Add files using upload-large-folder tool
Browse files- README.md +1 -1
- chat_template.jinja +67 -133
- config.json +1754 -4
- generation_config.json +2 -1
- model-00001-of-00013.safetensors +2 -2
- model-00002-of-00013.safetensors +2 -2
- model-00003-of-00013.safetensors +2 -2
- model-00004-of-00013.safetensors +2 -2
- model-00005-of-00013.safetensors +2 -2
- model-00006-of-00013.safetensors +2 -2
- model-00007-of-00013.safetensors +2 -2
- model-00008-of-00013.safetensors +2 -2
- model-00009-of-00013.safetensors +2 -2
- model-00010-of-00013.safetensors +2 -2
- model-00011-of-00013.safetensors +2 -2
- model-00012-of-00013.safetensors +2 -2
- model-00013-of-00013.safetensors +2 -2
- model.safetensors.index.json +287 -395
README.md
CHANGED
|
@@ -12,7 +12,7 @@ base_model: openai/gpt-oss-120b
|
|
| 12 |
|
| 13 |
This model [NexVeridian/gpt-oss-120b-4bit](https://huggingface.co/NexVeridian/gpt-oss-120b-4bit) was
|
| 14 |
converted to MLX format from [openai/gpt-oss-120b](https://huggingface.co/openai/gpt-oss-120b)
|
| 15 |
-
using mlx-lm version **0.
|
| 16 |
|
| 17 |
## Use with mlx
|
| 18 |
|
|
|
|
| 12 |
|
| 13 |
This model [NexVeridian/gpt-oss-120b-4bit](https://huggingface.co/NexVeridian/gpt-oss-120b-4bit) was
|
| 14 |
converted to MLX format from [openai/gpt-oss-120b](https://huggingface.co/openai/gpt-oss-120b)
|
| 15 |
+
using mlx-lm version **0.27.0**.
|
| 16 |
|
| 17 |
## Use with mlx
|
| 18 |
|
chat_template.jinja
CHANGED
|
@@ -84,8 +84,7 @@
|
|
| 84 |
|
| 85 |
{%- elif param_spec.type == "object" -%}
|
| 86 |
{%- if param_spec.properties -%}
|
| 87 |
-
{{- "{
|
| 88 |
-
" }}
|
| 89 |
{%- for prop_name, prop_spec in param_spec.properties.items() -%}
|
| 90 |
{{- prop_name -}}
|
| 91 |
{%- if prop_name not in (param_spec.required or []) -%}
|
|
@@ -107,24 +106,17 @@
|
|
| 107 |
{%- endmacro -%}
|
| 108 |
|
| 109 |
{%- macro render_tool_namespace(namespace_name, tools) -%}
|
| 110 |
-
{{- "## " + namespace_name + "
|
| 111 |
-
|
| 112 |
-
" }}
|
| 113 |
-
{{- "namespace " + namespace_name + " {
|
| 114 |
-
|
| 115 |
-
" }}
|
| 116 |
{%- for tool in tools %}
|
| 117 |
{%- set tool = tool.function %}
|
| 118 |
-
{{- "// " + tool.description + "
|
| 119 |
-
" }}
|
| 120 |
{{- "type "+ tool.name + " = " }}
|
| 121 |
{%- if tool.parameters and tool.parameters.properties %}
|
| 122 |
-
{{- "(_: {
|
| 123 |
-
" }}
|
| 124 |
{%- for param_name, param_spec in tool.parameters.properties.items() %}
|
| 125 |
{%- if param_spec.description %}
|
| 126 |
-
{{- "// " + param_spec.description + "
|
| 127 |
-
" }}
|
| 128 |
{%- endif %}
|
| 129 |
{{- param_name }}
|
| 130 |
{%- if param_name not in (tool.parameters.required or []) -%}
|
|
@@ -142,20 +134,14 @@
|
|
| 142 |
{%- endif -%}
|
| 143 |
{%- endif -%}
|
| 144 |
{%- if not loop.last %}
|
| 145 |
-
{{- "
|
| 146 |
-
" }}
|
| 147 |
{%- else %}
|
| 148 |
-
{{- "
|
| 149 |
-
" }}
|
| 150 |
{%- endif -%}
|
| 151 |
{%- endfor %}
|
| 152 |
-
{{- "}) => any
|
| 153 |
-
|
| 154 |
-
" }}
|
| 155 |
{%- else -%}
|
| 156 |
-
{{- "() => any
|
| 157 |
-
|
| 158 |
-
" }}
|
| 159 |
{%- endif -%}
|
| 160 |
{%- endfor %}
|
| 161 |
{{- "} // namespace " + namespace_name }}
|
|
@@ -163,92 +149,46 @@
|
|
| 163 |
|
| 164 |
{%- macro render_builtin_tools(browser_tool, python_tool) -%}
|
| 165 |
{%- if browser_tool %}
|
| 166 |
-
{{- "## browser
|
| 167 |
-
|
| 168 |
-
" }}
|
| 169 |
-
{{- "//
|
| 170 |
-
" }}
|
| 171 |
-
{{- "//
|
| 172 |
-
" }}
|
| 173 |
-
{{- "
|
| 174 |
-
" }}
|
| 175 |
-
{{- "
|
| 176 |
-
" }}
|
| 177 |
-
{{- "
|
| 178 |
-
" }}
|
| 179 |
-
{{- "
|
| 180 |
-
" }}
|
| 181 |
-
{{- "
|
| 182 |
-
|
| 183 |
-
" }}
|
| 184 |
-
{{- "//
|
| 185 |
-
" }}
|
| 186 |
-
{{- "type
|
| 187 |
-
" }}
|
| 188 |
-
{{- "
|
| 189 |
-
" }}
|
| 190 |
-
{{- "
|
| 191 |
-
" }}
|
| 192 |
-
{{- "source?: string
|
| 193 |
-
" }}
|
| 194 |
-
{{- "
|
| 195 |
-
|
| 196 |
-
" }}
|
| 197 |
-
{{- "
|
| 198 |
-
" }}
|
| 199 |
-
{{- "//
|
| 200 |
-
" }}
|
| 201 |
-
{{- "// If `cursor` is not provided, the most recent page is implied.
|
| 202 |
-
" }}
|
| 203 |
-
{{- "// If `id` is a string, it is treated as a fully qualified URL associated with `source`.
|
| 204 |
-
" }}
|
| 205 |
-
{{- "// 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.
|
| 206 |
-
" }}
|
| 207 |
-
{{- "// Use this function without `id` to scroll to a new location of an opened page.
|
| 208 |
-
" }}
|
| 209 |
-
{{- "type open = (_: {
|
| 210 |
-
" }}
|
| 211 |
-
{{- "id?: number | string, // default: -1
|
| 212 |
-
" }}
|
| 213 |
-
{{- "cursor?: number, // default: -1
|
| 214 |
-
" }}
|
| 215 |
-
{{- "loc?: number, // default: -1
|
| 216 |
-
" }}
|
| 217 |
-
{{- "num_lines?: number, // default: -1
|
| 218 |
-
" }}
|
| 219 |
-
{{- "view_source?: boolean, // default: false
|
| 220 |
-
" }}
|
| 221 |
-
{{- "source?: string,
|
| 222 |
-
" }}
|
| 223 |
-
{{- "}) => any;
|
| 224 |
-
|
| 225 |
-
" }}
|
| 226 |
-
{{- "// Finds exact matches of `pattern` in the current page, or the page given by `cursor`.
|
| 227 |
-
" }}
|
| 228 |
-
{{- "type find = (_: {
|
| 229 |
-
" }}
|
| 230 |
-
{{- "pattern: string,
|
| 231 |
-
" }}
|
| 232 |
-
{{- "cursor?: number, // default: -1
|
| 233 |
-
" }}
|
| 234 |
-
{{- "}) => any;
|
| 235 |
-
|
| 236 |
-
" }}
|
| 237 |
-
{{- "} // namespace browser
|
| 238 |
-
|
| 239 |
-
" }}
|
| 240 |
{%- endif -%}
|
| 241 |
|
| 242 |
{%- if python_tool %}
|
| 243 |
-
{{- "## python
|
| 244 |
-
|
| 245 |
-
" }}
|
| 246 |
-
{{- "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).
|
| 247 |
-
|
| 248 |
-
" }}
|
| 249 |
-
{{- "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.
|
| 250 |
-
|
| 251 |
-
" }}
|
| 252 |
{%- endif -%}
|
| 253 |
{%- endmacro -%}
|
| 254 |
|
|
@@ -257,23 +197,15 @@
|
|
| 257 |
{%- if model_identity is not defined %}
|
| 258 |
{%- set model_identity = "You are ChatGPT, a large language model trained by OpenAI." %}
|
| 259 |
{%- endif %}
|
| 260 |
-
{{- model_identity + "
|
| 261 |
-
" }}
|
| 262 |
-
{{- "
|
| 263 |
-
" }}
|
| 264 |
-
{{- "Current date: " + strftime_now("%Y-%m-%d") + "
|
| 265 |
-
|
| 266 |
-
" }}
|
| 267 |
{%- if reasoning_effort is not defined %}
|
| 268 |
{%- set reasoning_effort = "medium" %}
|
| 269 |
{%- endif %}
|
| 270 |
-
{{- "Reasoning: " + reasoning_effort + "
|
| 271 |
-
|
| 272 |
-
" }}
|
| 273 |
{%- if builtin_tools %}
|
| 274 |
-
{{- "# Tools
|
| 275 |
-
|
| 276 |
-
" }}
|
| 277 |
{%- set available_builtin_tools = namespace(browser=false, python=false) %}
|
| 278 |
{%- for tool in builtin_tools %}
|
| 279 |
{%- if tool == "browser" %}
|
|
@@ -286,8 +218,7 @@
|
|
| 286 |
{%- endif -%}
|
| 287 |
{{- "# Valid channels: analysis, commentary, final. Channel must be included for every message." }}
|
| 288 |
{%- if tools -%}
|
| 289 |
-
{{- "
|
| 290 |
-
Calls to these tools must go to the commentary channel: 'functions'." }}
|
| 291 |
{%- endif -%}
|
| 292 |
{%- endmacro -%}
|
| 293 |
|
|
@@ -312,18 +243,12 @@ Calls to these tools must go to the commentary channel: 'functions'." }}
|
|
| 312 |
{%- if developer_message or tools %}
|
| 313 |
{{- "<|start|>developer<|message|>" }}
|
| 314 |
{%- if developer_message %}
|
| 315 |
-
{{- "# Instructions
|
| 316 |
-
|
| 317 |
-
" }}
|
| 318 |
{{- developer_message }}
|
|
|
|
| 319 |
{%- endif %}
|
| 320 |
{%- if tools -%}
|
| 321 |
-
{{- "
|
| 322 |
-
|
| 323 |
-
" }}
|
| 324 |
-
{{- "# Tools
|
| 325 |
-
|
| 326 |
-
" }}
|
| 327 |
{{- render_tool_namespace("functions", tools) }}
|
| 328 |
{%- endif -%}
|
| 329 |
{{- "<|end|>" }}
|
|
@@ -346,6 +271,15 @@ Calls to these tools must go to the commentary channel: 'functions'." }}
|
|
| 346 |
{%- endif %}
|
| 347 |
{%- endif %}
|
| 348 |
{%- if "tool_calls" in message %}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 349 |
{#- We assume max 1 tool call per message, and so we infer the tool call name #}
|
| 350 |
{#- in "tool" messages from the most recent assistant tool call name #}
|
| 351 |
{%- set tool_call = message.tool_calls[0] %}
|
|
@@ -354,9 +288,9 @@ Calls to these tools must go to the commentary channel: 'functions'." }}
|
|
| 354 |
{%- endif %}
|
| 355 |
{%- if message.content and message.thinking %}
|
| 356 |
{{- raise_exception("Cannot pass both content and thinking in an assistant message with tool calls! Put the analysis message in one or the other, but not both.") }}
|
| 357 |
-
{%- elif message.content %}
|
| 358 |
{{- "<|start|>assistant<|channel|>analysis<|message|>" + message.content + "<|end|>" }}
|
| 359 |
-
{%- elif message.thinking %}
|
| 360 |
{{- "<|start|>assistant<|channel|>analysis<|message|>" + message.thinking + "<|end|>" }}
|
| 361 |
{%- endif %}
|
| 362 |
{{- "<|start|>assistant to=" }}
|
|
|
|
| 84 |
|
| 85 |
{%- elif param_spec.type == "object" -%}
|
| 86 |
{%- if param_spec.properties -%}
|
| 87 |
+
{{- "{\n" }}
|
|
|
|
| 88 |
{%- for prop_name, prop_spec in param_spec.properties.items() -%}
|
| 89 |
{{- prop_name -}}
|
| 90 |
{%- if prop_name not in (param_spec.required or []) -%}
|
|
|
|
| 106 |
{%- endmacro -%}
|
| 107 |
|
| 108 |
{%- macro render_tool_namespace(namespace_name, tools) -%}
|
| 109 |
+
{{- "## " + namespace_name + "\n\n" }}
|
| 110 |
+
{{- "namespace " + namespace_name + " {\n\n" }}
|
|
|
|
|
|
|
|
|
|
|
|
|
| 111 |
{%- for tool in tools %}
|
| 112 |
{%- set tool = tool.function %}
|
| 113 |
+
{{- "// " + tool.description + "\n" }}
|
|
|
|
| 114 |
{{- "type "+ tool.name + " = " }}
|
| 115 |
{%- if tool.parameters and tool.parameters.properties %}
|
| 116 |
+
{{- "(_: {\n" }}
|
|
|
|
| 117 |
{%- for param_name, param_spec in tool.parameters.properties.items() %}
|
| 118 |
{%- if param_spec.description %}
|
| 119 |
+
{{- "// " + param_spec.description + "\n" }}
|
|
|
|
| 120 |
{%- endif %}
|
| 121 |
{{- param_name }}
|
| 122 |
{%- if param_name not in (tool.parameters.required or []) -%}
|
|
|
|
| 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 }}
|
|
|
|
| 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 |
|
|
|
|
| 197 |
{%- if model_identity is not defined %}
|
| 198 |
{%- set model_identity = "You are ChatGPT, a large language model trained by OpenAI." %}
|
| 199 |
{%- endif %}
|
| 200 |
+
{{- model_identity + "\n" }}
|
| 201 |
+
{{- "Knowledge cutoff: 2024-06\n" }}
|
| 202 |
+
{{- "Current date: " + strftime_now("%Y-%m-%d") + "\n\n" }}
|
|
|
|
|
|
|
|
|
|
|
|
|
| 203 |
{%- if reasoning_effort is not defined %}
|
| 204 |
{%- set reasoning_effort = "medium" %}
|
| 205 |
{%- endif %}
|
| 206 |
+
{{- "Reasoning: " + reasoning_effort + "\n\n" }}
|
|
|
|
|
|
|
| 207 |
{%- if builtin_tools %}
|
| 208 |
+
{{- "# Tools\n\n" }}
|
|
|
|
|
|
|
| 209 |
{%- set available_builtin_tools = namespace(browser=false, python=false) %}
|
| 210 |
{%- for tool in builtin_tools %}
|
| 211 |
{%- if tool == "browser" %}
|
|
|
|
| 218 |
{%- endif -%}
|
| 219 |
{{- "# Valid channels: analysis, commentary, final. Channel must be included for every message." }}
|
| 220 |
{%- if tools -%}
|
| 221 |
+
{{- "\nCalls to these tools must go to the commentary channel: 'functions'." }}
|
|
|
|
| 222 |
{%- endif -%}
|
| 223 |
{%- endmacro -%}
|
| 224 |
|
|
|
|
| 243 |
{%- if developer_message or tools %}
|
| 244 |
{{- "<|start|>developer<|message|>" }}
|
| 245 |
{%- if developer_message %}
|
| 246 |
+
{{- "# Instructions\n\n" }}
|
|
|
|
|
|
|
| 247 |
{{- developer_message }}
|
| 248 |
+
{{- "\n\n" }}
|
| 249 |
{%- endif %}
|
| 250 |
{%- if tools -%}
|
| 251 |
+
{{- "# Tools\n\n" }}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 252 |
{{- render_tool_namespace("functions", tools) }}
|
| 253 |
{%- endif -%}
|
| 254 |
{{- "<|end|>" }}
|
|
|
|
| 271 |
{%- endif %}
|
| 272 |
{%- endif %}
|
| 273 |
{%- if "tool_calls" in message %}
|
| 274 |
+
{#- We need very careful handling here - we want to drop the tool call analysis message if the model #}
|
| 275 |
+
{#- has output a later <|final|> message, but otherwise we want to retain it. This is the only case #}
|
| 276 |
+
{#- when we render CoT/analysis messages in inference. #}
|
| 277 |
+
{%- set future_final_message = namespace(found=false) %}
|
| 278 |
+
{%- for future_message in loop_messages[loop.index:] %}
|
| 279 |
+
{%- if future_message.role == 'assistant' and "tool_calls" not in future_message %}
|
| 280 |
+
{%- set future_final_message.found = true %}
|
| 281 |
+
{%- endif %}
|
| 282 |
+
{%- endfor %}
|
| 283 |
{#- We assume max 1 tool call per message, and so we infer the tool call name #}
|
| 284 |
{#- in "tool" messages from the most recent assistant tool call name #}
|
| 285 |
{%- set tool_call = message.tool_calls[0] %}
|
|
|
|
| 288 |
{%- endif %}
|
| 289 |
{%- if message.content and message.thinking %}
|
| 290 |
{{- raise_exception("Cannot pass both content and thinking in an assistant message with tool calls! Put the analysis message in one or the other, but not both.") }}
|
| 291 |
+
{%- elif message.content and not future_final_message.found %}
|
| 292 |
{{- "<|start|>assistant<|channel|>analysis<|message|>" + message.content + "<|end|>" }}
|
| 293 |
+
{%- elif message.thinking and not future_final_message.found %}
|
| 294 |
{{- "<|start|>assistant<|channel|>analysis<|message|>" + message.thinking + "<|end|>" }}
|
| 295 |
{%- endif %}
|
| 296 |
{{- "<|start|>assistant to=" }}
|
config.json
CHANGED
|
@@ -60,12 +60,1762 @@
|
|
| 60 |
"output_router_logits": false,
|
| 61 |
"pad_token_id": 199999,
|
| 62 |
"quantization": {
|
| 63 |
-
"group_size":
|
| 64 |
-
"bits": 4
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 65 |
},
|
| 66 |
"quantization_config": {
|
| 67 |
-
"group_size":
|
| 68 |
-
"bits": 4
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 69 |
},
|
| 70 |
"rms_norm_eps": 1e-05,
|
| 71 |
"rope_scaling": {
|
|
|
|
| 60 |
"output_router_logits": false,
|
| 61 |
"pad_token_id": 199999,
|
| 62 |
"quantization": {
|
| 63 |
+
"group_size": 32,
|
| 64 |
+
"bits": 4,
|
| 65 |
+
"mode": "mxfp4",
|
| 66 |
+
"model.embed_tokens": {
|
| 67 |
+
"group_size": 64,
|
| 68 |
+
"bits": 4,
|
| 69 |
+
"mode": "affine"
|
| 70 |
+
},
|
| 71 |
+
"model.layers.0.self_attn.q_proj": {
|
| 72 |
+
"group_size": 64,
|
| 73 |
+
"bits": 4,
|
| 74 |
+
"mode": "affine"
|
| 75 |
+
},
|
| 76 |
+
"model.layers.0.self_attn.k_proj": {
|
| 77 |
+
"group_size": 64,
|
| 78 |
+
"bits": 4,
|
| 79 |
+
"mode": "affine"
|
| 80 |
+
},
|
| 81 |
+
"model.layers.0.self_attn.v_proj": {
|
| 82 |
+
"group_size": 64,
|
| 83 |
+
"bits": 4,
|
| 84 |
+
"mode": "affine"
|
| 85 |
+
},
|
| 86 |
+
"model.layers.0.self_attn.o_proj": {
|
| 87 |
+
"group_size": 64,
|
| 88 |
+
"bits": 4,
|
| 89 |
+
"mode": "affine"
|
| 90 |
+
},
|
| 91 |
+
"model.layers.0.mlp.router": {
|
| 92 |
+
"group_size": 64,
|
| 93 |
+
"bits": 8
|
| 94 |
+
},
|
| 95 |
+
"model.layers.1.self_attn.q_proj": {
|
| 96 |
+
"group_size": 64,
|
| 97 |
+
"bits": 4,
|
| 98 |
+
"mode": "affine"
|
| 99 |
+
},
|
| 100 |
+
"model.layers.1.self_attn.k_proj": {
|
| 101 |
+
"group_size": 64,
|
| 102 |
+
"bits": 4,
|
| 103 |
+
"mode": "affine"
|
| 104 |
+
},
|
| 105 |
+
"model.layers.1.self_attn.v_proj": {
|
| 106 |
+
"group_size": 64,
|
| 107 |
+
"bits": 4,
|
| 108 |
+
"mode": "affine"
|
| 109 |
+
},
|
| 110 |
+
"model.layers.1.self_attn.o_proj": {
|
| 111 |
+
"group_size": 64,
|
| 112 |
+
"bits": 4,
|
| 113 |
+
"mode": "affine"
|
| 114 |
+
},
|
| 115 |
+
"model.layers.1.mlp.router": {
|
| 116 |
+
"group_size": 64,
|
| 117 |
+
"bits": 8
|
| 118 |
+
},
|
| 119 |
+
"model.layers.2.self_attn.q_proj": {
|
| 120 |
+
"group_size": 64,
|
| 121 |
+
"bits": 4,
|
| 122 |
+
"mode": "affine"
|
| 123 |
+
},
|
| 124 |
+
"model.layers.2.self_attn.k_proj": {
|
| 125 |
+
"group_size": 64,
|
| 126 |
+
"bits": 4,
|
| 127 |
+
"mode": "affine"
|
| 128 |
+
},
|
| 129 |
+
"model.layers.2.self_attn.v_proj": {
|
| 130 |
+
"group_size": 64,
|
| 131 |
+
"bits": 4,
|
| 132 |
+
"mode": "affine"
|
| 133 |
+
},
|
| 134 |
+
"model.layers.2.self_attn.o_proj": {
|
| 135 |
+
"group_size": 64,
|
| 136 |
+
"bits": 4,
|
| 137 |
+
"mode": "affine"
|
| 138 |
+
},
|
| 139 |
+
"model.layers.2.mlp.router": {
|
| 140 |
+
"group_size": 64,
|
| 141 |
+
"bits": 8
|
| 142 |
+
},
|
| 143 |
+
"model.layers.3.self_attn.q_proj": {
|
| 144 |
+
"group_size": 64,
|
| 145 |
+
"bits": 4,
|
| 146 |
+
"mode": "affine"
|
| 147 |
+
},
|
| 148 |
+
"model.layers.3.self_attn.k_proj": {
|
| 149 |
+
"group_size": 64,
|
| 150 |
+
"bits": 4,
|
| 151 |
+
"mode": "affine"
|
| 152 |
+
},
|
| 153 |
+
"model.layers.3.self_attn.v_proj": {
|
| 154 |
+
"group_size": 64,
|
| 155 |
+
"bits": 4,
|
| 156 |
+
"mode": "affine"
|
| 157 |
+
},
|
| 158 |
+
"model.layers.3.self_attn.o_proj": {
|
| 159 |
+
"group_size": 64,
|
| 160 |
+
"bits": 4,
|
| 161 |
+
"mode": "affine"
|
| 162 |
+
},
|
| 163 |
+
"model.layers.3.mlp.router": {
|
| 164 |
+
"group_size": 64,
|
| 165 |
+
"bits": 8
|
| 166 |
+
},
|
| 167 |
+
"model.layers.4.self_attn.q_proj": {
|
| 168 |
+
"group_size": 64,
|
| 169 |
+
"bits": 4,
|
| 170 |
+
"mode": "affine"
|
| 171 |
+
},
|
| 172 |
+
"model.layers.4.self_attn.k_proj": {
|
| 173 |
+
"group_size": 64,
|
| 174 |
+
"bits": 4,
|
| 175 |
+
"mode": "affine"
|
| 176 |
+
},
|
| 177 |
+
"model.layers.4.self_attn.v_proj": {
|
| 178 |
+
"group_size": 64,
|
| 179 |
+
"bits": 4,
|
| 180 |
+
"mode": "affine"
|
| 181 |
+
},
|
| 182 |
+
"model.layers.4.self_attn.o_proj": {
|
| 183 |
+
"group_size": 64,
|
| 184 |
+
"bits": 4,
|
| 185 |
+
"mode": "affine"
|
| 186 |
+
},
|
| 187 |
+
"model.layers.4.mlp.router": {
|
| 188 |
+
"group_size": 64,
|
| 189 |
+
"bits": 8
|
| 190 |
+
},
|
| 191 |
+
"model.layers.5.self_attn.q_proj": {
|
| 192 |
+
"group_size": 64,
|
| 193 |
+
"bits": 4,
|
| 194 |
+
"mode": "affine"
|
| 195 |
+
},
|
| 196 |
+
"model.layers.5.self_attn.k_proj": {
|
| 197 |
+
"group_size": 64,
|
| 198 |
+
"bits": 4,
|
| 199 |
+
"mode": "affine"
|
| 200 |
+
},
|
| 201 |
+
"model.layers.5.self_attn.v_proj": {
|
| 202 |
+
"group_size": 64,
|
| 203 |
+
"bits": 4,
|
| 204 |
+
"mode": "affine"
|
| 205 |
+
},
|
| 206 |
+
"model.layers.5.self_attn.o_proj": {
|
| 207 |
+
"group_size": 64,
|
| 208 |
+
"bits": 4,
|
| 209 |
+
"mode": "affine"
|
| 210 |
+
},
|
| 211 |
+
"model.layers.5.mlp.router": {
|
| 212 |
+
"group_size": 64,
|
| 213 |
+
"bits": 8
|
| 214 |
+
},
|
| 215 |
+
"model.layers.6.self_attn.q_proj": {
|
| 216 |
+
"group_size": 64,
|
| 217 |
+
"bits": 4,
|
| 218 |
+
"mode": "affine"
|
| 219 |
+
},
|
| 220 |
+
"model.layers.6.self_attn.k_proj": {
|
| 221 |
+
"group_size": 64,
|
| 222 |
+
"bits": 4,
|
| 223 |
+
"mode": "affine"
|
| 224 |
+
},
|
| 225 |
+
"model.layers.6.self_attn.v_proj": {
|
| 226 |
+
"group_size": 64,
|
| 227 |
+
"bits": 4,
|
| 228 |
+
"mode": "affine"
|
| 229 |
+
},
|
| 230 |
+
"model.layers.6.self_attn.o_proj": {
|
| 231 |
+
"group_size": 64,
|
| 232 |
+
"bits": 4,
|
| 233 |
+
"mode": "affine"
|
| 234 |
+
},
|
| 235 |
+
"model.layers.6.mlp.router": {
|
| 236 |
+
"group_size": 64,
|
| 237 |
+
"bits": 8
|
| 238 |
+
},
|
| 239 |
+
"model.layers.7.self_attn.q_proj": {
|
| 240 |
+
"group_size": 64,
|
| 241 |
+
"bits": 4,
|
| 242 |
+
"mode": "affine"
|
| 243 |
+
},
|
| 244 |
+
"model.layers.7.self_attn.k_proj": {
|
| 245 |
+
"group_size": 64,
|
| 246 |
+
"bits": 4,
|
| 247 |
+
"mode": "affine"
|
| 248 |
+
},
|
| 249 |
+
"model.layers.7.self_attn.v_proj": {
|
| 250 |
+
"group_size": 64,
|
| 251 |
+
"bits": 4,
|
| 252 |
+
"mode": "affine"
|
| 253 |
+
},
|
| 254 |
+
"model.layers.7.self_attn.o_proj": {
|
| 255 |
+
"group_size": 64,
|
| 256 |
+
"bits": 4,
|
| 257 |
+
"mode": "affine"
|
| 258 |
+
},
|
| 259 |
+
"model.layers.7.mlp.router": {
|
| 260 |
+
"group_size": 64,
|
| 261 |
+
"bits": 8
|
| 262 |
+
},
|
| 263 |
+
"model.layers.8.self_attn.q_proj": {
|
| 264 |
+
"group_size": 64,
|
| 265 |
+
"bits": 4,
|
| 266 |
+
"mode": "affine"
|
| 267 |
+
},
|
| 268 |
+
"model.layers.8.self_attn.k_proj": {
|
| 269 |
+
"group_size": 64,
|
| 270 |
+
"bits": 4,
|
| 271 |
+
"mode": "affine"
|
| 272 |
+
},
|
| 273 |
+
"model.layers.8.self_attn.v_proj": {
|
| 274 |
+
"group_size": 64,
|
| 275 |
+
"bits": 4,
|
| 276 |
+
"mode": "affine"
|
| 277 |
+
},
|
| 278 |
+
"model.layers.8.self_attn.o_proj": {
|
| 279 |
+
"group_size": 64,
|
| 280 |
+
"bits": 4,
|
| 281 |
+
"mode": "affine"
|
| 282 |
+
},
|
| 283 |
+
"model.layers.8.mlp.router": {
|
| 284 |
+
"group_size": 64,
|
| 285 |
+
"bits": 8
|
| 286 |
+
},
|
| 287 |
+
"model.layers.9.self_attn.q_proj": {
|
| 288 |
+
"group_size": 64,
|
| 289 |
+
"bits": 4,
|
| 290 |
+
"mode": "affine"
|
| 291 |
+
},
|
| 292 |
+
"model.layers.9.self_attn.k_proj": {
|
| 293 |
+
"group_size": 64,
|
| 294 |
+
"bits": 4,
|
| 295 |
+
"mode": "affine"
|
| 296 |
+
},
|
| 297 |
+
"model.layers.9.self_attn.v_proj": {
|
| 298 |
+
"group_size": 64,
|
| 299 |
+
"bits": 4,
|
| 300 |
+
"mode": "affine"
|
| 301 |
+
},
|
| 302 |
+
"model.layers.9.self_attn.o_proj": {
|
| 303 |
+
"group_size": 64,
|
| 304 |
+
"bits": 4,
|
| 305 |
+
"mode": "affine"
|
| 306 |
+
},
|
| 307 |
+
"model.layers.9.mlp.router": {
|
| 308 |
+
"group_size": 64,
|
| 309 |
+
"bits": 8
|
| 310 |
+
},
|
| 311 |
+
"model.layers.10.self_attn.q_proj": {
|
| 312 |
+
"group_size": 64,
|
| 313 |
+
"bits": 4,
|
| 314 |
+
"mode": "affine"
|
| 315 |
+
},
|
| 316 |
+
"model.layers.10.self_attn.k_proj": {
|
| 317 |
+
"group_size": 64,
|
| 318 |
+
"bits": 4,
|
| 319 |
+
"mode": "affine"
|
| 320 |
+
},
|
| 321 |
+
"model.layers.10.self_attn.v_proj": {
|
| 322 |
+
"group_size": 64,
|
| 323 |
+
"bits": 4,
|
| 324 |
+
"mode": "affine"
|
| 325 |
+
},
|
| 326 |
+
"model.layers.10.self_attn.o_proj": {
|
| 327 |
+
"group_size": 64,
|
| 328 |
+
"bits": 4,
|
| 329 |
+
