Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- chat_template.jinja +315 -0
- config.json +913 -0
- export_metadata.json +3 -0
- generation_config.json +11 -0
- model.safetensors +3 -0
- recipe.yaml +8 -0
- tokenizer.json +3 -0
- tokenizer_config.json +17 -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 +1,315 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{# Copyright 2025-present Unsloth. Apache 2.0 License. Unsloth chat template fixes. Edited from ggml-org & OpenAI #}
|
| 2 |
+
{#-
|
| 3 |
+
In addition to the normal inputs of `messages` and `tools`, this template also accepts the
|
| 4 |
+
following kwargs:
|
| 5 |
+
- "builtin_tools": A list, can contain "browser" and/or "python".
|
| 6 |
+
- "model_identity": A string that optionally describes the model identity.
|
| 7 |
+
- "reasoning_effort": A string that describes the reasoning effort, defaults to "medium".
|
| 8 |
+
#}
|
| 9 |
+
|
| 10 |
+
{#- Tool Definition Rendering ============================================== #}
|
| 11 |
+
{%- macro render_typescript_type(param_spec, required_params, is_nullable=false) -%}
|
| 12 |
+
{%- if param_spec.type == "array" -%}
|
| 13 |
+
{%- if param_spec['items'] -%}
|
| 14 |
+
{%- if param_spec['items']['type'] == "string" -%}
|
| 15 |
+
{{- "string[]" }}
|
| 16 |
+
{%- elif param_spec['items']['type'] == "number" -%}
|
| 17 |
+
{{- "number[]" }}
|
| 18 |
+
{%- elif param_spec['items']['type'] == "integer" -%}
|
| 19 |
+
{{- "number[]" }}
|
| 20 |
+
{%- elif param_spec['items']['type'] == "boolean" -%}
|
| 21 |
+
{{- "boolean[]" }}
|
| 22 |
+
{%- else -%}
|
| 23 |
+
{%- set inner_type = render_typescript_type(param_spec['items'], required_params) -%}
|
| 24 |
+
{%- if inner_type == "object | object" or inner_type|length > 50 -%}
|
| 25 |
+
{{- "any[]" }}
|
| 26 |
+
{%- else -%}
|
| 27 |
+
{{- inner_type + "[]" }}
|
| 28 |
+
{%- endif -%}
|
| 29 |
+
{%- endif -%}
|
| 30 |
+
{%- if param_spec.nullable -%}
|
| 31 |
+
{{- " | null" }}
|
| 32 |
+
{%- endif -%}
|
| 33 |
+
{%- else -%}
|
| 34 |
+
{{- "any[]" }}
|
| 35 |
+
{%- if param_spec.nullable -%}
|
| 36 |
+
{{- " | null" }}
|
| 37 |
+
{%- endif -%}
|
| 38 |
+
{%- endif -%}
|
| 39 |
+
{%- elif param_spec.type is defined and param_spec.type is iterable and param_spec.type is not string and param_spec.type is not mapping and param_spec.type[0] is defined -%}
|
| 40 |
+
{#- Handle array of types like ["object", "object"] from Union[dict, list] #}
|
| 41 |
+
{%- if param_spec.type | length > 1 -%}
|
| 42 |
+
{{- param_spec.type | join(" | ") }}
|
| 43 |
+
{%- else -%}
|
| 44 |
+
{{- param_spec.type[0] }}
|
| 45 |
+
{%- endif -%}
|
| 46 |
+
{%- elif param_spec.oneOf -%}
|
| 47 |
+
{#- Handle oneOf schemas - check for complex unions and fallback to any #}
|
| 48 |
+
{%- set has_object_variants = false -%}
|
| 49 |
+
{%- for variant in param_spec.oneOf -%}
|
| 50 |
+
{%- if variant.type == "object" -%}
|
| 51 |
+
{%- set has_object_variants = true -%}
|
| 52 |
+
{%- endif -%}
|
| 53 |
+
{%- endfor -%}
|
| 54 |
+
{%- if has_object_variants and param_spec.oneOf|length > 1 -%}
|
| 55 |
+
{{- "any" }}
|
| 56 |
+
{%- else -%}
|
| 57 |
+
{%- for variant in param_spec.oneOf -%}
|
| 58 |
+
{{- render_typescript_type(variant, required_params) -}}
|
| 59 |
+
{%- if variant.description %}
|
| 60 |
+
{{- "// " + variant.description }}
|
| 61 |
+
{%- endif -%}
|
| 62 |
+
{%- if variant.default is defined %}
|
| 63 |
+
{{ "// default: " + variant.default|tojson }}
|
| 64 |
+
{%- endif -%}
|
| 65 |
+
{%- if not loop.last %}
|
| 66 |
+
{{- " | " }}
|
| 67 |
+
{% endif -%}
|
| 68 |
+
{%- endfor -%}
|
| 69 |
+
{%- endif -%}
|
| 70 |
+
{%- elif param_spec.type == "string" -%}
|
| 71 |
+
{%- if param_spec.enum -%}
|
| 72 |
+
{{- '"' + param_spec.enum|join('" | "') + '"' -}}
|
| 73 |
+
{%- else -%}
|
| 74 |
+
{{- "string" }}
|
| 75 |
+
{%- if param_spec.nullable %}
|
| 76 |
+
{{- " | null" }}
|
| 77 |
+
{%- endif -%}
|
| 78 |
+
{%- endif -%}
|
| 79 |
+
{%- elif param_spec.type == "number" -%}
|
| 80 |
+
{{- "number" }}
|
| 81 |
+
{%- elif param_spec.type == "integer" -%}
|
| 82 |
+
{{- "number" }}
|
| 83 |
+
{%- elif param_spec.type == "boolean" -%}
|
| 84 |
+
{{- "boolean" }}
|
| 85 |
+
|
| 86 |
+
{%- elif param_spec.type == "object" -%}
|
| 87 |
+
{%- if param_spec.properties -%}
|
| 88 |
+
{{- "{\n" }}
|
| 89 |
+
{%- for prop_name, prop_spec in param_spec.properties.items() -%}
|
| 90 |
+
{{- prop_name -}}
|
| 91 |
+
{%- if prop_name not in (param_spec.required or []) -%}
|
| 92 |
+
{{- "?" }}
|
| 93 |
+
{%- endif -%}
|
| 94 |
+
{{- ": " }}
|
| 95 |
+
{{ render_typescript_type(prop_spec, param_spec.required or []) }}
|
| 96 |
+
{%- if not loop.last -%}
|
| 97 |
+
{{-", " }}
|
| 98 |
+
{%- endif -%}
|
| 99 |
+
{%- endfor -%}
|
| 100 |
+
{{- "}" }}
|
| 101 |
+
{%- else -%}
|
| 102 |
+
{{- "object" }}
|
| 103 |
+
{%- endif -%}
|
| 104 |
+
{%- else -%}
|
| 105 |
+
{{- "any" }}
|
| 106 |
+
{%- endif -%}
|
| 107 |
+
{%- endmacro -%}
|
| 108 |
+
|
| 109 |
+
{%- macro render_tool_namespace(namespace_name, tools) -%}
|
| 110 |
+
{{- "## " + namespace_name + "\n\n" }}
|
| 111 |
+
{{- "namespace " + namespace_name + " {\n\n" }}
|
| 112 |
+
{%- for tool in tools %}
|
| 113 |
+
{%- set tool = tool.function %}
|
| 114 |
+
{{- "// " + tool.description + "\n" }}
|
| 115 |
+
{{- "type "+ tool.name + " = " }}
|
| 116 |
+
{%- if tool.parameters and tool.parameters.properties -%}
|
| 117 |
+
{{- "(_: " }}
|
| 118 |
+
{{- "{\n" }}
|
| 119 |
+
{%- for param_name, param_spec in tool.parameters.properties.items() %}
|
| 120 |
+
{{- "// " + param_spec.description + "\n" }}
|
| 121 |
+
{{- param_name }}
|
| 122 |
+
{%- if param_name not in (tool.parameters.required or []) -%}
|
| 123 |
+
{{- "?" }}
|
| 124 |
+
{%- endif -%}
|
| 125 |
+
{{- ": " }}
|
| 126 |
+
{{- render_typescript_type(param_spec, tool.parameters.required or []) }}
|
| 127 |
+
{%- if param_spec.default is defined -%}
|
| 128 |
+
{%- if param_spec.enum %}
|
| 129 |
+
{{- ", // default: " + param_spec.default }}
|
| 130 |
+
{%- elif param_spec.oneOf %}
|
| 131 |
+
{{- "// default: " + param_spec.default }}
|
| 132 |
+
{%- else %}
|
| 133 |
+
{{- ", // default: " + param_spec.default|tojson }}
|
| 134 |
+
{%- endif -%}
|
| 135 |
+
{%- endif -%}
|
| 136 |
+
{%- if not loop.last %}
|
| 137 |
+
{{- ",\n" }}
|
| 138 |
+
{%- else %}
|
| 139 |
+
{{- "\n" }}
|
| 140 |
+
{%- endif -%}
|
| 141 |
+
{%- endfor %}
|
| 142 |
+
{{- "}) => any;\n\n" }}
|
| 143 |
+
{%- else -%}
|
| 144 |
+
{{- "() => any;\n\n" }}
|
| 145 |
+
{%- endif -%}
|
| 146 |
+
{%- endfor %}
|
| 147 |
+
{{- "} // namespace " + namespace_name }}
|
| 148 |
+
{%- endmacro -%}
|
| 149 |
+
|
| 150 |
+
{%- macro render_builtin_tools(browser_tool, python_tool) -%}
|
| 151 |
+
{%- if browser_tool %}
|
| 152 |
+
{{- "## browser\n\n" }}
|
| 153 |
+
{{- "// Tool for browsing.\n" }}
|
| 154 |
+
{{- "// The `cursor` appears in brackets before each browsing display: `[{cursor}]`.\n" }}
|
| 155 |
+
{{- "// Cite information from the tool using the following format:\n" }}
|
| 156 |
+
{{- "// `【{cursor}†L{line_start}(-L{line_end})?】`, for example: `【6†L9-L11】` or `【8†L3】`.\n" }}
|
| 157 |
+
{{- "// Do not quote more than 10 words directly from the tool output.\n" }}
