.blocks.22.norm1.weight": "model-00001-of-00003.safetensors",
|
| 752 |
+
"model.visual.blocks.22.norm2.bias": "model-00001-of-00003.safetensors",
|
| 753 |
+
"model.visual.blocks.22.norm2.weight": "model-00001-of-00003.safetensors",
|
| 754 |
+
"model.visual.blocks.23.attn.proj.bias": "model-00001-of-00003.safetensors",
|
| 755 |
+
"model.visual.blocks.23.attn.proj.weight": "model-00001-of-00003.safetensors",
|
| 756 |
+
"model.visual.blocks.23.attn.qkv.bias": "model-00001-of-00003.safetensors",
|
| 757 |
+
"model.visual.blocks.23.attn.qkv.weight": "model-00001-of-00003.safetensors",
|
| 758 |
+
"model.visual.blocks.23.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
|
| 759 |
+
"model.visual.blocks.23.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
|
| 760 |
+
"model.visual.blocks.23.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
|
| 761 |
+
"model.visual.blocks.23.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
|
| 762 |
+
"model.visual.blocks.23.norm1.bias": "model-00001-of-00003.safetensors",
|
| 763 |
+
"model.visual.blocks.23.norm1.weight": "model-00001-of-00003.safetensors",
|
| 764 |
+
"model.visual.blocks.23.norm2.bias": "model-00001-of-00003.safetensors",
|
| 765 |
+
"model.visual.blocks.23.norm2.weight": "model-00001-of-00003.safetensors",
|
| 766 |
+
"model.visual.blocks.24.attn.proj.bias": "model-00001-of-00003.safetensors",
|
| 767 |
+
"model.visual.blocks.24.attn.proj.weight": "model-00001-of-00003.safetensors",
|
| 768 |
+
"model.visual.blocks.24.attn.qkv.bias": "model-00001-of-00003.safetensors",
|
| 769 |
+
"model.visual.blocks.24.attn.qkv.weight": "model-00001-of-00003.safetensors",
|
| 770 |
+
"model.visual.blocks.24.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
|
| 771 |
+
"model.visual.blocks.24.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
|
| 772 |
+
"model.visual.blocks.24.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
|
| 773 |
+
"model.visual.blocks.24.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
|
| 774 |
+
"model.visual.blocks.24.norm1.bias": "model-00001-of-00003.safetensors",
|
| 775 |
+
"model.visual.blocks.24.norm1.weight": "model-00001-of-00003.safetensors",
|
| 776 |
+
"model.visual.blocks.24.norm2.bias": "model-00001-of-00003.safetensors",
|
| 777 |
+
"model.visual.blocks.24.norm2.weight": "model-00001-of-00003.safetensors",
|
| 778 |
+
"model.visual.blocks.25.attn.proj.bias": "model-00001-of-00003.safetensors",
|
| 779 |
+
"model.visual.blocks.25.attn.proj.weight": "model-00001-of-00003.safetensors",
|
| 780 |
+
"model.visual.blocks.25.attn.qkv.bias": "model-00001-of-00003.safetensors",
|
| 781 |
+
"model.visual.blocks.25.attn.qkv.weight": "model-00001-of-00003.safetensors",
|
| 782 |
+
"model.visual.blocks.25.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
|
| 783 |
+
"model.visual.blocks.25.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
|
| 784 |
+
"model.visual.blocks.25.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
|
| 785 |
+
"model.visual.blocks.25.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
|
| 786 |
+
"model.visual.blocks.25.norm1.bias": "model-00001-of-00003.safetensors",
|
| 787 |
+
"model.visual.blocks.25.norm1.weight": "model-00001-of-00003.safetensors",
|
| 788 |
+