"mode": "affine"
|
| 330 |
+
},
|
| 331 |
+
"model.layers.10.mlp.router": {
|
| 332 |
+
"group_size": 64,
|
| 333 |
+
"bits": 8
|
| 334 |
+
},
|
| 335 |
+
"model.layers.11.self_attn.q_proj": {
|
| 336 |
+
"group_size": 64,
|
| 337 |
+
"bits": 4,
|
| 338 |
+
"mode": "affine"
|
| 339 |
+
},
|
| 340 |
+
"model.layers.11.self_attn.k_proj": {
|
| 341 |
+
"group_size": 64,
|
| 342 |
+
"bits": 4,
|
| 343 |
+
"mode": "affine"
|
| 344 |
+
},
|
| 345 |
+
"model.layers.11.self_attn.v_proj": {
|
| 346 |
+
"group_size": 64,
|
| 347 |
+
"bits": 4,
|
| 348 |
+
"mode": "affine"
|
| 349 |
+
},
|
| 350 |
+
"model.layers.11.self_attn.o_proj": {
|
| 351 |
+
"group_size": 64,
|
| 352 |
+
"bits": 4,
|
| 353 |
+
"mode": "affine"
|
| 354 |
+
},
|
| 355 |
+
"model.layers.11.mlp.router": {
|
| 356 |
+
"group_size": 64,
|
| 357 |
+
"bits": 8
|
| 358 |
+
},
|
| 359 |
+
"model.layers.12.self_attn.q_proj": {
|
| 360 |
+
"group_size": 64,
|
| 361 |
+
"bits": 4,
|
| 362 |
+
"mode": "affine"
|
| 363 |
+
},
|
| 364 |
+
"model.layers.12.self_attn.k_proj": {
|
| 365 |
+
"group_size": 64,
|
| 366 |
+
"bits": 4,
|
| 367 |
+
"mode": "affine"
|
| 368 |
+
},
|
| 369 |
+
"model.layers.12.self_attn.v_proj": {
|
| 370 |
+
"group_size": 64,
|
| 371 |
+
"bits": 4,
|
| 372 |
+
"mode": "affine"
|
| 373 |
+
},
|
| 374 |
+
"model.layers.12.self_attn.o_proj": {
|
| 375 |
+
"group_size": 64,
|
| 376 |
+
"bits": 4,
|
| 377 |
+
"mode": "affine"
|
| 378 |
+
},
|
| 379 |
+
"model.layers.12.mlp.router": {
|
| 380 |
+
"group_size": 64,
|
| 381 |
+
"bits": 8
|
| 382 |
+
},
|
| 383 |
+
"model.layers.13.self_attn.q_proj": {
|
| 384 |
+
"group_size": 64,
|
| 385 |
+
"bits": 4,
|
| 386 |
+
"mode": "affine"
|
| 387 |
+
},
|
| 388 |
+
"model.layers.13.self_attn.k_proj": {
|
| 389 |
+
"group_size": 64,
|
| 390 |
+
"bits": 4,
|
| 391 |
+
"mode": "affine"
|
| 392 |
+
},
|
| 393 |
+
"model.layers.13.self_attn.v_proj": {
|
| 394 |
+
"group_size": 64,
|
| 395 |
+
"bits": 4,
|
| 396 |
+
"mode": "affine"
|
| 397 |
+
},
|
| 398 |
+
"model.layers.13.self_attn.o_proj": {
|
| 399 |
+
"group_size": 64,
|
| 400 |
+
"bits": 4,
|
| 401 |
+
"mode": "affine"
|
| 402 |
+
},
|
| 403 |
+
"model.layers.13.mlp.router": {
|
| 404 |
+
"group_size": 64,
|
| 405 |
+
"bits": 8
|
| 406 |
+
},
|
| 407 |
+
"model.layers.14.self_attn.q_proj": {
|
| 408 |
+
"group_size": 64,
|
| 409 |
+
"bits": 4,
|
| 410 |
+
"mode": "affine"
|
| 411 |
+
},
|
| 412 |
+
"model.layers.14.self_attn.k_proj": {
|
| 413 |
+
"group_size": 64,
|
| 414 |
+
"bits": 4,
|
| 415 |
+
"mode": "affine"
|
| 416 |
+
},
|
| 417 |
+
"model.layers.14.self_attn.v_proj": {
|
| 418 |
+
"group_size": 64,
|
| 419 |
+
"bits": 4,
|
| 420 |
+
"mode": "affine"
|
| 421 |
+
},
|
| 422 |
+
"model.layers.14.self_attn.o_proj": {
|
| 423 |
+
"group_size": 64,
|
| 424 |
+
"bits": 4,
|
| 425 |
+
"mode": "affine"
|
| 426 |
+
},
|
| 427 |
+
"model.layers.14.mlp.router": {
|
| 428 |
+
"group_size": 64,
|
| 429 |
+
"bits": 8
|
| 430 |
+
},
|
| 431 |
+
"model.layers.15.self_attn.q_proj": {
|
| 432 |
+
"group_size": 64,
|
| 433 |
+
"bits": 4,
|
| 434 |
+
"mode": "affine"
|
| 435 |
+
},
|
| 436 |
+
"model.layers.15.self_attn.k_proj": {
|
| 437 |
+
"group_size": 64,
|
| 438 |
+
"bits": 4,
|
| 439 |
+
"mode": "affine"
|
| 440 |
+
},
|
| 441 |
+
"model.layers.15.self_attn.v_proj": {
|
| 442 |
+
"group_size": 64,
|
| 443 |
+
"bits": 4,
|
| 444 |
+
"mode": "affine"
|
| 445 |
+
},
|
| 446 |
+
"model.layers.15.self_attn.o_proj": {
|
| 447 |
+
"group_size": 64,
|
| 448 |
+
"bits": 4,
|
| 449 |
+
"mode": "affine"
|
| 450 |
+
},
|
| 451 |
+
"model.layers.15.mlp.router": {
|
| 452 |
+
"group_size": 64,
|
| 453 |
+
"bits": 8
|
| 454 |
+
},
|
| 455 |
+
"model.layers.16.self_attn.q_proj": {
|
| 456 |
+
"group_size": 64,
|
| 457 |
+
"bits": 4,
|
| 458 |
+
"mode": "affine"
|
| 459 |
+
},
|
| 460 |
+
"model.layers.16.self_attn.k_proj": {
|
| 461 |
+
"group_size": 64,
|
| 462 |
+
"bits": 4,
|
| 463 |
+
"mode": "affine"
|
| 464 |
+
},
|
| 465 |
+
"model.layers.16.self_attn.v_proj": {
|
| 466 |
+
"group_size": 64,
|
| 467 |
+
"bits": 4,
|
| 468 |
+
"mode": "affine"
|
| 469 |
+
},
|
| 470 |
+
"model.layers.16.self_attn.o_proj": {
|
| 471 |
+
"group_size": 64,
|
| 472 |
+
"bits": 4,
|
| 473 |
+
"mode": "affine"
|
| 474 |
+
},
|
| 475 |
+
"model.layers.16.mlp.router": {
|
| 476 |
+
"group_size": 64,
|
| 477 |
+
"bits": 8
|
| 478 |
+
},
|
| 479 |
+
"model.layers.17.self_attn.q_proj": {
|
| 480 |
+
"group_size": 64,
|
| 481 |
+
"bits": 4,
|
| 482 |
+
"mode": "affine"
|
| 483 |
+
},
|
| 484 |
+
"model.layers.17.self_attn.k_proj": {
|
| 485 |
+
"group_size": 64,
|
| 486 |
+
"bits": 4,
|
| 487 |
+
"mode": "affine"
|
| 488 |
+
},
|
| 489 |
+
"model.layers.17.self_attn.v_proj": {
|
| 490 |
+
"group_size": 64,
|
| 491 |
+
"bits": 4,
|
| 492 |
+
"mode": "affine"
|
| 493 |
+
},
|
| 494 |
+
"model.layers.17.self_attn.o_proj": {
|
| 495 |
+
"group_size": 64,
|
| 496 |
+
"bits": 4,
|
| 497 |
+
"mode": "affine"
|
| 498 |
+
},
|
| 499 |
+
"model.layers.17.mlp.router": {
|
| 500 |
+
"group_size": 64,
|
| 501 |
+
"bits": 8
|
| 502 |
+
},
|
| 503 |
+
"model.layers.18.self_attn.q_proj": {
|
| 504 |
+
"group_size": 64,
|
| 505 |
+
"bits": 4,
|
| 506 |
+
"mode": "affine"
|
| 507 |
+
},
|
| 508 |
+
"model.layers.18.self_attn.k_proj": {
|
| 509 |
+
"group_size": 64,
|
| 510 |
+
"bits": 4,
|
| 511 |
+
"mode": "affine"
|
| 512 |
+
},
|
| 513 |
+
"model.layers.18.self_attn.v_proj": {
|
| 514 |
+
"group_size": 64,
|
| 515 |
+
"bits": 4,
|
| 516 |
+
"mode": "affine"
|
| 517 |
+
},
|
| 518 |
+
"model.layers.18.self_attn.o_proj": {
|
| 519 |
+
"group_size": 64,
|
| 520 |
+
"bits": 4,
|
| 521 |
+
"mode": "affine"
|
| 522 |
+
},
|
| 523 |
+
"model.layers.18.mlp.router": {
|
| 524 |
+
"group_size": 64,
|
| 525 |
+
"bits": 8
|
| 526 |
+
},
|
| 527 |
+
"model.layers.19.self_attn.q_proj": {
|
| 528 |
+
"group_size": 64,
|
| 529 |
+
"bits": 4,
|
| 530 |
+
"mode": "affine"
|
| 531 |
+
},
|
| 532 |
+
"model.layers.19.self_attn.k_proj": {
|
| 533 |
+
"group_size": 64,
|
| 534 |
+
"bits": 4,
|
| 535 |
+
"mode": "affine"
|
| 536 |
+
},
|
| 537 |
+
"model.layers.19.self_attn.v_proj": {
|
| 538 |
+
"group_size": 64,
|
| 539 |
+
"bits": 4,
|
| 540 |
+
"mode": "affine"
|
| 541 |
+
},
|
| 542 |
+
"model.layers.19.self_attn.o_proj": {
|
| 543 |
+
"group_size": 64,
|
| 544 |
+
"bits": 4,
|
| 545 |
+
"mode": "affine"
|
| 546 |
+
},
|
| 547 |
+
"model.layers.19.mlp.router": {
|
| 548 |
+
"group_size": 64,
|
| 549 |
+
"bits": 8
|
| 550 |
+
},
|
| 551 |
+
"model.layers.20.self_attn.q_proj": {
|
| 552 |
+
"group_size": 64,
|
| 553 |
+
"bits": 4,
|
| 554 |
+
"mode": "affine"
|
| 555 |
+
},
|
| 556 |
+
"model.layers.20.self_attn.k_proj": {
|
| 557 |
+
"group_size": 64,
|
| 558 |
+
"bits": 4,
|
| 559 |
+
"mode": "affine"
|
| 560 |
+
},
|
| 561 |
+
"model.layers.20.self_attn.v_proj": {
|
| 562 |
+
"group_size": 64,
|
| 563 |
+
"bits": 4,
|
| 564 |
+
"mode": "affine"
|
| 565 |
+
},
|
| 566 |
+
"model.layers.20.self_attn.o_proj": {
|
| 567 |
+
"group_size": 64,
|
| 568 |
+
"bits": 4,
|
| 569 |
+
"mode": "affine"
|
| 570 |
+
},
|
| 571 |
+
"model.layers.20.mlp.router": {
|
| 572 |
+
"group_size": 64,
|
| 573 |
+
"bits": 8
|
| 574 |
+
},
|
| 575 |
+
"model.layers.21.self_attn.q_proj": {
|
| 576 |
+
"group_size": 64,
|
| 577 |
+
"bits": 4,
|
| 578 |
+
"mode": "affine"
|
| 579 |
+
},
|
| 580 |
+
"model.layers.21.self_attn.k_proj": {
|
| 581 |
+
"group_size": 64,
|
| 582 |
+
"bits": 4,
|
| 583 |
+
"mode": "affine"
|
| 584 |
+
},
|
| 585 |
+
"model.layers.21.self_attn.v_proj": {
|
| 586 |
+
"group_size": 64,
|
| 587 |
+
"bits": 4,
|
| 588 |
+
"mode": "affine"
|
| 589 |
+
},
|
| 590 |
+
"model.layers.21.self_attn.o_proj": {
|
| 591 |
+
"group_size": 64,
|
| 592 |
+
"bits": 4,
|
| 593 |
+
"mode": "affine"
|
| 594 |
+
},
|
| 595 |
+
"model.layers.21.mlp.router": {
|
| 596 |
+
"group_size": 64,
|
| 597 |
+
"bits": 8
|
| 598 |
+
},
|
| 599 |
+
"model.layers.22.self_attn.q_proj": {
|
| 600 |
+
"group_size": 64,
|
| 601 |
+
"bits": 4,
|
| 602 |
+
"mode": "affine"
|
| 603 |
+
},
|
| 604 |
+
"model.layers.22.self_attn.k_proj": {
|
| 605 |
+
"group_size": 64,
|
| 606 |
+
"bits": 4,
|
| 607 |
+
"mode": "affine"
|
| 608 |
+
},
|
| 609 |
+
"model.layers.22.self_attn.v_proj": {
|
| 610 |
+
"group_size": 64,
|
| 611 |
+
"bits": 4,
|
| 612 |
+
"mode": "affine"
|
| 613 |
+
},
|
| 614 |
+
"model.layers.22.self_attn.o_proj": {
|
| 615 |
+
"group_size": 64,
|
| 616 |
+
"bits": 4,
|
| 617 |
+
"mode": "affine"
|
| 618 |
+
},
|
| 619 |
+
"model.layers.22.mlp.router": {
|
| 620 |
+
"group_size": 64,
|
| 621 |
+
"bits": 8
|
| 622 |
+
},
|
| 623 |
+
"model.layers.23.self_attn.q_proj": {
|
| 624 |
+
"group_size": 64,
|
| 625 |
+
"bits": 4,
|
| 626 |
+
"mode": "affine"
|
| 627 |
+
},
|
| 628 |
+
"model.layers.23.self_attn.k_proj": {
|
| 629 |
+
"group_size": 64,
|
| 630 |
+
"bits": 4,
|
| 631 |
+
"mode": "affine"
|
| 632 |
+
},
|
| 633 |
+
"model.layers.23.self_attn.v_proj": {
|
| 634 |
+
"group_size": 64,
|
| 635 |
+
"bits": 4,
|
| 636 |
+
"mode": "affine"
|
| 637 |
+
},
|
| 638 |
+
"model.layers.23.self_attn.o_proj": {
|
| 639 |
+
"group_size": 64,
|
| 640 |
+
"bits": 4,
|
| 641 |
+
"mode": "affine"
|
| 642 |
+
},
|
| 643 |
+
"model.layers.23.mlp.router": {
|
| 644 |
+
"group_size": 64,
|
| 645 |
+
"bits": 8
|
| 646 |
+
},
|
| 647 |
+
"model.layers.24.self_attn.q_proj": {
|
| 648 |
+
"group_size": 64,
|
| 649 |
+
"bits": 4,
|
| 650 |
+
"mode": "affine"
|
| 651 |
+
},
|
| 652 |
+
"model.layers.24.self_attn.k_proj": {
|
| 653 |
+
"group_size": 64,
|
| 654 |
+
"bits": 4,
|
| 655 |
+
"mode": "affine"
|
| 656 |
+
},
|
| 657 |
+
"model.layers.24.self_attn.v_proj": {
|
| 658 |
+
"group_size": 64,
|
| 659 |
+
"bits": 4,
|
| 660 |
+
"mode": "affine"
|
| 661 |
+
},
|
| 662 |
+
"model.layers.24.self_attn.o_proj": {
|
| 663 |
+
"group_size": 64,
|
| 664 |
+
"bits": 4,
|
| 665 |
+
"mode": "affine"
|
| 666 |
+
},
|
| 667 |
+
"model.layers.24.mlp.router": {
|
| 668 |
+
"group_size": 64,
|
| 669 |
+
"bits": 8
|
| 670 |
+
},
|
| 671 |
+
"model.layers.25.self_attn.q_proj": {
|
| 672 |
+
"group_size": 64,
|
| 673 |
+
"bits": 4,
|
| 674 |
+
"mode": "affine"
|
| 675 |
+
},
|
| 676 |
+
"model.layers.25.self_attn.k_proj": {
|
| 677 |
+
"group_size": 64,
|
| 678 |
+
"bits": 4,
|
| 679 |
+
"mode": "affine"
|
| 680 |
+
},
|
| 681 |
+
"model.layers.25.self_attn.v_proj": {
|
| 682 |
+
"group_size": 64,
|
| 683 |
+
"bits": 4,
|
| 684 |
+
"mode": "affine"
|
| 685 |
+
},
|
| 686 |
+
"model.layers.25.self_attn.o_proj": {
|
| 687 |
+
"group_size": 64,
|
| 688 |
+
"bits": 4,
|
| 689 |
+
"mode": "affine"
|
| 690 |
+
},
|
| 691 |
+
"model.layers.25.mlp.router": {
|
| 692 |
+
"group_size": 64,
|
| 693 |
+
"bits": 8
|
| 694 |
+
},
|
| 695 |
+
"model.layers.26.self_attn.q_proj": {
|
| 696 |
+
"group_size": 64,
|
| 697 |
+
"bits": 4,
|
| 698 |
+
"mode": "affine"
|
| 699 |
+
},
|
| 700 |
+
"model.layers.26.self_attn.k_proj": {
|
| 701 |
+
"group_size": 64,
|
| 702 |
+
"bits": 4,
|
| 703 |
+
"mode": "affine"
|
| 704 |
+
},
|
| 705 |
+
"model.layers.26.self_attn.v_proj": {
|
| 706 |
+
"group_size": 64,
|
| 707 |
+
"bits": 4,
|
| 708 |
+
"mode": "affine"
|
| 709 |
+
},
|
| 710 |
+
"model.layers.26.self_attn.o_proj": {
|
| 711 |
+
"group_size": 64,
|
| 712 |
+
"bits": 4,
|
| 713 |
+
"mode": "affine"
|
| 714 |
+
},
|
| 715 |
+
"model.layers.26.mlp.router": {
|
| 716 |
+
"group_size": 64,
|
| 717 |
+
"bits": 8
|
| 718 |
+
},
|
| 719 |
+
"model.layers.27.self_attn.q_proj": {
|
| 720 |
+
"group_size": 64,
|
| 721 |
+
"bits": 4,
|
| 722 |
+
"mode": "affine"
|
| 723 |
+
},
|
| 724 |
+
"model.layers.27.self_attn.k_proj": {
|
| 725 |
+
"group_size": 64,
|
| 726 |
+
"bits": 4,
|
| 727 |
+
"mode": "affine"
|
| 728 |
+
},
|
| 729 |
+
"model.layers.27.self_attn.v_proj": {
|
| 730 |
+
"group_size": 64,
|
| 731 |
+
"bits": 4,
|
| 732 |
+
"mode": "affine"
|
| 733 |
+
},
|
| 734 |
+
"model.layers.27.self_attn.o_proj": {
|
| 735 |
+
"group_size": 64,
|
| 736 |
+
"bits": 4,
|
| 737 |
+
"mode": "affine"
|
| 738 |
+
},
|
| 739 |
+
"model.layers.27.mlp.router": {
|
| 740 |
+
"group_size": 64,
|
| 741 |
+
"bits": 8
|
| 742 |
+
},
|
| 743 |
+
"model.layers.28.self_attn.q_proj": {
|
| 744 |
+
"group_size": 64,
|
| 745 |
+
"bits": 4,
|
| 746 |
+
"mode": "affine"
|
| 747 |
+
},
|
| 748 |
+
"model.layers.28.self_attn.k_proj": {
|
| 749 |
+
"group_size": 64,
|
| 750 |
+
"bits": 4,
|
| 751 |
+
"mode": "affine"
|
| 752 |
+
},
|
| 753 |
+
"model.layers.28.self_attn.v_proj": {
|
| 754 |
+
"group_size": 64,
|
| 755 |
+
"bits": 4,
|
| 756 |
+
"mode": "affine"
|
| 757 |
+
},
|
| 758 |
+
"model.layers.28.self_attn.o_proj": {
|
| 759 |
+
"group_size": 64,
|
| 760 |
+
"bits": 4,
|
| 761 |
+
"mode": "affine"
|
| 762 |
+
},
|
| 763 |
+
"model.layers.28.mlp.router": {
|
| 764 |
+
"group_size": 64,
|
| 765 |
+
"bits": 8
|
| 766 |
+
},
|
| 767 |
+
"model.layers.29.self_attn.q_proj": {
|
| 768 |
+
"group_size": 64,
|
| 769 |
+
"bits": 4,
|
| 770 |
+
"mode": "affine"
|
| 771 |
+
},
|
| 772 |
+
"model.layers.29.self_attn.k_proj": {
|
| 773 |
+
"group_size": 64,
|
| 774 |
+
"bits": 4,
|
| 775 |
+
"mode": "affine"
|
| 776 |
+
},
|
| 777 |
+
"model.layers.29.self_attn.v_proj": {
|
| 778 |
+
"group_size": 64,
|
| 779 |
+
"bits": 4,
|
| 780 |
+
"mode": "affine"
|
| 781 |
+
},
|
| 782 |
+
"model.layers.29.self_attn.o_proj": {
|
| 783 |
+
"group_size": 64,
|
| 784 |
+
"bits": 4,
|
| 785 |
+
"mode": "affine"
|
| 786 |
+
},
|
| 787 |
+
"model.layers.29.mlp.router": {
|
| 788 |
+
"group_size": 64,
|
| 789 |
+
"bits": 8
|
| 790 |
+
},
|
| 791 |
+
"model.layers.30.self_attn.q_proj": {
|
| 792 |
+
"group_size": 64,
|
| 793 |
+
"bits": 4,
|
| 794 |
+
"mode": "affine"
|
| 795 |
+
},
|
| 796 |
+
"model.layers.30.self_attn.k_proj": {
|
| 797 |
+
"group_size": 64,
|
| 798 |
+
"bits": 4,
|
| 799 |
+
"mode": "affine"
|
| 800 |
+
},
|
| 801 |
+
"model.layers.30.self_attn.v_proj": {
|
| 802 |
+
"group_size": 64,
|
| 803 |
+
"bits": 4,
|
| 804 |
+
"mode": "affine"
|
| 805 |
+
},
|
| 806 |
+
"model.layers.30.self_attn.o_proj": {
|
| 807 |
+
"group_size": 64,
|
| 808 |
+
"bits": 4,
|
| 809 |
+
"mode": "affine"
|
| 810 |
+
},
|
| 811 |
+
"model.layers.30.mlp.router": {
|
| 812 |
+
"group_size": 64,
|
| 813 |
+
"bits": 8
|
| 814 |
+
},
|
| 815 |
+
"model.layers.31.self_attn.q_proj": {
|
| 816 |
+
"group_size": 64,
|
| 817 |
+
"bits": 4,
|
| 818 |
+
"mode": "affine"
|
| 819 |
+
},
|
| 820 |
+
"model.layers.31.self_attn.k_proj": {
|
| 821 |
+
"group_size": 64,
|
| 822 |
+
"bits": 4,
|
| 823 |
+
"mode": "affine"
|
| 824 |
+
},
|
| 825 |
+
"model.layers.31.self_attn.v_proj": {
|
| 826 |
+
"group_size": 64,
|
| 827 |
+
"bits": 4,
|
| 828 |
+
"mode": "affine"
|
| 829 |
+
},
|
| 830 |
+
"model.layers.31.self_attn.o_proj": {
|
| 831 |
+
"group_size": 64,
|
| 832 |
+
"bits": 4,
|
| 833 |
+
"mode": "affine"
|
| 834 |
+
},
|
| 835 |
+
"model.layers.31.mlp.router": {
|
| 836 |
+
"group_size": 64,
|
| 837 |
+
"bits": 8
|
| 838 |
+
},
|
| 839 |
+
"model.layers.32.self_attn.q_proj": {
|
| 840 |
+
"group_size": 64,
|
| 841 |
+
"bits": 4,
|
| 842 |
+
"mode": "affine"
|
| 843 |
+
},
|
| 844 |
+
"model.layers.32.self_attn.k_proj": {
|
| 845 |
+
"group_size": 64,
|
| 846 |
+
"bits": 4,
|
| 847 |
+
"mode": "affine"
|
| 848 |
+
},
|
| 849 |
+
"model.layers.32.self_attn.v_proj": {
|
| 850 |
+
"group_size": 64,
|
| 851 |
+
"bits": 4,
|
| 852 |
+
"mode": "affine"
|
| 853 |
+
},
|
| 854 |
+
"model.layers.32.self_attn.o_proj": {
|
| 855 |
+
"group_size": 64,
|
| 856 |
+
"bits": 4,
|
| 857 |
+
"mode": "affine"
|
| 858 |
+
},
|
| 859 |
+
"model.layers.32.mlp.router": {
|
| 860 |
+
"group_size": 64,
|
| 861 |
+
"bits": 8
|
| 862 |
+
},
|
| 863 |
+
"model.layers.33.self_attn.q_proj": {
|
| 864 |
+
"group_size": 64,
|
| 865 |
+
"bits": 4,
|
| 866 |
+
"mode": "affine"
|
| 867 |
+
},
|
| 868 |
+
"model.layers.33.self_attn.k_proj": {
|
| 869 |
+
"group_size": 64,
|
| 870 |
+
"bits": 4,
|
| 871 |
+
"mode": "affine"
|
| 872 |
+
},
|
| 873 |
+
"model.layers.33.self_attn.v_proj": {
|
| 874 |
+
"group_size": 64,
|
| 875 |
+
"bits": 4,
|
| 876 |
+
"mode": "affine"
|
| 877 |
+
},
|
| 878 |
+
"model.layers.33.self_attn.o_proj": {
|
| 879 |
+
"group_size": 64,
|
| 880 |
+
"bits": 4,
|
| 881 |
+
"mode": "affine"
|
| 882 |
+
},
|
| 883 |
+
"model.layers.33.mlp.router": {
|
| 884 |
+
"group_size": 64,
|
| 885 |
+
"bits": 8
|
| 886 |
+
},
|
| 887 |
+
"model.layers.34.self_attn.q_proj": {
|
| 888 |
+
"group_size": 64,
|
| 889 |
+
"bits": 4,
|
| 890 |
+
"mode": "affine"
|
| 891 |
+
},
|
| 892 |
+
"model.layers.34.self_attn.k_proj": {
|
| 893 |
+
"group_size": 64,
|
| 894 |
+
"bits": 4,
|
| 895 |
+
"mode": "affine"
|
| 896 |
+
},
|
| 897 |
+
"model.layers.34.self_attn.v_proj": {
|
| 898 |
+
"group_size": 64,
|
| 899 |
+
"bits": 4,
|
| 900 |
+
"mode": "affine"
|
| 901 |
+
},
|
| 902 |
+
"model.layers.34.self_attn.o_proj": {
|
| 903 |
+
"group_size": 64,
|
| 904 |
+
"bits": 4,
|
| 905 |
+
"mode": "affine"
|
| 906 |
+
},
|
| 907 |
+
"model.layers.34.mlp.router": {
|
| 908 |
+
"group_size": 64,
|
| 909 |
+
"bits": 8
|
| 910 |
+
},
|
| 911 |
+
"model.layers.35.self_attn.q_proj": {
|
| 912 |
+
"group_size": 64,
|
| 913 |
+
"bits": 4,
|
| 914 |
+
"mode": "affine"
|
| 915 |
+
},
|
| 916 |
+
"model.layers.35.self_attn.k_proj": {
|
| 917 |
+
"group_size": 64,
|
| 918 |
+
"bits": 4,
|
| 919 |
+
"mode": "affine"
|
| 920 |
+
},
|
| 921 |
+
"model.layers.35.self_attn.v_proj": {
|
| 922 |
+
"group_size": 64,
|
| 923 |
+
"bits": 4,
|
| 924 |
+
"mode": "affine"
|
| 925 |
+
},
|
| 926 |
+
"model.layers.35.self_attn.o_proj": {
|
| 927 |
+
"group_size": 64,
|
| 928 |
+
"bits": 4,
|
| 929 |
+
"mode": "affine"
|
| 930 |
+
},
|
| 931 |
+
"model.layers.35.mlp.router": {
|
| 932 |
+
"group_size": 64,
|
| 933 |
+
"bits": 8
|
| 934 |
+
},
|
| 935 |
+
"lm_head": {
|
| 936 |
+
"group_size": 64,
|
| 937 |
+
"bits": 4,
|
| 938 |
+
"mode": "affine"
|
| 939 |
+
}
|
| 940 |
},
|
| 941 |
"quantization_config": {
|
| 942 |
+
"group_size": 32,
|
| 943 |
+
"bits": 4,
|
| 944 |
+
"mode": "mxfp4",
|
| 945 |
+
"model.embed_tokens": {
|
| 946 |
+
"group_size": 64,
|
| 947 |
+
"bits": 4,
|
| 948 |
+
"mode": "affine"
|
| 949 |
+
},
|
| 950 |
+
"model.layers.0.self_attn.q_proj": {
|
| 951 |
+
"group_size": 64,
|
| 952 |
+
"bits": 4,
|
| 953 |
+
"mode": "affine"
|
| 954 |
+
},
|
| 955 |
+
"model.layers.0.self_attn.k_proj": {
|
| 956 |
+
"group_size": 64,
|
| 957 |
+
"bits": 4,
|
| 958 |
+
"mode": "affine"
|
| 959 |
+
},
|
| 960 |
+
"model.layers.0.self_attn.v_proj": {
|
| 961 |
+
"group_size": 64,
|
| 962 |
+
"bits": 4,
|
| 963 |
+
"mode": "affine"
|
| 964 |
+
},
|
| 965 |
+
"model.layers.0.self_attn.o_proj": {
|
| 966 |
+
"group_size": 64,
|
| 967 |
+
"bits": 4,
|
| 968 |
+
"mode": "affine"
|
| 969 |
+
},
|
| 970 |
+
"model.layers.0.mlp.router": {
|
| 971 |
+
"group_size": 64,
|
| 972 |
+
"bits": 8
|
| 973 |
+
},
|
| 974 |
+
"model.layers.1.self_attn.q_proj": {
|
| 975 |
+
"group_size": 64,
|
| 976 |
+
"bits": 4,
|
| 977 |
+
"mode": "affine"
|
| 978 |
+
},
|
| 979 |
+
"model.layers.1.self_attn.k_proj": {
|
| 980 |
+
"group_size": 64,
|
| 981 |
+
"bits": 4,
|
| 982 |
+
"mode": "affine"
|
| 983 |
+
},
|
| 984 |
+
"model.layers.1.self_attn.v_proj": {
|
| 985 |
+
"group_size": 64,
|
| 986 |
+
"bits": 4,
|
| 987 |
+
"mode": "affine"
|
| 988 |
+
},
|
| 989 |
+
"model.layers.1.self_attn.o_proj": {
|
| 990 |
+
"group_size": 64,
|
| 991 |
+
"bits": 4,
|
| 992 |
+
"mode": "affine"
|
| 993 |
+
},
|
| 994 |
+
"model.layers.1.mlp.router": {
|
| 995 |
+
"group_size": 64,
|
| 996 |
+
"bits": 8
|
| 997 |
+
},
|
| 998 |
+
"model.layers.2.self_attn.q_proj": {
|
| 999 |
+
"group_size": 64,
|
| 1000 |
+
"bits": 4,
|
| 1001 |
+
"mode": "affine"
|
| 1002 |
+
},
|
| 1003 |
+
"model.layers.2.self_attn.k_proj": {
|
| 1004 |
+
"group_size": 64,
|
| 1005 |
+
"bits": 4,
|
| 1006 |
+
"mode": "affine"
|
| 1007 |
+
},
|
| 1008 |
+
"model.layers.2.self_attn.v_proj": {
|
| 1009 |
+
"group_size": 64,
|
| 1010 |
+
"bits": 4,
|
| 1011 |
+
"mode": "affine"
|
| 1012 |
+
},
|
| 1013 |
+
"model.layers.2.self_attn.o_proj": {
|
| 1014 |
+
"group_size": 64,
|
| 1015 |
+
"bits": 4,
|
| 1016 |
+
"mode": "affine"
|
| 1017 |
+
},
|
| 1018 |
+
"model.layers.2.mlp.router": {
|
| 1019 |
+
"group_size": 64,
|
| 1020 |
+
"bits": 8
|
| 1021 |
+
},
|
| 1022 |
+
"model.layers.3.self_attn.q_proj": {
|
| 1023 |
+
"group_size": 64,
|
| 1024 |
+
"bits": 4,
|
| 1025 |
+
"mode": "affine"
|
| 1026 |
+
},
|
| 1027 |
+
"model.layers.3.self_attn.k_proj": {
|
| 1028 |
+
"group_size": 64,
|
| 1029 |
+
"bits": 4,
|
| 1030 |
+
"mode": "affine"
|
| 1031 |
+
},
|
| 1032 |
+
"model.layers.3.self_attn.v_proj": {
|
| 1033 |
+
"group_size": 64,
|
| 1034 |
+
"bits": 4,
|
| 1035 |
+
"mode": "affine"
|
| 1036 |
+
},
|
| 1037 |
+
"model.layers.3.self_attn.o_proj": {
|
| 1038 |
+
"group_size": 64,
|
| 1039 |
+
"bits": 4,
|
| 1040 |
+
"mode": "affine"
|
| 1041 |
+
},
|
| 1042 |
+
"model.layers.3.mlp.router": {
|
| 1043 |
+
"group_size": 64,
|
| 1044 |
+
"bits": 8
|
| 1045 |
+
},
|
| 1046 |
+
"model.layers.4.self_attn.q_proj": {
|
| 1047 |
+
"group_size": 64,
|
| 1048 |
+
"bits": 4,
|
| 1049 |
+
"mode": "affine"
|
| 1050 |
+
},
|
| 1051 |
+
"model.layers.4.self_attn.k_proj": {
|
| 1052 |
+
"group_size": 64,
|
| 1053 |
+
"bits": 4,
|
| 1054 |
+
"mode": "affine"
|
| 1055 |
+
},
|
| 1056 |
+
"model.layers.4.self_attn.v_proj": {
|
| 1057 |
+
"group_size": 64,
|
| 1058 |
+
"bits": 4,
|
| 1059 |
+
"mode": "affine"
|
| 1060 |
+
},
|
| 1061 |
+
"model.layers.4.self_attn.o_proj": {
|
| 1062 |
+
"group_size": 64,
|
| 1063 |
+
"bits": 4,
|
| 1064 |
+
"mode": "affine"
|