|
| 158 |
+
{{- "// sources=web (default: web)\n" }}
|
| 159 |
+
{{- "namespace browser {\n\n" }}
|
| 160 |
+
{{- "// Searches for information related to `query` and displays `topn` results.\n" }}
|
| 161 |
+
{{- "type search = (_: {\n" }}
|
| 162 |
+
{{- "query: string,\n" }}
|
| 163 |
+
{{- "topn?: number, // default: 10\n" }}
|
| 164 |
+
{{- "source?: string,\n" }}
|
| 165 |
+
{{- "}) => any;\n\n" }}
|
| 166 |
+
{{- "// Opens the link `id` from the page indicated by `cursor` starting at line number `loc`, showing `num_lines` lines.\n" }}
|
| 167 |
+
{{- "// Valid link ids are displayed with the formatting: `【{id}†.*】`.\n" }}
|
| 168 |
+
{{- "// If `cursor` is not provided, the most recent page is implied.\n" }}
|
| 169 |
+
{{- "// If `id` is a string, it is treated as a fully qualified URL associated with `source`.\n" }}
|
| 170 |
+
{{- "// If `loc` is not provided, the viewport will be positioned at the beginning of the document or centered on the most relevant passage, if available.\n" }}
|
| 171 |
+
{{- "// Use this function without `id` to scroll to a new location of an opened page.\n" }}
|
| 172 |
+
{{- "type open = (_: {\n" }}
|
| 173 |
+
{{- "id?: number | string, // default: -1\n" }}
|
| 174 |
+
{{- "cursor?: number, // default: -1\n" }}
|
| 175 |
+
{{- "loc?: number, // default: -1\n" }}
|
| 176 |
+
{{- "num_lines?: number, // default: -1\n" }}
|
| 177 |
+
{{- "view_source?: boolean, // default: false\n" }}
|
| 178 |
+
{{- "source?: string,\n" }}
|
| 179 |
+
{{- "}) => any;\n\n" }}
|
| 180 |
+
{{- "// Finds exact matches of `pattern` in the current page, or the page given by `cursor`.\n" }}
|
| 181 |
+
{{- "type find = (_: {\n" }}
|
| 182 |
+
{{- "pattern: string,\n" }}
|
| 183 |
+
{{- "cursor?: number, // default: -1\n" }}
|
| 184 |
+
{{- "}) => any;\n\n" }}
|
| 185 |
+
{{- "} // namespace browser\n\n" }}
|
| 186 |
+
{%- endif -%}
|
| 187 |
+
|
| 188 |
+
{%- if python_tool %}
|
| 189 |
+
{{- "## python\n\n" }}
|
| 190 |
+
{{- "Use this tool to execute Python code in your chain of thought. The code will not be shown to the user. This tool should be used for internal reasoning, but not for code that is intended to be visible to the user (e.g. when creating plots, tables, or files).\n\n" }}
|
| 191 |
+
{{- "When you send a message containing Python code to python, it will be executed in a stateful Jupyter notebook environment. python will respond with the output of the execution or time out after 120.0 seconds. The drive at '/mnt/data' can be used to save and persist user files. Internet access for this session is UNKNOWN. Depends on the cluster.\n\n" }}
|
| 192 |
+
{%- endif -%}
|
| 193 |
+
{%- endmacro -%}
|
| 194 |
+
|
| 195 |
+
{#- System Message Construction ============================================ #}
|
| 196 |
+
{%- macro build_system_message() -%}
|
| 197 |
+
{%- if model_identity is not defined %}
|
| 198 |
+
{{- "You are ChatGPT, a large language model trained by OpenAI.\n" -}}
|
| 199 |
+
{%- else %}
|
| 200 |
+
{{- model_identity }}
|
| 201 |
+
{%- endif %}
|
| 202 |
+
{{- "Knowledge cutoff: 2024-06\n" }}
|
| 203 |
+
{{- "Current date: " + strftime_now("%Y-%m-%d") + "\n\n" }}
|
| 204 |
+
{%- if reasoning_effort is not defined %}
|
| 205 |
+
{%- set reasoning_effort = "medium" %}
|
| 206 |
+
{%- endif %}
|
| 207 |
+
{{- "Reasoning: " + reasoning_effort + "\n\n" }}
|
| 208 |
+
{%- if builtin_tools is defined %}
|
| 209 |
+
{{- "# Tools\n\n" }}
|
| 210 |
+
{%- set available_builtin_tools = namespace(browser=false, python=false) %}
|
| 211 |
+
{%- for tool in builtin_tools %}
|
| 212 |
+
{%- if tool == "browser" %}
|
| 213 |
+
{%- set available_builtin_tools.browser = true %}
|
| 214 |
+
{%- elif tool == "python" %}
|
| 215 |
+
{%- set available_builtin_tools.python = true %}
|
| 216 |
+
{%- endif %}
|
| 217 |
+
{%- endfor %}
|
| 218 |
+
{{- render_builtin_tools(available_builtin_tools.browser, available_builtin_tools.python) }}
|
| 219 |
+
{%- endif -%}
|
| 220 |
+
{{- "# Valid channels: analysis, commentary, final. Channel must be included for every message." }}
|
| 221 |
+
{%- if tools is defined -%}
|
| 222 |
+
{{- "\nCalls to these tools must go to the commentary channel: 'functions'." }}
|
| 223 |
+
{%- endif -%}
|
| 224 |
+
{%- endmacro -%}
|
| 225 |
+
|
| 226 |
+
{#- Main Template Logic ================================================= #}
|
| 227 |
+
{#- Set defaults #}
|
| 228 |
+
|
| 229 |
+
{#- Render system message #}
|
| 230 |
+
{{- "<|start|>system<|message|>" }}
|
| 231 |
+
{{- build_system_message() }}
|
| 232 |
+
{{- "<|end|>" }}
|
| 233 |
+
|
| 234 |
+
{#- Extract developer message #}
|
| 235 |
+
{%- if messages[0].role == "developer" or messages[0].role == "system" %}
|
| 236 |
+
{%- set developer_message = messages[0].content %}
|
| 237 |
+
{%- set loop_messages = messages[1:] %}
|
| 238 |
+
{%- else %}
|
| 239 |
+
{%- set developer_message = "" %}
|
| 240 |
+
{%- set loop_messages = messages %}
|
| 241 |
+
{%- endif %}
|
| 242 |
+
|
| 243 |
+
{#- Render developer message #}
|
| 244 |
+
{%- if developer_message or tools %}
|
| 245 |
+
{{- "<|start|>developer<|message|>" }}
|
| 246 |
+
{%- if developer_message %}
|
| 247 |
+
{{- "# Instructions\n\n" }}
|
| 248 |
+
{{- developer_message }}
|
| 249 |
+
{%- endif %}
|
| 250 |
+
{%- if tools -%}
|
| 251 |
+
{{- "\n\n" }}
|
| 252 |
+
{{- "# Tools\n\n" }}
|
| 253 |
+
{{- render_tool_namespace("functions", tools) }}
|
| 254 |
+
{%- endif -%}
|
| 255 |
+
{{- "<|end|>" }}
|
| 256 |
+
{%- endif %}
|
| 257 |
+
|
| 258 |
+
{#- Render messages #}
|
| 259 |
+
{%- set last_tool_call = namespace(name=none) %}
|
| 260 |
+
{%- for message in loop_messages -%}
|
| 261 |
+
{#- At this point only assistant/user/tool messages should remain #}
|
| 262 |
+
{%- if message.role == 'assistant' -%}
|
| 263 |
+
{%- if "tool_calls" in message %}
|
| 264 |
+
{#- We assume max 1 tool call per message, and so we infer the tool call name #}
|
| 265 |
+
{#- in "tool" messages from the most recent assistant tool call name #}
|
| 266 |
+
{%- set tool_call = message.tool_calls[0] %}
|
| 267 |
+
{%- if tool_call.function %}
|
| 268 |
+
{%- set tool_call = tool_call.function %}
|
| 269 |
+
{%- endif %}
|
| 270 |
+
{%- if message.content %}
|
| 271 |
+
{{- "<|start|>assistant<|channel|>analysis<|message|>" + message.content + "<|end|>" }}
|
| 272 |
+
{%- endif %}
|
| 273 |
+
{{- "<|start|>assistant to=" }}
|
| 274 |
+
{{- "functions." + tool_call.name + "<|channel|>commentary json<|message|>" }}
|
| 275 |
+
{{- tool_call.arguments|tojson }}
|
| 276 |
+
{{- "<|call|>" }}
|
| 277 |
+
{%- set last_tool_call.name = tool_call.name %}
|
| 278 |
+
{%- elif "thinking" in message and loop.last and not add_generation_prompt %}
|
| 279 |
+
{#- Only render the CoT if the final turn is an assistant turn and add_generation_prompt is false #}
|
| 280 |
+
{#- This is a situation that should only occur in training, never in inference. #}
|
| 281 |
+
{{- "<|start|>assistant<|channel|>analysis<|message|>" + message.thinking + "<|end|>" }}
|
| 282 |
+
{#- <|return|> indicates the end of generation, but <|end|> does not #}
|
| 283 |
+
{#- <|return|> should never be an input to the model, but we include it as the final token #}