"model.visual.blocks.25.norm2.bias": "model-00001-of-00003.safetensors",
|
| 789 |
+
"model.visual.blocks.25.norm2.weight": "model-00001-of-00003.safetensors",
|
| 790 |
+
"model.visual.blocks.26.attn.proj.bias": "model-00001-of-00003.safetensors",
|
| 791 |
+
"model.visual.blocks.26.attn.proj.weight": "model-00001-of-00003.safetensors",
|
| 792 |
+
"model.visual.blocks.26.attn.qkv.bias": "model-00001-of-00003.safetensors",
|
| 793 |
+
"model.visual.blocks.26.attn.qkv.weight": "model-00001-of-00003.safetensors",
|
| 794 |
+
"model.visual.blocks.26.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
|
| 795 |
+
"model.visual.blocks.26.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
|
| 796 |
+
"model.visual.blocks.26.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
|
| 797 |
+
"model.visual.blocks.26.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
|
| 798 |
+
"model.visual.blocks.26.norm1.bias": "model-00001-of-00003.safetensors",
|
| 799 |
+
"model.visual.blocks.26.norm1.weight": "model-00001-of-00003.safetensors",
|
| 800 |
+
"model.visual.blocks.26.norm2.bias": "model-00001-of-00003.safetensors",
|
| 801 |
+
"model.visual.blocks.26.norm2.weight": "model-00001-of-00003.safetensors",
|
| 802 |
+
"model.visual.blocks.3.attn.proj.bias": "model-00001-of-00003.safetensors",
|
| 803 |
+
"model.visual.blocks.3.attn.proj.weight": "model-00001-of-00003.safetensors",
|
| 804 |
+
"model.visual.blocks.3.attn.qkv.bias": "model-00001-of-00003.safetensors",
|
| 805 |
+
"model.visual.blocks.3.attn.qkv.weight": "model-00001-of-00003.safetensors",
|
| 806 |
+
"model.visual.blocks.3.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
|
| 807 |
+
"model.visual.blocks.3.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
|
| 808 |
+
"model.visual.blocks.3.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
|
| 809 |
+
"model.visual.blocks.3.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
|
| 810 |
+
"model.visual.blocks.3.norm1.bias": "model-00001-of-00003.safetensors",
|
| 811 |
+
"model.visual.blocks.3.norm1.weight": "model-00001-of-00003.safetensors",
|
| 812 |
+
"model.visual.blocks.3.norm2.bias": "model-00001-of-00003.safetensors",
|
| 813 |
+
"model.visual.blocks.3.norm2.weight": "model-00001-of-00003.safetensors",
|
| 814 |
+
"model.visual.blocks.4.attn.proj.bias": "model-00001-of-00003.safetensors",
|
| 815 |
+
"model.visual.blocks.4.attn.proj.weight": "model-00001-of-00003.safetensors",
|
| 816 |
+
"model.visual.blocks.4.attn.qkv.bias": "model-00001-of-00003.safetensors",
|
| 817 |
+
"model.visual.blocks.4.attn.qkv.weight": "model-00001-of-00003.safetensors",
|
| 818 |
+
"model.visual.blocks.4.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
|
| 819 |
+
"model.visual.blocks.4.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
|
| 820 |
+
"model.visual.blocks.4.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
|
| 821 |
+
"model.visual.blocks.4.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
|
| 822 |
+
"model.visual.blocks.4.norm1.bias": "model-00001-of-00003.safetensors",
|
| 823 |
+
"model.visual.blocks.4.norm1.weight": "model-00001-of-00003.safetensors",
|
| 824 |
+
"model.visual.blocks.4.norm2.bias": "model-00001-of-00003.safetensors",
|
| 825 |
+