| 1065 |
+
},
|
| 1066 |
+
"model.layers.4.mlp.router": {
|
| 1067 |
+
"group_size": 64,
|
| 1068 |
+
"bits": 8
|
| 1069 |
+
},
|
| 1070 |
+
"model.layers.5.self_attn.q_proj": {
|
| 1071 |
+
"group_size": 64,
|
| 1072 |
+
"bits": 4,
|
| 1073 |
+
"mode": "affine"
|
| 1074 |
+
},
|
| 1075 |
+
"model.layers.5.self_attn.k_proj": {
|
| 1076 |
+
"group_size": 64,
|
| 1077 |
+
"bits": 4,
|
| 1078 |
+
"mode": "affine"
|
| 1079 |
+
},
|
| 1080 |
+
"model.layers.5.self_attn.v_proj": {
|
| 1081 |
+
"group_size": 64,
|
| 1082 |
+
"bits": 4,
|
| 1083 |
+
"mode": "affine"
|
| 1084 |
+
},
|
| 1085 |
+
"model.layers.5.self_attn.o_proj": {
|
| 1086 |
+
"group_size": 64,
|
| 1087 |
+
"bits": 4,
|
| 1088 |
+
"mode": "affine"
|
| 1089 |
+
},
|
| 1090 |
+
"model.layers.5.mlp.router": {
|
| 1091 |
+
"group_size": 64,
|
| 1092 |
+
"bits": 8
|
| 1093 |
+
},
|
| 1094 |
+
"model.layers.6.self_attn.q_proj": {
|
| 1095 |
+
"group_size": 64,
|
| 1096 |
+
"bits": 4,
|
| 1097 |
+
"mode": "affine"
|
| 1098 |
+
},
|
| 1099 |
+
"model.layers.6.self_attn.k_proj": {
|
| 1100 |
+
"group_size": 64,
|
| 1101 |
+
"bits": 4,
|
| 1102 |
+
"mode": "affine"
|
| 1103 |
+
},
|
| 1104 |
+
"model.layers.6.self_attn.v_proj": {
|
| 1105 |
+
"group_size": 64,
|
| 1106 |
+
"bits": 4,
|
| 1107 |
+
"mode": "affine"
|
| 1108 |
+
},
|
| 1109 |
+
"model.layers.6.self_attn.o_proj": {
|
| 1110 |
+
"group_size": 64,
|
| 1111 |
+
"bits": 4,
|
| 1112 |
+
"mode": "affine"
|
| 1113 |
+
},
|
| 1114 |
+
"model.layers.6.mlp.router": {
|
| 1115 |
+
"group_size": 64,
|
| 1116 |
+
"bits": 8
|
| 1117 |
+
},
|
| 1118 |
+
"model.layers.7.self_attn.q_proj": {
|
| 1119 |
+
"group_size": 64,
|
| 1120 |
+
"bits": 4,
|
| 1121 |
+
"mode": "affine"
|
| 1122 |
+
},
|
| 1123 |
+
"model.layers.7.self_attn.k_proj": {
|
| 1124 |
+
"group_size": 64,
|
| 1125 |
+
"bits": 4,
|
| 1126 |
+
"mode": "affine"
|
| 1127 |
+
},
|
| 1128 |
+
"model.layers.7.self_attn.v_proj": {
|
| 1129 |
+
"group_size": 64,
|
| 1130 |
+
"bits": 4,
|
| 1131 |
+
"mode": "affine"
|
| 1132 |
+
},
|
| 1133 |
+
"model.layers.7.self_attn.o_proj": {
|
| 1134 |
+
"group_size": 64,
|
| 1135 |
+
"bits": 4,
|
| 1136 |
+
"mode": "affine"
|
| 1137 |
+
},
|
| 1138 |
+
"model.layers.7.mlp.router": {
|
| 1139 |
+
"group_size": 64,
|
| 1140 |
+
"bits": 8
|
| 1141 |
+
},
|
| 1142 |
+
"model.layers.8.self_attn.q_proj": {
|
| 1143 |
+
"group_size": 64,
|
| 1144 |
+
"bits": 4,
|
| 1145 |
+
"mode": "affine"
|
| 1146 |
+
},
|
| 1147 |
+
"model.layers.8.self_attn.k_proj": {
|
| 1148 |
+
"group_size": 64,
|
| 1149 |
+
"bits": 4,
|
| 1150 |
+
"mode": "affine"
|
| 1151 |
+
},
|
| 1152 |
+
"model.layers.8.self_attn.v_proj": {
|
| 1153 |
+
"group_size": 64,
|
| 1154 |
+
"bits": 4,
|
| 1155 |
+
"mode": "affine"
|
| 1156 |
+
},
|
| 1157 |
+
"model.layers.8.self_attn.o_proj": {
|
| 1158 |
+
"group_size": 64,
|
| 1159 |
+
"bits": 4,
|
| 1160 |
+
"mode": "affine"
|
| 1161 |
+
},
|
| 1162 |
+
"model.layers.8.mlp.router": {
|
| 1163 |
+
"group_size": 64,
|
| 1164 |
+
"bits": 8
|
| 1165 |
+
},
|
| 1166 |
+
"model.layers.9.self_attn.q_proj": {
|
| 1167 |
+
"group_size": 64,
|
| 1168 |
+
"bits": 4,
|
| 1169 |
+
"mode": "affine"
|
| 1170 |
+
},
|
| 1171 |
+
"model.layers.9.self_attn.k_proj": {
|
| 1172 |
+
"group_size": 64,
|
| 1173 |
+
"bits": 4,
|
| 1174 |
+
"mode": "affine"
|
| 1175 |
+
},
|
| 1176 |
+
"model.layers.9.self_attn.v_proj": {
|
| 1177 |
+
"group_size": 64,
|
| 1178 |
+
"bits": 4,
|
| 1179 |
+
"mode": "affine"
|
| 1180 |
+
},
|
| 1181 |
+
"model.layers.9.self_attn.o_proj": {
|
| 1182 |
+
"group_size": 64,
|
| 1183 |
+
"bits": 4,
|
| 1184 |
+
"mode": "affine"
|
| 1185 |
+
},
|
| 1186 |
+
"model.layers.9.mlp.router": {
|
| 1187 |
+
"group_size": 64,
|
| 1188 |
+
"bits": 8
|
| 1189 |
+
},
|
| 1190 |
+
"model.layers.10.self_attn.q_proj": {
|
| 1191 |
+
"group_size": 64,
|
| 1192 |
+
"bits": 4,
|
| 1193 |
+
"mode": "affine"
|
| 1194 |
+
},
|
| 1195 |
+
"model.layers.10.self_attn.k_proj": {
|
| 1196 |
+
"group_size": 64,
|
| 1197 |
+
"bits": 4,
|
| 1198 |
+
"mode": "affine"
|
| 1199 |
+
},
|
| 1200 |
+
"model.layers.10.self_attn.v_proj": {
|
| 1201 |
+
"group_size": 64,
|
| 1202 |
+
"bits": 4,
|
| 1203 |
+
"mode": "affine"
|
| 1204 |
+
},
|
| 1205 |
+
"model.layers.10.self_attn.o_proj": {
|
| 1206 |
+
"group_size": 64,
|
| 1207 |
+
"bits": 4,
|
| 1208 |
+
"mode": "affine"
|
| 1209 |
+
},
|
| 1210 |
+
"model.layers.10.mlp.router": {
|
| 1211 |
+
"group_size": 64,
|
| 1212 |
+
"bits": 8
|
| 1213 |
+
},
|
| 1214 |
+
"model.layers.11.self_attn.q_proj": {
|
| 1215 |
+
"group_size": 64,
|
| 1216 |
+
"bits": 4,
|
| 1217 |
+
"mode": "affine"
|
| 1218 |
+
},
|
| 1219 |
+
"model.layers.11.self_attn.k_proj": {
|
| 1220 |
+
"group_size": 64,
|
| 1221 |
+
"bits": 4,
|
| 1222 |
+
"mode": "affine"
|
| 1223 |
+
},
|
| 1224 |
+
"model.layers.11.self_attn.v_proj": {
|
| 1225 |
+
"group_size": 64,
|
| 1226 |
+
"bits": 4,
|
| 1227 |
+
"mode": "affine"
|
| 1228 |
+
},
|
| 1229 |
+
"model.layers.11.self_attn.o_proj": {
|
| 1230 |
+
"group_size": 64,
|
| 1231 |
+
"bits": 4,
|
| 1232 |
+
"mode": "affine"
|
| 1233 |
+
},
|
| 1234 |
+
"model.layers.11.mlp.router": {
|
| 1235 |
+
"group_size": 64,
|
| 1236 |
+
"bits": 8
|
| 1237 |
+
},
|
| 1238 |
+
"model.layers.12.self_attn.q_proj": {
|
| 1239 |
+
"group_size": 64,
|
| 1240 |
+
"bits": 4,
|
| 1241 |
+
"mode": "affine"
|
| 1242 |
+
},
|
| 1243 |
+
"model.layers.12.self_attn.k_proj": {
|
| 1244 |
+
"group_size": 64,
|
| 1245 |
+
"bits": 4,
|
| 1246 |
+
"mode": "affine"
|
| 1247 |
+
},
|
| 1248 |
+
"model.layers.12.self_attn.v_proj": {
|
| 1249 |
+
"group_size": 64,
|
| 1250 |
+
"bits": 4,
|
| 1251 |
+
"mode": "affine"
|
| 1252 |
+
},
|
| 1253 |
+
"model.layers.12.self_attn.o_proj": {
|
| 1254 |
+
"group_size": 64,
|
| 1255 |
+
"bits": 4,
|
| 1256 |
+
"mode": "affine"
|
| 1257 |
+
},
|
| 1258 |
+
"model.layers.12.mlp.router": {
|
| 1259 |
+
"group_size": 64,
|
| 1260 |
+
"bits": 8
|
| 1261 |
+
},
|
| 1262 |
+
"model.layers.13.self_attn.q_proj": {
|
| 1263 |
+
"group_size": 64,
|
| 1264 |
+
"bits": 4,
|
| 1265 |
+
"mode": "affine"
|
| 1266 |
+
},
|
| 1267 |
+
"model.layers.13.self_attn.k_proj": {
|
| 1268 |
+
"group_size": 64,
|
| 1269 |
+
"bits": 4,
|
| 1270 |
+
"mode": "affine"
|
| 1271 |
+
},
|
| 1272 |
+
"model.layers.13.self_attn.v_proj": {
|
| 1273 |
+
"group_size": 64,
|
| 1274 |
+
"bits": 4,
|
| 1275 |
+
"mode": "affine"
|
| 1276 |
+
},
|
| 1277 |
+
"model.layers.13.self_attn.o_proj": {
|
| 1278 |
+
"group_size": 64,
|
| 1279 |
+
"bits": 4,
|
| 1280 |
+
"mode": "affine"
|
| 1281 |
+
},
|
| 1282 |
+
"model.layers.13.mlp.router": {
|
| 1283 |
+
"group_size": 64,
|
| 1284 |
+
"bits": 8
|
| 1285 |
+
},
|
| 1286 |
+
"model.layers.14.self_attn.q_proj": {
|
| 1287 |
+
"group_size": 64,
|
| 1288 |
+
"bits": 4,
|
| 1289 |
+
"mode": "affine"
|
| 1290 |
+
},
|
| 1291 |
+
"model.layers.14.self_attn.k_proj": {
|
| 1292 |
+
"group_size": 64,
|
| 1293 |
+
"bits": 4,
|
| 1294 |
+
"mode": "affine"
|
| 1295 |
+
},
|
| 1296 |
+
"model.layers.14.self_attn.v_proj": {
|
| 1297 |
+
"group_size": 64,
|
| 1298 |
+
"bits": 4,
|
| 1299 |
+
"mode": "affine"
|
| 1300 |
+
},
|
| 1301 |
+
"model.layers.14.self_attn.o_proj": {
|
| 1302 |
+
"group_size": 64,
|
| 1303 |
+
"bits": 4,
|
| 1304 |
+
"mode": "affine"
|
| 1305 |
+
},
|
| 1306 |
+
"model.layers.14.mlp.router": {
|
| 1307 |
+
"group_size": 64,
|
| 1308 |
+
"bits": 8
|
| 1309 |
+
},
|
| 1310 |
+
"model.layers.15.self_attn.q_proj": {
|
| 1311 |
+
"group_size": 64,
|
| 1312 |
+
"bits": 4,
|
| 1313 |
+
"mode": "affine"
|
| 1314 |
+
},
|
| 1315 |
+
"model.layers.15.self_attn.k_proj": {
|
| 1316 |
+
"group_size": 64,
|
| 1317 |
+
"bits": 4,
|
| 1318 |
+
"mode": "affine"
|
| 1319 |
+
},
|
| 1320 |
+
"model.layers.15.self_attn.v_proj": {
|
| 1321 |
+
"group_size": 64,
|
| 1322 |
+
"bits": 4,
|
| 1323 |
+
"mode": "affine"
|
| 1324 |
+
},
|
| 1325 |
+
"model.layers.15.self_attn.o_proj": {
|
| 1326 |
+
"group_size": 64,
|
| 1327 |
+
"bits": 4,
|
| 1328 |
+
"mode": "affine"
|
| 1329 |
+
},
|
| 1330 |
+
"model.layers.15.mlp.router": {
|
| 1331 |
+
"group_size": 64,
|
| 1332 |
+
"bits": 8
|
| 1333 |
+
},
|
| 1334 |
+
"model.layers.16.self_attn.q_proj": {
|
| 1335 |
+
"group_size": 64,
|
| 1336 |
+
"bits": 4,
|
| 1337 |
+
"mode": "affine"
|
| 1338 |
+
},
|
| 1339 |
+
"model.layers.16.self_attn.k_proj": {
|
| 1340 |
+
"group_size": 64,
|
| 1341 |
+
"bits": 4,
|
| 1342 |
+
"mode": "affine"
|
| 1343 |
+
},
|
| 1344 |
+
"model.layers.16.self_attn.v_proj": {
|
| 1345 |
+
"group_size": 64,
|
| 1346 |
+
"bits": 4,
|
| 1347 |
+
"mode": "affine"
|
| 1348 |
+
},
|
| 1349 |
+
"model.layers.16.self_attn.o_proj": {
|
| 1350 |
+
"group_size": 64,
|
| 1351 |
+
"bits": 4,
|
| 1352 |
+
"mode": "affine"
|
| 1353 |
+
},
|
| 1354 |
+
"model.layers.16.mlp.router": {
|
| 1355 |
+
"group_size": 64,
|
| 1356 |
+
"bits": 8
|
| 1357 |
+
},
|
| 1358 |
+
"model.layers.17.self_attn.q_proj": {
|
| 1359 |
+
"group_size": 64,
|
| 1360 |
+
"bits": 4,
|
| 1361 |
+
"mode": "affine"
|
| 1362 |
+
},
|
| 1363 |
+
"model.layers.17.self_attn.k_proj": {
|
| 1364 |
+
"group_size": 64,
|
| 1365 |
+
"bits": 4,
|
| 1366 |
+
"mode": "affine"
|
| 1367 |
+
},
|
| 1368 |
+
"model.layers.17.self_attn.v_proj": {
|
| 1369 |
+
"group_size": 64,
|
| 1370 |
+
"bits": 4,
|
| 1371 |
+
"mode": "affine"
|
| 1372 |
+
},
|
| 1373 |
+
"model.layers.17.self_attn.o_proj": {
|
| 1374 |
+
"group_size": 64,
|
| 1375 |
+
"bits": 4,
|
| 1376 |
+
"mode": "affine"
|
| 1377 |
+
},
|
| 1378 |
+
"model.layers.17.mlp.router": {
|
| 1379 |
+
"group_size": 64,
|
| 1380 |
+
"bits": 8
|
| 1381 |
+
},
|
| 1382 |
+
"model.layers.18.self_attn.q_proj": {
|
| 1383 |
+
"group_size": 64,
|
| 1384 |
+
"bits": 4,
|
| 1385 |
+
"mode": "affine"
|
| 1386 |
+
},
|
| 1387 |
+
"model.layers.18.self_attn.k_proj": {
|
| 1388 |
+
"group_size": 64,
|
| 1389 |
+
"bits": 4,
|
| 1390 |
+
"mode": "affine"
|
| 1391 |
+
},
|
| 1392 |
+
"model.layers.18.self_attn.v_proj": {
|
| 1393 |
+
"group_size": 64,
|
| 1394 |
+
"bits": 4,
|
| 1395 |
+
"mode": "affine"
|
| 1396 |
+
},
|
| 1397 |
+
"model.layers.18.self_attn.o_proj": {
|
| 1398 |
+
"group_size": 64,
|
| 1399 |
+
"bits": 4,
|
| 1400 |
+
"mode": "affine"
|
| 1401 |
+
},
|
| 1402 |
+
"model.layers.18.mlp.router": {
|
| 1403 |
+
"group_size": 64,
|
| 1404 |
+
"bits": 8
|
| 1405 |
+
},
|
| 1406 |
+
"model.layers.19.self_attn.q_proj": {
|
| 1407 |
+
"group_size": 64,
|
| 1408 |
+
"bits": 4,
|
| 1409 |
+
"mode": "affine"
|
| 1410 |
+
},
|
| 1411 |
+
"model.layers.19.self_attn.k_proj": {
|
| 1412 |
+
"group_size": 64,
|
| 1413 |
+
"bits": 4,
|
| 1414 |
+
"mode": "affine"
|
| 1415 |
+
},
|
| 1416 |
+
"model.layers.19.self_attn.v_proj": {
|
| 1417 |
+
"group_size": 64,
|
| 1418 |
+
"bits": 4,
|
| 1419 |
+
"mode": "affine"
|
| 1420 |
+
},
|
| 1421 |
+
"model.layers.19.self_attn.o_proj": {
|
| 1422 |
+
"group_size": 64,
|
| 1423 |
+
"bits": 4,
|
| 1424 |
+
"mode": "affine"
|
| 1425 |
+
},
|
| 1426 |
+
"model.layers.19.mlp.router": {
|
| 1427 |
+
"group_size": 64,
|
| 1428 |
+
"bits": 8
|
| 1429 |
+
},
|
| 1430 |
+
"model.layers.20.self_attn.q_proj": {
|
| 1431 |
+
"group_size": 64,
|
| 1432 |
+
"bits": 4,
|
| 1433 |
+
"mode": "affine"
|
| 1434 |
+
},
|
| 1435 |
+
"model.layers.20.self_attn.k_proj": {
|
| 1436 |
+
"group_size": 64,
|
| 1437 |
+
"bits": 4,
|
| 1438 |
+
"mode": "affine"
|
| 1439 |
+
},
|
| 1440 |
+
"model.layers.20.self_attn.v_proj": {
|
| 1441 |
+
"group_size": 64,
|
| 1442 |
+
"bits": 4,
|
| 1443 |
+
"mode": "affine"
|
| 1444 |
+
},
|
| 1445 |
+
"model.layers.20.self_attn.o_proj": {
|
| 1446 |
+
"group_size": 64,
|
| 1447 |
+
"bits": 4,
|
| 1448 |
+
"mode": "affine"
|
| 1449 |
+
},
|
| 1450 |
+
"model.layers.20.mlp.router": {
|
| 1451 |
+
"group_size": 64,
|
| 1452 |
+
"bits": 8
|
| 1453 |
+
},
|
| 1454 |
+
"model.layers.21.self_attn.q_proj": {
|
| 1455 |
+
"group_size": 64,
|
| 1456 |
+
"bits": 4,
|
| 1457 |
+
"mode": "affine"
|
| 1458 |
+
},
|
| 1459 |
+
"model.layers.21.self_attn.k_proj": {
|
| 1460 |
+
"group_size": 64,
|
| 1461 |
+
"bits": 4,
|
| 1462 |
+
"mode": "affine"
|
| 1463 |
+
},
|
| 1464 |
+
"model.layers.21.self_attn.v_proj": {
|
| 1465 |
+
"group_size": 64,
|
| 1466 |
+
"bits": 4,
|
| 1467 |
+
"mode": "affine"
|
| 1468 |
+
},
|
| 1469 |
+
"model.layers.21.self_attn.o_proj": {
|
| 1470 |
+
"group_size": 64,
|
| 1471 |
+
"bits": 4,
|
| 1472 |
+
"mode": "affine"
|
| 1473 |
+
},
|
| 1474 |
+
"model.layers.21.mlp.router": {
|
| 1475 |
+
"group_size": 64,
|
| 1476 |
+
"bits": 8
|
| 1477 |
+
},
|
| 1478 |
+
"model.layers.22.self_attn.q_proj": {
|
| 1479 |
+
"group_size": 64,
|
| 1480 |
+
"bits": 4,
|
| 1481 |
+
"mode": "affine"
|
| 1482 |
+
},
|
| 1483 |
+
"model.layers.22.self_attn.k_proj": {
|
| 1484 |
+
"group_size": 64,
|
| 1485 |
+
"bits": 4,
|
| 1486 |
+
"mode": "affine"
|
| 1487 |
+
},
|
| 1488 |
+
"model.layers.22.self_attn.v_proj": {
|
| 1489 |
+
"group_size": 64,
|
| 1490 |
+
"bits": 4,
|
| 1491 |
+
"mode": "affine"
|
| 1492 |
+
},
|
| 1493 |
+
"model.layers.22.self_attn.o_proj": {
|
| 1494 |
+
"group_size": 64,
|
| 1495 |
+
"bits": 4,
|
| 1496 |
+
"mode": "affine"
|
| 1497 |
+
},
|
| 1498 |
+
"model.layers.22.mlp.router": {
|
| 1499 |
+
"group_size": 64,
|
| 1500 |
+
"bits": 8
|
| 1501 |
+
},
|
| 1502 |
+
"model.layers.23.self_attn.q_proj": {
|
| 1503 |
+
"group_size": 64,
|
| 1504 |
+
"bits": 4,
|
| 1505 |
+
"mode": "affine"
|
| 1506 |
+
},
|
| 1507 |
+
"model.layers.23.self_attn.k_proj": {
|
| 1508 |
+
"group_size": 64,
|
| 1509 |
+
"bits": 4,
|
| 1510 |
+
"mode": "affine"
|
| 1511 |
+
},
|
| 1512 |
+
"model.layers.23.self_attn.v_proj": {
|
| 1513 |
+
"group_size": 64,
|
| 1514 |
+
"bits": 4,
|
| 1515 |
+
"mode": "affine"
|
| 1516 |
+
},
|
| 1517 |
+
"model.layers.23.self_attn.o_proj": {
|
| 1518 |
+
"group_size": 64,
|
| 1519 |
+
"bits": 4,
|
| 1520 |
+
"mode": "affine"
|
| 1521 |
+
},
|
| 1522 |
+
"model.layers.23.mlp.router": {
|
| 1523 |
+
"group_size": 64,
|
| 1524 |
+
"bits": 8
|
| 1525 |
+
},
|
| 1526 |
+
"model.layers.24.self_attn.q_proj": {
|
| 1527 |
+
"group_size": 64,
|
| 1528 |
+
"bits": 4,
|
| 1529 |
+
"mode": "affine"
|
| 1530 |
+
},
|
| 1531 |
+
"model.layers.24.self_attn.k_proj": {
|
| 1532 |
+
"group_size": 64,
|
| 1533 |
+
"bits": 4,
|
| 1534 |
+
"mode": "affine"
|
| 1535 |
+
},
|
| 1536 |
+
"model.layers.24.self_attn.v_proj": {
|
| 1537 |
+
"group_size": 64,
|
| 1538 |
+
"bits": 4,
|
| 1539 |
+
"mode": "affine"
|
| 1540 |
+
},
|
| 1541 |
+
"model.layers.24.self_attn.o_proj": {
|
| 1542 |
+
"group_size": 64,
|
| 1543 |
+
"bits": 4,
|
| 1544 |
+
"mode": "affine"
|
| 1545 |
+
},
|
| 1546 |
+
"model.layers.24.mlp.router": {
|
| 1547 |
+
"group_size": 64,
|
| 1548 |
+
"bits": 8
|
| 1549 |
+
},
|
| 1550 |
+
"model.layers.25.self_attn.q_proj": {
|
| 1551 |
+
"group_size": 64,
|
| 1552 |
+
"bits": 4,
|
| 1553 |
+
"mode": "affine"
|
| 1554 |
+
},
|
| 1555 |
+
"model.layers.25.self_attn.k_proj": {
|
| 1556 |
+
"group_size": 64,
|
| 1557 |
+
"bits": 4,
|
| 1558 |
+
"mode": "affine"
|
| 1559 |
+
},
|
| 1560 |
+
"model.layers.25.self_attn.v_proj": {
|
| 1561 |
+
"group_size": 64,
|
| 1562 |
+
"bits": 4,
|
| 1563 |
+
"mode": "affine"
|
| 1564 |
+
},
|
| 1565 |
+
"model.layers.25.self_attn.o_proj": {
|
| 1566 |
+
"group_size": 64,
|
| 1567 |
+
"bits": 4,
|
| 1568 |
+
"mode": "affine"
|
| 1569 |
+
},
|
| 1570 |
+
"model.layers.25.mlp.router": {
|
| 1571 |
+
"group_size": 64,
|
| 1572 |
+
"bits": 8
|
| 1573 |
+
},
|
| 1574 |
+
"model.layers.26.self_attn.q_proj": {
|
| 1575 |
+
"group_size": 64,
|
| 1576 |
+
"bits": 4,
|
| 1577 |
+
"mode": "affine"
|
| 1578 |
+
},
|
| 1579 |
+
"model.layers.26.self_attn.k_proj": {
|
| 1580 |
+
"group_size": 64,
|
| 1581 |
+
"bits": 4,
|
| 1582 |
+
"mode": "affine"
|
| 1583 |
+
},
|
| 1584 |
+
"model.layers.26.self_attn.v_proj": {
|
| 1585 |
+
"group_size": 64,
|
| 1586 |
+
"bits": 4,
|
| 1587 |
+
"mode": "affine"
|
| 1588 |
+
},
|
| 1589 |
+
"model.layers.26.self_attn.o_proj": {
|
| 1590 |
+
"group_size": 64,
|
| 1591 |
+
"bits": 4,
|
| 1592 |
+
"mode": "affine"
|
| 1593 |
+
},
|
| 1594 |
+
"model.layers.26.mlp.router": {
|
| 1595 |
+
"group_size": 64,
|
| 1596 |
+
"bits": 8
|
| 1597 |
+
},
|
| 1598 |
+
"model.layers.27.self_attn.q_proj": {
|
| 1599 |
+
"group_size": 64,
|
| 1600 |
+
"bits": 4,
|
| 1601 |
+
"mode": "affine"
|
| 1602 |
+
},
|
| 1603 |
+
"model.layers.27.self_attn.k_proj": {
|
| 1604 |
+
"group_size": 64,
|
| 1605 |
+
"bits": 4,
|
| 1606 |
+
"mode": "affine"
|
| 1607 |
+
},
|
| 1608 |
+
"model.layers.27.self_attn.v_proj": {
|
| 1609 |
+
"group_size": 64,
|
| 1610 |
+
"bits": 4,
|
| 1611 |
+
"mode": "affine"
|
| 1612 |
+
},
|
| 1613 |
+
"model.layers.27.self_attn.o_proj": {
|
| 1614 |
+
"group_size": 64,
|
| 1615 |
+
"bits": 4,
|
| 1616 |
+
"mode": "affine"
|
| 1617 |
+
},
|
| 1618 |
+
"model.layers.27.mlp.router": {
|
| 1619 |
+
"group_size": 64,
|
| 1620 |
+
"bits": 8
|
| 1621 |
+
},
|
| 1622 |
+
"model.layers.28.self_attn.q_proj": {
|
| 1623 |
+
"group_size": 64,
|
| 1624 |
+
"bits": 4,
|
| 1625 |
+
"mode": "affine"
|
| 1626 |
+
},
|
| 1627 |
+
"model.layers.28.self_attn.k_proj": {
|
| 1628 |
+
"group_size": 64,
|
| 1629 |
+
"bits": 4,
|
| 1630 |
+
"mode": "affine"
|
| 1631 |
+
},
|
| 1632 |
+
"model.layers.28.self_attn.v_proj": {
|
| 1633 |
+
"group_size": 64,
|
| 1634 |
+
"bits": 4,
|
| 1635 |
+
"mode": "affine"
|
| 1636 |
+
},
|
| 1637 |
+
"model.layers.28.self_attn.o_proj": {
|
| 1638 |
+
"group_size": 64,
|
| 1639 |
+
"bits": 4,
|
| 1640 |
+
"mode": "affine"
|
| 1641 |
+
},
|
| 1642 |
+
"model.layers.28.mlp.router": {
|
| 1643 |
+
"group_size": 64,
|
| 1644 |
+
"bits": 8
|
| 1645 |
+
},
|
| 1646 |
+
"model.layers.29.self_attn.q_proj": {
|
| 1647 |
+
"group_size": 64,
|
| 1648 |
+
"bits": 4,
|
| 1649 |
+
"mode": "affine"
|
| 1650 |
+
},
|
| 1651 |
+
"model.layers.29.self_attn.k_proj": {
|
| 1652 |
+
"group_size": 64,
|
| 1653 |
+
"bits": 4,
|
| 1654 |
+
"mode": "affine"
|
| 1655 |
+
},
|
| 1656 |
+
"model.layers.29.self_attn.v_proj": {
|
| 1657 |
+
"group_size": 64,
|
| 1658 |
+
"bits": 4,
|
| 1659 |
+
"mode": "affine"
|
| 1660 |
+
},
|
| 1661 |
+
"model.layers.29.self_attn.o_proj": {
|
| 1662 |
+
"group_size": 64,
|
| 1663 |
+
"bits": 4,
|
| 1664 |
+
"mode": "affine"
|
| 1665 |
+
},
|
| 1666 |
+
"model.layers.29.mlp.router": {
|
| 1667 |
+
"group_size": 64,
|
| 1668 |
+
"bits": 8
|
| 1669 |
+
},
|
| 1670 |
+
"model.layers.30.self_attn.q_proj": {
|
| 1671 |
+
"group_size": 64,
|
| 1672 |
+
"bits": 4,
|
| 1673 |
+
"mode": "affine"
|
| 1674 |
+
},
|
| 1675 |
+
"model.layers.30.self_attn.k_proj": {
|
| 1676 |
+
"group_size": 64,
|
| 1677 |
+
"bits": 4,
|
| 1678 |
+
"mode": "affine"
|
| 1679 |
+
},
|
| 1680 |
+
"model.layers.30.self_attn.v_proj": {
|
| 1681 |
+
"group_size": 64,
|
| 1682 |
+
"bits": 4,
|
| 1683 |
+
"mode": "affine"
|
| 1684 |
+
},
|
| 1685 |
+
"model.layers.30.self_attn.o_proj": {
|
| 1686 |
+
"group_size": 64,
|
| 1687 |
+
"bits": 4,
|
| 1688 |
+
"mode": "affine"
|
| 1689 |
+
},
|
| 1690 |
+
"model.layers.30.mlp.router": {
|
| 1691 |
+
"group_size": 64,
|
| 1692 |
+
"bits": 8
|
| 1693 |
+
},
|
| 1694 |
+
"model.layers.31.self_attn.q_proj": {
|
| 1695 |
+
"group_size": 64,
|
| 1696 |
+
"bits": 4,
|
| 1697 |
+
"mode": "affine"
|
| 1698 |
+
},
|
| 1699 |
+
"model.layers.31.self_attn.k_proj": {
|
| 1700 |
+
"group_size": 64,
|
| 1701 |
+
"bits": 4,
|
| 1702 |
+
"mode": "affine"
|
| 1703 |
+
},
|
| 1704 |
+
"model.layers.31.self_attn.v_proj": {
|
| 1705 |
+
"group_size": 64,
|
| 1706 |
+
"bits": 4,
|
| 1707 |
+
"mode": "affine"
|
| 1708 |
+
},
|
| 1709 |
+
"model.layers.31.self_attn.o_proj": {
|
| 1710 |
+
"group_size": 64,
|
| 1711 |
+
"bits": 4,
|
| 1712 |
+
"mode": "affine"
|
| 1713 |
+
},
|
| 1714 |
+
"model.layers.31.mlp.router": {
|
| 1715 |
+
"group_size": 64,
|
| 1716 |
+
"bits": 8
|
| 1717 |
+
},
|
| 1718 |
+
"model.layers.32.self_attn.q_proj": {
|
| 1719 |
+
"group_size": 64,
|
| 1720 |
+
"bits": 4,
|
| 1721 |
+
"mode": "affine"
|
| 1722 |
+
},
|
| 1723 |
+
"model.layers.32.self_attn.k_proj": {
|
| 1724 |
+
"group_size": 64,
|
| 1725 |
+
"bits": 4,
|
| 1726 |
+
"mode": "affine"
|
| 1727 |
+
},
|
| 1728 |
+
"model.layers.32.self_attn.v_proj": {
|
| 1729 |
+
"group_size": 64,
|
| 1730 |
+
"bits": 4,
|
| 1731 |
+
"mode": "affine"
|
| 1732 |
+
},
|
| 1733 |
+
"model.layers.32.self_attn.o_proj": {
|
| 1734 |
+
"group_size": 64,
|
| 1735 |
+
"bits": 4,
|
| 1736 |
+
"mode": "affine"
|
| 1737 |
+
},
|
| 1738 |
+
"model.layers.32.mlp.router": {
|
| 1739 |
+
"group_size": 64,
|
| 1740 |
+
"bits": 8
|
| 1741 |
+
},
|
| 1742 |
+
"model.layers.33.self_attn.q_proj": {
|
| 1743 |
+
"group_size": 64,
|
| 1744 |
+
"bits": 4,
|
| 1745 |
+
"mode": "affine"
|
| 1746 |
+
},
|
| 1747 |
+
"model.layers.33.self_attn.k_proj": {
|
| 1748 |
+
"group_size": 64,
|
| 1749 |
+
"bits": 4,
|
| 1750 |
+
"mode": "affine"
|
| 1751 |
+
},
|
| 1752 |
+
"model.layers.33.self_attn.v_proj": {
|
| 1753 |
+
"group_size": 64,
|
| 1754 |
+
"bits": 4,
|
| 1755 |
+
"mode": "affine"
|
| 1756 |
+
},
|
| 1757 |
+
"model.layers.33.self_attn.o_proj": {
|
| 1758 |
+
"group_size": 64,
|
| 1759 |
+
"bits": 4,
|
| 1760 |
+
"mode": "affine"
|
| 1761 |
+
},
|
| 1762 |
+
"model.layers.33.mlp.router": {
|
| 1763 |
+
"group_size": 64,
|
| 1764 |
+
"bits": 8
|
| 1765 |
+
},
|
| 1766 |
+
"model.layers.34.self_attn.q_proj": {
|
| 1767 |
+
"group_size": 64,
|
| 1768 |
+
"bits": 4,
|
| 1769 |
+
"mode": "affine"
|
| 1770 |
+
},
|
| 1771 |
+
"model.layers.34.self_attn.k_proj": {
|
| 1772 |
+
"group_size": 64,
|
| 1773 |
+
"bits": 4,
|
| 1774 |
+
"mode": "affine"
|
| 1775 |
+
},
|
| 1776 |
+
"model.layers.34.self_attn.v_proj": {