|
| 284 |
+
{#- when training, so the model learns to emit it. #}
|
| 285 |
+
{{- "<|start|>assistant<|channel|>final<|message|>" + message.content + "<|return|>" }}
|
| 286 |
+
{%- set last_tool_call.name = none %}
|
| 287 |
+
{%- elif "thinking" in message %}
|
| 288 |
+
{#- CoT is dropped during all previous turns, so we never render it for inference #}
|
| 289 |
+
{{- "<|start|>assistant<|channel|>final<|message|>" + message.content + "<|end|>" }}
|
| 290 |
+
{%- set last_tool_call.name = none %}
|
| 291 |
+
{%- elif loop.last and not add_generation_prompt %}
|
| 292 |
+
{#- <|return|> indicates the end of generation, but <|end|> does not #}
|
| 293 |
+
{#- <|return|> should never be an input to the model, but we include it as the final token #}
|
| 294 |
+
{#- when training, so the model learns to emit it. #}
|
| 295 |
+
{{- "<|start|>assistant<|message|>" + message.content + "<|return|>" }}
|
| 296 |
+
{%- else %}
|
| 297 |
+
{{- "<|start|>assistant<|message|>" + message.content + "<|end|>" }}
|
| 298 |
+
{%- set last_tool_call.name = none %}
|
| 299 |
+
{%- endif %}
|
| 300 |
+
{%- elif message.role == 'tool' -%}
|
| 301 |
+
{%- if last_tool_call.name is none %}
|
| 302 |
+
{{- raise_exception("Message has tool role, but there was no previous assistant message with a tool call!") }}
|
| 303 |
+
{%- endif %}
|
| 304 |
+
{{- "<|start|>functions." + last_tool_call.name }}
|
| 305 |
+
{{- " to=assistant<|channel|>commentary<|message|>" + message.content|tojson + "<|end|>" }}
|
| 306 |
+
{%- else -%}
|
| 307 |
+
{{- "<|start|>user<|message|>" + message.content + "<|end|>" }}
|
| 308 |
+
{%- endif -%}
|
| 309 |
+
{%- endfor -%}
|
| 310 |
+
|
| 311 |
+
{#- Generation prompt #}
|
| 312 |
+
{%- if add_generation_prompt -%}
|
| 313 |
+
<|start|>assistant
|
| 314 |
+
{%- endif -%}
|
| 315 |
+
{# Copyright 2025-present Unsloth. Apache 2.0 License. Unsloth chat template fixes. Edited from ggml-org & OpenAI #}
|
config.json
ADDED
|
@@ -0,0 +1,913 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"GptOssForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": true,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": null,
|
| 8 |
+
"dtype": "bfloat16",
|
| 9 |
+
"eos_token_id": 200002,
|
| 10 |
+
"experts_per_token": 4,
|
| 11 |
+
"head_dim": 64,
|
| 12 |
+
"hidden_act": "silu",
|
| 13 |
+
"hidden_size": 2880,
|
| 14 |
+
"initial_context_length": 4096,
|
| 15 |
+
"initializer_range": 0.02,
|
| 16 |
+
"intermediate_size": 2880,
|
| 17 |
+
"layer_types": [
|
| 18 |
+
"sliding_attention",
|
| 19 |
+
"full_attention",
|
| 20 |
+
"sliding_attention",
|
| 21 |
+
"full_attention",
|
| 22 |
+
"sliding_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"sliding_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"sliding_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"sliding_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"sliding_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"sliding_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"sliding_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"sliding_attention",
|
| 37 |
+
"full_attention",
|
| 38 |
+
"sliding_attention",
|
| 39 |
+
"full_attention",
|
| 40 |
+
"sliding_attention",
|
| 41 |
+
"full_attention"
|
| 42 |
+
],
|
| 43 |
+
"max_position_embeddings": 131072,
|
| 44 |
+
"model_name": "unsloth/gpt-oss-20b-unsloth-bnb-4bit",
|
| 45 |
+
"model_type": "gpt_oss",
|
| 46 |
+
"num_attention_heads": 64,
|
| 47 |
+
"num_experts_per_tok": 4,
|
| 48 |
+
"num_hidden_layers": 24,
|
| 49 |
+
"num_key_value_heads": 8,
|
| 50 |
+
"num_local_experts": 32,
|
| 51 |
+
"output_router_logits": false,
|
| 52 |
+
"pad_token_id": 199999,
|
| 53 |
+
"quantization_config": {
|
| 54 |
+
"config_groups": {
|
| 55 |
+
"group_0": {
|
| 56 |
+
"format": "mxfp4-pack-quantized",
|
| 57 |
+
"input_activations": {
|
| 58 |
+
"actorder": null,
|
| 59 |
+
"block_structure": null,
|
| 60 |
+
"dynamic": true,
|
| 61 |
+
"group_size": 32,
|
| 62 |
+
"num_bits": 4,
|
| 63 |
+
"observer": null,
|
| 64 |
+
"observer_kwargs": {},
|
| 65 |
+
"scale_dtype": "torch.uint8",
|
| 66 |
+
"strategy": "group",
|
| 67 |
+
"symmetric": true,
|
| 68 |
+
"type": "float",
|
| 69 |
+
"zp_dtype": null
|
| 70 |
+
},
|
| 71 |
+
"output_activations": null,
|
| 72 |
+
"targets": [
|
| 73 |
+
"Linear"
|
| 74 |
+
],
|
| 75 |
+
"weights": {
|
| 76 |
+
"actorder": null,
|
| 77 |
+
"block_structure": null,
|
| 78 |
+
"dynamic": false,
|
| 79 |
+
"group_size": 32,
|
| 80 |
+
"num_bits": 4,
|
| 81 |
+
"observer": "memoryless_minmax",
|
| 82 |
+
"observer_kwargs": {},
|
| 83 |
+
"scale_dtype": "torch.uint8",
|
| 84 |
+
"strategy": "group",
|
| 85 |
+
"symmetric": true,
|
| 86 |
+
"type": "float",
|
| 87 |
+
"zp_dtype": null
|
| 88 |
+
}
|
| 89 |
+
}
|
| 90 |
+
},
|
| 91 |
+
"format": "mxfp4-pack-quantized",
|
| 92 |
+
"global_compression_ratio": null,
|
| 93 |
+
"ignore": [
|
| 94 |
+
"model.layers.0.mlp.router",
|
| 95 |
+
"model.layers.0.mlp.experts.0",
|
| 96 |
+
"model.layers.0.mlp.experts.1",
|
| 97 |
+
"model.layers.0.mlp.experts.2",
|
| 98 |
+
"model.layers.0.mlp.experts.3",
|
| 99 |
+
"model.layers.0.mlp.experts.4",
|
| 100 |
+
"model.layers.0.mlp.experts.5",
|
| 101 |
+
"model.layers.0.mlp.experts.6",
|
| 102 |
+
"model.layers.0.mlp.experts.7",
|
| 103 |
+
"model.layers.0.mlp.experts.8",
|
| 104 |
+
"model.layers.0.mlp.experts.9",
|
| 105 |
+
"model.layers.0.mlp.experts.10",
|
| 106 |
+
"model.layers.0.mlp.experts.11",
|
| 107 |
+
"model.layers.0.mlp.experts.12",
|
| 108 |
+
"model.layers.0.mlp.experts.13",
|
| 109 |
+
"model.layers.0.mlp.experts.14",
|
| 110 |
+
"model.layers.0.mlp.experts.15",
|
| 111 |
+
"model.layers.0.mlp.experts.16",
|
| 112 |
+
"model.layers.0.mlp.experts.17",
|
| 113 |
+
"model.layers.0.mlp.experts.18",
|
| 114 |
+
"model.layers.0.mlp.experts.19",
|
| 115 |
+
"model.layers.0.mlp.experts.20",
|
| 116 |
+
"model.layers.0.mlp.experts.21",
|
| 117 |
+
"model.layers.0.mlp.experts.22",
|
| 118 |
+
"model.layers.0.mlp.experts.23",
|
| 119 |
+
"model.layers.0.mlp.experts.24",
|
| 120 |
+
"model.layers.0.mlp.experts.25",
|
| 121 |
+
"model.layers.0.mlp.experts.26",
|
| 122 |
+
"model.layers.0.mlp.experts.27",
|
| 123 |
+
"model.layers.0.mlp.experts.28",
|
| 124 |
+
"model.layers.0.mlp.experts.29",
|
| 125 |
+
"model.layers.0.mlp.experts.30",
|
| 126 |
+
"model.layers.0.mlp.experts.31",
|
| 127 |
+
"model.layers.1.mlp.router",
|
| 128 |
+
"model.layers.1.mlp.experts.0",
|
| 129 |
+
"model.layers.1.mlp.experts.1",
|
| 130 |
+
"model.layers.1.mlp.experts.2",
|
| 131 |
+
"model.layers.1.mlp.experts.3",
|
| 132 |
+
"model.layers.1.mlp.experts.4",
|
| 133 |
+
"model.layers.1.mlp.experts.5",
|
| 134 |
+
"model.layers.1.mlp.experts.6",
|
| 135 |
+
"model.layers.1.mlp.experts.7",
|
| 136 |
+
"model.layers.1.mlp.experts.8",
|
| 137 |
+
"model.layers.1.mlp.experts.9",
|
| 138 |
+
"model.layers.1.mlp.experts.10",
|
| 139 |
+
"model.layers.1.mlp.experts.11",
|
| 140 |
+
"model.layers.1.mlp.experts.12",
|
| 141 |
+
"model.layers.1.mlp.experts.13",
|
| 142 |
+
"model.layers.1.mlp.experts.14",
|
| 143 |
+
"model.layers.1.mlp.experts.15",
|
| 144 |
+
"model.layers.1.mlp.experts.16",
|
| 145 |
+
"model.layers.1.mlp.experts.17",
|
| 146 |
+