"model.visual.blocks.4.norm2.weight": "model-00001-of-00003.safetensors",
|
| 826 |
+
"model.visual.blocks.5.attn.proj.bias": "model-00001-of-00003.safetensors",
|
| 827 |
+
"model.visual.blocks.5.attn.proj.weight": "model-00001-of-00003.safetensors",
|
| 828 |
+
"model.visual.blocks.5.attn.qkv.bias": "model-00001-of-00003.safetensors",
|
| 829 |
+
"model.visual.blocks.5.attn.qkv.weight": "model-00001-of-00003.safetensors",
|
| 830 |
+
"model.visual.blocks.5.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
|
| 831 |
+
"model.visual.blocks.5.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
|
| 832 |
+
"model.visual.blocks.5.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
|
| 833 |
+
"model.visual.blocks.5.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
|
| 834 |
+
"model.visual.blocks.5.norm1.bias": "model-00001-of-00003.safetensors",
|
| 835 |
+
"model.visual.blocks.5.norm1.weight": "model-00001-of-00003.safetensors",
|
| 836 |
+
"model.visual.blocks.5.norm2.bias": "model-00001-of-00003.safetensors",
|
| 837 |
+
"model.visual.blocks.5.norm2.weight": "model-00001-of-00003.safetensors",
|
| 838 |
+
"model.visual.blocks.6.attn.proj.bias": "model-00001-of-00003.safetensors",
|
| 839 |
+
"model.visual.blocks.6.attn.proj.weight": "model-00001-of-00003.safetensors",
|
| 840 |
+
"model.visual.blocks.6.attn.qkv.bias": "model-00001-of-00003.safetensors",
|
| 841 |
+
"model.visual.blocks.6.attn.qkv.weight": "model-00001-of-00003.safetensors",
|
| 842 |
+
"model.visual.blocks.6.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
|
| 843 |
+
"model.visual.blocks.6.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
|
| 844 |
+
"model.visual.blocks.6.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
|
| 845 |
+
"model.visual.blocks.6.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
|
| 846 |
+
"model.visual.blocks.6.norm1.bias": "model-00001-of-00003.safetensors",
|
| 847 |
+
"model.visual.blocks.6.norm1.weight": "model-00001-of-00003.safetensors",
|
| 848 |
+
"model.visual.blocks.6.norm2.bias": "model-00001-of-00003.safetensors",
|
| 849 |
+
"model.visual.blocks.6.norm2.weight": "model-00001-of-00003.safetensors",
|
| 850 |
+
"model.visual.blocks.7.attn.proj.bias": "model-00001-of-00003.safetensors",
|
| 851 |
+
"model.visual.blocks.7.attn.proj.weight": "model-00001-of-00003.safetensors",
|
| 852 |
+
"model.visual.blocks.7.attn.qkv.bias": "model-00001-of-00003.safetensors",
|
| 853 |
+
"model.visual.blocks.7.attn.qkv.weight": "model-00001-of-00003.safetensors",
|
| 854 |
+
"model.visual.blocks.7.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
|
| 855 |
+
"model.visual.blocks.7.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
|
| 856 |
+
"model.visual.blocks.7.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
|
| 857 |
+
"model.visual.blocks.7.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
|
| 858 |
+
"model.visual.blocks.7.norm1.bias": "model-00001-of-00003.safetensors",
|
| 859 |
+
"model.visual.blocks.7.norm1.weight": "model-00001-of-00003.safetensors",
|
| 860 |
+
"model.visual.blocks.7.norm2.bias": "model-00001-of-00003.safetensors",
|
| 861 |
+
"model.visual.blocks.7.norm2.weight": "model-00001-of-00003.safetensors",
|
| 862 |
+