|
| 1777 |
+
"group_size": 64,
|
| 1778 |
+
"bits": 4,
|
| 1779 |
+
"mode": "affine"
|
| 1780 |
+
},
|
| 1781 |
+
"model.layers.34.self_attn.o_proj": {
|
| 1782 |
+
"group_size": 64,
|
| 1783 |
+
"bits": 4,
|
| 1784 |
+
"mode": "affine"
|
| 1785 |
+
},
|
| 1786 |
+
"model.layers.34.mlp.router": {
|
| 1787 |
+
"group_size": 64,
|
| 1788 |
+
"bits": 8
|
| 1789 |
+
},
|
| 1790 |
+
"model.layers.35.self_attn.q_proj": {
|
| 1791 |
+
"group_size": 64,
|
| 1792 |
+
"bits": 4,
|
| 1793 |
+
"mode": "affine"
|
| 1794 |
+
},
|
| 1795 |
+
"model.layers.35.self_attn.k_proj": {
|
| 1796 |
+
"group_size": 64,
|
| 1797 |
+
"bits": 4,
|
| 1798 |
+
"mode": "affine"
|
| 1799 |
+
},
|
| 1800 |
+
"model.layers.35.self_attn.v_proj": {
|
| 1801 |
+
"group_size": 64,
|
| 1802 |
+
"bits": 4,
|
| 1803 |
+
"mode": "affine"
|
| 1804 |
+
},
|
| 1805 |
+
"model.layers.35.self_attn.o_proj": {
|
| 1806 |
+
"group_size": 64,
|
| 1807 |
+
"bits": 4,
|
| 1808 |
+
"mode": "affine"
|
| 1809 |
+
},
|
| 1810 |
+
"model.layers.35.mlp.router": {
|
| 1811 |
+
"group_size": 64,
|
| 1812 |
+
"bits": 8
|
| 1813 |
+
},
|
| 1814 |
+
"lm_head": {
|
| 1815 |
+
"group_size": 64,
|
| 1816 |
+
"bits": 4,
|
| 1817 |
+
"mode": "affine"
|
| 1818 |
+
}
|
| 1819 |
},
|
| 1820 |
"rms_norm_eps": 1e-05,
|
| 1821 |
"rope_scaling": {
|
generation_config.json
CHANGED
|
@@ -3,7 +3,8 @@
|
|
| 3 |
"do_sample": true,
|
| 4 |
"eos_token_id": [
|
| 5 |
200002,
|
| 6 |
-
199999
|
|
|
|
| 7 |
],
|
| 8 |
"pad_token_id": 199999,
|
| 9 |
"transformers_version": "4.55.0.dev0"
|
|
|
|
| 3 |
"do_sample": true,
|
| 4 |
"eos_token_id": [
|
| 5 |
200002,
|
| 6 |
+
199999,
|
| 7 |
+
200012
|
| 8 |
],
|
| 9 |
"pad_token_id": 199999,
|
| 10 |
"transformers_version": "4.55.0.dev0"
|
model-00001-of-00013.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fd358642c5c70080f15ae4dc4850d13e282be56ee2cb81cd7e47b2ddb37ce5ae
|
| 3 |
+
size 4889475597
|
model-00002-of-00013.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:59bc7abcaca624b31a08e062799142e8553b915911ff097295d6c8577036a7b6
|
| 3 |
+
size 5128867805
|
model-00003-of-00013.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:764b6a85f3aebda5a289fb3291c43cc2402ff7e8f1514cbf2f00e78b2deda216
|
| 3 |
+
size 5128867817
|
model-00004-of-00013.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a4e4d2a84ad98021d777f53d4717eaec17338ea5079361197221164c61c199ca
|
| 3 |
+
size 5128867806
|
model-00005-of-00013.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:48971dbba87d315c9af96143f879b674329edf65526f3db41f0a3f854b4d6ba2
|
| 3 |
+
size 5128867937
|
model-00006-of-00013.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:975f0a09177a331a08411a72bf80fd345f59e0c5de6ca2c86a8fe1249f76a2d5
|
| 3 |
+
size 5128867857
|
model-00007-of-00013.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1699fcaaebbf59a72e6c4b85b760ac6e27d1c26d6d235a555d46195e1574fee3
|
| 3 |
+
size 5128867933
|
model-00008-of-00013.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:207457e810f88fe7285104104a58c1b5b1571f3dbd0c45add65b5a979595f5eb
|
| 3 |
+
size 5128867907
|
model-00009-of-00013.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:901125482399ebb09a78767b7b6d1b05549a5b8ee6482a25684283745773ca90
|
| 3 |
+
size 5128867905
|
model-00010-of-00013.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f39dc4bd4780653eb4a874a9cf23477cb123cd7798c367142c81be40dd2be4a6
|
| 3 |
+
size 5128867921
|
model-00011-of-00013.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c44627235138c1553e1036d9043b492a065be604fc22c5d845b16d90e69ba4ee
|
| 3 |
+
size 5128867937
|
model-00012-of-00013.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b2fe971dce8a424b9687fc79ca1332616e1bfb5f6d6f77bf6fb115767a63a186
|
| 3 |
+
size 5128867921
|
model-00013-of-00013.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cc4057ba3da05c4e0d33e3435b19a12dacefb6fe222c7e95c7aa83dab35f28af
|
| 3 |
+
size 890923814
|
model.safetensors.index.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
-
"total_size":
|
| 4 |
"total_parameters": 116829154368
|
| 5 |
},
|
| 6 |
"weight_map": {
|
|
@@ -12,15 +12,12 @@
|
|
| 12 |
"model.embed_tokens.weight": "model-00001-of-00013.safetensors",
|
| 13 |
"model.layers.0.input_layernorm.weight": "model-00001-of-00013.safetensors",
|
| 14 |
"model.layers.0.mlp.experts.down_proj.bias": "model-00001-of-00013.safetensors",
|
| 15 |
-
"model.layers.0.mlp.experts.down_proj.biases": "model-00001-of-00013.safetensors",
|
| 16 |
"model.layers.0.mlp.experts.down_proj.scales": "model-00001-of-00013.safetensors",
|
| 17 |
"model.layers.0.mlp.experts.down_proj.weight": "model-00001-of-00013.safetensors",
|
| 18 |
"model.layers.0.mlp.experts.gate_proj.bias": "model-00001-of-00013.safetensors",
|
| 19 |
-
"model.layers.0.mlp.experts.gate_proj.biases": "model-00001-of-00013.safetensors",
|
| 20 |
"model.layers.0.mlp.experts.gate_proj.scales": "model-00001-of-00013.safetensors",
|
| 21 |
"model.layers.0.mlp.experts.gate_proj.weight": "model-00001-of-00013.safetensors",
|
| 22 |
"model.layers.0.mlp.experts.up_proj.bias": "model-00001-of-00013.safetensors",
|
| 23 |
-
"model.layers.0.mlp.experts.up_proj.biases": "model-00001-of-00013.safetensors",
|
| 24 |
"model.layers.0.mlp.experts.up_proj.scales": "model-00001-of-00013.safetensors",
|
| 25 |
"model.layers.0.mlp.experts.up_proj.weight": "model-00001-of-00013.safetensors",
|
| 26 |
"model.layers.0.mlp.router.bias": "model-00001-of-00013.safetensors",
|
|
@@ -47,15 +44,12 @@
|
|
| 47 |
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
|
| 48 |
"model.layers.1.input_layernorm.weight": "model-00001-of-00013.safetensors",
|
| 49 |
"model.layers.1.mlp.experts.down_proj.bias": "model-00001-of-00013.safetensors",
|
| 50 |
-
"model.layers.1.mlp.experts.down_proj.biases": "model-00001-of-00013.safetensors",
|
| 51 |
"model.layers.1.mlp.experts.down_proj.scales": "model-00001-of-00013.safetensors",
|
| 52 |
"model.layers.1.mlp.experts.down_proj.weight": "model-00001-of-00013.safetensors",
|
| 53 |
"model.layers.1.mlp.experts.gate_proj.bias": "model-00001-of-00013.safetensors",
|
| 54 |
-
"model.layers.1.mlp.experts.gate_proj.biases": "model-00001-of-00013.safetensors",
|
| 55 |
"model.layers.1.mlp.experts.gate_proj.scales": "model-00001-of-00013.safetensors",
|
| 56 |
"model.layers.1.mlp.experts.gate_proj.weight": "model-00001-of-00013.safetensors",
|
| 57 |
"model.layers.1.mlp.experts.up_proj.bias": "model-00001-of-00013.safetensors",
|
| 58 |
-
"model.layers.1.mlp.experts.up_proj.biases": "model-00001-of-00013.safetensors",
|
| 59 |
"model.layers.1.mlp.experts.up_proj.scales": "model-00001-of-00013.safetensors",
|
| 60 |
"model.layers.1.mlp.experts.up_proj.weight": "model-00001-of-00013.safetensors",
|
| 61 |
"model.layers.1.mlp.router.bias": "model-00001-of-00013.safetensors",
|
|
@@ -82,15 +76,12 @@
|
|
| 82 |
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
|
| 83 |
"model.layers.10.input_layernorm.weight": "model-00004-of-00013.safetensors",
|
| 84 |
"model.layers.10.mlp.experts.down_proj.bias": "model-00004-of-00013.safetensors",
|
| 85 |
-
"model.layers.10.mlp.experts.down_proj.biases": "model-00004-of-00013.safetensors",
|
| 86 |
"model.layers.10.mlp.experts.down_proj.scales": "model-00004-of-00013.safetensors",
|
| 87 |
"model.layers.10.mlp.experts.down_proj.weight": "model-00004-of-00013.safetensors",
|
| 88 |
"model.layers.10.mlp.experts.gate_proj.bias": "model-00004-of-00013.safetensors",
|
| 89 |
-
"model.layers.10.mlp.experts.gate_proj.biases": "model-00004-of-00013.safetensors",
|
| 90 |
"model.layers.10.mlp.experts.gate_proj.scales": "model-00004-of-00013.safetensors",
|
| 91 |
"model.layers.10.mlp.experts.gate_proj.weight": "model-00004-of-00013.safetensors",
|
| 92 |
"model.layers.10.mlp.experts.up_proj.bias": "model-00004-of-00013.safetensors",
|
| 93 |
-
"model.layers.10.mlp.experts.up_proj.biases": "model-00004-of-00013.safetensors",
|
| 94 |
"model.layers.10.mlp.experts.up_proj.scales": "model-00004-of-00013.safetensors",
|
| 95 |
"model.layers.10.mlp.experts.up_proj.weight": "model-00004-of-00013.safetensors",
|
| 96 |
"model.layers.10.mlp.router.bias": "model-00004-of-00013.safetensors",
|
|
@@ -117,17 +108,14 @@
|
|
| 117 |
"model.layers.10.self_attn.v_proj.weight": "model-00004-of-00013.safetensors",
|
| 118 |
"model.layers.11.input_layernorm.weight": "model-00005-of-00013.safetensors",
|
| 119 |
"model.layers.11.mlp.experts.down_proj.bias": "model-00005-of-00013.safetensors",
|
| 120 |
-
"model.layers.11.mlp.experts.down_proj.biases": "model-00005-of-00013.safetensors",
|
| 121 |
"model.layers.11.mlp.experts.down_proj.scales": "model-00005-of-00013.safetensors",
|
| 122 |
"model.layers.11.mlp.experts.down_proj.weight": "model-00005-of-00013.safetensors",
|
| 123 |
-
"model.layers.11.mlp.experts.gate_proj.bias": "model-
|
| 124 |
-
"model.layers.11.mlp.experts.gate_proj.
|
| 125 |
-
"model.layers.11.mlp.experts.gate_proj.scales": "model-00005-of-00013.safetensors",
|
| 126 |
"model.layers.11.mlp.experts.gate_proj.weight": "model-00004-of-00013.safetensors",
|
| 127 |
-
"model.layers.11.mlp.experts.up_proj.bias": "model-
|
| 128 |
-
"model.layers.11.mlp.experts.up_proj.
|
| 129 |
-
"model.layers.11.mlp.experts.up_proj.
|
| 130 |
-
"model.layers.11.mlp.experts.up_proj.weight": "model-00005-of-00013.safetensors",
|
| 131 |
"model.layers.11.mlp.router.bias": "model-00005-of-00013.safetensors",
|
| 132 |
"model.layers.11.mlp.router.biases": "model-00005-of-00013.safetensors",
|
| 133 |
"model.layers.11.mlp.router.scales": "model-00005-of-00013.safetensors",
|
|
@@ -152,15 +140,12 @@
|
|
| 152 |
"model.layers.11.self_attn.v_proj.weight": "model-00004-of-00013.safetensors",
|
| 153 |
"model.layers.12.input_layernorm.weight": "model-00005-of-00013.safetensors",
|
| 154 |
"model.layers.12.mlp.experts.down_proj.bias": "model-00005-of-00013.safetensors",
|
| 155 |
-
"model.layers.12.mlp.experts.down_proj.biases": "model-00005-of-00013.safetensors",
|
| 156 |
"model.layers.12.mlp.experts.down_proj.scales": "model-00005-of-00013.safetensors",
|
| 157 |
"model.layers.12.mlp.experts.down_proj.weight": "model-00005-of-00013.safetensors",
|
| 158 |
"model.layers.12.mlp.experts.gate_proj.bias": "model-00005-of-00013.safetensors",
|
| 159 |
-
"model.layers.12.mlp.experts.gate_proj.biases": "model-00005-of-00013.safetensors",
|
| 160 |
"model.layers.12.mlp.experts.gate_proj.scales": "model-00005-of-00013.safetensors",
|
| 161 |
"model.layers.12.mlp.experts.gate_proj.weight": "model-00005-of-00013.safetensors",
|
| 162 |
"model.layers.12.mlp.experts.up_proj.bias": "model-00005-of-00013.safetensors",
|
| 163 |
-
"model.layers.12.mlp.experts.up_proj.biases": "model-00005-of-00013.safetensors",
|
| 164 |
"model.layers.12.mlp.experts.up_proj.scales": "model-00005-of-00013.safetensors",
|
| 165 |
"model.layers.12.mlp.experts.up_proj.weight": "model-00005-of-00013.safetensors",
|
| 166 |
"model.layers.12.mlp.router.bias": "model-00005-of-00013.safetensors",
|
|
@@ -187,15 +172,12 @@
|
|
| 187 |
"model.layers.12.self_attn.v_proj.weight": "model-00005-of-00013.safetensors",
|
| 188 |
"model.layers.13.input_layernorm.weight": "model-00005-of-00013.safetensors",
|
| 189 |
"model.layers.13.mlp.experts.down_proj.bias": "model-00005-of-00013.safetensors",
|
| 190 |
-
"model.layers.13.mlp.experts.down_proj.biases": "model-00005-of-00013.safetensors",
|
| 191 |
"model.layers.13.mlp.experts.down_proj.scales": "model-00005-of-00013.safetensors",
|
| 192 |
"model.layers.13.mlp.experts.down_proj.weight": "model-00005-of-00013.safetensors",
|
| 193 |
"model.layers.13.mlp.experts.gate_proj.bias": "model-00005-of-00013.safetensors",
|
| 194 |
-
"model.layers.13.mlp.experts.gate_proj.biases": "model-00005-of-00013.safetensors",
|
| 195 |
"model.layers.13.mlp.experts.gate_proj.scales": "model-00005-of-00013.safetensors",
|
| 196 |
"model.layers.13.mlp.experts.gate_proj.weight": "model-00005-of-00013.safetensors",
|
| 197 |
"model.layers.13.mlp.experts.up_proj.bias": "model-00005-of-00013.safetensors",
|
| 198 |
-
"model.layers.13.mlp.experts.up_proj.biases": "model-00005-of-00013.safetensors",
|
| 199 |
"model.layers.13.mlp.experts.up_proj.scales": "model-00005-of-00013.safetensors",
|
| 200 |
"model.layers.13.mlp.experts.up_proj.weight": "model-00005-of-00013.safetensors",
|
| 201 |
"model.layers.13.mlp.router.bias": "model-00005-of-00013.safetensors",
|
|
@@ -222,17 +204,14 @@
|
|
| 222 |
"model.layers.13.self_attn.v_proj.weight": "model-00005-of-00013.safetensors",
|
| 223 |
"model.layers.14.input_layernorm.weight": "model-00006-of-00013.safetensors",
|
| 224 |
"model.layers.14.mlp.experts.down_proj.bias": "model-00006-of-00013.safetensors",
|
| 225 |
-
"model.layers.14.mlp.experts.down_proj.biases": "model-00006-of-00013.safetensors",
|
| 226 |
"model.layers.14.mlp.experts.down_proj.scales": "model-00006-of-00013.safetensors",
|
| 227 |
"model.layers.14.mlp.experts.down_proj.weight": "model-00006-of-00013.safetensors",
|
| 228 |
-
"model.layers.14.mlp.experts.gate_proj.bias": "model-
|
| 229 |
-
"model.layers.14.mlp.experts.gate_proj.
|
| 230 |
-
"model.layers.14.mlp.experts.gate_proj.
|
| 231 |
-
"model.layers.14.mlp.experts.
|
| 232 |
-
"model.layers.14.mlp.experts.up_proj.
|
| 233 |
-
"model.layers.14.mlp.experts.up_proj.
|
| 234 |
-
"model.layers.14.mlp.experts.up_proj.scales": "model-00006-of-00013.safetensors",
|
| 235 |
-
"model.layers.14.mlp.experts.up_proj.weight": "model-00006-of-00013.safetensors",
|
| 236 |
"model.layers.14.mlp.router.bias": "model-00006-of-00013.safetensors",
|
| 237 |
"model.layers.14.mlp.router.biases": "model-00006-of-00013.safetensors",
|
| 238 |
"model.layers.14.mlp.router.scales": "model-00006-of-00013.safetensors",
|
|
@@ -257,15 +236,12 @@
|
|
| 257 |
"model.layers.14.self_attn.v_proj.weight": "model-00005-of-00013.safetensors",
|
| 258 |
"model.layers.15.input_layernorm.weight": "model-00006-of-00013.safetensors",
|
| 259 |
"model.layers.15.mlp.experts.down_proj.bias": "model-00006-of-00013.safetensors",
|
| 260 |
-
"model.layers.15.mlp.experts.down_proj.biases": "model-00006-of-00013.safetensors",
|
| 261 |
"model.layers.15.mlp.experts.down_proj.scales": "model-00006-of-00013.safetensors",
|
| 262 |
"model.layers.15.mlp.experts.down_proj.weight": "model-00006-of-00013.safetensors",
|
| 263 |
"model.layers.15.mlp.experts.gate_proj.bias": "model-00006-of-00013.safetensors",
|
| 264 |
-
"model.layers.15.mlp.experts.gate_proj.biases": "model-00006-of-00013.safetensors",
|
| 265 |
"model.layers.15.mlp.experts.gate_proj.scales": "model-00006-of-00013.safetensors",
|
| 266 |
"model.layers.15.mlp.experts.gate_proj.weight": "model-00006-of-00013.safetensors",
|
| 267 |
"model.layers.15.mlp.experts.up_proj.bias": "model-00006-of-00013.safetensors",
|
| 268 |
-
"model.layers.15.mlp.experts.up_proj.biases": "model-00006-of-00013.safetensors",
|
| 269 |
"model.layers.15.mlp.experts.up_proj.scales": "model-00006-of-00013.safetensors",
|
| 270 |
"model.layers.15.mlp.experts.up_proj.weight": "model-00006-of-00013.safetensors",
|
| 271 |
"model.layers.15.mlp.router.bias": "model-00006-of-00013.safetensors",
|
|
@@ -290,24 +266,21 @@
|
|
| 290 |
"model.layers.15.self_attn.v_proj.biases": "model-00006-of-00013.safetensors",
|
| 291 |
"model.layers.15.self_attn.v_proj.scales": "model-00006-of-00013.safetensors",
|
| 292 |
"model.layers.15.self_attn.v_proj.weight": "model-00006-of-00013.safetensors",
|
| 293 |
-
"model.layers.16.input_layernorm.weight": "model-
|
| 294 |
-
"model.layers.16.mlp.experts.down_proj.bias": "model-
|
| 295 |
-
"model.layers.16.mlp.experts.down_proj.
|
| 296 |
-
"model.layers.16.mlp.experts.down_proj.scales": "model-00007-of-00013.safetensors",
|
| 297 |
"model.layers.16.mlp.experts.down_proj.weight": "model-00006-of-00013.safetensors",
|
| 298 |
"model.layers.16.mlp.experts.gate_proj.bias": "model-00006-of-00013.safetensors",
|
| 299 |
-
"model.layers.16.mlp.experts.gate_proj.biases": "model-00006-of-00013.safetensors",
|
| 300 |
"model.layers.16.mlp.experts.gate_proj.scales": "model-00006-of-00013.safetensors",
|
| 301 |
"model.layers.16.mlp.experts.gate_proj.weight": "model-00006-of-00013.safetensors",
|
| 302 |
"model.layers.16.mlp.experts.up_proj.bias": "model-00006-of-00013.safetensors",
|
| 303 |
-
"model.layers.16.mlp.experts.up_proj.biases": "model-00006-of-00013.safetensors",
|
| 304 |
"model.layers.16.mlp.experts.up_proj.scales": "model-00006-of-00013.safetensors",
|
| 305 |
"model.layers.16.mlp.experts.up_proj.weight": "model-00006-of-00013.safetensors",
|
| 306 |
-
"model.layers.16.mlp.router.bias": "model-
|
| 307 |
-
"model.layers.16.mlp.router.biases": "model-
|
| 308 |
-
"model.layers.16.mlp.router.scales": "model-
|
| 309 |
-
"model.layers.16.mlp.router.weight": "model-
|
| 310 |
-
"model.layers.16.post_attention_layernorm.weight": "model-
|
| 311 |
"model.layers.16.self_attn.k_proj.bias": "model-00006-of-00013.safetensors",
|
| 312 |
"model.layers.16.self_attn.k_proj.biases": "model-00006-of-00013.safetensors",
|
| 313 |
"model.layers.16.self_attn.k_proj.scales": "model-00006-of-00013.safetensors",
|
|
@@ -327,50 +300,44 @@
|
|
| 327 |
"model.layers.16.self_attn.v_proj.weight": "model-00006-of-00013.safetensors",
|
| 328 |
"model.layers.17.input_layernorm.weight": "model-00007-of-00013.safetensors",
|
| 329 |
"model.layers.17.mlp.experts.down_proj.bias": "model-00007-of-00013.safetensors",
|
| 330 |
-
"model.layers.17.mlp.experts.down_proj.biases": "model-00007-of-00013.safetensors",
|
| 331 |
"model.layers.17.mlp.experts.down_proj.scales": "model-00007-of-00013.safetensors",
|
| 332 |
"model.layers.17.mlp.experts.down_proj.weight": "model-00007-of-00013.safetensors",
|
| 333 |
-
"model.layers.17.mlp.experts.gate_proj.bias": "model-
|
| 334 |
-
"model.layers.17.mlp.experts.gate_proj.
|
| 335 |
-
"model.layers.17.mlp.experts.gate_proj.
|
| 336 |
-
"model.layers.17.mlp.experts.
|
| 337 |
-
"model.layers.17.mlp.experts.up_proj.
|
| 338 |
-
"model.layers.17.mlp.experts.up_proj.
|
| 339 |
-
"model.layers.17.mlp.experts.up_proj.scales": "model-00007-of-00013.safetensors",
|
| 340 |
-
"model.layers.17.mlp.experts.up_proj.weight": "model-00007-of-00013.safetensors",
|
| 341 |
"model.layers.17.mlp.router.bias": "model-00007-of-00013.safetensors",
|
| 342 |
"model.layers.17.mlp.router.biases": "model-00007-of-00013.safetensors",
|
| 343 |
"model.layers.17.mlp.router.scales": "model-00007-of-00013.safetensors",
|
| 344 |
"model.layers.17.mlp.router.weight": "model-00007-of-00013.safetensors",
|
| 345 |
"model.layers.17.post_attention_layernorm.weight": "model-00007-of-00013.safetensors",
|
| 346 |
-
"model.layers.17.self_attn.k_proj.bias": "model-
|
| 347 |
-
"model.layers.17.self_attn.k_proj.biases": "model-
|
| 348 |
-
"model.layers.17.self_attn.k_proj.scales": "model-
|
| 349 |
-
"model.layers.17.self_attn.k_proj.weight": "model-
|
| 350 |
-
"model.layers.17.self_attn.o_proj.bias": "model-
|
| 351 |
-
"model.layers.17.self_attn.o_proj.biases": "model-
|
| 352 |
-
"model.layers.17.self_attn.o_proj.scales": "model-
|
| 353 |
-
"model.layers.17.self_attn.o_proj.weight": "model-
|
| 354 |
-
"model.layers.17.self_attn.q_proj.bias": "model-
|
| 355 |
-
"model.layers.17.self_attn.q_proj.biases": "model-
|
| 356 |
-
"model.layers.17.self_attn.q_proj.scales": "model-
|
| 357 |
-
"model.layers.17.self_attn.q_proj.weight": "model-
|
| 358 |
-
"model.layers.17.self_attn.sinks": "model-
|
| 359 |
-
"model.layers.17.self_attn.v_proj.bias": "model-
|
| 360 |
-
"model.layers.17.self_attn.v_proj.biases": "model-
|
| 361 |
-
"model.layers.17.self_attn.v_proj.scales": "model-
|
| 362 |
-
"model.layers.17.self_attn.v_proj.weight": "model-
|
| 363 |
"model.layers.18.input_layernorm.weight": "model-00007-of-00013.safetensors",
|
| 364 |
"model.layers.18.mlp.experts.down_proj.bias": "model-00007-of-00013.safetensors",
|
| 365 |
-
"model.layers.18.mlp.experts.down_proj.biases": "model-00007-of-00013.safetensors",
|
| 366 |
"model.layers.18.mlp.experts.down_proj.scales": "model-00007-of-00013.safetensors",
|
| 367 |
"model.layers.18.mlp.experts.down_proj.weight": "model-00007-of-00013.safetensors",
|
| 368 |
"model.layers.18.mlp.experts.gate_proj.bias": "model-00007-of-00013.safetensors",
|
| 369 |
-
"model.layers.18.mlp.experts.gate_proj.biases": "model-00007-of-00013.safetensors",
|
| 370 |
"model.layers.18.mlp.experts.gate_proj.scales": "model-00007-of-00013.safetensors",
|
| 371 |
"model.layers.18.mlp.experts.gate_proj.weight": "model-00007-of-00013.safetensors",
|
| 372 |
"model.layers.18.mlp.experts.up_proj.bias": "model-00007-of-00013.safetensors",
|
| 373 |
-
"model.layers.18.mlp.experts.up_proj.biases": "model-00007-of-00013.safetensors",
|
| 374 |
"model.layers.18.mlp.experts.up_proj.scales": "model-00007-of-00013.safetensors",
|
| 375 |
"model.layers.18.mlp.experts.up_proj.weight": "model-00007-of-00013.safetensors",
|
| 376 |
"model.layers.18.mlp.router.bias": "model-00007-of-00013.safetensors",
|
|
@@ -395,24 +362,21 @@
|
|
| 395 |
"model.layers.18.self_attn.v_proj.biases": "model-00007-of-00013.safetensors",
|
| 396 |
"model.layers.18.self_attn.v_proj.scales": "model-00007-of-00013.safetensors",
|
| 397 |
"model.layers.18.self_attn.v_proj.weight": "model-00007-of-00013.safetensors",
|
| 398 |
-
"model.layers.19.input_layernorm.weight": "model-
|
| 399 |
-
"model.layers.19.mlp.experts.down_proj.bias": "model-
|
| 400 |
-
"model.layers.19.mlp.experts.down_proj.