"model.layers.1.mlp.experts.18",
|
| 147 |
+
"model.layers.1.mlp.experts.19",
|
| 148 |
+
"model.layers.1.mlp.experts.20",
|
| 149 |
+
"model.layers.1.mlp.experts.21",
|
| 150 |
+
"model.layers.1.mlp.experts.22",
|
| 151 |
+
"model.layers.1.mlp.experts.23",
|
| 152 |
+
"model.layers.1.mlp.experts.24",
|
| 153 |
+
"model.layers.1.mlp.experts.25",
|
| 154 |
+
"model.layers.1.mlp.experts.26",
|
| 155 |
+
"model.layers.1.mlp.experts.27",
|
| 156 |
+
"model.layers.1.mlp.experts.28",
|
| 157 |
+
"model.layers.1.mlp.experts.29",
|
| 158 |
+
"model.layers.1.mlp.experts.30",
|
| 159 |
+
"model.layers.1.mlp.experts.31",
|
| 160 |
+
"model.layers.2.mlp.router",
|
| 161 |
+
"model.layers.2.mlp.experts.0",
|
| 162 |
+
"model.layers.2.mlp.experts.1",
|
| 163 |
+
"model.layers.2.mlp.experts.2",
|
| 164 |
+
"model.layers.2.mlp.experts.3",
|
| 165 |
+
"model.layers.2.mlp.experts.4",
|
| 166 |
+
"model.layers.2.mlp.experts.5",
|
| 167 |
+
"model.layers.2.mlp.experts.6",
|
| 168 |
+
"model.layers.2.mlp.experts.7",
|
| 169 |
+
"model.layers.2.mlp.experts.8",
|
| 170 |
+
"model.layers.2.mlp.experts.9",
|
| 171 |
+
"model.layers.2.mlp.experts.10",
|
| 172 |
+
"model.layers.2.mlp.experts.11",
|
| 173 |
+
"model.layers.2.mlp.experts.12",
|
| 174 |
+
"model.layers.2.mlp.experts.13",
|
| 175 |
+
"model.layers.2.mlp.experts.14",
|
| 176 |
+
"model.layers.2.mlp.experts.15",
|
| 177 |
+
"model.layers.2.mlp.experts.16",
|
| 178 |
+
"model.layers.2.mlp.experts.17",
|
| 179 |
+
"model.layers.2.mlp.experts.18",
|
| 180 |
+
"model.layers.2.mlp.experts.19",
|
| 181 |
+
"model.layers.2.mlp.experts.20",
|
| 182 |
+
"model.layers.2.mlp.experts.21",
|
| 183 |
+
"model.layers.2.mlp.experts.22",
|
| 184 |
+
"model.layers.2.mlp.experts.23",
|
| 185 |
+
"model.layers.2.mlp.experts.24",
|
| 186 |
+
"model.layers.2.mlp.experts.25",
|
| 187 |
+
"model.layers.2.mlp.experts.26",
|
| 188 |
+
"model.layers.2.mlp.experts.27",
|
| 189 |
+
"model.layers.2.mlp.experts.28",
|
| 190 |
+
"model.layers.2.mlp.experts.29",
|
| 191 |
+
"model.layers.2.mlp.experts.30",
|
| 192 |
+
"model.layers.2.mlp.experts.31",
|
| 193 |
+
"model.layers.3.mlp.router",
|
| 194 |
+
"model.layers.3.mlp.experts.0",
|
| 195 |
+
"model.layers.3.mlp.experts.1",
|
| 196 |
+
"model.layers.3.mlp.experts.2",
|
| 197 |
+
"model.layers.3.mlp.experts.3",
|
| 198 |
+
"model.layers.3.mlp.experts.4",
|
| 199 |
+
"model.layers.3.mlp.experts.5",
|
| 200 |
+
"model.layers.3.mlp.experts.6",
|
| 201 |
+
"model.layers.3.mlp.experts.7",
|
| 202 |
+
"model.layers.3.mlp.experts.8",
|
| 203 |
+
"model.layers.3.mlp.experts.9",
|
| 204 |
+
"model.layers.3.mlp.experts.10",
|
| 205 |
+
"model.layers.3.mlp.experts.11",
|
| 206 |
+
"model.layers.3.mlp.experts.12",
|
| 207 |
+
"model.layers.3.mlp.experts.13",
|
| 208 |
+
"model.layers.3.mlp.experts.14",
|
| 209 |
+
"model.layers.3.mlp.experts.15",
|
| 210 |
+
"model.layers.3.mlp.experts.16",
|
| 211 |
+
"model.layers.3.mlp.experts.17",
|
| 212 |
+
"model.layers.3.mlp.experts.18",
|
| 213 |
+
"model.layers.3.mlp.experts.19",
|
| 214 |
+
"model.layers.3.mlp.experts.20",
|
| 215 |
+
"model.layers.3.mlp.experts.21",
|
| 216 |
+
"model.layers.3.mlp.experts.22",
|
| 217 |
+
"model.layers.3.mlp.experts.23",
|
| 218 |
+
"model.layers.3.mlp.experts.24",
|
| 219 |
+
"model.layers.3.mlp.experts.25",
|
| 220 |
+
"model.layers.3.mlp.experts.26",
|
| 221 |
+
"model.layers.3.mlp.experts.27",
|
| 222 |
+
"model.layers.3.mlp.experts.28",
|
| 223 |
+
"model.layers.3.mlp.experts.29",
|
| 224 |
+
"model.layers.3.mlp.experts.30",
|
| 225 |
+
"model.layers.3.mlp.experts.31",
|
| 226 |
+
"model.layers.4.mlp.router",
|
| 227 |
+
"model.layers.4.mlp.experts.0",
|
| 228 |
+
"model.layers.4.mlp.experts.1",
|
| 229 |
+
"model.layers.4.mlp.experts.2",
|
| 230 |
+
"model.layers.4.mlp.experts.3",
|
| 231 |
+
"model.layers.4.mlp.experts.4",
|
| 232 |
+
"model.layers.4.mlp.experts.5",
|
| 233 |
+
"model.layers.4.mlp.experts.6",
|
| 234 |
+
"model.layers.4.mlp.experts.7",
|
| 235 |
+
"model.layers.4.mlp.experts.8",
|
| 236 |
+
"model.layers.4.mlp.experts.9",
|
| 237 |
+
"model.layers.4.mlp.experts.10",
|
| 238 |
+
"model.layers.4.mlp.experts.11",
|
| 239 |
+
"model.layers.4.mlp.experts.12",
|
| 240 |
+
"model.layers.4.mlp.experts.13",
|
| 241 |
+
"model.layers.4.mlp.experts.14",
|
| 242 |
+
"model.layers.4.mlp.experts.15",
|
| 243 |
+
"model.layers.4.mlp.experts.16",
|
| 244 |
+
"model.layers.4.mlp.experts.17",
|
| 245 |
+
"model.layers.4.mlp.experts.18",
|
| 246 |
+
"model.layers.4.mlp.experts.19",
|
| 247 |
+
"model.layers.4.mlp.experts.20",
|
| 248 |
+
"model.layers.4.mlp.experts.21",
|
| 249 |
+
"model.layers.4.mlp.experts.22",
|
| 250 |
+
"model.layers.4.mlp.experts.23",
|
| 251 |
+
"model.layers.4.mlp.experts.24",
|
| 252 |
+
"model.layers.4.mlp.experts.25",
|
| 253 |
+
"model.layers.4.mlp.experts.26",
|
| 254 |
+
"model.layers.4.mlp.experts.27",
|
| 255 |
+
"model.layers.4.mlp.experts.28",
|
| 256 |
+
"model.layers.4.mlp.experts.29",
|
| 257 |
+
"model.layers.4.mlp.experts.30",
|
| 258 |
+
"model.layers.4.mlp.experts.31",
|
| 259 |
+
"model.layers.5.mlp.router",
|
| 260 |
+
"model.layers.5.mlp.experts.0",
|
| 261 |
+
"model.layers.5.mlp.experts.1",
|
| 262 |
+
"model.layers.5.mlp.experts.2",
|
| 263 |
+
"model.layers.5.mlp.experts.3",
|
| 264 |
+
"model.layers.5.mlp.experts.4",
|
| 265 |
+
"model.layers.5.mlp.experts.5",
|
| 266 |
+
"model.layers.5.mlp.experts.6",
|
| 267 |
+
"model.layers.5.mlp.experts.7",
|
| 268 |
+
"model.layers.5.mlp.experts.8",
|
| 269 |
+
"model.layers.5.mlp.experts.9",
|
| 270 |
+
"model.layers.5.mlp.experts.10",
|
| 271 |
+
"model.layers.5.mlp.experts.11",
|
| 272 |
+
"model.layers.5.mlp.experts.12",
|
| 273 |
+
"model.layers.5.mlp.experts.13",
|
| 274 |
+
"model.layers.5.mlp.experts.14",
|
| 275 |
+
"model.layers.5.mlp.experts.15",
|
| 276 |
+
"model.layers.5.mlp.experts.16",
|
| 277 |
+
"model.layers.5.mlp.experts.17",
|
| 278 |
+
"model.layers.5.mlp.experts.18",
|
| 279 |
+
"model.layers.5.mlp.experts.19",
|
| 280 |
+
"model.layers.5.mlp.experts.20",
|
| 281 |
+
"model.layers.5.mlp.experts.21",
|
| 282 |
+
"model.layers.5.mlp.experts.22",
|
| 283 |
+
"model.layers.5.mlp.experts.23",
|
| 284 |
+
"model.layers.5.mlp.experts.24",
|
| 285 |
+
"model.layers.5.mlp.experts.25",
|
| 286 |
+
"model.layers.5.mlp.experts.26",
|
| 287 |
+
"model.layers.5.mlp.experts.27",
|
| 288 |
+
"model.layers.5.mlp.experts.28",
|
| 289 |
+
"model.layers.5.mlp.experts.29",
|
| 290 |
+
"model.layers.5.mlp.experts.30",
|
| 291 |
+
"model.layers.5.mlp.experts.31",
|
| 292 |
+
"model.layers.6.mlp.router",
|
| 293 |
+
"model.layers.6.mlp.experts.0",
|
| 294 |
+
"model.layers.6.mlp.experts.1",
|
| 295 |
+
"model.layers.6.mlp.experts.2",
|
| 296 |
+
"model.layers.6.mlp.experts.3",
|
| 297 |
+
"model.layers.6.mlp.experts.4",
|
| 298 |
+
"model.layers.6.mlp.experts.5",
|
| 299 |
+
"model.layers.6.mlp.experts.6",
|
| 300 |
+
"model.layers.6.mlp.experts.7",
|
| 301 |
+
"model.layers.6.mlp.experts.8",
|
| 302 |
+
"model.layers.6.mlp.experts.9",
|
| 303 |
+
"model.layers.6.mlp.experts.10",
|
| 304 |
+
"model.layers.6.mlp.experts.11",
|
| 305 |
+
"model.layers.6.mlp.experts.12",
|
| 306 |
+
"model.layers.6.mlp.experts.13",
|
| 307 |
+
"model.layers.6.mlp.experts.14",
|
| 308 |
+