"model.visual.blocks.8.attn.proj.bias": "model-00001-of-00003.safetensors",
|
| 863 |
+
"model.visual.blocks.8.attn.proj.weight": "model-00001-of-00003.safetensors",
|
| 864 |
+
"model.visual.blocks.8.attn.qkv.bias": "model-00001-of-00003.safetensors",
|
| 865 |
+
"model.visual.blocks.8.attn.qkv.weight": "model-00001-of-00003.safetensors",
|
| 866 |
+
"model.visual.blocks.8.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
|
| 867 |
+
"model.visual.blocks.8.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
|
| 868 |
+
"model.visual.blocks.8.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
|
| 869 |
+
"model.visual.blocks.8.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
|
| 870 |
+
"model.visual.blocks.8.norm1.bias": "model-00001-of-00003.safetensors",
|
| 871 |
+
"model.visual.blocks.8.norm1.weight": "model-00001-of-00003.safetensors",
|
| 872 |
+
"model.visual.blocks.8.norm2.bias": "model-00001-of-00003.safetensors",
|
| 873 |
+
"model.visual.blocks.8.norm2.weight": "model-00001-of-00003.safetensors",
|
| 874 |
+
"model.visual.blocks.9.attn.proj.bias": "model-00001-of-00003.safetensors",
|
| 875 |
+
"model.visual.blocks.9.attn.proj.weight": "model-00001-of-00003.safetensors",
|
| 876 |
+
"model.visual.blocks.9.attn.qkv.bias": "model-00001-of-00003.safetensors",
|
| 877 |
+
"model.visual.blocks.9.attn.qkv.weight": "model-00001-of-00003.safetensors",
|
| 878 |
+
"model.visual.blocks.9.mlp.linear_fc1.bias": "model-00001-of-00003.safetensors",
|
| 879 |
+
"model.visual.blocks.9.mlp.linear_fc1.weight": "model-00001-of-00003.safetensors",
|
| 880 |
+
"model.visual.blocks.9.mlp.linear_fc2.bias": "model-00001-of-00003.safetensors",
|
| 881 |
+
"model.visual.blocks.9.mlp.linear_fc2.weight": "model-00001-of-00003.safetensors",
|
| 882 |
+
"model.visual.blocks.9.norm1.bias": "model-00001-of-00003.safetensors",
|
| 883 |
+
"model.visual.blocks.9.norm1.weight": "model-00001-of-00003.safetensors",
|
| 884 |
+
"model.visual.blocks.9.norm2.bias": "model-00001-of-00003.safetensors",
|
| 885 |
+
"model.visual.blocks.9.norm2.weight": "model-00001-of-00003.safetensors",
|
| 886 |
+
"model.visual.merger.linear_fc1.bias": "model-00001-of-00003.safetensors",
|
| 887 |
+
"model.visual.merger.linear_fc1.weight": "model-00001-of-00003.safetensors",
|
| 888 |
+
"model.visual.merger.linear_fc2.bias": "model-00001-of-00003.safetensors",
|
| 889 |
+
"model.visual.merger.linear_fc2.weight": "model-00001-of-00003.safetensors",
|
| 890 |
+
"model.visual.merger.norm.bias": "model-00001-of-00003.safetensors",
|
| 891 |
+
"model.visual.merger.norm.weight": "model-00001-of-00003.safetensors",
|
| 892 |
+
"model.visual.patch_embed.proj.bias": "model-00001-of-00003.safetensors",
|
| 893 |
+
"model.visual.patch_embed.proj.weight": "model-00001-of-00003.safetensors",
|
| 894 |
+
"model.visual.pos_embed.weight": "model-00001-of-00003.safetensors"
|
| 895 |
+
}
|
| 896 |
+
}
|
processor_config.json
ADDED
|
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"image_processor": {
|
| 3 |
+
"data_format": "channels_first",
|
| 4 |
+
"do_convert_rgb": true,
|
| 5 |
+
"do_normalize": true,
|
| 6 |
+
"do_rescale": true,
|
| 7 |
+
"do_resize": true,
|
| 8 |
+
"image_mean": [
|
| 9 |
+
0.5,
|
| 10 |
+
0.5,
|
| 11 |
+
0.5
|
| 12 |
+
],
|
| 13 |
+