|
| 401 |
-
"model.layers.19.mlp.experts.down_proj.
|
| 402 |
-
"model.layers.19.mlp.experts.down_proj.weight": "model-00008-of-00013.safetensors",
|
| 403 |
"model.layers.19.mlp.experts.gate_proj.bias": "model-00007-of-00013.safetensors",
|
| 404 |
-
"model.layers.19.mlp.experts.gate_proj.biases": "model-00007-of-00013.safetensors",
|
| 405 |
"model.layers.19.mlp.experts.gate_proj.scales": "model-00007-of-00013.safetensors",
|
| 406 |
"model.layers.19.mlp.experts.gate_proj.weight": "model-00007-of-00013.safetensors",
|
| 407 |
"model.layers.19.mlp.experts.up_proj.bias": "model-00007-of-00013.safetensors",
|
| 408 |
-
"model.layers.19.mlp.experts.up_proj.biases": "model-00007-of-00013.safetensors",
|
| 409 |
"model.layers.19.mlp.experts.up_proj.scales": "model-00007-of-00013.safetensors",
|
| 410 |
"model.layers.19.mlp.experts.up_proj.weight": "model-00007-of-00013.safetensors",
|
| 411 |
-
"model.layers.19.mlp.router.bias": "model-
|
| 412 |
-
"model.layers.19.mlp.router.biases": "model-
|
| 413 |
-
"model.layers.19.mlp.router.scales": "model-
|
| 414 |
-
"model.layers.19.mlp.router.weight": "model-
|
| 415 |
-
"model.layers.19.post_attention_layernorm.weight": "model-
|
| 416 |
"model.layers.19.self_attn.k_proj.bias": "model-00007-of-00013.safetensors",
|
| 417 |
"model.layers.19.self_attn.k_proj.biases": "model-00007-of-00013.safetensors",
|
| 418 |
"model.layers.19.self_attn.k_proj.scales": "model-00007-of-00013.safetensors",
|
|
@@ -432,15 +396,12 @@
|
|
| 432 |
"model.layers.19.self_attn.v_proj.weight": "model-00007-of-00013.safetensors",
|
| 433 |
"model.layers.2.input_layernorm.weight": "model-00002-of-00013.safetensors",
|
| 434 |
"model.layers.2.mlp.experts.down_proj.bias": "model-00002-of-00013.safetensors",
|
| 435 |
-
"model.layers.2.mlp.experts.down_proj.biases": "model-00002-of-00013.safetensors",
|
| 436 |
"model.layers.2.mlp.experts.down_proj.scales": "model-00002-of-00013.safetensors",
|
| 437 |
"model.layers.2.mlp.experts.down_proj.weight": "model-00002-of-00013.safetensors",
|
| 438 |
"model.layers.2.mlp.experts.gate_proj.bias": "model-00001-of-00013.safetensors",
|
| 439 |
-
"model.layers.2.mlp.experts.gate_proj.biases": "model-00001-of-00013.safetensors",
|
| 440 |
"model.layers.2.mlp.experts.gate_proj.scales": "model-00001-of-00013.safetensors",
|
| 441 |
"model.layers.2.mlp.experts.gate_proj.weight": "model-00001-of-00013.safetensors",
|
| 442 |
"model.layers.2.mlp.experts.up_proj.bias": "model-00001-of-00013.safetensors",
|
| 443 |
-
"model.layers.2.mlp.experts.up_proj.biases": "model-00001-of-00013.safetensors",
|
| 444 |
"model.layers.2.mlp.experts.up_proj.scales": "model-00001-of-00013.safetensors",
|
| 445 |
"model.layers.2.mlp.experts.up_proj.weight": "model-00001-of-00013.safetensors",
|
| 446 |
"model.layers.2.mlp.router.bias": "model-00002-of-00013.safetensors",
|
|
@@ -467,50 +428,44 @@
|
|
| 467 |
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
|
| 468 |
"model.layers.20.input_layernorm.weight": "model-00008-of-00013.safetensors",
|
| 469 |
"model.layers.20.mlp.experts.down_proj.bias": "model-00008-of-00013.safetensors",
|
| 470 |
-
"model.layers.20.mlp.experts.down_proj.biases": "model-00008-of-00013.safetensors",
|
| 471 |
"model.layers.20.mlp.experts.down_proj.scales": "model-00008-of-00013.safetensors",
|
| 472 |
"model.layers.20.mlp.experts.down_proj.weight": "model-00008-of-00013.safetensors",
|
| 473 |
-
"model.layers.20.mlp.experts.gate_proj.bias": "model-
|
| 474 |
-
"model.layers.20.mlp.experts.gate_proj.
|
| 475 |
-
"model.layers.20.mlp.experts.gate_proj.
|
| 476 |
-
"model.layers.20.mlp.experts.
|
| 477 |
-
"model.layers.20.mlp.experts.up_proj.
|
| 478 |
-
"model.layers.20.mlp.experts.up_proj.
|
| 479 |
-
"model.layers.20.mlp.experts.up_proj.scales": "model-00008-of-00013.safetensors",
|
| 480 |
-
"model.layers.20.mlp.experts.up_proj.weight": "model-00008-of-00013.safetensors",
|
| 481 |
"model.layers.20.mlp.router.bias": "model-00008-of-00013.safetensors",
|
| 482 |
"model.layers.20.mlp.router.biases": "model-00008-of-00013.safetensors",
|
| 483 |
"model.layers.20.mlp.router.scales": "model-00008-of-00013.safetensors",
|
| 484 |
"model.layers.20.mlp.router.weight": "model-00008-of-00013.safetensors",
|
| 485 |
"model.layers.20.post_attention_layernorm.weight": "model-00008-of-00013.safetensors",
|
| 486 |
-
"model.layers.20.self_attn.k_proj.bias": "model-
|
| 487 |
-
"model.layers.20.self_attn.k_proj.biases": "model-
|
| 488 |
-
"model.layers.20.self_attn.k_proj.scales": "model-
|
| 489 |
-
"model.layers.20.self_attn.k_proj.weight": "model-
|
| 490 |
-
"model.layers.20.self_attn.o_proj.bias": "model-
|
| 491 |
-
"model.layers.20.self_attn.o_proj.biases": "model-
|
| 492 |
-
"model.layers.20.self_attn.o_proj.scales": "model-
|
| 493 |
-
"model.layers.20.self_attn.o_proj.weight": "model-
|
| 494 |
-
"model.layers.20.self_attn.q_proj.bias": "model-
|
| 495 |
-
"model.layers.20.self_attn.q_proj.biases": "model-
|
| 496 |
-
"model.layers.20.self_attn.q_proj.scales": "model-
|
| 497 |
-
"model.layers.20.self_attn.q_proj.weight": "model-
|
| 498 |
-
"model.layers.20.self_attn.sinks": "model-
|
| 499 |
-
"model.layers.20.self_attn.v_proj.bias": "model-
|
| 500 |
-
"model.layers.20.self_attn.v_proj.biases": "model-
|
| 501 |
-
"model.layers.20.self_attn.v_proj.scales": "model-
|
| 502 |
-
"model.layers.20.self_attn.v_proj.weight": "model-
|
| 503 |
"model.layers.21.input_layernorm.weight": "model-00008-of-00013.safetensors",
|
| 504 |
"model.layers.21.mlp.experts.down_proj.bias": "model-00008-of-00013.safetensors",
|
| 505 |
-
"model.layers.21.mlp.experts.down_proj.biases": "model-00008-of-00013.safetensors",
|
| 506 |
"model.layers.21.mlp.experts.down_proj.scales": "model-00008-of-00013.safetensors",
|
| 507 |
"model.layers.21.mlp.experts.down_proj.weight": "model-00008-of-00013.safetensors",
|
| 508 |
"model.layers.21.mlp.experts.gate_proj.bias": "model-00008-of-00013.safetensors",
|
| 509 |
-
"model.layers.21.mlp.experts.gate_proj.biases": "model-00008-of-00013.safetensors",
|
| 510 |
"model.layers.21.mlp.experts.gate_proj.scales": "model-00008-of-00013.safetensors",
|
| 511 |
"model.layers.21.mlp.experts.gate_proj.weight": "model-00008-of-00013.safetensors",
|
| 512 |
"model.layers.21.mlp.experts.up_proj.bias": "model-00008-of-00013.safetensors",
|
| 513 |
-
"model.layers.21.mlp.experts.up_proj.biases": "model-00008-of-00013.safetensors",
|
| 514 |
"model.layers.21.mlp.experts.up_proj.scales": "model-00008-of-00013.safetensors",
|
| 515 |
"model.layers.21.mlp.experts.up_proj.weight": "model-00008-of-00013.safetensors",
|
| 516 |
"model.layers.21.mlp.router.bias": "model-00008-of-00013.safetensors",
|
|
@@ -535,24 +490,21 @@
|
|
| 535 |
"model.layers.21.self_attn.v_proj.biases": "model-00008-of-00013.safetensors",
|
| 536 |
"model.layers.21.self_attn.v_proj.scales": "model-00008-of-00013.safetensors",
|
| 537 |
"model.layers.21.self_attn.v_proj.weight": "model-00008-of-00013.safetensors",
|
| 538 |
-
"model.layers.22.input_layernorm.weight": "model-
|
| 539 |
-
"model.layers.22.mlp.experts.down_proj.bias": "model-
|
| 540 |
-
"model.layers.22.mlp.experts.down_proj.
|
| 541 |
-
"model.layers.22.mlp.experts.down_proj.
|
| 542 |
-
"model.layers.22.mlp.experts.down_proj.weight": "model-00009-of-00013.safetensors",
|
| 543 |
"model.layers.22.mlp.experts.gate_proj.bias": "model-00008-of-00013.safetensors",
|
| 544 |
-
"model.layers.22.mlp.experts.gate_proj.biases": "model-00008-of-00013.safetensors",
|
| 545 |
"model.layers.22.mlp.experts.gate_proj.scales": "model-00008-of-00013.safetensors",
|
| 546 |
"model.layers.22.mlp.experts.gate_proj.weight": "model-00008-of-00013.safetensors",
|
| 547 |
-
"model.layers.22.mlp.experts.up_proj.bias": "model-
|
| 548 |
-
"model.layers.22.mlp.experts.up_proj.
|
| 549 |
-
"model.layers.22.mlp.experts.up_proj.scales": "model-00009-of-00013.safetensors",
|
| 550 |
"model.layers.22.mlp.experts.up_proj.weight": "model-00008-of-00013.safetensors",
|
| 551 |
-
"model.layers.22.mlp.router.bias": "model-
|
| 552 |
-
"model.layers.22.mlp.router.biases": "model-
|
| 553 |
-
"model.layers.22.mlp.router.scales": "model-
|
| 554 |
-
"model.layers.22.mlp.router.weight": "model-
|
| 555 |
-
"model.layers.22.post_attention_layernorm.weight": "model-
|
| 556 |
"model.layers.22.self_attn.k_proj.bias": "model-00008-of-00013.safetensors",
|
| 557 |
"model.layers.22.self_attn.k_proj.biases": "model-00008-of-00013.safetensors",
|
| 558 |
"model.layers.22.self_attn.k_proj.scales": "model-00008-of-00013.safetensors",
|
|
@@ -572,50 +524,44 @@
|
|
| 572 |
"model.layers.22.self_attn.v_proj.weight": "model-00008-of-00013.safetensors",
|
| 573 |
"model.layers.23.input_layernorm.weight": "model-00009-of-00013.safetensors",
|
| 574 |
"model.layers.23.mlp.experts.down_proj.bias": "model-00009-of-00013.safetensors",
|
| 575 |
-
"model.layers.23.mlp.experts.down_proj.biases": "model-00009-of-00013.safetensors",
|
| 576 |
"model.layers.23.mlp.experts.down_proj.scales": "model-00009-of-00013.safetensors",
|
| 577 |
"model.layers.23.mlp.experts.down_proj.weight": "model-00009-of-00013.safetensors",
|
| 578 |
-
"model.layers.23.mlp.experts.gate_proj.bias": "model-
|
| 579 |
-
"model.layers.23.mlp.experts.gate_proj.
|
| 580 |
-
"model.layers.23.mlp.experts.gate_proj.
|
| 581 |
-
"model.layers.23.mlp.experts.
|
| 582 |
-
"model.layers.23.mlp.experts.up_proj.
|
| 583 |
-
"model.layers.23.mlp.experts.up_proj.
|
| 584 |
-
"model.layers.23.mlp.experts.up_proj.scales": "model-00009-of-00013.safetensors",
|
| 585 |
-
"model.layers.23.mlp.experts.up_proj.weight": "model-00009-of-00013.safetensors",
|
| 586 |
"model.layers.23.mlp.router.bias": "model-00009-of-00013.safetensors",
|
| 587 |
"model.layers.23.mlp.router.biases": "model-00009-of-00013.safetensors",
|
| 588 |
"model.layers.23.mlp.router.scales": "model-00009-of-00013.safetensors",
|
| 589 |
"model.layers.23.mlp.router.weight": "model-00009-of-00013.safetensors",
|
| 590 |
"model.layers.23.post_attention_layernorm.weight": "model-00009-of-00013.safetensors",
|
| 591 |
-
"model.layers.23.self_attn.k_proj.bias": "model-
|
| 592 |
-
"model.layers.23.self_attn.k_proj.biases": "model-
|
| 593 |
-
"model.layers.23.self_attn.k_proj.scales": "model-
|
| 594 |
-
"model.layers.23.self_attn.k_proj.weight": "model-
|
| 595 |
-
"model.layers.23.self_attn.o_proj.bias": "model-
|
| 596 |
-
"model.layers.23.self_attn.o_proj.biases": "model-
|
| 597 |
-
"model.layers.23.self_attn.o_proj.scales": "model-
|
| 598 |
-
"model.layers.23.self_attn.o_proj.weight": "model-
|
| 599 |
-
"model.layers.23.self_attn.q_proj.bias": "model-
|
| 600 |
-
"model.layers.23.self_attn.q_proj.biases": "model-
|
| 601 |
-
"model.layers.23.self_attn.q_proj.scales": "model-
|
| 602 |
-
"model.layers.23.self_attn.q_proj.weight": "model-
|
| 603 |
-
"model.layers.23.self_attn.sinks": "model-
|
| 604 |
-
"model.layers.23.self_attn.v_proj.bias": "model-
|
| 605 |
-
"model.layers.23.self_attn.v_proj.biases": "model-
|
| 606 |
-
"model.layers.23.self_attn.v_proj.scales": "model-
|
| 607 |
-
"model.layers.23.self_attn.v_proj.weight": "model-
|
| 608 |
"model.layers.24.input_layernorm.weight": "model-00009-of-00013.safetensors",
|
| 609 |
"model.layers.24.mlp.experts.down_proj.bias": "model-00009-of-00013.safetensors",
|
| 610 |
-
"model.layers.24.mlp.experts.down_proj.biases": "model-00009-of-00013.safetensors",
|
| 611 |
"model.layers.24.mlp.experts.down_proj.scales": "model-00009-of-00013.safetensors",
|
| 612 |
"model.layers.24.mlp.experts.down_proj.weight": "model-00009-of-00013.safetensors",
|
| 613 |
"model.layers.24.mlp.experts.gate_proj.bias": "model-00009-of-00013.safetensors",
|
| 614 |
-
"model.layers.24.mlp.experts.gate_proj.biases": "model-00009-of-00013.safetensors",
|
| 615 |
"model.layers.24.mlp.experts.gate_proj.scales": "model-00009-of-00013.safetensors",
|
| 616 |
"model.layers.24.mlp.experts.gate_proj.weight": "model-00009-of-00013.safetensors",
|
| 617 |
"model.layers.24.mlp.experts.up_proj.bias": "model-00009-of-00013.safetensors",
|
| 618 |
-
"model.layers.24.mlp.experts.up_proj.biases": "model-00009-of-00013.safetensors",
|
| 619 |
"model.layers.24.mlp.experts.up_proj.scales": "model-00009-of-00013.safetensors",
|
| 620 |
"model.layers.24.mlp.experts.up_proj.weight": "model-00009-of-00013.safetensors",
|
| 621 |
"model.layers.24.mlp.router.bias": "model-00009-of-00013.safetensors",
|
|
@@ -640,24 +586,21 @@
|
|
| 640 |
"model.layers.24.self_attn.v_proj.biases": "model-00009-of-00013.safetensors",
|
| 641 |
"model.layers.24.self_attn.v_proj.scales": "model-00009-of-00013.safetensors",
|
| 642 |
"model.layers.24.self_attn.v_proj.weight": "model-00009-of-00013.safetensors",
|
| 643 |
-
"model.layers.25.input_layernorm.weight": "model-
|
| 644 |
-
"model.layers.25.mlp.experts.down_proj.bias": "model-
|
| 645 |
-
"model.layers.25.mlp.experts.down_proj.
|
| 646 |
-
"model.layers.25.mlp.experts.down_proj.
|
| 647 |
-
"model.layers.25.mlp.experts.down_proj.weight": "model-00010-of-00013.safetensors",
|
| 648 |
"model.layers.25.mlp.experts.gate_proj.bias": "model-00009-of-00013.safetensors",
|
| 649 |
-
"model.layers.25.mlp.experts.gate_proj.biases": "model-00009-of-00013.safetensors",
|
| 650 |
"model.layers.25.mlp.experts.gate_proj.scales": "model-00009-of-00013.safetensors",
|
| 651 |
"model.layers.25.mlp.experts.gate_proj.weight": "model-00009-of-00013.safetensors",
|
| 652 |
-
"model.layers.25.mlp.experts.up_proj.bias": "model-
|
| 653 |
-
"model.layers.25.mlp.experts.up_proj.
|
| 654 |
-
"model.layers.25.mlp.experts.up_proj.
|
| 655 |
-
"model.layers.25.mlp.
|
| 656 |
-
"model.layers.25.mlp.router.
|
| 657 |
-
"model.layers.25.mlp.router.
|
| 658 |
-
"model.layers.25.mlp.router.
|
| 659 |
-
"model.layers.25.
|
| 660 |
-
"model.layers.25.post_attention_layernorm.weight": "model-00010-of-00013.safetensors",
|
| 661 |
"model.layers.25.self_attn.k_proj.bias": "model-00009-of-00013.safetensors",
|
| 662 |
"model.layers.25.self_attn.k_proj.biases": "model-00009-of-00013.safetensors",
|
| 663 |
"model.layers.25.self_attn.k_proj.scales": "model-00009-of-00013.safetensors",
|
|
@@ -677,50 +620,44 @@
|
|
| 677 |
"model.layers.25.self_attn.v_proj.weight": "model-00009-of-00013.safetensors",
|
| 678 |
"model.layers.26.input_layernorm.weight": "model-00010-of-00013.safetensors",
|
| 679 |
"model.layers.26.mlp.experts.down_proj.bias": "model-00010-of-00013.safetensors",
|
| 680 |
-
"model.layers.26.mlp.experts.down_proj.biases": "model-00010-of-00013.safetensors",
|
| 681 |
"model.layers.26.mlp.experts.down_proj.scales": "model-00010-of-00013.safetensors",
|
| 682 |
"model.layers.26.mlp.experts.down_proj.weight": "model-00010-of-00013.safetensors",
|
| 683 |
-
"model.layers.26.mlp.experts.gate_proj.bias": "model-
|
| 684 |
-
"model.layers.26.mlp.experts.gate_proj.
|
| 685 |
-
"model.layers.26.mlp.experts.gate_proj.
|
| 686 |
-
"model.layers.26.mlp.experts.
|
| 687 |
-
"model.layers.26.mlp.experts.up_proj.
|
| 688 |
-
"model.layers.26.mlp.experts.up_proj.
|
| 689 |
-
"model.layers.26.mlp.experts.up_proj.scales": "model-00010-of-00013.safetensors",
|
| 690 |
-
"model.layers.26.mlp.experts.up_proj.weight": "model-00010-of-00013.safetensors",
|
| 691 |
"model.layers.26.mlp.router.bias": "model-00010-of-00013.safetensors",
|
| 692 |
"model.layers.26.mlp.router.biases": "model-00010-of-00013.safetensors",
|
| 693 |
"model.layers.26.mlp.router.scales": "model-00010-of-00013.safetensors",
|
| 694 |
"model.layers.26.mlp.router.weight": "model-00010-of-00013.safetensors",
|
| 695 |
"model.layers.26.post_attention_layernorm.weight": "model-00010-of-00013.safetensors",
|
| 696 |
-
"model.layers.26.self_attn.k_proj.bias": "model-
|
| 697 |
-
"model.layers.26.self_attn.k_proj.biases": "model-
|
| 698 |
-
"model.layers.26.self_attn.k_proj.scales": "model-
|
| 699 |
-
"model.layers.26.self_attn.k_proj.weight": "model-
|
| 700 |
-
"model.layers.26.self_attn.o_proj.bias": "model-
|
| 701 |
-
"model.layers.26.self_attn.o_proj.biases": "model-
|
| 702 |
-
"model.layers.26.self_attn.o_proj.scales": "model-
|
| 703 |
-
"model.layers.26.self_attn.o_proj.weight": "model-
|
| 704 |
-
"model.layers.26.self_attn.q_proj.bias": "model-
|
| 705 |
-
"model.layers.26.self_attn.q_proj.biases": "model-
|
| 706 |
-
"model.layers.26.self_attn.q_proj.scales": "model-
|
| 707 |
-
"model.layers.26.self_attn.q_proj.weight": "model-
|
| 708 |
-
"model.layers.26.self_attn.sinks": "model-
|
| 709 |
-
"model.layers.26.self_attn.v_proj.bias": "model-
|
| 710 |
-
"model.layers.26.self_attn.v_proj.biases": "model-
|
| 711 |
-
"model.layers.26.self_attn.v_proj.scales": "model-
|
| 712 |
-
"model.layers.26.self_attn.v_proj.weight": "model-
|
| 713 |
"model.layers.27.input_layernorm.weight": "model-00010-of-00013.safetensors",
|
| 714 |
"model.layers.27.mlp.experts.down_proj.bias": "model-00010-of-00013.safetensors",
|
| 715 |
-
"model.layers.27.mlp.experts.down_proj.biases": "model-00010-of-00013.safetensors",
|
| 716 |
"model.layers.27.mlp.experts.down_proj.scales": "model-00010-of-00013.safetensors",
|
| 717 |
"model.layers.27.mlp.experts.down_proj.weight": "model-00010-of-00013.safetensors",
|
| 718 |
"model.layers.27.mlp.experts.gate_proj.bias": "model-00010-of-00013.safetensors",
|
| 719 |
-
"model.layers.27.mlp.experts.gate_proj.biases": "model-00010-of-00013.safetensors",
|
| 720 |
"model.layers.27.mlp.experts.gate_proj.scales": "model-00010-of-00013.safetensors",
|
| 721 |
"model.layers.27.mlp.experts.gate_proj.weight": "model-00010-of-00013.safetensors",
|
| 722 |
"model.layers.27.mlp.experts.up_proj.bias": "model-00010-of-00013.safetensors",
|
| 723 |
-
"model.layers.27.mlp.experts.up_proj.biases": "model-00010-of-00013.safetensors",
|
| 724 |
"model.layers.27.mlp.experts.up_proj.scales": "model-00010-of-00013.safetensors",
|
| 725 |
"model.layers.27.mlp.experts.up_proj.weight": "model-00010-of-00013.safetensors",
|
| 726 |
"model.layers.27.mlp.router.bias": "model-00010-of-00013.safetensors",
|
|
@@ -745,24 +682,21 @@
|
|
| 745 |
"model.layers.27.self_attn.v_proj.biases": "model-00010-of-00013.safetensors",
|
| 746 |
"model.layers.27.self_attn.v_proj.scales": "model-00010-of-00013.safetensors",
|
| 747 |
"model.layers.27.self_attn.v_proj.weight": "model-00010-of-00013.safetensors",
|
| 748 |
-
"model.layers.28.input_layernorm.weight": "model-
|
| 749 |
-
"model.layers.28.mlp.experts.down_proj.bias": "model-
|
| 750 |
-
"model.layers.28.mlp.experts.down_proj.
|
| 751 |
-
"model.layers.28.mlp.experts.down_proj.
|
| 752 |
-
"model.layers.28.mlp.experts.
|
| 753 |
-
"model.layers.28.mlp.experts.gate_proj.
|
| 754 |
-
"model.layers.28.mlp.experts.gate_proj.biases": "model-00011-of-00013.safetensors",
|
| 755 |
-
"model.layers.28.mlp.experts.gate_proj.scales": "model-00011-of-00013.safetensors",
|
| 756 |
"model.layers.28.mlp.experts.gate_proj.weight": "model-00010-of-00013.safetensors",
|
| 757 |
-
"model.layers.28.mlp.experts.up_proj.bias": "model-
|
| 758 |
-
"model.layers.28.mlp.experts.up_proj.
|
| 759 |
-
"model.layers.28.mlp.experts.up_proj.
|
| 760 |
-
"model.layers.28.mlp.
|
| 761 |
-
"model.layers.28.mlp.router.
|
| 762 |
-
"model.layers.28.mlp.router.
|
| 763 |
-
"model.layers.28.mlp.router.
|
| 764 |
-
"model.layers.28.
|
| 765 |
-
"model.layers.28.post_attention_layernorm.weight": "model-00011-of-00013.safetensors",
|
| 766 |
"model.layers.28.self_attn.k_proj.bias": "model-00010-of-00013.safetensors",
|
| 767 |
"model.layers.28.self_attn.k_proj.biases": "model-00010-of-00013.safetensors",
|
| 768 |
"model.layers.28.self_attn.k_proj.scales": "model-00010-of-00013.safetensors",
|
|
@@ -782,50 +716,44 @@
|
|
| 782 |
"model.layers.28.self_attn.v_proj.weight": "model-00010-of-00013.safetensors",
|
| 783 |
"model.layers.29.input_layernorm.weight": "model-00011-of-00013.safetensors",
|
| 784 |
"model.layers.29.mlp.experts.down_proj.bias": "model-00011-of-00013.safetensors",
|
| 785 |
-
"model.layers.29.mlp.experts.down_proj.biases": "model-00011-of-00013.safetensors",
|
| 786 |
"model.layers.29.mlp.experts.down_proj.scales": "model-00011-of-00013.safetensors",
|
| 787 |
"model.layers.29.mlp.experts.down_proj.weight": "model-00011-of-00013.safetensors",
|
| 788 |
-
"model.layers.29.mlp.experts.gate_proj.bias": "model-
|
| 789 |
-
"model.layers.29.mlp.experts.gate_proj.
|
| 790 |
-
"model.layers.29.mlp.experts.gate_proj.
|
| 791 |
-
"model.layers.29.mlp.experts.
|
| 792 |
-
"model.layers.29.mlp.experts.up_proj.
|
| 793 |
-
"model.layers.29.mlp.experts.up_proj.
|
| 794 |
-
"model.layers.29.mlp.experts.up_proj.scales": "model-00011-of-00013.safetensors",
|
| 795 |
-
"model.layers.29.mlp.experts.up_proj.weight": "model-00011-of-00013.safetensors",
|
| 796 |
"model.layers.29.mlp.router.bias": "model-00011-of-00013.safetensors",
|
| 797 |
"model.layers.29.mlp.router.biases": "model-00011-of-00013.safetensors",
|
| 798 |
"model.layers.29.mlp.router.scales": "model-00011-of-00013.safetensors",
|
| 799 |
"model.layers.29.mlp.router.weight": "model-00011-of-00013.safetensors",
|
| 800 |
"model.layers.29.post_attention_layernorm.weight": "model-00011-of-00013.safetensors",
|
| 801 |
-
"model.layers.29.self_attn.k_proj.bias": "model-
|
| 802 |
-
"model.layers.29.self_attn.k_proj.biases": "model-
|
| 803 |
-
"model.layers.29.self_attn.k_proj.scales": "model-
|
| 804 |
-
"model.layers.29.self_attn.k_proj.weight": "model-
|
| 805 |
-
"model.layers.29.self_attn.o_proj.bias": "model-
|
| 806 |
-
"model.layers.29.self_attn.o_proj.biases": "model-
|
| 807 |
-
"model.layers.29.self_attn.o_proj.scales": "model-
|
| 808 |
-
"model.layers.29.self_attn.o_proj.weight": "model-
|
| 809 |
-
"model.layers.29.self_attn.q_proj.bias": "model-
|
| 810 |
-
"model.layers.29.self_attn.q_proj.biases": "model-
|
| 811 |
-
"model.layers.29.self_attn.q_proj.scales": "model-
|
| 812 |
-
"model.layers.29.self_attn.q_proj.weight": "model-
|
| 813 |
-
"model.layers.29.self_attn.sinks": "model-
|
| 814 |
-
"model.layers.29.self_attn.v_proj.bias": "model-
|
| 815 |
-
"model.layers.29.self_attn.v_proj.biases": "model-
|
| 816 |
-
"model.layers.29.self_attn.v_proj.scales": "model-
|
| 817 |
-
"model.layers.29.self_attn.v_proj.weight": "model-
|
| 818 |
"model.layers.3.input_layernorm.weight": "model-00002-of-00013.safetensors",
|
| 819 |
"model.layers.3.mlp.experts.down_proj.bias": "model-00002-of-00013.safetensors",
|
| 820 |
-
"model.layers.3.mlp.experts.down_proj.biases": "model-00002-of-00013.safetensors",
|
| 821 |
"model.layers.3.mlp.experts.down_proj.scales": "model-00002-of-00013.safetensors",
|
| 822 |
"model.layers.3.mlp.experts.down_proj.weight": "model-00002-of-00013.safetensors",
|
| 823 |
"model.layers.3.mlp.experts.gate_proj.bias": "model-00002-of-00013.safetensors",
|
| 824 |
-
"model.layers.3.mlp.experts.gate_proj.biases": "model-00002-of-00013.safetensors",
|
| 825 |
"model.layers.3.mlp.experts.gate_proj.scales": "model-00002-of-00013.safetensors",
|
| 826 |
"model.layers.3.mlp.experts.gate_proj.weight": "model-00002-of-00013.safetensors",
|
| 827 |
"model.layers.3.mlp.experts.up_proj.bias": "model-00002-of-00013.safetensors",
|
| 828 |
-
"model.layers.3.mlp.experts.up_proj.biases": "model-00002-of-00013.safetensors",
|
| 829 |
"model.layers.3.mlp.experts.up_proj.scales": "model-00002-of-00013.safetensors",
|
| 830 |
"model.layers.3.mlp.experts.up_proj.weight": "model-00002-of-00013.safetensors",
|
| 831 |
"model.layers.3.mlp.router.bias": "model-00002-of-00013.safetensors",
|
|
@@ -852,15 +780,12 @@
|
|
| 852 |
"model.layers.3.self_attn.v_proj.weight": "model-00002-of-00013.safetensors",
|
| 853 |
"model.layers.30.input_layernorm.weight": "model-00011-of-00013.safetensors",
|
| 854 |
"model.layers.30.mlp.experts.down_proj.bias": "model-00011-of-00013.safetensors",
|
| 855 |
-
"model.layers.30.mlp.experts.down_proj.biases": "model-00011-of-00013.safetensors",
|
| 856 |
"model.layers.30.mlp.experts.down_proj.scales": "model-00011-of-00013.safetensors",
|
| 857 |
"model.layers.30.mlp.experts.down_proj.weight": "model-00011-of-00013.safetensors",
|
| 858 |
"model.layers.30.mlp.experts.gate_proj.bias": "model-00011-of-00013.safetensors",
|
| 859 |
-
"model.layers.30.mlp.experts.gate_proj.biases": "model-00011-of-00013.safetensors",
|
| 860 |
"model.layers.30.mlp.experts.gate_proj.scales": "model-00011-of-00013.safetensors",
|
| 861 |
"model.layers.30.mlp.experts.gate_proj.weight": "model-00011-of-00013.safetensors",
|
| 862 |
"model.layers.30.mlp.experts.up_proj.bias": "model-00011-of-00013.safetensors",
|
| 863 |
-
"model.layers.30.mlp.experts.up_proj.biases": "model-00011-of-00013.safetensors",
|
| 864 |
"model.layers.30.mlp.experts.up_proj.scales": "model-00011-of-00013.safetensors",
|
| 865 |
"model.layers.30.mlp.experts.up_proj.weight": "model-00011-of-00013.safetensors",
|
| 866 |
"model.layers.30.mlp.router.bias": "model-00011-of-00013.safetensors",
|
|
@@ -885,24 +810,21 @@
|
|
| 885 |
"model.layers.30.self_attn.v_proj.biases": "model-00011-of-00013.safetensors",
|
| 886 |
"model.layers.30.self_attn.v_proj.scales": "model-00011-of-00013.safetensors",
|
| 887 |
"model.layers.30.self_attn.v_proj.weight": "model-00011-of-00013.safetensors",
|
| 888 |
-
"model.layers.31.input_layernorm.weight": "model-
|
| 889 |
-
"model.layers.31.mlp.experts.down_proj.bias": "model-
|
| 890 |
-
"model.layers.31.mlp.experts.down_proj.