"model.layers.6.mlp.experts.15",
|
| 309 |
+
"model.layers.6.mlp.experts.16",
|
| 310 |
+
"model.layers.6.mlp.experts.17",
|
| 311 |
+
"model.layers.6.mlp.experts.18",
|
| 312 |
+
"model.layers.6.mlp.experts.19",
|
| 313 |
+
"model.layers.6.mlp.experts.20",
|
| 314 |
+
"model.layers.6.mlp.experts.21",
|
| 315 |
+
"model.layers.6.mlp.experts.22",
|
| 316 |
+
"model.layers.6.mlp.experts.23",
|
| 317 |
+
"model.layers.6.mlp.experts.24",
|
| 318 |
+
"model.layers.6.mlp.experts.25",
|
| 319 |
+
"model.layers.6.mlp.experts.26",
|
| 320 |
+
"model.layers.6.mlp.experts.27",
|
| 321 |
+
"model.layers.6.mlp.experts.28",
|
| 322 |
+
"model.layers.6.mlp.experts.29",
|
| 323 |
+
"model.layers.6.mlp.experts.30",
|
| 324 |
+
"model.layers.6.mlp.experts.31",
|
| 325 |
+
"model.layers.7.mlp.router",
|
| 326 |
+
"model.layers.7.mlp.experts.0",
|
| 327 |
+
"model.layers.7.mlp.experts.1",
|
| 328 |
+
"model.layers.7.mlp.experts.2",
|
| 329 |
+
"model.layers.7.mlp.experts.3",
|
| 330 |
+
"model.layers.7.mlp.experts.4",
|
| 331 |
+
"model.layers.7.mlp.experts.5",
|
| 332 |
+
"model.layers.7.mlp.experts.6",
|
| 333 |
+
"model.layers.7.mlp.experts.7",
|
| 334 |
+
"model.layers.7.mlp.experts.8",
|
| 335 |
+
"model.layers.7.mlp.experts.9",
|
| 336 |
+
"model.layers.7.mlp.experts.10",
|
| 337 |
+
"model.layers.7.mlp.experts.11",
|
| 338 |
+
"model.layers.7.mlp.experts.12",
|
| 339 |
+
"model.layers.7.mlp.experts.13",
|
| 340 |
+
"model.layers.7.mlp.experts.14",
|
| 341 |
+
"model.layers.7.mlp.experts.15",
|
| 342 |
+
"model.layers.7.mlp.experts.16",
|
| 343 |
+
"model.layers.7.mlp.experts.17",
|
| 344 |
+
"model.layers.7.mlp.experts.18",
|
| 345 |
+
"model.layers.7.mlp.experts.19",
|
| 346 |
+
"model.layers.7.mlp.experts.20",
|
| 347 |
+
"model.layers.7.mlp.experts.21",
|
| 348 |
+
"model.layers.7.mlp.experts.22",
|
| 349 |
+
"model.layers.7.mlp.experts.23",
|
| 350 |
+
"model.layers.7.mlp.experts.24",
|
| 351 |
+
"model.layers.7.mlp.experts.25",
|
| 352 |
+
"model.layers.7.mlp.experts.26",
|
| 353 |
+
"model.layers.7.mlp.experts.27",
|
| 354 |
+
"model.layers.7.mlp.experts.28",
|
| 355 |
+
"model.layers.7.mlp.experts.29",
|
| 356 |
+
"model.layers.7.mlp.experts.30",
|
| 357 |
+
"model.layers.7.mlp.experts.31",
|
| 358 |
+
"model.layers.8.mlp.router",
|
| 359 |
+
"model.layers.8.mlp.experts.0",
|
| 360 |
+
"model.layers.8.mlp.experts.1",
|
| 361 |
+
"model.layers.8.mlp.experts.2",
|
| 362 |
+
"model.layers.8.mlp.experts.3",
|
| 363 |
+
"model.layers.8.mlp.experts.4",
|
| 364 |
+
"model.layers.8.mlp.experts.5",
|
| 365 |
+
"model.layers.8.mlp.experts.6",
|
| 366 |
+
"model.layers.8.mlp.experts.7",
|
| 367 |
+
"model.layers.8.mlp.experts.8",
|
| 368 |
+
"model.layers.8.mlp.experts.9",
|
| 369 |
+
"model.layers.8.mlp.experts.10",
|
| 370 |
+
"model.layers.8.mlp.experts.11",
|
| 371 |
+
"model.layers.8.mlp.experts.12",
|
| 372 |
+
"model.layers.8.mlp.experts.13",
|
| 373 |
+
"model.layers.8.mlp.experts.14",
|
| 374 |
+
"model.layers.8.mlp.experts.15",
|
| 375 |
+
"model.layers.8.mlp.experts.16",
|
| 376 |
+
"model.layers.8.mlp.experts.17",
|
| 377 |
+
"model.layers.8.mlp.experts.18",
|
| 378 |
+
"model.layers.8.mlp.experts.19",
|
| 379 |
+
"model.layers.8.mlp.experts.20",
|
| 380 |
+
"model.layers.8.mlp.experts.21",
|
| 381 |
+
"model.layers.8.mlp.experts.22",
|
| 382 |
+
"model.layers.8.mlp.experts.23",
|
| 383 |
+
"model.layers.8.mlp.experts.24",
|
| 384 |
+
"model.layers.8.mlp.experts.25",
|
| 385 |
+
"model.layers.8.mlp.experts.26",
|
| 386 |
+
"model.layers.8.mlp.experts.27",
|
| 387 |
+
"model.layers.8.mlp.experts.28",
|
| 388 |
+
"model.layers.8.mlp.experts.29",
|
| 389 |
+
"model.layers.8.mlp.experts.30",
|
| 390 |
+
"model.layers.8.mlp.experts.31",
|
| 391 |
+
"model.layers.9.mlp.router",
|
| 392 |
+
"model.layers.9.mlp.experts.0",
|
| 393 |
+
"model.layers.9.mlp.experts.1",
|
| 394 |
+
"model.layers.9.mlp.experts.2",
|
| 395 |
+
"model.layers.9.mlp.experts.3",
|
| 396 |
+
"model.layers.9.mlp.experts.4",
|
| 397 |
+
"model.layers.9.mlp.experts.5",
|
| 398 |
+
"model.layers.9.mlp.experts.6",
|
| 399 |
+
"model.layers.9.mlp.experts.7",
|
| 400 |
+
"model.layers.9.mlp.experts.8",
|
| 401 |
+
"model.layers.9.mlp.experts.9",
|
| 402 |
+
"model.layers.9.mlp.experts.10",
|
| 403 |
+
"model.layers.9.mlp.experts.11",
|
| 404 |
+
"model.layers.9.mlp.experts.12",
|
| 405 |
+
"model.layers.9.mlp.experts.13",
|
| 406 |
+
"model.layers.9.mlp.experts.14",
|
| 407 |
+
"model.layers.9.mlp.experts.15",
|
| 408 |
+
"model.layers.9.mlp.experts.16",
|
| 409 |
+
"model.layers.9.mlp.experts.17",
|
| 410 |
+
"model.layers.9.mlp.experts.18",
|
| 411 |
+
"model.layers.9.mlp.experts.19",
|
| 412 |
+
"model.layers.9.mlp.experts.20",
|
| 413 |
+
"model.layers.9.mlp.experts.21",
|
| 414 |
+
"model.layers.9.mlp.experts.22",
|
| 415 |
+
"model.layers.9.mlp.experts.23",
|
| 416 |
+
"model.layers.9.mlp.experts.24",
|
| 417 |
+
"model.layers.9.mlp.experts.25",
|
| 418 |
+
"model.layers.9.mlp.experts.26",
|
| 419 |
+
"model.layers.9.mlp.experts.27",
|
| 420 |
+
"model.layers.9.mlp.experts.28",
|
| 421 |
+
"model.layers.9.mlp.experts.29",
|
| 422 |
+
"model.layers.9.mlp.experts.30",
|
| 423 |
+
"model.layers.9.mlp.experts.31",
|
| 424 |
+
"model.layers.10.mlp.router",
|
| 425 |
+
"model.layers.10.mlp.experts.0",
|
| 426 |
+
"model.layers.10.mlp.experts.1",
|
| 427 |
+
"model.layers.10.mlp.experts.2",
|
| 428 |
+
"model.layers.10.mlp.experts.3",
|
| 429 |
+
"model.layers.10.mlp.experts.4",
|
| 430 |
+
"model.layers.10.mlp.experts.5",
|
| 431 |
+
"model.layers.10.mlp.experts.6",
|
| 432 |
+
"model.layers.10.mlp.experts.7",
|
| 433 |
+
"model.layers.10.mlp.experts.8",
|
| 434 |
+
"model.layers.10.mlp.experts.9",
|
| 435 |
+
"model.layers.10.mlp.experts.10",
|
| 436 |
+
"model.layers.10.mlp.experts.11",
|
| 437 |
+
"model.layers.10.mlp.experts.12",
|
| 438 |
+
"model.layers.10.mlp.experts.13",
|
| 439 |
+
"model.layers.10.mlp.experts.14",
|
| 440 |
+
"model.layers.10.mlp.experts.15",
|
| 441 |
+
"model.layers.10.mlp.experts.16",
|
| 442 |
+
"model.layers.10.mlp.experts.17",
|
| 443 |
+
"model.layers.10.mlp.experts.18",
|
| 444 |
+
"model.layers.10.mlp.experts.19",
|
| 445 |
+
"model.layers.10.mlp.experts.20",
|
| 446 |
+
"model.layers.10.mlp.experts.21",
|
| 447 |
+
"model.layers.10.mlp.experts.22",
|
| 448 |
+
"model.layers.10.mlp.experts.23",
|
| 449 |
+
"model.layers.10.mlp.experts.24",
|
| 450 |
+
"model.layers.10.mlp.experts.25",
|
| 451 |
+
"model.layers.10.mlp.experts.26",
|
| 452 |
+
"model.layers.10.mlp.experts.27",
|
| 453 |
+
"model.layers.10.mlp.experts.28",
|
| 454 |
+
"model.layers.10.mlp.experts.29",
|
| 455 |
+
"model.layers.10.mlp.experts.30",
|
| 456 |
+
"model.layers.10.mlp.experts.31",
|
| 457 |
+
"model.layers.11.mlp.router",
|
| 458 |
+
"model.layers.11.mlp.experts.0",
|
| 459 |
+
"model.layers.11.mlp.experts.1",
|
| 460 |
+
"model.layers.11.mlp.experts.2",
|
| 461 |
+
"model.layers.11.mlp.experts.3",
|
| 462 |
+
"model.layers.11.mlp.experts.4",
|
| 463 |
+
"model.layers.11.mlp.experts.5",
|
| 464 |
+
"model.layers.11.mlp.experts.6",
|
| 465 |
+
"model.layers.11.mlp.experts.7",
|
| 466 |
+
"model.layers.11.mlp.experts.8",
|
| 467 |
+
"model.layers.11.mlp.experts.9",
|
| 468 |
+
"model.layers.11.mlp.experts.10",