"image_processor_type": "Qwen2VLImageProcessor",
|
| 14 |
+
"image_std": [
|
| 15 |
+
0.5,
|
| 16 |
+
0.5,
|
| 17 |
+
0.5
|
| 18 |
+
],
|
| 19 |
+
"merge_size": 2,
|
| 20 |
+
"patch_size": 16,
|
| 21 |
+
"resample": 3,
|
| 22 |
+
"rescale_factor": 0.00392156862745098,
|
| 23 |
+
"size": {
|
| 24 |
+
"longest_edge": 16777216,
|
| 25 |
+
"shortest_edge": 65536
|
| 26 |
+
},
|
| 27 |
+
"temporal_patch_size": 2
|
| 28 |
+
},
|
| 29 |
+
"processor_class": "Qwen3VLProcessor",
|
| 30 |
+
"video_processor": {
|
| 31 |
+
"data_format": "channels_first",
|
| 32 |
+
"default_to_square": true,
|
| 33 |
+
"do_convert_rgb": true,
|
| 34 |
+
"do_normalize": true,
|
| 35 |
+
"do_rescale": true,
|
| 36 |
+
"do_resize": true,
|
| 37 |
+
"do_sample_frames": true,
|
| 38 |
+
"fps": 2,
|
| 39 |
+
"image_mean": [
|
| 40 |
+
0.5,
|
| 41 |
+
0.5,
|
| 42 |
+
0.5
|
| 43 |
+
],
|
| 44 |
+
"image_std": [
|
| 45 |
+
0.5,
|
| 46 |
+
0.5,
|
| 47 |
+
0.5
|
| 48 |
+
],
|
| 49 |
+
"max_frames": 768,
|
| 50 |
+
"max_video_tokens": 768,
|
| 51 |
+
"merge_size": 2,
|
| 52 |
+
"min_frames": 4,
|
| 53 |
+
"patch_size": 16,
|
| 54 |
+
"resample": 3,
|
| 55 |
+
"rescale_factor": 0.00392156862745098,
|
| 56 |
+
"return_metadata": false,
|
| 57 |
+
"size": {
|
| 58 |
+
"longest_edge": 25165824,
|
| 59 |
+
"shortest_edge": 4096
|
| 60 |
+
},
|
| 61 |
+
"temporal_patch_size": 2,
|
| 62 |
+
"video_processor_type": "Qwen3VLVideoProcessor"
|
| 63 |
+
}
|
| 64 |
+
}
|
recipe.yaml
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
default_stage:
|
| 2 |
+
default_modifiers:
|
| 3 |
+
QuantizationModifier:
|
| 4 |
+
targets: [Linear]
|
| 5 |
+
ignore: ['re:.*lm_head', 're:.*embed_tokens$', 're:.*visual.*', 're:.*model.visual.*',
|
| 6 |
+
're:.*linear_attn.*']
|
| 7 |
+
scheme: FP8_DYNAMIC
|
| 8 |
+
bypass_divisibility_checks: false
|
| 9 |
+
requires_calibration_data: false
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
|
| 3 |
+
size 19989325
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"audio_bos_token": "<|audio_start|>",
|
| 4 |
+
"audio_eos_token": "<|audio_end|>",
|
| 5 |
+
"audio_token": "<|audio_pad|>",
|
| 6 |
+
"backend": "tokenizers",
|
| 7 |
+
"bos_token": null,
|
| 8 |
+
"clean_up_tokenization_spaces": false,
|
| 9 |
+
"eos_token": "<|im_end|>",
|
| 10 |
+
"errors": "replace",
|
| 11 |
+
"image_token": "<|image_pad|>",
|
| 12 |
+
"is_local": false,
|
| 13 |
+
"local_files_only": false,
|
| 14 |
+
"model_max_length": 262144,
|
| 15 |
+
"model_specific_special_tokens": {
|
| 16 |
+
"audio_bos_token": "<|audio_start|>",
|
| 17 |
+
"audio_eos_token": "<|audio_end|>",
|
| 18 |
+
"audio_token": "<|audio_pad|>",
|
| 19 |
+
"image_token": "<|image_pad|>",
|
| 20 |
+
"video_token": "<|video_pad|>",
|
| 21 |
+
"vision_bos_token": "<|vision_start|>",
|
| 22 |
+
"vision_eos_token": "<|vision_end|>"
|
| 23 |
+
},
|
| 24 |
+
"pad_token": "<|endoftext|>",
|
| 25 |
+
"pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
|
| 26 |
+
"processor_class": "Qwen3VLProcessor",
|
| 27 |
+
"split_special_tokens": false,
|
| 28 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 29 |
+
"unk_token": null,
|
| 30 |
+
"video_token": "<|video_pad|>",
|
| 31 |
+
"vision_bos_token": "<|vision_start|>",
|
| 32 |
+
"vision_eos_token": "<|vision_end|>"
|
| 33 |
+
}
|