|
| 891 |
-
"model.layers.31.mlp.experts.down_proj.
|
| 892 |
-
"model.layers.31.mlp.experts.
|
| 893 |
-
"model.layers.31.mlp.experts.gate_proj.
|
| 894 |
-
"model.layers.31.mlp.experts.gate_proj.
|
| 895 |
-
"model.layers.31.mlp.experts.
|
| 896 |
-
"model.layers.31.mlp.experts.
|
| 897 |
-
"model.layers.31.mlp.experts.up_proj.
|
| 898 |
-
"model.layers.31.mlp.
|
| 899 |
-
"model.layers.31.mlp.
|
| 900 |
-
"model.layers.31.mlp.
|
| 901 |
-
"model.layers.31.mlp.router.
|
| 902 |
-
"model.layers.31.
|
| 903 |
-
"model.layers.31.mlp.router.scales": "model-00012-of-00013.safetensors",
|
| 904 |
-
"model.layers.31.mlp.router.weight": "model-00012-of-00013.safetensors",
|
| 905 |
-
"model.layers.31.post_attention_layernorm.weight": "model-00012-of-00013.safetensors",
|
| 906 |
"model.layers.31.self_attn.k_proj.bias": "model-00011-of-00013.safetensors",
|
| 907 |
"model.layers.31.self_attn.k_proj.biases": "model-00011-of-00013.safetensors",
|
| 908 |
"model.layers.31.self_attn.k_proj.scales": "model-00011-of-00013.safetensors",
|
|
@@ -922,57 +844,51 @@
|
|
| 922 |
"model.layers.31.self_attn.v_proj.weight": "model-00011-of-00013.safetensors",
|
| 923 |
"model.layers.32.input_layernorm.weight": "model-00012-of-00013.safetensors",
|
| 924 |
"model.layers.32.mlp.experts.down_proj.bias": "model-00012-of-00013.safetensors",
|
| 925 |
-
"model.layers.32.mlp.experts.down_proj.biases": "model-00012-of-00013.safetensors",
|
| 926 |
"model.layers.32.mlp.experts.down_proj.scales": "model-00012-of-00013.safetensors",
|
| 927 |
"model.layers.32.mlp.experts.down_proj.weight": "model-00012-of-00013.safetensors",
|
| 928 |
-
"model.layers.32.mlp.experts.gate_proj.bias": "model-
|
| 929 |
-
"model.layers.32.mlp.experts.gate_proj.
|
| 930 |
-
"model.layers.32.mlp.experts.gate_proj.
|
| 931 |
-
"model.layers.32.mlp.experts.
|
| 932 |
-
"model.layers.32.mlp.experts.up_proj.
|
| 933 |
-
"model.layers.32.mlp.experts.up_proj.
|
| 934 |
-
"model.layers.32.mlp.experts.up_proj.scales": "model-00012-of-00013.safetensors",
|
| 935 |
-
"model.layers.32.mlp.experts.up_proj.weight": "model-00012-of-00013.safetensors",
|
| 936 |
"model.layers.32.mlp.router.bias": "model-00012-of-00013.safetensors",
|
| 937 |
"model.layers.32.mlp.router.biases": "model-00012-of-00013.safetensors",
|
| 938 |
"model.layers.32.mlp.router.scales": "model-00012-of-00013.safetensors",
|
| 939 |
"model.layers.32.mlp.router.weight": "model-00012-of-00013.safetensors",
|
| 940 |
"model.layers.32.post_attention_layernorm.weight": "model-00012-of-00013.safetensors",
|
| 941 |
-
"model.layers.32.self_attn.k_proj.bias": "model-
|
| 942 |
-
"model.layers.32.self_attn.k_proj.biases": "model-
|
| 943 |
-
"model.layers.32.self_attn.k_proj.scales": "model-
|
| 944 |
-
"model.layers.32.self_attn.k_proj.weight": "model-
|
| 945 |
-
"model.layers.32.self_attn.o_proj.bias": "model-
|
| 946 |
-
"model.layers.32.self_attn.o_proj.biases": "model-
|
| 947 |
-
"model.layers.32.self_attn.o_proj.scales": "model-
|
| 948 |
-
"model.layers.32.self_attn.o_proj.weight": "model-
|
| 949 |
-
"model.layers.32.self_attn.q_proj.bias": "model-
|
| 950 |
-
"model.layers.32.self_attn.q_proj.biases": "model-
|
| 951 |
-
"model.layers.32.self_attn.q_proj.scales": "model-
|
| 952 |
-
"model.layers.32.self_attn.q_proj.weight": "model-
|
| 953 |
-
"model.layers.32.self_attn.sinks": "model-
|
| 954 |
-
"model.layers.32.self_attn.v_proj.bias": "model-
|
| 955 |
-
"model.layers.32.self_attn.v_proj.biases": "model-
|
| 956 |
-
"model.layers.32.self_attn.v_proj.scales": "model-
|
| 957 |
-
"model.layers.32.self_attn.v_proj.weight": "model-
|
| 958 |
-
"model.layers.33.input_layernorm.weight": "model-
|
| 959 |
-
"model.layers.33.mlp.experts.down_proj.bias": "model-
|
| 960 |
-
"model.layers.33.mlp.experts.down_proj.
|
| 961 |
-
"model.layers.33.mlp.experts.down_proj.scales": "model-00013-of-00013.safetensors",
|
| 962 |
"model.layers.33.mlp.experts.down_proj.weight": "model-00012-of-00013.safetensors",
|
| 963 |
"model.layers.33.mlp.experts.gate_proj.bias": "model-00012-of-00013.safetensors",
|
| 964 |
-
"model.layers.33.mlp.experts.gate_proj.biases": "model-00012-of-00013.safetensors",
|
| 965 |
"model.layers.33.mlp.experts.gate_proj.scales": "model-00012-of-00013.safetensors",
|
| 966 |
"model.layers.33.mlp.experts.gate_proj.weight": "model-00012-of-00013.safetensors",
|
| 967 |
"model.layers.33.mlp.experts.up_proj.bias": "model-00012-of-00013.safetensors",
|
| 968 |
-
"model.layers.33.mlp.experts.up_proj.biases": "model-00012-of-00013.safetensors",
|
| 969 |
"model.layers.33.mlp.experts.up_proj.scales": "model-00012-of-00013.safetensors",
|
| 970 |
"model.layers.33.mlp.experts.up_proj.weight": "model-00012-of-00013.safetensors",
|
| 971 |
-
"model.layers.33.mlp.router.bias": "model-
|
| 972 |
-
"model.layers.33.mlp.router.biases": "model-
|
| 973 |
-
"model.layers.33.mlp.router.scales": "model-
|
| 974 |
-
"model.layers.33.mlp.router.weight": "model-
|
| 975 |
-
"model.layers.33.post_attention_layernorm.weight": "model-
|
| 976 |
"model.layers.33.self_attn.k_proj.bias": "model-00012-of-00013.safetensors",
|
| 977 |
"model.layers.33.self_attn.k_proj.biases": "model-00012-of-00013.safetensors",
|
| 978 |
"model.layers.33.self_attn.k_proj.scales": "model-00012-of-00013.safetensors",
|
|
@@ -990,87 +906,78 @@
|
|
| 990 |
"model.layers.33.self_attn.v_proj.biases": "model-00012-of-00013.safetensors",
|
| 991 |
"model.layers.33.self_attn.v_proj.scales": "model-00012-of-00013.safetensors",
|
| 992 |
"model.layers.33.self_attn.v_proj.weight": "model-00012-of-00013.safetensors",
|
| 993 |
-
"model.layers.34.input_layernorm.weight": "model-
|
| 994 |
-
"model.layers.34.mlp.experts.down_proj.bias": "model-
|
| 995 |
-
"model.layers.34.mlp.experts.down_proj.
|
| 996 |
-
"model.layers.34.mlp.experts.down_proj.
|
| 997 |
-
"model.layers.34.mlp.experts.
|
| 998 |
-
"model.layers.34.mlp.experts.gate_proj.
|
| 999 |
-
"model.layers.34.mlp.experts.gate_proj.
|
| 1000 |
-
"model.layers.34.mlp.experts.
|
| 1001 |
-
"model.layers.34.mlp.experts.
|
| 1002 |
-
"model.layers.34.mlp.experts.up_proj.
|
| 1003 |
-
"model.layers.34.mlp.
|
| 1004 |
-
"model.layers.34.mlp.
|
| 1005 |
-
"model.layers.34.mlp.
|
| 1006 |
-
"model.layers.34.mlp.router.
|
| 1007 |
-
"model.layers.34.
|
| 1008 |
-
"model.layers.34.
|
| 1009 |
-
"model.layers.34.
|
| 1010 |
-
"model.layers.34.
|
| 1011 |
-
"model.layers.34.self_attn.k_proj.
|
| 1012 |
-
"model.layers.34.self_attn.
|
| 1013 |
-
"model.layers.34.self_attn.
|
| 1014 |
-
"model.layers.34.self_attn.
|
| 1015 |
-
"model.layers.34.self_attn.o_proj.
|
| 1016 |
-
"model.layers.34.self_attn.
|
| 1017 |
-
"model.layers.34.self_attn.
|
| 1018 |
-
"model.layers.34.self_attn.
|
| 1019 |
-
"model.layers.34.self_attn.q_proj.
|
| 1020 |
-
"model.layers.34.self_attn.
|
| 1021 |
-
"model.layers.34.self_attn.
|
| 1022 |
-
"model.layers.34.self_attn.
|
| 1023 |
-
"model.layers.34.self_attn.
|
| 1024 |
-
"model.layers.34.self_attn.v_proj.
|
| 1025 |
-
"model.layers.34.self_attn.v_proj.biases": "model-00013-of-00013.safetensors",
|
| 1026 |
-
"model.layers.34.self_attn.v_proj.scales": "model-00013-of-00013.safetensors",
|
| 1027 |
-
"model.layers.34.self_attn.v_proj.weight": "model-00013-of-00013.safetensors",
|
| 1028 |
"model.layers.35.input_layernorm.weight": "model-00013-of-00013.safetensors",
|
| 1029 |
"model.layers.35.mlp.experts.down_proj.bias": "model-00013-of-00013.safetensors",
|
| 1030 |
-
"model.layers.35.mlp.experts.down_proj.biases": "model-00013-of-00013.safetensors",
|
| 1031 |
"model.layers.35.mlp.experts.down_proj.scales": "model-00013-of-00013.safetensors",
|
| 1032 |
"model.layers.35.mlp.experts.down_proj.weight": "model-00013-of-00013.safetensors",
|
| 1033 |
-
"model.layers.35.mlp.experts.gate_proj.bias": "model-
|
| 1034 |
-
"model.layers.35.mlp.experts.gate_proj.
|
| 1035 |
-
"model.layers.35.mlp.experts.gate_proj.
|
| 1036 |
-
"model.layers.35.mlp.experts.
|
| 1037 |
-
"model.layers.35.mlp.experts.up_proj.
|
| 1038 |
-
"model.layers.35.mlp.experts.up_proj.
|
| 1039 |
-
"model.layers.35.mlp.experts.up_proj.scales": "model-00013-of-00013.safetensors",
|
| 1040 |
-
"model.layers.35.mlp.experts.up_proj.weight": "model-00013-of-00013.safetensors",
|
| 1041 |
"model.layers.35.mlp.router.bias": "model-00013-of-00013.safetensors",
|
| 1042 |
"model.layers.35.mlp.router.biases": "model-00013-of-00013.safetensors",
|
| 1043 |
"model.layers.35.mlp.router.scales": "model-00013-of-00013.safetensors",
|
| 1044 |
"model.layers.35.mlp.router.weight": "model-00013-of-00013.safetensors",
|
| 1045 |
"model.layers.35.post_attention_layernorm.weight": "model-00013-of-00013.safetensors",
|
| 1046 |
-
"model.layers.35.self_attn.k_proj.bias": "model-
|
| 1047 |
-
"model.layers.35.self_attn.k_proj.biases": "model-
|
| 1048 |
-
"model.layers.35.self_attn.k_proj.scales": "model-
|
| 1049 |
-
"model.layers.35.self_attn.k_proj.weight": "model-
|
| 1050 |
-
"model.layers.35.self_attn.o_proj.bias": "model-
|
| 1051 |
-
"model.layers.35.self_attn.o_proj.biases": "model-
|
| 1052 |
-
"model.layers.35.self_attn.o_proj.scales": "model-
|
| 1053 |
-
"model.layers.35.self_attn.o_proj.weight": "model-
|
| 1054 |
-
"model.layers.35.self_attn.q_proj.bias": "model-
|
| 1055 |
-
"model.layers.35.self_attn.q_proj.biases": "model-
|
| 1056 |
-
"model.layers.35.self_attn.q_proj.scales": "model-
|
| 1057 |
-
"model.layers.35.self_attn.q_proj.weight": "model-
|
| 1058 |
-
"model.layers.35.self_attn.sinks": "model-
|
| 1059 |
-
"model.layers.35.self_attn.v_proj.bias": "model-
|
| 1060 |
-
"model.layers.35.self_attn.v_proj.biases": "model-
|
| 1061 |
-
"model.layers.35.self_attn.v_proj.scales": "model-
|
| 1062 |
-
"model.layers.35.self_attn.v_proj.weight": "model-
|
| 1063 |
"model.layers.4.input_layernorm.weight": "model-00002-of-00013.safetensors",
|
| 1064 |
"model.layers.4.mlp.experts.down_proj.bias": "model-00002-of-00013.safetensors",
|
| 1065 |
-
"model.layers.4.mlp.experts.down_proj.biases": "model-00002-of-00013.safetensors",
|
| 1066 |
"model.layers.4.mlp.experts.down_proj.scales": "model-00002-of-00013.safetensors",
|
| 1067 |
"model.layers.4.mlp.experts.down_proj.weight": "model-00002-of-00013.safetensors",
|
| 1068 |
"model.layers.4.mlp.experts.gate_proj.bias": "model-00002-of-00013.safetensors",
|
| 1069 |
-
"model.layers.4.mlp.experts.gate_proj.biases": "model-00002-of-00013.safetensors",
|
| 1070 |
"model.layers.4.mlp.experts.gate_proj.scales": "model-00002-of-00013.safetensors",
|
| 1071 |
"model.layers.4.mlp.experts.gate_proj.weight": "model-00002-of-00013.safetensors",
|
| 1072 |
"model.layers.4.mlp.experts.up_proj.bias": "model-00002-of-00013.safetensors",
|
| 1073 |
-
"model.layers.4.mlp.experts.up_proj.biases": "model-00002-of-00013.safetensors",
|
| 1074 |
"model.layers.4.mlp.experts.up_proj.scales": "model-00002-of-00013.safetensors",
|
| 1075 |
"model.layers.4.mlp.experts.up_proj.weight": "model-00002-of-00013.safetensors",
|
| 1076 |
"model.layers.4.mlp.router.bias": "model-00002-of-00013.safetensors",
|
|
@@ -1097,16 +1004,13 @@
|
|
| 1097 |
"model.layers.4.self_attn.v_proj.weight": "model-00002-of-00013.safetensors",
|
| 1098 |
"model.layers.5.input_layernorm.weight": "model-00003-of-00013.safetensors",
|
| 1099 |
"model.layers.5.mlp.experts.down_proj.bias": "model-00003-of-00013.safetensors",
|
| 1100 |
-
"model.layers.5.mlp.experts.down_proj.biases": "model-00003-of-00013.safetensors",
|
| 1101 |
"model.layers.5.mlp.experts.down_proj.scales": "model-00003-of-00013.safetensors",
|
| 1102 |
"model.layers.5.mlp.experts.down_proj.weight": "model-00003-of-00013.safetensors",
|
| 1103 |
"model.layers.5.mlp.experts.gate_proj.bias": "model-00002-of-00013.safetensors",
|
| 1104 |
-
"model.layers.5.mlp.experts.gate_proj.biases": "model-00002-of-00013.safetensors",
|
| 1105 |
"model.layers.5.mlp.experts.gate_proj.scales": "model-00002-of-00013.safetensors",
|
| 1106 |
"model.layers.5.mlp.experts.gate_proj.weight": "model-00002-of-00013.safetensors",
|
| 1107 |
-
"model.layers.5.mlp.experts.up_proj.bias": "model-
|
| 1108 |
-
"model.layers.5.mlp.experts.up_proj.
|
| 1109 |
-
"model.layers.5.mlp.experts.up_proj.scales": "model-00003-of-00013.safetensors",
|
| 1110 |
"model.layers.5.mlp.experts.up_proj.weight": "model-00002-of-00013.safetensors",
|
| 1111 |
"model.layers.5.mlp.router.bias": "model-00003-of-00013.safetensors",
|
| 1112 |
"model.layers.5.mlp.router.biases": "model-00003-of-00013.safetensors",
|
|
@@ -1132,15 +1036,12 @@
|
|
| 1132 |
"model.layers.5.self_attn.v_proj.weight": "model-00002-of-00013.safetensors",
|
| 1133 |
"model.layers.6.input_layernorm.weight": "model-00003-of-00013.safetensors",
|
| 1134 |
"model.layers.6.mlp.experts.down_proj.bias": "model-00003-of-00013.safetensors",
|
| 1135 |
-
"model.layers.6.mlp.experts.down_proj.biases": "model-00003-of-00013.safetensors",
|
| 1136 |
"model.layers.6.mlp.experts.down_proj.scales": "model-00003-of-00013.safetensors",
|
| 1137 |
"model.layers.6.mlp.experts.down_proj.weight": "model-00003-of-00013.safetensors",
|
| 1138 |
"model.layers.6.mlp.experts.gate_proj.bias": "model-00003-of-00013.safetensors",
|
| 1139 |
-
"model.layers.6.mlp.experts.gate_proj.biases": "model-00003-of-00013.safetensors",
|
| 1140 |
"model.layers.6.mlp.experts.gate_proj.scales": "model-00003-of-00013.safetensors",
|
| 1141 |
"model.layers.6.mlp.experts.gate_proj.weight": "model-00003-of-00013.safetensors",
|
| 1142 |
"model.layers.6.mlp.experts.up_proj.bias": "model-00003-of-00013.safetensors",
|
| 1143 |
-
"model.layers.6.mlp.experts.up_proj.biases": "model-00003-of-00013.safetensors",
|
| 1144 |
"model.layers.6.mlp.experts.up_proj.scales": "model-00003-of-00013.safetensors",
|
| 1145 |
"model.layers.6.mlp.experts.up_proj.weight": "model-00003-of-00013.safetensors",
|
| 1146 |
"model.layers.6.mlp.router.bias": "model-00003-of-00013.safetensors",
|
|
@@ -1167,15 +1068,12 @@
|
|
| 1167 |
"model.layers.6.self_attn.v_proj.weight": "model-00003-of-00013.safetensors",
|
| 1168 |
"model.layers.7.input_layernorm.weight": "model-00003-of-00013.safetensors",
|
| 1169 |
"model.layers.7.mlp.experts.down_proj.bias": "model-00003-of-00013.safetensors",
|
| 1170 |
-
"model.layers.7.mlp.experts.down_proj.biases": "model-00003-of-00013.safetensors",
|
| 1171 |
"model.layers.7.mlp.experts.down_proj.scales": "model-00003-of-00013.safetensors",
|
| 1172 |
"model.layers.7.mlp.experts.down_proj.weight": "model-00003-of-00013.safetensors",
|
| 1173 |
"model.layers.7.mlp.experts.gate_proj.bias": "model-00003-of-00013.safetensors",
|
| 1174 |
-
"model.layers.7.mlp.experts.gate_proj.biases": "model-00003-of-00013.safetensors",
|
| 1175 |
"model.layers.7.mlp.experts.gate_proj.scales": "model-00003-of-00013.safetensors",
|
| 1176 |
"model.layers.7.mlp.experts.gate_proj.weight": "model-00003-of-00013.safetensors",
|
| 1177 |
"model.layers.7.mlp.experts.up_proj.bias": "model-00003-of-00013.safetensors",
|
| 1178 |
-
"model.layers.7.mlp.experts.up_proj.biases": "model-00003-of-00013.safetensors",
|
| 1179 |
"model.layers.7.mlp.experts.up_proj.scales": "model-00003-of-00013.safetensors",
|
| 1180 |
"model.layers.7.mlp.experts.up_proj.weight": "model-00003-of-00013.safetensors",
|
| 1181 |
"model.layers.7.mlp.router.bias": "model-00003-of-00013.safetensors",
|
|
@@ -1202,17 +1100,14 @@
|
|
| 1202 |
"model.layers.7.self_attn.v_proj.weight": "model-00003-of-00013.safetensors",
|
| 1203 |
"model.layers.8.input_layernorm.weight": "model-00004-of-00013.safetensors",
|
| 1204 |
"model.layers.8.mlp.experts.down_proj.bias": "model-00004-of-00013.safetensors",
|
| 1205 |
-
"model.layers.8.mlp.experts.down_proj.biases": "model-00004-of-00013.safetensors",
|
| 1206 |
"model.layers.8.mlp.experts.down_proj.scales": "model-00004-of-00013.safetensors",
|
| 1207 |
"model.layers.8.mlp.experts.down_proj.weight": "model-00004-of-00013.safetensors",
|
| 1208 |
"model.layers.8.mlp.experts.gate_proj.bias": "model-00003-of-00013.safetensors",
|
| 1209 |
-
"model.layers.8.mlp.experts.gate_proj.biases": "model-00003-of-00013.safetensors",
|
| 1210 |
"model.layers.8.mlp.experts.gate_proj.scales": "model-00003-of-00013.safetensors",
|
| 1211 |
"model.layers.8.mlp.experts.gate_proj.weight": "model-00003-of-00013.safetensors",
|
| 1212 |
-
"model.layers.8.mlp.experts.up_proj.bias": "model-
|
| 1213 |
-
"model.layers.8.mlp.experts.up_proj.
|
| 1214 |
-
"model.layers.8.mlp.experts.up_proj.