|
| 469 |
+
"model.layers.11.mlp.experts.11",
|
| 470 |
+
"model.layers.11.mlp.experts.12",
|
| 471 |
+
"model.layers.11.mlp.experts.13",
|
| 472 |
+
"model.layers.11.mlp.experts.14",
|
| 473 |
+
"model.layers.11.mlp.experts.15",
|
| 474 |
+
"model.layers.11.mlp.experts.16",
|
| 475 |
+
"model.layers.11.mlp.experts.17",
|
| 476 |
+
"model.layers.11.mlp.experts.18",
|
| 477 |
+
"model.layers.11.mlp.experts.19",
|
| 478 |
+
"model.layers.11.mlp.experts.20",
|
| 479 |
+
"model.layers.11.mlp.experts.21",
|
| 480 |
+
"model.layers.11.mlp.experts.22",
|
| 481 |
+
"model.layers.11.mlp.experts.23",
|
| 482 |
+
"model.layers.11.mlp.experts.24",
|
| 483 |
+
"model.layers.11.mlp.experts.25",
|
| 484 |
+
"model.layers.11.mlp.experts.26",
|
| 485 |
+
"model.layers.11.mlp.experts.27",
|
| 486 |
+
"model.layers.11.mlp.experts.28",
|
| 487 |
+
"model.layers.11.mlp.experts.29",
|
| 488 |
+
"model.layers.11.mlp.experts.30",
|
| 489 |
+
"model.layers.11.mlp.experts.31",
|
| 490 |
+
"model.layers.12.mlp.router",
|
| 491 |
+
"model.layers.12.mlp.experts.0",
|
| 492 |
+
"model.layers.12.mlp.experts.1",
|
| 493 |
+
"model.layers.12.mlp.experts.2",
|
| 494 |
+
"model.layers.12.mlp.experts.3",
|
| 495 |
+
"model.layers.12.mlp.experts.4",
|
| 496 |
+
"model.layers.12.mlp.experts.5",
|
| 497 |
+
"model.layers.12.mlp.experts.6",
|
| 498 |
+
"model.layers.12.mlp.experts.7",
|
| 499 |
+
"model.layers.12.mlp.experts.8",
|
| 500 |
+
"model.layers.12.mlp.experts.9",
|
| 501 |
+
"model.layers.12.mlp.experts.10",
|
| 502 |
+
"model.layers.12.mlp.experts.11",
|
| 503 |
+
"model.layers.12.mlp.experts.12",
|
| 504 |
+
"model.layers.12.mlp.experts.13",
|
| 505 |
+
"model.layers.12.mlp.experts.14",
|
| 506 |
+
"model.layers.12.mlp.experts.15",
|
| 507 |
+
"model.layers.12.mlp.experts.16",
|
| 508 |
+
"model.layers.12.mlp.experts.17",
|
| 509 |
+
"model.layers.12.mlp.experts.18",
|
| 510 |
+
"model.layers.12.mlp.experts.19",
|
| 511 |
+
"model.layers.12.mlp.experts.20",
|
| 512 |
+
"model.layers.12.mlp.experts.21",
|
| 513 |
+
"model.layers.12.mlp.experts.22",
|
| 514 |
+
"model.layers.12.mlp.experts.23",
|
| 515 |
+
"model.layers.12.mlp.experts.24",
|
| 516 |
+
"model.layers.12.mlp.experts.25",
|
| 517 |
+
"model.layers.12.mlp.experts.26",
|
| 518 |
+
"model.layers.12.mlp.experts.27",
|
| 519 |
+
"model.layers.12.mlp.experts.28",
|
| 520 |
+
"model.layers.12.mlp.experts.29",
|
| 521 |
+
"model.layers.12.mlp.experts.30",
|
| 522 |
+
"model.layers.12.mlp.experts.31",
|
| 523 |
+
"model.layers.13.mlp.router",
|
| 524 |
+
"model.layers.13.mlp.experts.0",
|
| 525 |
+
"model.layers.13.mlp.experts.1",
|
| 526 |
+
"model.layers.13.mlp.experts.2",
|
| 527 |
+
"model.layers.13.mlp.experts.3",
|
| 528 |
+
"model.layers.13.mlp.experts.4",
|
| 529 |
+
"model.layers.13.mlp.experts.5",
|
| 530 |
+
"model.layers.13.mlp.experts.6",
|
| 531 |
+
"model.layers.13.mlp.experts.7",
|
| 532 |
+
"model.layers.13.mlp.experts.8",
|
| 533 |
+
"model.layers.13.mlp.experts.9",
|
| 534 |
+
"model.layers.13.mlp.experts.10",
|
| 535 |
+
"model.layers.13.mlp.experts.11",
|
| 536 |
+
"model.layers.13.mlp.experts.12",
|
| 537 |
+
"model.layers.13.mlp.experts.13",
|
| 538 |
+
"model.layers.13.mlp.experts.14",
|
| 539 |
+
"model.layers.13.mlp.experts.15",
|
| 540 |
+
"model.layers.13.mlp.experts.16",
|
| 541 |
+
"model.layers.13.mlp.experts.17",
|
| 542 |
+
"model.layers.13.mlp.experts.18",
|
| 543 |
+
"model.layers.13.mlp.experts.19",
|
| 544 |
+
"model.layers.13.mlp.experts.20",
|
| 545 |
+
"model.layers.13.mlp.experts.21",
|
| 546 |
+
"model.layers.13.mlp.experts.22",
|
| 547 |
+
"model.layers.13.mlp.experts.23",
|
| 548 |
+
"model.layers.13.mlp.experts.24",
|
| 549 |
+
"model.layers.13.mlp.experts.25",
|
| 550 |
+
"model.layers.13.mlp.experts.26",
|
| 551 |
+
"model.layers.13.mlp.experts.27",
|
| 552 |
+
"model.layers.13.mlp.experts.28",
|
| 553 |
+
"model.layers.13.mlp.experts.29",
|
| 554 |
+
"model.layers.13.mlp.experts.30",
|
| 555 |
+
"model.layers.13.mlp.experts.31",
|
| 556 |
+
"model.layers.14.mlp.router",
|
| 557 |
+
"model.layers.14.mlp.experts.0",
|
| 558 |
+
"model.layers.14.mlp.experts.1",
|
| 559 |
+
"model.layers.14.mlp.experts.2",
|
| 560 |
+
"model.layers.14.mlp.experts.3",
|
| 561 |
+
"model.layers.14.mlp.experts.4",
|
| 562 |
+
"model.layers.14.mlp.experts.5",
|
| 563 |
+
"model.layers.14.mlp.experts.6",
|
| 564 |
+
"model.layers.14.mlp.experts.7",
|
| 565 |
+
"model.layers.14.mlp.experts.8",
|
| 566 |
+
"model.layers.14.mlp.experts.9",
|
| 567 |
+
"model.layers.14.mlp.experts.10",
|
| 568 |
+
"model.layers.14.mlp.experts.11",
|
| 569 |
+
"model.layers.14.mlp.experts.12",
|
| 570 |
+
"model.layers.14.mlp.experts.13",
|
| 571 |
+
"model.layers.14.mlp.experts.14",
|
| 572 |
+
"model.layers.14.mlp.experts.15",
|
| 573 |
+
"model.layers.14.mlp.experts.16",
|
| 574 |
+
"model.layers.14.mlp.experts.17",
|
| 575 |
+
"model.layers.14.mlp.experts.18",
|
| 576 |
+
"model.layers.14.mlp.experts.19",
|
| 577 |
+
"model.layers.14.mlp.experts.20",
|
| 578 |
+
"model.layers.14.mlp.experts.21",
|
| 579 |
+
"model.layers.14.mlp.experts.22",
|
| 580 |
+
"model.layers.14.mlp.experts.23",
|
| 581 |
+
"model.layers.14.mlp.experts.24",
|
| 582 |
+
"model.layers.14.mlp.experts.25",
|
| 583 |
+
"model.layers.14.mlp.experts.26",
|
| 584 |
+
"model.layers.14.mlp.experts.27",
|
| 585 |
+
"model.layers.14.mlp.experts.28",
|
| 586 |
+
"model.layers.14.mlp.experts.29",
|
| 587 |
+
"model.layers.14.mlp.experts.30",
|
| 588 |
+
"model.layers.14.mlp.experts.31",
|
| 589 |
+
"model.layers.15.mlp.router",
|
| 590 |
+
"model.layers.15.mlp.experts.0",
|
| 591 |
+
"model.layers.15.mlp.experts.1",
|
| 592 |
+
"model.layers.15.mlp.experts.2",
|
| 593 |
+
"model.layers.15.mlp.experts.3",
|
| 594 |
+
"model.layers.15.mlp.experts.4",
|
| 595 |
+
"model.layers.15.mlp.experts.5",
|
| 596 |
+
"model.layers.15.mlp.experts.6",
|
| 597 |
+
"model.layers.15.mlp.experts.7",
|
| 598 |
+
"model.layers.15.mlp.experts.8",
|
| 599 |
+
"model.layers.15.mlp.experts.9",
|
| 600 |
+
"model.layers.15.mlp.experts.10",
|
| 601 |
+
"model.layers.15.mlp.experts.11",
|
| 602 |
+
"model.layers.15.mlp.experts.12",
|
| 603 |
+
"model.layers.15.mlp.experts.13",
|
| 604 |
+
"model.layers.15.mlp.experts.14",
|
| 605 |
+
"model.layers.15.mlp.experts.15",
|
| 606 |
+
"model.layers.15.mlp.experts.16",
|
| 607 |
+
"model.layers.15.mlp.experts.17",
|
| 608 |
+
"model.layers.15.mlp.experts.18",
|
| 609 |
+
"model.layers.15.mlp.experts.19",
|
| 610 |
+
"model.layers.15.mlp.experts.20",
|
| 611 |
+
"model.layers.15.mlp.experts.21",
|
| 612 |
+
"model.layers.15.mlp.experts.22",
|
| 613 |
+
"model.layers.15.mlp.experts.23",
|
| 614 |
+
"model.layers.15.mlp.experts.24",
|
| 615 |
+
"model.layers.15.mlp.experts.25",
|
| 616 |
+
"model.layers.15.mlp.experts.26",
|
| 617 |
+
"model.layers.15.mlp.experts.27",
|
| 618 |
+
"model.layers.15.mlp.experts.28",
|
| 619 |
+
"model.layers.15.mlp.experts.29",
|
| 620 |
+
"model.layers.15.mlp.experts.30",
|
| 621 |
+
"model.layers.15.mlp.experts.31",
|
| 622 |
+
"model.layers.16.mlp.router",
|
| 623 |
+
"model.layers.16.mlp.experts.0",
|
| 624 |
+
"model.layers.16.mlp.experts.1",
|
| 625 |
+
"model.layers.16.mlp.experts.2",
|
| 626 |
+
"model.layers.16.mlp.experts.3",