|
| 1215 |
-
"model.layers.8.mlp.experts.up_proj.weight": "model-00004-of-00013.safetensors",
|
| 1216 |
"model.layers.8.mlp.router.bias": "model-00004-of-00013.safetensors",
|
| 1217 |
"model.layers.8.mlp.router.biases": "model-00004-of-00013.safetensors",
|
| 1218 |
"model.layers.8.mlp.router.scales": "model-00004-of-00013.safetensors",
|
|
@@ -1237,15 +1132,12 @@
|
|
| 1237 |
"model.layers.8.self_attn.v_proj.weight": "model-00003-of-00013.safetensors",
|
| 1238 |
"model.layers.9.input_layernorm.weight": "model-00004-of-00013.safetensors",
|
| 1239 |
"model.layers.9.mlp.experts.down_proj.bias": "model-00004-of-00013.safetensors",
|
| 1240 |
-
"model.layers.9.mlp.experts.down_proj.biases": "model-00004-of-00013.safetensors",
|
| 1241 |
"model.layers.9.mlp.experts.down_proj.scales": "model-00004-of-00013.safetensors",
|
| 1242 |
"model.layers.9.mlp.experts.down_proj.weight": "model-00004-of-00013.safetensors",
|
| 1243 |
"model.layers.9.mlp.experts.gate_proj.bias": "model-00004-of-00013.safetensors",
|
| 1244 |
-
"model.layers.9.mlp.experts.gate_proj.biases": "model-00004-of-00013.safetensors",
|
| 1245 |
"model.layers.9.mlp.experts.gate_proj.scales": "model-00004-of-00013.safetensors",
|
| 1246 |
"model.layers.9.mlp.experts.gate_proj.weight": "model-00004-of-00013.safetensors",
|
| 1247 |
"model.layers.9.mlp.experts.up_proj.bias": "model-00004-of-00013.safetensors",
|
| 1248 |
-
"model.layers.9.mlp.experts.up_proj.biases": "model-00004-of-00013.safetensors",
|
| 1249 |
"model.layers.9.mlp.experts.up_proj.scales": "model-00004-of-00013.safetensors",
|
| 1250 |
"model.layers.9.mlp.experts.up_proj.weight": "model-00004-of-00013.safetensors",
|
| 1251 |
"model.layers.9.mlp.router.bias": "model-00004-of-00013.safetensors",
|
|
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
+
"total_size": 62197812864,
|
| 4 |
"total_parameters": 116829154368
|
| 5 |
},
|
| 6 |
"weight_map": {
|
|
|
|
| 12 |
"model.embed_tokens.weight": "model-00001-of-00013.safetensors",
|
| 13 |
"model.layers.0.input_layernorm.weight": "model-00001-of-00013.safetensors",
|
| 14 |
"model.layers.0.mlp.experts.down_proj.bias": "model-00001-of-00013.safetensors",
|
|
|
|
| 15 |
"model.layers.0.mlp.experts.down_proj.scales": "model-00001-of-00013.safetensors",
|
| 16 |
"model.layers.0.mlp.experts.down_proj.weight": "model-00001-of-00013.safetensors",
|
| 17 |
"model.layers.0.mlp.experts.gate_proj.bias": "model-00001-of-00013.safetensors",
|
|
|
|
| 18 |
"model.layers.0.mlp.experts.gate_proj.scales": "model-00001-of-00013.safetensors",
|
| 19 |
"model.layers.0.mlp.experts.gate_proj.weight": "model-00001-of-00013.safetensors",
|
| 20 |
"model.layers.0.mlp.experts.up_proj.bias": "model-00001-of-00013.safetensors",
|
|
|
|
| 21 |
"model.layers.0.mlp.experts.up_proj.scales": "model-00001-of-00013.safetensors",
|
| 22 |
"model.layers.0.mlp.experts.up_proj.weight": "model-00001-of-00013.safetensors",
|
| 23 |
"model.layers.0.mlp.router.bias": "model-00001-of-00013.safetensors",
|
|
|
|
| 44 |
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
|
| 45 |
"model.layers.1.input_layernorm.weight": "model-00001-of-00013.safetensors",
|
| 46 |
"model.layers.1.mlp.experts.down_proj.bias": "model-00001-of-00013.safetensors",
|
|
|
|
| 47 |
"model.layers.1.mlp.experts.down_proj.scales": "model-00001-of-00013.safetensors",
|
| 48 |
"model.layers.1.mlp.experts.down_proj.weight": "model-00001-of-00013.safetensors",
|
| 49 |
"model.layers.1.mlp.experts.gate_proj.bias": "model-00001-of-00013.safetensors",
|
|
|
|
| 50 |
"model.layers.1.mlp.experts.gate_proj.scales": "model-00001-of-00013.safetensors",
|
| 51 |
"model.layers.1.mlp.experts.gate_proj.weight": "model-00001-of-00013.safetensors",
|
| 52 |
"model.layers.1.mlp.experts.up_proj.bias": "model-00001-of-00013.safetensors",
|
|
|
|
| 53 |
"model.layers.1.mlp.experts.up_proj.scales": "model-00001-of-00013.safetensors",
|
| 54 |
"model.layers.1.mlp.experts.up_proj.weight": "model-00001-of-00013.safetensors",
|
| 55 |
"model.layers.1.mlp.router.bias": "model-00001-of-00013.safetensors",
|
|
|
|
| 76 |
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
|
| 77 |
"model.layers.10.input_layernorm.weight": "model-00004-of-00013.safetensors",
|
| 78 |
"model.layers.10.mlp.experts.down_proj.bias": "model-00004-of-00013.safetensors",
|
|
|
|
| 79 |
"model.layers.10.mlp.experts.down_proj.scales": "model-00004-of-00013.safetensors",
|
| 80 |
"model.layers.10.mlp.experts.down_proj.weight": "model-00004-of-00013.safetensors",
|
| 81 |
"model.layers.10.mlp.experts.gate_proj.bias": "model-00004-of-00013.safetensors",
|
|
|
|
| 82 |
"model.layers.10.mlp.experts.gate_proj.scales": "model-00004-of-00013.safetensors",
|
| 83 |
"model.layers.10.mlp.experts.gate_proj.weight": "model-00004-of-00013.safetensors",
|
| 84 |
"model.layers.10.mlp.experts.up_proj.bias": "model-00004-of-00013.safetensors",
|
|
|
|
| 85 |
"model.layers.10.mlp.experts.up_proj.scales": "model-00004-of-00013.safetensors",
|
| 86 |
"model.layers.10.mlp.experts.up_proj.weight": "model-00004-of-00013.safetensors",
|
| 87 |
"model.layers.10.mlp.router.bias": "model-00004-of-00013.safetensors",
|
|
|
|
| 108 |
"model.layers.10.self_attn.v_proj.weight": "model-00004-of-00013.safetensors",
|
| 109 |
"model.layers.11.input_layernorm.weight": "model-00005-of-00013.safetensors",
|
| 110 |
"model.layers.11.mlp.experts.down_proj.bias": "model-00005-of-00013.safetensors",
|
|
|
|
| 111 |
"model.layers.11.mlp.experts.down_proj.scales": "model-00005-of-00013.safetensors",
|
| 112 |
"model.layers.11.mlp.experts.down_proj.weight": "model-00005-of-00013.safetensors",
|
| 113 |
+
"model.layers.11.mlp.experts.gate_proj.bias": "model-00004-of-00013.safetensors",
|
| 114 |
+
"model.layers.11.mlp.experts.gate_proj.scales": "model-00004-of-00013.safetensors",
|
|
|
|
| 115 |
"model.layers.11.mlp.experts.gate_proj.weight": "model-00004-of-00013.safetensors",
|
| 116 |
+
"model.layers.11.mlp.experts.up_proj.bias": "model-00004-of-00013.safetensors",
|
| 117 |
+
"model.layers.11.mlp.experts.up_proj.scales": "model-00004-of-00013.safetensors",
|
| 118 |
+
"model.layers.11.mlp.experts.up_proj.weight": "model-00004-of-00013.safetensors",
|
|
|
|
| 119 |
"model.layers.11.mlp.router.bias": "model-00005-of-00013.safetensors",
|
| 120 |
"model.layers.11.mlp.router.biases": "model-00005-of-00013.safetensors",
|
| 121 |
"model.layers.11.mlp.router.scales": "model-00005-of-00013.safetensors",
|
|
|
|
| 140 |
"model.layers.11.self_attn.v_proj.weight": "model-00004-of-00013.safetensors",
|
| 141 |
"model.layers.12.input_layernorm.weight": "model-00005-of-00013.safetensors",
|
| 142 |
"model.layers.12.mlp.experts.down_proj.bias": "model-00005-of-00013.safetensors",
|
|
|
|
| 143 |
"model.layers.12.mlp.experts.down_proj.scales": "model-00005-of-00013.safetensors",
|
| 144 |
"model.layers.12.mlp.experts.down_proj.weight": "model-00005-of-00013.safetensors",
|
| 145 |
"model.layers.12.mlp.experts.gate_proj.bias": "model-00005-of-00013.safetensors",
|
|
|
|
| 146 |
"model.layers.12.mlp.experts.gate_proj.scales": "model-00005-of-00013.safetensors",
|
| 147 |
"model.layers.12.mlp.experts.gate_proj.weight": "model-00005-of-00013.safetensors",
|
| 148 |
"model.layers.12.mlp.experts.up_proj.bias": "model-00005-of-00013.safetensors",
|
|
|
|
| 149 |
"model.layers.12.mlp.experts.up_proj.scales": "model-00005-of-00013.safetensors",
|
| 150 |
"model.layers.12.mlp.experts.up_proj.weight": "model-00005-of-00013.safetensors",
|
| 151 |
"model.layers.12.mlp.router.bias": "model-00005-of-00013.safetensors",
|
|
|
|
| 172 |
"model.layers.12.self_attn.v_proj.weight": "model-00005-of-00013.safetensors",
|
| 173 |
"model.layers.13.input_layernorm.weight": "model-00005-of-00013.safetensors",
|
| 174 |
"model.layers.13.mlp.experts.down_proj.bias": "model-00005-of-00013.safetensors",
|
|
|
|
| 175 |
"model.layers.13.mlp.experts.down_proj.scales": "model-00005-of-00013.safetensors",
|
| 176 |
"model.layers.13.mlp.experts.down_proj.weight": "model-00005-of-00013.safetensors",
|
| 177 |
"model.layers.13.mlp.experts.gate_proj.bias": "model-00005-of-00013.safetensors",
|
|
|
|
| 178 |
"model.layers.13.mlp.experts.gate_proj.scales": "model-00005-of-00013.safetensors",
|
| 179 |
"model.layers.13.mlp.experts.gate_proj.weight": "model-00005-of-00013.safetensors",
|
| 180 |
"model.layers.13.mlp.experts.up_proj.bias": "model-00005-of-00013.safetensors",
|
|
|
|
| 181 |
"model.layers.13.mlp.experts.up_proj.scales": "model-00005-of-00013.safetensors",
|
| 182 |
"model.layers.13.mlp.experts.up_proj.weight": "model-00005-of-00013.safetensors",
|
| 183 |
"model.layers.13.mlp.router.bias": "model-00005-of-00013.safetensors",
|
|
|
|
| 204 |
"model.layers.13.self_attn.v_proj.weight": "model-00005-of-00013.safetensors",
|
| 205 |
"model.layers.14.input_layernorm.weight": "model-00006-of-00013.safetensors",
|
| 206 |
"model.layers.14.mlp.experts.down_proj.bias": "model-00006-of-00013.safetensors",
|
|
|
|
| 207 |
"model.layers.14.mlp.experts.down_proj.scales": "model-00006-of-00013.safetensors",
|
| 208 |
"model.layers.14.mlp.experts.down_proj.weight": "model-00006-of-00013.safetensors",
|
| 209 |
+
"model.layers.14.mlp.experts.gate_proj.bias": "model-00005-of-00013.safetensors",
|
| 210 |
+
"model.layers.14.mlp.experts.gate_proj.scales": "model-00005-of-00013.safetensors",
|
| 211 |
+
"model.layers.14.mlp.experts.gate_proj.weight": "model-00005-of-00013.safetensors",
|
| 212 |
+
"model.layers.14.mlp.experts.up_proj.bias": "model-00005-of-00013.safetensors",
|
| 213 |
+
"model.layers.14.mlp.experts.up_proj.scales": "model-00005-of-00013.safetensors",
|
| 214 |
+
"model.layers.14.mlp.experts.up_proj.weight": "model-00005-of-00013.safetensors",
|
|
|
|
|
|
|
| 215 |
"model.layers.14.mlp.router.bias": "model-00006-of-00013.safetensors",
|
| 216 |
"model.layers.14.mlp.router.biases": "model-00006-of-00013.safetensors",
|
| 217 |
"model.layers.14.mlp.router.scales": "model-00006-of-00013.safetensors",
|
|
|
|
| 236 |
"model.layers.14.self_attn.v_proj.weight": "model-00005-of-00013.safetensors",
|
| 237 |
"model.layers.15.input_layernorm.weight": "model-00006-of-00013.safetensors",
|
| 238 |
"model.layers.15.mlp.experts.down_proj.bias": "model-00006-of-00013.safetensors",
|
|
|
|
| 239 |
"model.layers.15.mlp.experts.down_proj.scales": "model-00006-of-00013.safetensors",
|
| 240 |
"model.layers.15.mlp.experts.down_proj.weight": "model-00006-of-00013.safetensors",
|
| 241 |
"model.layers.15.mlp.experts.gate_proj.bias": "model-00006-of-00013.safetensors",
|
|
|
|
| 242 |
"model.layers.15.mlp.experts.gate_proj.scales": "model-00006-of-00013.safetensors",
|
| 243 |
"model.layers.15.mlp.experts.gate_proj.weight": "model-00006-of-00013.safetensors",
|
| 244 |
"model.layers.15.mlp.experts.up_proj.bias": "model-00006-of-00013.safetensors",
|
|
|
|
| 245 |
"model.layers.15.mlp.experts.up_proj.scales": "model-00006-of-00013.safetensors",
|
| 246 |
"model.layers.15.mlp.experts.up_proj.weight": "model-00006-of-00013.safetensors",
|
| 247 |
"model.layers.15.mlp.router.bias": "model-00006-of-00013.safetensors",
|
|
|
|
| 266 |
"model.layers.15.self_attn.v_proj.biases": "model-00006-of-00013.safetensors",
|
| 267 |
"model.layers.15.self_attn.v_proj.scales": "model-00006-of-00013.safetensors",
|
| 268 |
"model.layers.15.self_attn.v_proj.weight": "model-00006-of-00013.safetensors",
|
| 269 |
+
"model.layers.16.input_layernorm.weight": "model-00006-of-00013.safetensors",
|
| 270 |
+
"model.layers.16.mlp.experts.down_proj.bias": "model-00006-of-00013.safetensors",
|
| 271 |
+
"model.layers.16.mlp.experts.down_proj.scales": "model-00006-of-00013.safetensors",
|
|
|
|
| 272 |
"model.layers.16.mlp.experts.down_proj.weight": "model-00006-of-00013.safetensors",
|
| 273 |
"model.layers.16.mlp.experts.gate_proj.bias": "model-00006-of-00013.safetensors",
|
|
|
|
| 274 |
"model.layers.16.mlp.experts.gate_proj.scales": "model-00006-of-00013.safetensors",
|
| 275 |
"model.layers.16.mlp.experts.gate_proj.weight": "model-00006-of-00013.safetensors",
|
| 276 |
"model.layers.16.mlp.experts.up_proj.bias": "model-00006-of-00013.safetensors",
|
|
|
|
| 277 |
"model.layers.16.mlp.experts.up_proj.scales": "model-00006-of-00013.safetensors",
|
| 278 |
"model.layers.16.mlp.experts.up_proj.weight": "model-00006-of-00013.safetensors",
|
| 279 |
+
"model.layers.16.mlp.router.bias": "model-00006-of-00013.safetensors",
|
| 280 |
+
"model.layers.16.mlp.router.biases": "model-00006-of-00013.safetensors",
|
| 281 |
+
"model.layers.16.mlp.router.scales": "model-00006-of-00013.safetensors",
|
| 282 |
+
"model.layers.16.mlp.router.weight": "model-00006-of-00013.safetensors",
|
| 283 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00006-of-00013.safetensors",
|
| 284 |
"model.layers.16.self_attn.k_proj.bias": "model-00006-of-00013.safetensors",
|
| 285 |
"model.layers.16.self_attn.k_proj.biases": "model-00006-of-00013.safetensors",
|
| 286 |
"model.layers.16.self_attn.k_proj.scales": "model-00006-of-00013.safetensors",
|
|
|
|
| 300 |
"model.layers.16.self_attn.v_proj.weight": "model-00006-of-00013.safetensors",
|
| 301 |
"model.layers.17.input_layernorm.weight": "model-00007-of-00013.safetensors",
|
| 302 |
"model.layers.17.mlp.experts.down_proj.bias": "model-00007-of-00013.safetensors",
|
|
|
|
| 303 |
"model.layers.17.mlp.experts.down_proj.scales": "model-00007-of-00013.safetensors",
|
| 304 |
"model.layers.17.mlp.experts.down_proj.weight": "model-00007-of-00013.safetensors",
|
| 305 |
+
"model.layers.17.mlp.experts.gate_proj.bias": "model-00006-of-00013.safetensors",
|
| 306 |
+
"model.layers.17.mlp.experts.gate_proj.scales": "model-00006-of-00013.safetensors",
|
| 307 |
+
"model.layers.17.mlp.experts.gate_proj.weight": "model-00006-of-00013.safetensors",
|
| 308 |
+
"model.layers.17.mlp.experts.up_proj.bias": "model-00006-of-00013.safetensors",
|
| 309 |
+
"model.layers.17.mlp.experts.up_proj.scales": "model-00006-of-00013.safetensors",
|
| 310 |
+
"model.layers.17.mlp.experts.up_proj.weight": "model-00006-of-00013.safetensors",
|
|
|
|
|
|
|
| 311 |
"model.layers.17.mlp.router.bias": "model-00007-of-00013.safetensors",
|
| 312 |
"model.layers.17.mlp.router.biases": "model-00007-of-00013.safetensors",
|
| 313 |
"model.layers.17.mlp.router.scales": "model-00007-of-00013.safetensors",
|
| 314 |
"model.layers.17.mlp.router.weight": "model-00007-of-00013.safetensors",
|
| 315 |
"model.layers.17.post_attention_layernorm.weight": "model-00007-of-00013.safetensors",
|
| 316 |
+
"model.layers.17.self_attn.k_proj.bias": "model-00006-of-00013.safetensors",
|
| 317 |
+
"model.layers.17.self_attn.k_proj.biases": "model-00006-of-00013.safetensors",
|
| 318 |
+
"model.layers.17.self_attn.k_proj.scales": "model-00006-of-00013.safetensors",
|
| 319 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00006-of-00013.safetensors",
|
| 320 |
+
"model.layers.17.self_attn.o_proj.bias": "model-00006-of-00013.safetensors",
|
| 321 |
+
"model.layers.17.self_attn.o_proj.biases": "model-00006-of-00013.safetensors",
|
| 322 |
+
"model.layers.17.self_attn.o_proj.scales": "model-00006-of-00013.safetensors",
|
| 323 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00006-of-00013.safetensors",
|
| 324 |
+
"model.layers.17.self_attn.q_proj.bias": "model-00006-of-00013.safetensors",
|
| 325 |
+
"model.layers.17.self_attn.q_proj.biases": "model-00006-of-00013.safetensors",
|
| 326 |
+
"model.layers.17.self_attn.q_proj.scales": "model-00006-of-00013.safetensors",
|
| 327 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00006-of-00013.safetensors",
|
| 328 |
+
"model.layers.17.self_attn.sinks": "model-00006-of-00013.safetensors",
|
| 329 |
+
"model.layers.17.self_attn.v_proj.bias": "model-00006-of-00013.safetensors",
|
| 330 |
+
"model.layers.17.self_attn.v_proj.biases": "model-00006-of-00013.safetensors",
|
| 331 |
+
"model.layers.17.self_attn.v_proj.scales": "model-00006-of-00013.safetensors",
|
| 332 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00006-of-00013.safetensors",
|
| 333 |
"model.layers.18.input_layernorm.weight": "model-00007-of-00013.safetensors",
|
| 334 |
"model.layers.18.mlp.experts.down_proj.bias": "model-00007-of-00013.safetensors",
|
|
|
|
| 335 |
"model.layers.18.mlp.experts.down_proj.scales": "model-00007-of-00013.safetensors",
|
| 336 |
"model.layers.18.mlp.experts.down_proj.weight": "model-00007-of-00013.safetensors",
|
| 337 |
"model.layers.18.mlp.experts.gate_proj.bias": "model-00007-of-00013.safetensors",
|
|
|
|
| 338 |
"model.layers.18.mlp.experts.gate_proj.scales": "model-00007-of-00013.safetensors",
|
| 339 |
"model.layers.18.mlp.experts.gate_proj.weight": "model-00007-of-00013.safetensors",
|
| 340 |
"model.layers.18.mlp.experts.up_proj.bias": "model-00007-of-00013.safetensors",
|
|
|
|
| 341 |
"model.layers.18.mlp.experts.up_proj.scales": "model-00007-of-00013.safetensors",
|
| 342 |
"model.layers.18.mlp.experts.up_proj.weight": "model-00007-of-00013.safetensors",
|
| 343 |
"model.layers.18.mlp.router.bias": "model-00007-of-00013.safetensors",
|
|
|
|
| 362 |
"model.layers.18.self_attn.v_proj.biases": "model-00007-of-00013.safetensors",
|
| 363 |
"model.layers.18.self_attn.v_proj.scales": "model-00007-of-00013.safetensors",
|
| 364 |
"model.layers.18.self_attn.v_proj.weight": "model-00007-of-00013.safetensors",
|
| 365 |
+
"model.layers.19.input_layernorm.weight": "model-00007-of-00013.safetensors",
|
| 366 |
+
"model.layers.19.mlp.experts.down_proj.bias": "model-00007-of-00013.safetensors",
|
| 367 |
+
"model.layers.19.mlp.experts.down_proj.scales": "model-00007-of-00013.safetensors",
|
| 368 |
+
"model.layers.19.mlp.experts.down_proj.weight": "model-00007-of-00013.safetensors",
|
|
|
|
| 369 |
"model.layers.19.mlp.experts.gate_proj.bias": "model-00007-of-00013.safetensors",
|
|
|
|
| 370 |
"model.layers.19.mlp.experts.gate_proj.scales": "model-00007-of-00013.safetensors",
|
| 371 |
"model.layers.19.mlp.experts.gate_proj.weight": "model-00007-of-00013.safetensors",
|
| 372 |
"model.layers.19.mlp.experts.up_proj.bias": "model-00007-of-00013.safetensors",
|
|
|
|
| 373 |
"model.layers.19.mlp.experts.up_proj.scales": "model-00007-of-00013.safetensors",
|
| 374 |
"model.layers.19.mlp.experts.up_proj.weight": "model-00007-of-00013.safetensors",
|
| 375 |
+
"model.layers.19.mlp.router.bias": "model-00007-of-00013.safetensors",
|
| 376 |
+
"model.layers.19.mlp.router.biases": "model-00007-of-00013.safetensors",
|
| 377 |
+
"model.layers.19.mlp.router.scales": "model-00007-of-00013.safetensors",
|
| 378 |
+
"model.layers.19.mlp.router.weight": "model-00007-of-00013.safetensors",
|
| 379 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00007-of-00013.safetensors",
|
| 380 |
"model.layers.19.self_attn.k_proj.bias": "model-00007-of-00013.safetensors",
|
| 381 |
"model.layers.19.self_attn.k_proj.biases": "model-00007-of-00013.safetensors",
|
| 382 |
"model.layers.19.self_attn.k_proj.scales": "model-00007-of-00013.safetensors",
|
|
|
|
| 396 |
"model.layers.19.self_attn.v_proj.weight": "model-00007-of-00013.safetensors",
|
| 397 |
"model.layers.2.input_layernorm.weight": "model-00002-of-00013.safetensors",
|
| 398 |
"model.layers.2.mlp.experts.down_proj.bias": "model-00002-of-00013.safetensors",
|
|
|
|
| 399 |
"model.layers.2.mlp.experts.down_proj.scales": "model-00002-of-00013.safetensors",
|
| 400 |
"model.layers.2.mlp.experts.down_proj.weight": "model-00002-of-00013.safetensors",
|
| 401 |
"model.layers.2.mlp.experts.gate_proj.bias": "model-00001-of-00013.safetensors",
|
|
|
|
| 402 |
"model.layers.2.mlp.experts.gate_proj.scales": "model-00001-of-00013.safetensors",
|
| 403 |
"model.layers.2.mlp.experts.gate_proj.weight": "model-00001-of-00013.safetensors",
|
| 404 |
"model.layers.2.mlp.experts.up_proj.bias": "model-00001-of-00013.safetensors",
|
|
|
|
| 405 |
"model.layers.2.mlp.experts.up_proj.scales": "model-00001-of-00013.safetensors",
|
| 406 |
"model.layers.2.mlp.experts.up_proj.weight": "model-00001-of-00013.safetensors",
|
| 407 |
"model.layers.2.mlp.router.bias": "model-00002-of-00013.safetensors",
|
|
|
|
| 428 |
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
|
| 429 |
"model.layers.20.input_layernorm.weight": "model-00008-of-00013.safetensors",
|
| 430 |
"model.layers.20.mlp.experts.down_proj.bias": "model-00008-of-00013.safetensors",
|
|
|
|
| 431 |
"model.layers.20.mlp.experts.down_proj.scales": "model-00008-of-00013.safetensors",
|
| 432 |
"model.layers.20.mlp.experts.down_proj.weight": "model-00008-of-00013.safetensors",
|
| 433 |
+
"model.layers.20.mlp.experts.gate_proj.bias": "model-00007-of-00013.safetensors",
|
| 434 |
+
"model.layers.20.mlp.experts.gate_proj.scales": "model-00007-of-00013.safetensors",
|
| 435 |
+
"model.layers.20.mlp.experts.gate_proj.weight": "model-00007-of-00013.safetensors",
|
| 436 |
+
"model.layers.20.mlp.experts.up_proj.bias": "model-00007-of-00013.safetensors",
|
| 437 |
+
"model.layers.20.mlp.experts.up_proj.scales": "model-00007-of-00013.safetensors",
|
| 438 |
+
"model.layers.20.mlp.experts.up_proj.weight": "model-00007-of-00013.safetensors",
|
|
|
|
|
|
|
| 439 |
"model.layers.20.mlp.router.bias": "model-00008-of-00013.safetensors",
|
| 440 |
"model.layers.20.mlp.router.biases": "model-00008-of-00013.safetensors",
|
| 441 |
"model.layers.20.mlp.router.scales": "model-00008-of-00013.safetensors",
|
| 442 |
"model.layers.20.mlp.router.weight": "model-00008-of-00013.safetensors",
|
| 443 |
"model.layers.20.post_attention_layernorm.weight": "model-00008-of-00013.safetensors",
|
| 444 |
+
"model.layers.20.self_attn.k_proj.bias": "model-00007-of-00013.safetensors",
|
| 445 |
+
"model.layers.20.self_attn.k_proj.biases": "model-00007-of-00013.safetensors",
|
| 446 |
+
"model.layers.20.self_attn.k_proj.scales": "model-00007-of-00013.safetensors",
|
| 447 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00007-of-00013.safetensors",
|
| 448 |
+
"model.layers.20.self_attn.o_proj.bias": "model-00007-of-00013.safetensors",
|
| 449 |
+
"model.layers.20.self_attn.o_proj.biases": "model-00007-of-00013.safetensors",
|
| 450 |
+
"model.layers.20.self_attn.o_proj.scales": "model-00007-of-00013.safetensors",
|
| 451 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00007-of-00013.safetensors",
|
| 452 |
+
"model.layers.20.self_attn.q_proj.bias": "model-00007-of-00013.safetensors",
|
| 453 |
+
"model.layers.20.self_attn.q_proj.biases": "model-00007-of-00013.safetensors",
|
| 454 |
+
"model.layers.20.self_attn.q_proj.scales": "model-00007-of-00013.safetensors",
|
| 455 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00007-of-00013.safetensors",
|
| 456 |
+
"model.layers.20.self_attn.sinks": "model-00007-of-00013.safetensors",
|
| 457 |
+
"model.layers.20.self_attn.v_proj.bias": "model-00007-of-00013.safetensors",
|
| 458 |
+
"model.layers.20.self_attn.v_proj.biases": "model-00007-of-00013.safetensors",
|
| 459 |
+
"model.layers.20.self_attn.v_proj.scales": "model-00007-of-00013.safetensors",
|
| 460 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00007-of-00013.safetensors",
|
| 461 |
"model.layers.21.input_layernorm.weight": "model-00008-of-00013.safetensors",
|
| 462 |
"model.layers.21.mlp.experts.down_proj.bias": "model-00008-of-00013.safetensors",
|
|
|
|
| 463 |
"model.layers.21.mlp.experts.down_proj.scales": "model-00008-of-00013.safetensors",
|
| 464 |
"model.layers.21.mlp.experts.down_proj.weight": "model-00008-of-00013.safetensors",
|
| 465 |
"model.layers.21.mlp.experts.gate_proj.bias": "model-00008-of-00013.safetensors",
|
|
|
|
| 466 |
"model.layers.21.mlp.experts.gate_proj.scales": "model-00008-of-00013.safetensors",
|
| 467 |
"model.layers.21.mlp.experts.gate_proj.weight": "model-00008-of-00013.safetensors",
|
| 468 |
"model.layers.21.mlp.experts.up_proj.bias": "model-00008-of-00013.safetensors",
|
|
|
|
| 469 |
"model.layers.21.mlp.experts.up_proj.scales": "model-00008-of-00013.safetensors",
|
| 470 |
"model.layers.21.mlp.experts.up_proj.weight": "model-00008-of-00013.safetensors",
|
| 471 |
"model.layers.21.mlp.router.bias": "model-00008-of-00013.safetensors",
|
|
|
|
| 490 |
"model.layers.21.self_attn.v_proj.biases": "model-00008-of-00013.safetensors",
|
| 491 |
"model.layers.21.self_attn.v_proj.scales": "model-00008-of-00013.safetensors",
|
| 492 |
"model.layers.21.self_attn.v_proj.weight": "model-00008-of-00013.safetensors",
|
| 493 |
+
"model.layers.22.input_layernorm.weight": "model-00008-of-00013.safetensors",
|
| 494 |
+
"model.layers.22.mlp.experts.down_proj.bias": "model-00008-of-00013.safetensors",
|
| 495 |
+
"model.layers.22.mlp.experts.down_proj.scales": "model-00008-of-00013.safetensors",
|
| 496 |
+
"model.layers.22.mlp.experts.down_proj.weight": "model-00008-of-00013.safetensors",
|
|
|
|
| 497 |
"model.layers.22.mlp.experts.gate_proj.bias": "model-00008-of-00013.safetensors",
|
|
|
|
| 498 |
"model.layers.22.mlp.experts.gate_proj.scales": "model-00008-of-00013.safetensors",
|
| 499 |
"model.layers.22.mlp.experts.gate_proj.weight": "model-00008-of-00013.safetensors",
|
| 500 |
+
"model.layers.22.mlp.experts.up_proj.bias": "model-00008-of-00013.safetensors",
|
| 501 |
+
"model.layers.22.mlp.experts.up_proj.scales": "model-00008-of-00013.safetensors",
|
|
|
|
| 502 |
"model.layers.22.mlp.experts.up_proj.weight": "model-00008-of-00013.safetensors",
|
| 503 |
+
"model.layers.22.mlp.router.bias": "model-00008-of-00013.safetensors",
|
| 504 |
+
"model.layers.22.mlp.router.biases": "model-00008-of-00013.safetensors",
|
| 505 |
+
"model.layers.22.mlp.router.scales": "model-00008-of-00013.safetensors",
|
| 506 |
+
"model.layers.22.mlp.router.weight": "model-00008-of-00013.safetensors",
|
| 507 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00008-of-00013.safetensors",
|
| 508 |
"model.layers.22.self_attn.k_proj.bias": "model-00008-of-00013.safetensors",
|
| 509 |
"model.layers.22.self_attn.k_proj.biases": "model-00008-of-00013.safetensors",
|
| 510 |
"model.layers.22.self_attn.k_proj.scales": "model-00008-of-00013.safetensors",
|
|
|
|
| 524 |
"model.layers.22.self_attn.v_proj.weight": "model-00008-of-00013.safetensors",
|
| 525 |
"model.layers.23.input_layernorm.weight": "model-00009-of-00013.safetensors",
|
| 526 |
"model.layers.23.mlp.experts.down_proj.bias": "model-00009-of-00013.safetensors",
|
|
|
|
| 527 |
"model.layers.23.mlp.experts.down_proj.scales": "model-00009-of-00013.safetensors",
|
| 528 |
"model.layers.23.mlp.experts.down_proj.weight": "model-00009-of-00013.safetensors",
|
| 529 |
+
"model.layers.23.mlp.experts.gate_proj.bias": "model-00008-of-00013.safetensors",
|
| 530 |
+
"model.layers.23.mlp.experts.gate_proj.scales": "model-00008-of-00013.safetensors",
|
| 531 |
+
"model.layers.23.mlp.experts.gate_proj.weight": "model-00008-of-00013.safetensors",
|
| 532 |
+
"model.layers.23.mlp.experts.up_proj.bias": "model-00008-of-00013.safetensors",
|
| 533 |
+
"model.layers.23.mlp.experts.up_proj.scales": "model-00008-of-00013.safetensors",
|
| 534 |
+
"model.layers.23.mlp.experts.up_proj.weight": "model-00008-of-00013.safetensors",
|
|
|
|
|
|
|
| 535 |
"model.layers.23.mlp.router.bias": "model-00009-of-00013.safetensors",
|
| 536 |
"model.layers.23.mlp.router.biases": "model-00009-of-00013.safetensors",
|
| 537 |
"model.layers.23.mlp.router.scales": "model-00009-of-00013.safetensors",
|
| 538 |
"model.layers.23.mlp.router.weight": "model-00009-of-00013.safetensors",
|
| 539 |
"model.layers.23.post_attention_layernorm.weight": "model-00009-of-00013.safetensors",
|
| 540 |
+
"model.layers.23.self_attn.k_proj.bias": "model-00008-of-00013.safetensors",
|
| 541 |
+
"model.layers.23.self_attn.k_proj.biases": "model-00008-of-00013.safetensors",
|
| 542 |
+
"model.layers.23.self_attn.k_proj.scales": "model-00008-of-00013.safetensors",
|
| 543 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00008-of-00013.safetensors",
|
| 544 |
+
"model.layers.23.self_attn.o_proj.bias": "model-00008-of-00013.safetensors",
|
| 545 |
+
"model.layers.23.self_attn.o_proj.biases": "model-00008-of-00013.safetensors",
|
| 546 |
+
"model.layers.23.self_attn.o_proj.scales": "model-00008-of-00013.safetensors",
|
| 547 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00008-of-00013.safetensors",
|
| 548 |
+
"model.layers.23.self_attn.q_proj.bias": "model-00008-of-00013.safetensors",
|
| 549 |
+
"model.layers.23.self_attn.q_proj.biases": "model-00008-of-00013.safetensors",
|
| 550 |
+
"model.layers.23.self_attn.q_proj.scales": "model-00008-of-00013.safetensors",
|
| 551 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00008-of-00013.safetensors",
|
| 552 |
+
"model.layers.23.self_attn.sinks": "model-00008-of-00013.safetensors",