|
| 627 |
+
"model.layers.16.mlp.experts.4",
|
| 628 |
+
"model.layers.16.mlp.experts.5",
|
| 629 |
+
"model.layers.16.mlp.experts.6",
|
| 630 |
+
"model.layers.16.mlp.experts.7",
|
| 631 |
+
"model.layers.16.mlp.experts.8",
|
| 632 |
+
"model.layers.16.mlp.experts.9",
|
| 633 |
+
"model.layers.16.mlp.experts.10",
|
| 634 |
+
"model.layers.16.mlp.experts.11",
|
| 635 |
+
"model.layers.16.mlp.experts.12",
|
| 636 |
+
"model.layers.16.mlp.experts.13",
|
| 637 |
+
"model.layers.16.mlp.experts.14",
|
| 638 |
+
"model.layers.16.mlp.experts.15",
|
| 639 |
+
"model.layers.16.mlp.experts.16",
|
| 640 |
+
"model.layers.16.mlp.experts.17",
|
| 641 |
+
"model.layers.16.mlp.experts.18",
|
| 642 |
+
"model.layers.16.mlp.experts.19",
|
| 643 |
+
"model.layers.16.mlp.experts.20",
|
| 644 |
+
"model.layers.16.mlp.experts.21",
|
| 645 |
+
"model.layers.16.mlp.experts.22",
|
| 646 |
+
"model.layers.16.mlp.experts.23",
|
| 647 |
+
"model.layers.16.mlp.experts.24",
|
| 648 |
+
"model.layers.16.mlp.experts.25",
|
| 649 |
+
"model.layers.16.mlp.experts.26",
|
| 650 |
+
"model.layers.16.mlp.experts.27",
|
| 651 |
+
"model.layers.16.mlp.experts.28",
|
| 652 |
+
"model.layers.16.mlp.experts.29",
|
| 653 |
+
"model.layers.16.mlp.experts.30",
|
| 654 |
+
"model.layers.16.mlp.experts.31",
|
| 655 |
+
"model.layers.17.mlp.router",
|
| 656 |
+
"model.layers.17.mlp.experts.0",
|
| 657 |
+
"model.layers.17.mlp.experts.1",
|
| 658 |
+
"model.layers.17.mlp.experts.2",
|
| 659 |
+
"model.layers.17.mlp.experts.3",
|
| 660 |
+
"model.layers.17.mlp.experts.4",
|
| 661 |
+
"model.layers.17.mlp.experts.5",
|
| 662 |
+
"model.layers.17.mlp.experts.6",
|
| 663 |
+
"model.layers.17.mlp.experts.7",
|
| 664 |
+
"model.layers.17.mlp.experts.8",
|
| 665 |
+
"model.layers.17.mlp.experts.9",
|
| 666 |
+
"model.layers.17.mlp.experts.10",
|
| 667 |
+
"model.layers.17.mlp.experts.11",
|
| 668 |
+
"model.layers.17.mlp.experts.12",
|
| 669 |
+
"model.layers.17.mlp.experts.13",
|
| 670 |
+
"model.layers.17.mlp.experts.14",
|
| 671 |
+
"model.layers.17.mlp.experts.15",
|
| 672 |
+
"model.layers.17.mlp.experts.16",
|
| 673 |
+
"model.layers.17.mlp.experts.17",
|
| 674 |
+
"model.layers.17.mlp.experts.18",
|
| 675 |
+
"model.layers.17.mlp.experts.19",
|
| 676 |
+
"model.layers.17.mlp.experts.20",
|
| 677 |
+
"model.layers.17.mlp.experts.21",
|
| 678 |
+
"model.layers.17.mlp.experts.22",
|
| 679 |
+
"model.layers.17.mlp.experts.23",
|
| 680 |
+
"model.layers.17.mlp.experts.24",
|
| 681 |
+
"model.layers.17.mlp.experts.25",
|
| 682 |
+
"model.layers.17.mlp.experts.26",
|
| 683 |
+
"model.layers.17.mlp.experts.27",
|
| 684 |
+
"model.layers.17.mlp.experts.28",
|
| 685 |
+
"model.layers.17.mlp.experts.29",
|
| 686 |
+
"model.layers.17.mlp.experts.30",
|
| 687 |
+
"model.layers.17.mlp.experts.31",
|
| 688 |
+
"model.layers.18.mlp.router",
|
| 689 |
+
"model.layers.18.mlp.experts.0",
|
| 690 |
+
"model.layers.18.mlp.experts.1",
|
| 691 |
+
"model.layers.18.mlp.experts.2",
|
| 692 |
+
"model.layers.18.mlp.experts.3",
|
| 693 |
+
"model.layers.18.mlp.experts.4",
|
| 694 |
+
"model.layers.18.mlp.experts.5",
|
| 695 |
+
"model.layers.18.mlp.experts.6",
|
| 696 |
+
"model.layers.18.mlp.experts.7",
|
| 697 |
+
"model.layers.18.mlp.experts.8",
|
| 698 |
+
"model.layers.18.mlp.experts.9",
|
| 699 |
+
"model.layers.18.mlp.experts.10",
|
| 700 |
+
"model.layers.18.mlp.experts.11",
|
| 701 |
+
"model.layers.18.mlp.experts.12",
|
| 702 |
+
"model.layers.18.mlp.experts.13",
|
| 703 |
+
"model.layers.18.mlp.experts.14",
|
| 704 |
+
"model.layers.18.mlp.experts.15",
|
| 705 |
+
"model.layers.18.mlp.experts.16",
|
| 706 |
+
"model.layers.18.mlp.experts.17",
|
| 707 |
+
"model.layers.18.mlp.experts.18",
|
| 708 |
+
"model.layers.18.mlp.experts.19",
|
| 709 |
+
"model.layers.18.mlp.experts.20",
|
| 710 |
+
"model.layers.18.mlp.experts.21",
|
| 711 |
+
"model.layers.18.mlp.experts.22",
|
| 712 |
+
"model.layers.18.mlp.experts.23",
|
| 713 |
+
"model.layers.18.mlp.experts.24",
|
| 714 |
+
"model.layers.18.mlp.experts.25",
|
| 715 |
+
"model.layers.18.mlp.experts.26",
|
| 716 |
+
"model.layers.18.mlp.experts.27",
|
| 717 |
+
"model.layers.18.mlp.experts.28",
|
| 718 |
+
"model.layers.18.mlp.experts.29",
|
| 719 |
+
"model.layers.18.mlp.experts.30",
|
| 720 |
+
"model.layers.18.mlp.experts.31",
|
| 721 |
+
"model.layers.19.mlp.router",
|
| 722 |
+
"model.layers.19.mlp.experts.0",
|
| 723 |
+
"model.layers.19.mlp.experts.1",
|
| 724 |
+
"model.layers.19.mlp.experts.2",
|
| 725 |
+
"model.layers.19.mlp.experts.3",
|
| 726 |
+
"model.layers.19.mlp.experts.4",
|
| 727 |
+
"model.layers.19.mlp.experts.5",
|
| 728 |
+
"model.layers.19.mlp.experts.6",
|
| 729 |
+
"model.layers.19.mlp.experts.7",
|
| 730 |
+
"model.layers.19.mlp.experts.8",
|
| 731 |
+
"model.layers.19.mlp.experts.9",
|
| 732 |
+
"model.layers.19.mlp.experts.10",
|
| 733 |
+
"model.layers.19.mlp.experts.11",
|
| 734 |
+
"model.layers.19.mlp.experts.12",
|
| 735 |
+
"model.layers.19.mlp.experts.13",
|
| 736 |
+
"model.layers.19.mlp.experts.14",
|
| 737 |
+
"model.layers.19.mlp.experts.15",
|
| 738 |
+
"model.layers.19.mlp.experts.16",
|
| 739 |
+
"model.layers.19.mlp.experts.17",
|
| 740 |
+
"model.layers.19.mlp.experts.18",
|
| 741 |
+
"model.layers.19.mlp.experts.19",
|
| 742 |
+
"model.layers.19.mlp.experts.20",
|
| 743 |
+
"model.layers.19.mlp.experts.21",
|
| 744 |
+
"model.layers.19.mlp.experts.22",
|
| 745 |
+
"model.layers.19.mlp.experts.23",
|
| 746 |
+
"model.layers.19.mlp.experts.24",
|
| 747 |
+
"model.layers.19.mlp.experts.25",
|
| 748 |
+
"model.layers.19.mlp.experts.26",
|
| 749 |
+
"model.layers.19.mlp.experts.27",
|
| 750 |
+
"model.layers.19.mlp.experts.28",
|
| 751 |
+
"model.layers.19.mlp.experts.29",
|
| 752 |
+
"model.layers.19.mlp.experts.30",
|
| 753 |
+
"model.layers.19.mlp.experts.31",
|
| 754 |
+
"model.layers.20.mlp.router",
|
| 755 |
+
"model.layers.20.mlp.experts.0",
|
| 756 |
+
"model.layers.20.mlp.experts.1",
|
| 757 |
+
"model.layers.20.mlp.experts.2",
|
| 758 |
+
"model.layers.20.mlp.experts.3",
|
| 759 |
+
"model.layers.20.mlp.experts.4",
|
| 760 |
+
"model.layers.20.mlp.experts.5",
|
| 761 |
+
"model.layers.20.mlp.experts.6",
|
| 762 |
+
"model.layers.20.mlp.experts.7",
|
| 763 |
+
"model.layers.20.mlp.experts.8",
|
| 764 |
+
"model.layers.20.mlp.experts.9",
|
| 765 |
+
"model.layers.20.mlp.experts.10",
|
| 766 |
+
"model.layers.20.mlp.experts.11",
|
| 767 |
+
"model.layers.20.mlp.experts.12",
|
| 768 |
+
"model.layers.20.mlp.experts.13",
|
| 769 |
+
"model.layers.20.mlp.experts.14",
|
| 770 |
+
"model.layers.20.mlp.experts.15",
|
| 771 |
+
"model.layers.20.mlp.experts.16",
|
| 772 |
+
"model.layers.20.mlp.experts.17",
|
| 773 |
+
"model.layers.20.mlp.experts.18",
|
| 774 |
+
"model.layers.20.mlp.experts.19",
|
| 775 |
+
"model.layers.20.mlp.experts.20",
|
| 776 |
+
"model.layers.20.mlp.experts.21",
|
| 777 |
+
"model.layers.20.mlp.experts.22",
|
| 778 |
+
"model.layers.20.mlp.experts.23",
|
| 779 |
+
"model.layers.20.mlp.experts.24",
|
| 780 |
+
"model.layers.20.mlp.experts.25",
|
| 781 |
+
"model.layers.20.mlp.experts.26",
|
| 782 |
+
"model.layers.20.mlp.experts.27",
|
| 783 |
+
"model.layers.20.mlp.experts.28",
|
| 784 |
+
"model.layers.20.mlp.experts.29",
|
| 785 |
+
"model.layers.20.mlp.experts.30",
|
| 786 |
+
"model.layers.20.mlp.experts.31",
|
| 787 |
+
"model.layers.21.mlp.router",
|
| 788 |
+
"model.layers.21.mlp.experts.0",
|
| 789 |
+
"model.layers.21.mlp.experts.1",
|
| 790 |
+
"model.layers.21.mlp.experts.2",
|
| 791 |
+
"model.layers.21.mlp.experts.3",
|
| 792 |
+
"model.layers.21.mlp.experts.4",
|
| 793 |
+
"model.layers.21.mlp.experts.5",
|
| 794 |
+
"model.layers.21.mlp.experts.6",
|
| 795 |
+
"model.layers.21.mlp.experts.7",
|
| 796 |
+
"model.layers.21.mlp.experts.8",
|
| 797 |
+
"model.layers.21.mlp.experts.9",
|
| 798 |
+
"model.layers.21.mlp.experts.10",
|
| 799 |
+
"model.layers.21.mlp.experts.11",
|
| 800 |
+
"model.layers.21.mlp.experts.12",
|
| 801 |
+
"model.layers.21.mlp.experts.13",
|
| 802 |
+
"model.layers.21.mlp.experts.14",
|
| 803 |
+
"model.layers.21.mlp.experts.15",
|
| 804 |
+
"model.layers.21.mlp.experts.16",
|
| 805 |
+
"model.layers.21.mlp.experts.17",
|
| 806 |
+
"model.layers.21.mlp.experts.18",
|
| 807 |
+
"model.layers.21.mlp.experts.19",
|
| 808 |
+
"model.layers.21.mlp.experts.20",
|
| 809 |
+
"model.layers.21.mlp.experts.21",
|
| 810 |
+
"model.layers.21.mlp.experts.22",
|
| 811 |
+
"model.layers.21.mlp.experts.23",
|
| 812 |
+
"model.layers.21.mlp.experts.24",
|
| 813 |
+
"model.layers.21.mlp.experts.25",
|
| 814 |
+
"model.layers.21.mlp.experts.26",
|
| 815 |
+
"model.layers.21.mlp.experts.27",
|
| 816 |
+
"model.layers.21.mlp.experts.28",
|
| 817 |
+
"model.layers.21.mlp.experts.29",
|
| 818 |
+
"model.layers.21.mlp.experts.30",
|
| 819 |
+
"model.layers.21.mlp.experts.31",
|
| 820 |
+
"model.layers.22.mlp.router",
|
| 821 |
+
"model.layers.22.mlp.experts.0",
|
| 822 |
+
"model.layers.22.mlp.experts.1",
|
| 823 |
+
"model.layers.22.mlp.experts.2",
|
| 824 |
+
"model.layers.22.mlp.experts.3",
|
| 825 |
+
"model.layers.22.mlp.experts.4",
|
| 826 |
+
"model.layers.22.mlp.experts.5",
|
| 827 |
+
"model.layers.22.mlp.experts.6",
|
| 828 |
+
"model.layers.22.mlp.experts.7",
|
| 829 |
+
"model.layers.22.mlp.experts.8",
|
| 830 |
+
"model.layers.22.mlp.experts.9",
|
| 831 |
+
"model.layers.22.mlp.experts.10",
|
| 832 |
+
"model.layers.22.mlp.experts.11",
|
| 833 |
+
"model.layers.22.mlp.experts.12",
|
| 834 |
+
"model.layers.22.mlp.experts.13",
|
| 835 |
+
"model.layers.22.mlp.experts.14",
|
| 836 |
+
"model.layers.22.mlp.experts.15",
|
| 837 |
+
"model.layers.22.mlp.experts.16",
|
| 838 |
+
"model.layers.22.mlp.experts.17",
|
| 839 |
+
"model.layers.22.mlp.experts.18",
|
| 840 |
+
"model.layers.22.mlp.experts.19",
|
| 841 |
+
"model.layers.22.mlp.experts.20",
|
| 842 |
+
"model.layers.22.mlp.experts.21",
|
| 843 |
+
"model.layers.22.mlp.experts.22",
|
| 844 |
+
"model.layers.22.mlp.experts.23",
|
| 845 |
+
"model.layers.22.mlp.experts.24",
|
| 846 |
+
"model.layers.22.mlp.experts.25",
|
| 847 |
+
"model.layers.22.mlp.experts.26",
|
| 848 |
+
"model.layers.22.mlp.experts.27",
|
| 849 |
+
"model.layers.22.mlp.experts.28",
|
| 850 |
+
"model.layers.22.mlp.experts.29",
|
| 851 |
+
"model.layers.22.mlp.experts.30",
|
| 852 |
+
"model.layers.22.mlp.experts.31",
|
| 853 |
+
"model.layers.23.mlp.router",
|
| 854 |
+
"model.layers.23.mlp.experts.0",
|
| 855 |
+
"model.layers.23.mlp.experts.1",
|
| 856 |
+
"model.layers.23.mlp.experts.2",
|
| 857 |
+
"model.layers.23.mlp.experts.3",
|
| 858 |
+
"model.layers.23.mlp.experts.4",
|
| 859 |
+
"model.layers.23.mlp.experts.5",
|
| 860 |
+
"model.layers.23.mlp.experts.6",
|
| 861 |
+
"model.layers.23.mlp.experts.7",
|
| 862 |
+
"model.layers.23.mlp.experts.8",
|
| 863 |
+
"model.layers.23.mlp.experts.9",
|
| 864 |
+
"model.layers.23.mlp.experts.10",
|
| 865 |
+
"model.layers.23.mlp.experts.11",
|
| 866 |
+
"model.layers.23.mlp.experts.12",
|
| 867 |
+
"model.layers.23.mlp.experts.13",
|
| 868 |
+
"model.layers.23.mlp.experts.14",
|
| 869 |
+
"model.layers.23.mlp.experts.15",
|
| 870 |
+
"model.layers.23.mlp.experts.16",
|
| 871 |
+
"model.layers.23.mlp.experts.17",
|
| 872 |
+
"model.layers.23.mlp.experts.18",
|
| 873 |
+
"model.layers.23.mlp.experts.19",
|
| 874 |
+
"model.layers.23.mlp.experts.20",
|
| 875 |
+
"model.layers.23.mlp.experts.21",
|
| 876 |
+
"model.layers.23.mlp.experts.22",
|
| 877 |
+
"model.layers.23.mlp.experts.23",
|
| 878 |
+
"model.layers.23.mlp.experts.24",
|
| 879 |
+
"model.layers.23.mlp.experts.25",
|
| 880 |
+
"model.layers.23.mlp.experts.26",
|
| 881 |
+
"model.layers.23.mlp.experts.27",
|
| 882 |
+
"model.layers.23.mlp.experts.28",
|
| 883 |
+
"model.layers.23.mlp.experts.29",
|
| 884 |
+
"model.layers.23.mlp.experts.30",
|
| 885 |
+
"model.layers.23.mlp.experts.31",
|
| 886 |
+
"lm_head"
|
| 887 |
+
],
|
| 888 |
+
"kv_cache_scheme": null,
|
| 889 |
+
"quant_method": "compressed-tensors",
|
| 890 |
+
"quantization_status": "compressed",
|
| 891 |
+
"sparsity_config": {},
|
| 892 |
+
"transform_config": {},
|
| 893 |
+
"version": "0.17.2.a20260702"
|
| 894 |
+
},
|
| 895 |
+
"rms_norm_eps": 1e-05,
|
| 896 |
+
"rope_parameters": {
|
| 897 |
+
"beta_fast": 32.0,
|
| 898 |
+
"beta_slow": 1.0,
|
| 899 |
+
"factor": 32.0,
|
| 900 |
+
"original_max_position_embeddings": 4096,
|
| 901 |
+
"rope_theta": 150000,
|
| 902 |
+
"rope_type": "yarn",
|
| 903 |
+
"truncate": false
|
| 904 |
+
},
|
| 905 |
+
"router_aux_loss_coef": 0.9,
|
| 906 |
+
"sliding_window": 128,
|
| 907 |
+
"swiglu_limit": 7.0,
|
| 908 |
+
"tie_word_embeddings": false,
|
| 909 |
+
"transformers_version": "5.10.2",
|
| 910 |
+
"unsloth_version": "2026.7.3",
|
| 911 |
+
"use_cache": false,
|
| 912 |
+
"vocab_size": 201088
|
| 913 |
+
}
|
export_metadata.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"base_model": "unsloth/gpt-oss-20b-unsloth-bnb-4bit"
|
| 3 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 199998,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
200002,
|
| 6 |
+
199999
|
| 7 |
+
],
|
| 8 |
+
"max_length": 131072,
|
| 9 |
+
"pad_token_id": 199999,
|
| 10 |
+
"transformers_version": "5.10.2"
|
| 11 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:908668149abc0e2fa1744c422c134a9fa8b53a37f173e44f8ab83c34e8b16013
|
| 3 |
+
size 12826567496
|
recipe.yaml
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
default_stage:
|
| 2 |
+
default_modifiers:
|
| 3 |
+
QuantizationModifier:
|
| 4 |
+
targets: [Linear]
|
| 5 |
+
ignore: [lm_head, 're:.*\.linear_attn\..*', 're:.*\.visual\..*', 're:.*mtp.*', 're:.*\.gate$',
|
| 6 |
+
're:.*\.shared_expert_gate$']
|
| 7 |
+
scheme: MXFP4
|
| 8 |
+
bypass_divisibility_checks: false
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0614fe83cadab421296e664e1f48f4261fa8fef6e03e63bb75c20f38e37d07d3
|
| 3 |
+
size 27868174
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"backend": "tokenizers",
|
| 3 |
+
"bos_token": "<|startoftext|>",
|
| 4 |
+
"clean_up_tokenization_spaces": false,
|
| 5 |
+
"eos_token": "<|return|>",
|
| 6 |
+
"is_local": true,
|
| 7 |
+
"local_files_only": false,
|
| 8 |
+
"model_input_names": [
|
| 9 |
+
"input_ids",
|
| 10 |
+
"attention_mask"
|
| 11 |
+
],
|
| 12 |
+
"model_max_length": 131072,
|
| 13 |
+
"pad_token": "<|reserved_200017|>",
|
| 14 |
+
"padding_side": "left",
|
| 15 |
+
"tokenizer_class": "TokenizersBackend",
|
| 16 |
+
"unk_token": null
|
| 17 |
+
}
|