|
| 553 |
+
"model.layers.23.self_attn.v_proj.bias": "model-00008-of-00013.safetensors",
|
| 554 |
+
"model.layers.23.self_attn.v_proj.biases": "model-00008-of-00013.safetensors",
|
| 555 |
+
"model.layers.23.self_attn.v_proj.scales": "model-00008-of-00013.safetensors",
|
| 556 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00008-of-00013.safetensors",
|
| 557 |
"model.layers.24.input_layernorm.weight": "model-00009-of-00013.safetensors",
|
| 558 |
"model.layers.24.mlp.experts.down_proj.bias": "model-00009-of-00013.safetensors",
|
|
|
|
| 559 |
"model.layers.24.mlp.experts.down_proj.scales": "model-00009-of-00013.safetensors",
|
| 560 |
"model.layers.24.mlp.experts.down_proj.weight": "model-00009-of-00013.safetensors",
|
| 561 |
"model.layers.24.mlp.experts.gate_proj.bias": "model-00009-of-00013.safetensors",
|
|
|
|
| 562 |
"model.layers.24.mlp.experts.gate_proj.scales": "model-00009-of-00013.safetensors",
|
| 563 |
"model.layers.24.mlp.experts.gate_proj.weight": "model-00009-of-00013.safetensors",
|
| 564 |
"model.layers.24.mlp.experts.up_proj.bias": "model-00009-of-00013.safetensors",
|
|
|
|
| 565 |
"model.layers.24.mlp.experts.up_proj.scales": "model-00009-of-00013.safetensors",
|
| 566 |
"model.layers.24.mlp.experts.up_proj.weight": "model-00009-of-00013.safetensors",
|
| 567 |
"model.layers.24.mlp.router.bias": "model-00009-of-00013.safetensors",
|
|
|
|
| 586 |
"model.layers.24.self_attn.v_proj.biases": "model-00009-of-00013.safetensors",
|
| 587 |
"model.layers.24.self_attn.v_proj.scales": "model-00009-of-00013.safetensors",
|
| 588 |
"model.layers.24.self_attn.v_proj.weight": "model-00009-of-00013.safetensors",
|
| 589 |
+
"model.layers.25.input_layernorm.weight": "model-00009-of-00013.safetensors",
|
| 590 |
+
"model.layers.25.mlp.experts.down_proj.bias": "model-00009-of-00013.safetensors",
|
| 591 |
+
"model.layers.25.mlp.experts.down_proj.scales": "model-00009-of-00013.safetensors",
|
| 592 |
+
"model.layers.25.mlp.experts.down_proj.weight": "model-00009-of-00013.safetensors",
|
|
|
|
| 593 |
"model.layers.25.mlp.experts.gate_proj.bias": "model-00009-of-00013.safetensors",
|
|
|
|
| 594 |
"model.layers.25.mlp.experts.gate_proj.scales": "model-00009-of-00013.safetensors",
|
| 595 |
"model.layers.25.mlp.experts.gate_proj.weight": "model-00009-of-00013.safetensors",
|
| 596 |
+
"model.layers.25.mlp.experts.up_proj.bias": "model-00009-of-00013.safetensors",
|
| 597 |
+
"model.layers.25.mlp.experts.up_proj.scales": "model-00009-of-00013.safetensors",
|
| 598 |
+
"model.layers.25.mlp.experts.up_proj.weight": "model-00009-of-00013.safetensors",
|
| 599 |
+
"model.layers.25.mlp.router.bias": "model-00009-of-00013.safetensors",
|
| 600 |
+
"model.layers.25.mlp.router.biases": "model-00009-of-00013.safetensors",
|
| 601 |
+
"model.layers.25.mlp.router.scales": "model-00009-of-00013.safetensors",
|
| 602 |
+
"model.layers.25.mlp.router.weight": "model-00009-of-00013.safetensors",
|
| 603 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00009-of-00013.safetensors",
|
|
|
|
| 604 |
"model.layers.25.self_attn.k_proj.bias": "model-00009-of-00013.safetensors",
|
| 605 |
"model.layers.25.self_attn.k_proj.biases": "model-00009-of-00013.safetensors",
|
| 606 |
"model.layers.25.self_attn.k_proj.scales": "model-00009-of-00013.safetensors",
|
|
|
|
| 620 |
"model.layers.25.self_attn.v_proj.weight": "model-00009-of-00013.safetensors",
|
| 621 |
"model.layers.26.input_layernorm.weight": "model-00010-of-00013.safetensors",
|
| 622 |
"model.layers.26.mlp.experts.down_proj.bias": "model-00010-of-00013.safetensors",
|
|
|
|
| 623 |
"model.layers.26.mlp.experts.down_proj.scales": "model-00010-of-00013.safetensors",
|
| 624 |
"model.layers.26.mlp.experts.down_proj.weight": "model-00010-of-00013.safetensors",
|
| 625 |
+
"model.layers.26.mlp.experts.gate_proj.bias": "model-00009-of-00013.safetensors",
|
| 626 |
+
"model.layers.26.mlp.experts.gate_proj.scales": "model-00009-of-00013.safetensors",
|
| 627 |
+
"model.layers.26.mlp.experts.gate_proj.weight": "model-00009-of-00013.safetensors",
|
| 628 |
+
"model.layers.26.mlp.experts.up_proj.bias": "model-00009-of-00013.safetensors",
|
| 629 |
+
"model.layers.26.mlp.experts.up_proj.scales": "model-00009-of-00013.safetensors",
|
| 630 |
+
"model.layers.26.mlp.experts.up_proj.weight": "model-00009-of-00013.safetensors",
|
|
|
|
|
|
|
| 631 |
"model.layers.26.mlp.router.bias": "model-00010-of-00013.safetensors",
|
| 632 |
"model.layers.26.mlp.router.biases": "model-00010-of-00013.safetensors",
|
| 633 |
"model.layers.26.mlp.router.scales": "model-00010-of-00013.safetensors",
|
| 634 |
"model.layers.26.mlp.router.weight": "model-00010-of-00013.safetensors",
|
| 635 |
"model.layers.26.post_attention_layernorm.weight": "model-00010-of-00013.safetensors",
|
| 636 |
+
"model.layers.26.self_attn.k_proj.bias": "model-00009-of-00013.safetensors",
|
| 637 |
+
"model.layers.26.self_attn.k_proj.biases": "model-00009-of-00013.safetensors",
|
| 638 |
+
"model.layers.26.self_attn.k_proj.scales": "model-00009-of-00013.safetensors",
|
| 639 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00009-of-00013.safetensors",
|
| 640 |
+
"model.layers.26.self_attn.o_proj.bias": "model-00009-of-00013.safetensors",
|
| 641 |
+
"model.layers.26.self_attn.o_proj.biases": "model-00009-of-00013.safetensors",
|
| 642 |
+
"model.layers.26.self_attn.o_proj.scales": "model-00009-of-00013.safetensors",
|
| 643 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00009-of-00013.safetensors",
|
| 644 |
+
"model.layers.26.self_attn.q_proj.bias": "model-00009-of-00013.safetensors",
|
| 645 |
+
"model.layers.26.self_attn.q_proj.biases": "model-00009-of-00013.safetensors",
|
| 646 |
+
"model.layers.26.self_attn.q_proj.scales": "model-00009-of-00013.safetensors",
|
| 647 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00009-of-00013.safetensors",
|
| 648 |
+
"model.layers.26.self_attn.sinks": "model-00009-of-00013.safetensors",
|
| 649 |
+
"model.layers.26.self_attn.v_proj.bias": "model-00009-of-00013.safetensors",
|
| 650 |
+
"model.layers.26.self_attn.v_proj.biases": "model-00009-of-00013.safetensors",
|
| 651 |
+
"model.layers.26.self_attn.v_proj.scales": "model-00009-of-00013.safetensors",
|
| 652 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00009-of-00013.safetensors",
|
| 653 |
"model.layers.27.input_layernorm.weight": "model-00010-of-00013.safetensors",
|
| 654 |
"model.layers.27.mlp.experts.down_proj.bias": "model-00010-of-00013.safetensors",
|
|
|
|
| 655 |
"model.layers.27.mlp.experts.down_proj.scales": "model-00010-of-00013.safetensors",
|
| 656 |
"model.layers.27.mlp.experts.down_proj.weight": "model-00010-of-00013.safetensors",
|
| 657 |
"model.layers.27.mlp.experts.gate_proj.bias": "model-00010-of-00013.safetensors",
|
|
|
|
| 658 |
"model.layers.27.mlp.experts.gate_proj.scales": "model-00010-of-00013.safetensors",
|
| 659 |
"model.layers.27.mlp.experts.gate_proj.weight": "model-00010-of-00013.safetensors",
|
| 660 |
"model.layers.27.mlp.experts.up_proj.bias": "model-00010-of-00013.safetensors",
|
|
|
|
| 661 |
"model.layers.27.mlp.experts.up_proj.scales": "model-00010-of-00013.safetensors",
|
| 662 |
"model.layers.27.mlp.experts.up_proj.weight": "model-00010-of-00013.safetensors",
|
| 663 |
"model.layers.27.mlp.router.bias": "model-00010-of-00013.safetensors",
|
|
|
|
| 682 |
"model.layers.27.self_attn.v_proj.biases": "model-00010-of-00013.safetensors",
|
| 683 |
"model.layers.27.self_attn.v_proj.scales": "model-00010-of-00013.safetensors",
|
| 684 |
"model.layers.27.self_attn.v_proj.weight": "model-00010-of-00013.safetensors",
|
| 685 |
+
"model.layers.28.input_layernorm.weight": "model-00010-of-00013.safetensors",
|
| 686 |
+
"model.layers.28.mlp.experts.down_proj.bias": "model-00010-of-00013.safetensors",
|
| 687 |
+
"model.layers.28.mlp.experts.down_proj.scales": "model-00010-of-00013.safetensors",
|
| 688 |
+
"model.layers.28.mlp.experts.down_proj.weight": "model-00010-of-00013.safetensors",
|
| 689 |
+
"model.layers.28.mlp.experts.gate_proj.bias": "model-00010-of-00013.safetensors",
|
| 690 |
+
"model.layers.28.mlp.experts.gate_proj.scales": "model-00010-of-00013.safetensors",
|
|
|
|
|
|
|
| 691 |
"model.layers.28.mlp.experts.gate_proj.weight": "model-00010-of-00013.safetensors",
|
| 692 |
+
"model.layers.28.mlp.experts.up_proj.bias": "model-00010-of-00013.safetensors",
|
| 693 |
+
"model.layers.28.mlp.experts.up_proj.scales": "model-00010-of-00013.safetensors",
|
| 694 |
+
"model.layers.28.mlp.experts.up_proj.weight": "model-00010-of-00013.safetensors",
|
| 695 |
+
"model.layers.28.mlp.router.bias": "model-00010-of-00013.safetensors",
|
| 696 |
+
"model.layers.28.mlp.router.biases": "model-00010-of-00013.safetensors",
|
| 697 |
+
"model.layers.28.mlp.router.scales": "model-00010-of-00013.safetensors",
|
| 698 |
+
"model.layers.28.mlp.router.weight": "model-00010-of-00013.safetensors",
|
| 699 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00010-of-00013.safetensors",
|
|
|
|
| 700 |
"model.layers.28.self_attn.k_proj.bias": "model-00010-of-00013.safetensors",
|
| 701 |
"model.layers.28.self_attn.k_proj.biases": "model-00010-of-00013.safetensors",
|
| 702 |
"model.layers.28.self_attn.k_proj.scales": "model-00010-of-00013.safetensors",
|
|
|
|
| 716 |
"model.layers.28.self_attn.v_proj.weight": "model-00010-of-00013.safetensors",
|
| 717 |
"model.layers.29.input_layernorm.weight": "model-00011-of-00013.safetensors",
|
| 718 |
"model.layers.29.mlp.experts.down_proj.bias": "model-00011-of-00013.safetensors",
|
|
|
|
| 719 |
"model.layers.29.mlp.experts.down_proj.scales": "model-00011-of-00013.safetensors",
|
| 720 |
"model.layers.29.mlp.experts.down_proj.weight": "model-00011-of-00013.safetensors",
|
| 721 |
+
"model.layers.29.mlp.experts.gate_proj.bias": "model-00010-of-00013.safetensors",
|
| 722 |
+
"model.layers.29.mlp.experts.gate_proj.scales": "model-00010-of-00013.safetensors",
|
| 723 |
+
"model.layers.29.mlp.experts.gate_proj.weight": "model-00010-of-00013.safetensors",
|
| 724 |
+
"model.layers.29.mlp.experts.up_proj.bias": "model-00010-of-00013.safetensors",
|
| 725 |
+
"model.layers.29.mlp.experts.up_proj.scales": "model-00010-of-00013.safetensors",
|
| 726 |
+
"model.layers.29.mlp.experts.up_proj.weight": "model-00010-of-00013.safetensors",
|
|
|
|
|
|
|
| 727 |
"model.layers.29.mlp.router.bias": "model-00011-of-00013.safetensors",
|
| 728 |
"model.layers.29.mlp.router.biases": "model-00011-of-00013.safetensors",
|
| 729 |
"model.layers.29.mlp.router.scales": "model-00011-of-00013.safetensors",
|
| 730 |
"model.layers.29.mlp.router.weight": "model-00011-of-00013.safetensors",
|
| 731 |
"model.layers.29.post_attention_layernorm.weight": "model-00011-of-00013.safetensors",
|
| 732 |
+
"model.layers.29.self_attn.k_proj.bias": "model-00010-of-00013.safetensors",
|
| 733 |
+
"model.layers.29.self_attn.k_proj.biases": "model-00010-of-00013.safetensors",
|
| 734 |
+
"model.layers.29.self_attn.k_proj.scales": "model-00010-of-00013.safetensors",
|
| 735 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00010-of-00013.safetensors",
|
| 736 |
+
"model.layers.29.self_attn.o_proj.bias": "model-00010-of-00013.safetensors",
|
| 737 |
+
"model.layers.29.self_attn.o_proj.biases": "model-00010-of-00013.safetensors",
|
| 738 |
+
"model.layers.29.self_attn.o_proj.scales": "model-00010-of-00013.safetensors",
|
| 739 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00010-of-00013.safetensors",
|
| 740 |
+
"model.layers.29.self_attn.q_proj.bias": "model-00010-of-00013.safetensors",
|
| 741 |
+
"model.layers.29.self_attn.q_proj.biases": "model-00010-of-00013.safetensors",
|
| 742 |
+
"model.layers.29.self_attn.q_proj.scales": "model-00010-of-00013.safetensors",
|
| 743 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00010-of-00013.safetensors",
|
| 744 |
+
"model.layers.29.self_attn.sinks": "model-00010-of-00013.safetensors",
|
| 745 |
+
"model.layers.29.self_attn.v_proj.bias": "model-00010-of-00013.safetensors",
|
| 746 |
+
"model.layers.29.self_attn.v_proj.biases": "model-00010-of-00013.safetensors",
|
| 747 |
+
"model.layers.29.self_attn.v_proj.scales": "model-00010-of-00013.safetensors",
|
| 748 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00010-of-00013.safetensors",
|
| 749 |
"model.layers.3.input_layernorm.weight": "model-00002-of-00013.safetensors",
|
| 750 |
"model.layers.3.mlp.experts.down_proj.bias": "model-00002-of-00013.safetensors",
|
|
|
|
| 751 |
"model.layers.3.mlp.experts.down_proj.scales": "model-00002-of-00013.safetensors",
|
| 752 |
"model.layers.3.mlp.experts.down_proj.weight": "model-00002-of-00013.safetensors",
|
| 753 |
"model.layers.3.mlp.experts.gate_proj.bias": "model-00002-of-00013.safetensors",
|
|
|
|
| 754 |
"model.layers.3.mlp.experts.gate_proj.scales": "model-00002-of-00013.safetensors",
|
| 755 |
"model.layers.3.mlp.experts.gate_proj.weight": "model-00002-of-00013.safetensors",
|
| 756 |
"model.layers.3.mlp.experts.up_proj.bias": "model-00002-of-00013.safetensors",
|
|
|
|
| 757 |
"model.layers.3.mlp.experts.up_proj.scales": "model-00002-of-00013.safetensors",
|
| 758 |
"model.layers.3.mlp.experts.up_proj.weight": "model-00002-of-00013.safetensors",
|
| 759 |
"model.layers.3.mlp.router.bias": "model-00002-of-00013.safetensors",
|
|
|
|
| 780 |
"model.layers.3.self_attn.v_proj.weight": "model-00002-of-00013.safetensors",
|
| 781 |
"model.layers.30.input_layernorm.weight": "model-00011-of-00013.safetensors",
|
| 782 |
"model.layers.30.mlp.experts.down_proj.bias": "model-00011-of-00013.safetensors",
|
|
|
|
| 783 |
"model.layers.30.mlp.experts.down_proj.scales": "model-00011-of-00013.safetensors",
|
| 784 |
"model.layers.30.mlp.experts.down_proj.weight": "model-00011-of-00013.safetensors",
|
| 785 |
"model.layers.30.mlp.experts.gate_proj.bias": "model-00011-of-00013.safetensors",
|
|
|
|
| 786 |
"model.layers.30.mlp.experts.gate_proj.scales": "model-00011-of-00013.safetensors",
|
| 787 |
"model.layers.30.mlp.experts.gate_proj.weight": "model-00011-of-00013.safetensors",
|
| 788 |
"model.layers.30.mlp.experts.up_proj.bias": "model-00011-of-00013.safetensors",
|
|
|
|
| 789 |
"model.layers.30.mlp.experts.up_proj.scales": "model-00011-of-00013.safetensors",
|
| 790 |
"model.layers.30.mlp.experts.up_proj.weight": "model-00011-of-00013.safetensors",
|
| 791 |
"model.layers.30.mlp.router.bias": "model-00011-of-00013.safetensors",
|
|
|
|
| 810 |
"model.layers.30.self_attn.v_proj.biases": "model-00011-of-00013.safetensors",
|
| 811 |
"model.layers.30.self_attn.v_proj.scales": "model-00011-of-00013.safetensors",
|
| 812 |
"model.layers.30.self_attn.v_proj.weight": "model-00011-of-00013.safetensors",
|
| 813 |
+
"model.layers.31.input_layernorm.weight": "model-00011-of-00013.safetensors",
|
| 814 |
+
"model.layers.31.mlp.experts.down_proj.bias": "model-00011-of-00013.safetensors",
|
| 815 |
+
"model.layers.31.mlp.experts.down_proj.scales": "model-00011-of-00013.safetensors",
|
| 816 |
+
"model.layers.31.mlp.experts.down_proj.weight": "model-00011-of-00013.safetensors",
|
| 817 |
+
"model.layers.31.mlp.experts.gate_proj.bias": "model-00011-of-00013.safetensors",
|
| 818 |
+
"model.layers.31.mlp.experts.gate_proj.scales": "model-00011-of-00013.safetensors",
|
| 819 |
+
"model.layers.31.mlp.experts.gate_proj.weight": "model-00011-of-00013.safetensors",
|
| 820 |
+
"model.layers.31.mlp.experts.up_proj.bias": "model-00011-of-00013.safetensors",
|
| 821 |
+
"model.layers.31.mlp.experts.up_proj.scales": "model-00011-of-00013.safetensors",
|
| 822 |
+
"model.layers.31.mlp.experts.up_proj.weight": "model-00011-of-00013.safetensors",
|
| 823 |
+
"model.layers.31.mlp.router.bias": "model-00011-of-00013.safetensors",
|
| 824 |
+
"model.layers.31.mlp.router.biases": "model-00011-of-00013.safetensors",
|
| 825 |
+
"model.layers.31.mlp.router.scales": "model-00011-of-00013.safetensors",
|
| 826 |
+
"model.layers.31.mlp.router.weight": "model-00011-of-00013.safetensors",
|
| 827 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00011-of-00013.safetensors",
|
|
|
|
|
|
|
|
|
|
| 828 |
"model.layers.31.self_attn.k_proj.bias": "model-00011-of-00013.safetensors",
|
| 829 |
"model.layers.31.self_attn.k_proj.biases": "model-00011-of-00013.safetensors",
|
| 830 |
"model.layers.31.self_attn.k_proj.scales": "model-00011-of-00013.safetensors",
|
|
|
|
| 844 |
"model.layers.31.self_attn.v_proj.weight": "model-00011-of-00013.safetensors",
|
| 845 |
"model.layers.32.input_layernorm.weight": "model-00012-of-00013.safetensors",
|
| 846 |
"model.layers.32.mlp.experts.down_proj.bias": "model-00012-of-00013.safetensors",
|
|
|
|
| 847 |
"model.layers.32.mlp.experts.down_proj.scales": "model-00012-of-00013.safetensors",
|
| 848 |
"model.layers.32.mlp.experts.down_proj.weight": "model-00012-of-00013.safetensors",
|
| 849 |
+
"model.layers.32.mlp.experts.gate_proj.bias": "model-00011-of-00013.safetensors",
|
| 850 |
+
"model.layers.32.mlp.experts.gate_proj.scales": "model-00011-of-00013.safetensors",
|
| 851 |
+
"model.layers.32.mlp.experts.gate_proj.weight": "model-00011-of-00013.safetensors",
|
| 852 |
+
"model.layers.32.mlp.experts.up_proj.bias": "model-00011-of-00013.safetensors",
|
| 853 |
+
"model.layers.32.mlp.experts.up_proj.scales": "model-00011-of-00013.safetensors",
|
| 854 |
+
"model.layers.32.mlp.experts.up_proj.weight": "model-00011-of-00013.safetensors",
|
|
|
|
|
|
|
| 855 |
"model.layers.32.mlp.router.bias": "model-00012-of-00013.safetensors",
|
| 856 |
"model.layers.32.mlp.router.biases": "model-00012-of-00013.safetensors",
|
| 857 |
"model.layers.32.mlp.router.scales": "model-00012-of-00013.safetensors",
|
| 858 |
"model.layers.32.mlp.router.weight": "model-00012-of-00013.safetensors",
|
| 859 |
"model.layers.32.post_attention_layernorm.weight": "model-00012-of-00013.safetensors",
|
| 860 |
+
"model.layers.32.self_attn.k_proj.bias": "model-00011-of-00013.safetensors",
|
| 861 |
+
"model.layers.32.self_attn.k_proj.biases": "model-00011-of-00013.safetensors",
|
| 862 |
+
"model.layers.32.self_attn.k_proj.scales": "model-00011-of-00013.safetensors",
|
| 863 |
+
"model.layers.32.self_attn.k_proj.weight": "model-00011-of-00013.safetensors",
|
| 864 |
+
"model.layers.32.self_attn.o_proj.bias": "model-00011-of-00013.safetensors",
|
| 865 |
+
"model.layers.32.self_attn.o_proj.biases": "model-00011-of-00013.safetensors",
|
| 866 |
+
"model.layers.32.self_attn.o_proj.scales": "model-00011-of-00013.safetensors",
|
| 867 |
+
"model.layers.32.self_attn.o_proj.weight": "model-00011-of-00013.safetensors",
|
| 868 |
+
"model.layers.32.self_attn.q_proj.bias": "model-00011-of-00013.safetensors",
|
| 869 |
+
"model.layers.32.self_attn.q_proj.biases": "model-00011-of-00013.safetensors",
|
| 870 |
+
"model.layers.32.self_attn.q_proj.scales": "model-00011-of-00013.safetensors",
|
| 871 |
+
"model.layers.32.self_attn.q_proj.weight": "model-00011-of-00013.safetensors",
|
| 872 |
+
"model.layers.32.self_attn.sinks": "model-00011-of-00013.safetensors",
|
| 873 |
+
"model.layers.32.self_attn.v_proj.bias": "model-00011-of-00013.safetensors",
|
| 874 |
+
"model.layers.32.self_attn.v_proj.biases": "model-00011-of-00013.safetensors",
|
| 875 |
+
"model.layers.32.self_attn.v_proj.scales": "model-00011-of-00013.safetensors",
|
| 876 |
+
"model.layers.32.self_attn.v_proj.weight": "model-00011-of-00013.safetensors",
|
| 877 |
+
"model.layers.33.input_layernorm.weight": "model-00012-of-00013.safetensors",
|
| 878 |
+
"model.layers.33.mlp.experts.down_proj.bias": "model-00012-of-00013.safetensors",
|
| 879 |
+
"model.layers.33.mlp.experts.down_proj.scales": "model-00012-of-00013.safetensors",
|
|
|
|
| 880 |
"model.layers.33.mlp.experts.down_proj.weight": "model-00012-of-00013.safetensors",
|
| 881 |
"model.layers.33.mlp.experts.gate_proj.bias": "model-00012-of-00013.safetensors",
|
|
|
|
| 882 |
"model.layers.33.mlp.experts.gate_proj.scales": "model-00012-of-00013.safetensors",
|
| 883 |
"model.layers.33.mlp.experts.gate_proj.weight": "model-00012-of-00013.safetensors",
|
| 884 |
"model.layers.33.mlp.experts.up_proj.bias": "model-00012-of-00013.safetensors",
|
|
|
|
| 885 |
"model.layers.33.mlp.experts.up_proj.scales": "model-00012-of-00013.safetensors",
|
| 886 |
"model.layers.33.mlp.experts.up_proj.weight": "model-00012-of-00013.safetensors",
|
| 887 |
+
"model.layers.33.mlp.router.bias": "model-00012-of-00013.safetensors",
|
| 888 |
+
"model.layers.33.mlp.router.biases": "model-00012-of-00013.safetensors",
|
| 889 |
+
"model.layers.33.mlp.router.scales": "model-00012-of-00013.safetensors",
|
| 890 |
+
"model.layers.33.mlp.router.weight": "model-00012-of-00013.safetensors",
|
| 891 |
+
"model.layers.33.post_attention_layernorm.weight": "model-00012-of-00013.safetensors",
|
| 892 |
"model.layers.33.self_attn.k_proj.bias": "model-00012-of-00013.safetensors",
|
| 893 |
"model.layers.33.self_attn.k_proj.biases": "model-00012-of-00013.safetensors",
|
| 894 |
"model.layers.33.self_attn.k_proj.scales": "model-00012-of-00013.safetensors",
|
|
|
|
| 906 |
"model.layers.33.self_attn.v_proj.biases": "model-00012-of-00013.safetensors",
|
| 907 |
"model.layers.33.self_attn.v_proj.scales": "model-00012-of-00013.safetensors",
|
| 908 |
"model.layers.33.self_attn.v_proj.weight": "model-00012-of-00013.safetensors",
|
| 909 |
+
"model.layers.34.input_layernorm.weight": "model-00012-of-00013.safetensors",
|
| 910 |
+
"model.layers.34.mlp.experts.down_proj.bias": "model-00012-of-00013.safetensors",
|
| 911 |
+
"model.layers.34.mlp.experts.down_proj.scales": "model-00012-of-00013.safetensors",
|
| 912 |
+
"model.layers.34.mlp.experts.down_proj.weight": "model-00012-of-00013.safetensors",
|
| 913 |
+
"model.layers.34.mlp.experts.gate_proj.bias": "model-00012-of-00013.safetensors",
|
| 914 |
+
"model.layers.34.mlp.experts.gate_proj.scales": "model-00012-of-00013.safetensors",
|
| 915 |
+
"model.layers.34.mlp.experts.gate_proj.weight": "model-00012-of-00013.safetensors",
|
| 916 |
+
"model.layers.34.mlp.experts.up_proj.bias": "model-00012-of-00013.safetensors",
|
| 917 |
+
"model.layers.34.mlp.experts.up_proj.scales": "model-00012-of-00013.safetensors",
|
| 918 |
+
"model.layers.34.mlp.experts.up_proj.weight": "model-00012-of-00013.safetensors",
|
| 919 |
+
"model.layers.34.mlp.router.bias": "model-00012-of-00013.safetensors",
|
| 920 |
+
"model.layers.34.mlp.router.biases": "model-00012-of-00013.safetensors",
|
| 921 |
+
"model.layers.34.mlp.router.scales": "model-00012-of-00013.safetensors",
|
| 922 |
+
"model.layers.34.mlp.router.weight": "model-00012-of-00013.safetensors",
|
| 923 |
+
"model.layers.34.post_attention_layernorm.weight": "model-00012-of-00013.safetensors",
|
| 924 |
+
"model.layers.34.self_attn.k_proj.bias": "model-00012-of-00013.safetensors",
|
| 925 |
+
"model.layers.34.self_attn.k_proj.biases": "model-00012-of-00013.safetensors",
|
| 926 |
+
"model.layers.34.self_attn.k_proj.scales": "model-00012-of-00013.safetensors",
|
| 927 |
+
"model.layers.34.self_attn.k_proj.weight": "model-00012-of-00013.safetensors",
|
| 928 |
+
"model.layers.34.self_attn.o_proj.bias": "model-00012-of-00013.safetensors",
|
| 929 |
+
"model.layers.34.self_attn.o_proj.biases": "model-00012-of-00013.safetensors",
|
| 930 |
+
"model.layers.34.self_attn.o_proj.scales": "model-00012-of-00013.safetensors",
|
| 931 |
+
"model.layers.34.self_attn.o_proj.weight": "model-00012-of-00013.safetensors",
|
| 932 |
+
"model.layers.34.self_attn.q_proj.bias": "model-00012-of-00013.safetensors",
|
| 933 |
+
"model.layers.34.self_attn.q_proj.biases": "model-00012-of-00013.safetensors",
|
| 934 |
+
"model.layers.34.self_attn.q_proj.scales": "model-00012-of-00013.safetensors",
|
| 935 |
+
"model.layers.34.self_attn.q_proj.weight": "model-00012-of-00013.safetensors",
|
| 936 |
+
"model.layers.34.self_attn.sinks": "model-00012-of-00013.safetensors",
|
| 937 |
+
"model.layers.34.self_attn.v_proj.bias": "model-00012-of-00013.safetensors",
|
| 938 |
+
"model.layers.34.self_attn.v_proj.biases": "model-00012-of-00013.safetensors",
|
| 939 |
+
"model.layers.34.self_attn.v_proj.scales": "model-00012-of-00013.safetensors",
|
| 940 |
+
"model.layers.34.self_attn.v_proj.weight": "model-00012-of-00013.safetensors",
|
|
|
|
|
|
|
|
|
|
| 941 |
"model.layers.35.input_layernorm.weight": "model-00013-of-00013.safetensors",
|
| 942 |
"model.layers.35.mlp.experts.down_proj.bias": "model-00013-of-00013.safetensors",
|
|
|
|
| 943 |
"model.layers.35.mlp.experts.down_proj.scales": "model-00013-of-00013.safetensors",
|
| 944 |
"model.layers.35.mlp.experts.down_proj.weight": "model-00013-of-00013.safetensors",
|
| 945 |
+
"model.layers.35.mlp.experts.gate_proj.bias": "model-00012-of-00013.safetensors",
|
| 946 |
+
"model.layers.35.mlp.experts.gate_proj.scales": "model-00012-of-00013.safetensors",
|
| 947 |
+
"model.layers.35.mlp.experts.gate_proj.weight": "model-00012-of-00013.safetensors",
|
| 948 |
+
"model.layers.35.mlp.experts.up_proj.bias": "model-00012-of-00013.safetensors",
|
| 949 |
+
"model.layers.35.mlp.experts.up_proj.scales": "model-00012-of-00013.safetensors",
|
| 950 |
+
"model.layers.35.mlp.experts.up_proj.weight": "model-00012-of-00013.safetensors",
|
|
|
|
|
|
|
| 951 |
"model.layers.35.mlp.router.bias": "model-00013-of-00013.safetensors",
|
| 952 |
"model.layers.35.mlp.router.biases": "model-00013-of-00013.safetensors",
|
| 953 |
"model.layers.35.mlp.router.scales": "model-00013-of-00013.safetensors",
|
| 954 |
"model.layers.35.mlp.router.weight": "model-00013-of-00013.safetensors",
|
| 955 |
"model.layers.35.post_attention_layernorm.weight": "model-00013-of-00013.safetensors",
|
| 956 |
+
"model.layers.35.self_attn.k_proj.bias": "model-00012-of-00013.safetensors",
|
| 957 |
+
"model.layers.35.self_attn.k_proj.biases": "model-00012-of-00013.safetensors",
|
| 958 |
+
"model.layers.35.self_attn.k_proj.scales": "model-00012-of-00013.safetensors",
|
| 959 |
+
"model.layers.35.self_attn.k_proj.weight": "model-00012-of-00013.safetensors",
|
| 960 |
+
"model.layers.35.self_attn.o_proj.bias": "model-00012-of-00013.safetensors",
|
| 961 |
+
"model.layers.35.self_attn.o_proj.biases": "model-00012-of-00013.safetensors",
|
| 962 |
+
"model.layers.35.self_attn.o_proj.scales": "model-00012-of-00013.safetensors",
|
| 963 |
+
"model.layers.35.self_attn.o_proj.weight": "model-00012-of-00013.safetensors",
|
| 964 |
+
"model.layers.35.self_attn.q_proj.bias": "model-00012-of-00013.safetensors",
|
| 965 |
+
"model.layers.35.self_attn.q_proj.biases": "model-00012-of-00013.safetensors",
|
| 966 |
+
"model.layers.35.self_attn.q_proj.scales": "model-00012-of-00013.safetensors",
|
| 967 |
+
"model.layers.35.self_attn.q_proj.weight": "model-00012-of-00013.safetensors",
|
| 968 |
+
"model.layers.35.self_attn.sinks": "model-00012-of-00013.safetensors",
|
| 969 |
+
"model.layers.35.self_attn.v_proj.bias": "model-00012-of-00013.safetensors",
|
| 970 |
+
"model.layers.35.self_attn.v_proj.biases": "model-00012-of-00013.safetensors",
|
| 971 |
+
"model.layers.35.self_attn.v_proj.scales": "model-00012-of-00013.safetensors",
|
| 972 |
+
"model.layers.35.self_attn.v_proj.weight": "model-00012-of-00013.safetensors",
|
| 973 |
"model.layers.4.input_layernorm.weight": "model-00002-of-00013.safetensors",
|
| 974 |
"model.layers.4.mlp.experts.down_proj.bias": "model-00002-of-00013.safetensors",
|
|
|
|
| 975 |
"model.layers.4.mlp.experts.down_proj.scales": "model-00002-of-00013.safetensors",
|
| 976 |
"model.layers.4.mlp.experts.down_proj.weight": "model-00002-of-00013.safetensors",
|
| 977 |
"model.layers.4.mlp.experts.gate_proj.bias": "model-00002-of-00013.safetensors",
|
|
|
|
| 978 |
"model.layers.4.mlp.experts.gate_proj.scales": "model-00002-of-00013.safetensors",
|
| 979 |
"model.layers.4.mlp.experts.gate_proj.weight": "model-00002-of-00013.safetensors",
|
| 980 |
"model.layers.4.mlp.experts.up_proj.bias": "model-00002-of-00013.safetensors",
|
|
|
|
| 981 |
"model.layers.4.mlp.experts.up_proj.scales": "model-00002-of-00013.safetensors",
|
| 982 |
"model.layers.4.mlp.experts.up_proj.weight": "model-00002-of-00013.safetensors",
|
| 983 |
"model.layers.4.mlp.router.bias": "model-00002-of-00013.safetensors",
|
|
|
|
| 1004 |
"model.layers.4.self_attn.v_proj.weight": "model-00002-of-00013.safetensors",
|
| 1005 |
"model.layers.5.input_layernorm.weight": "model-00003-of-00013.safetensors",
|
| 1006 |
"model.layers.5.mlp.experts.down_proj.bias": "model-00003-of-00013.safetensors",
|
|
|
|
| 1007 |
"model.layers.5.mlp.experts.down_proj.scales": "model-00003-of-00013.safetensors",
|
| 1008 |
"model.layers.5.mlp.experts.down_proj.weight": "model-00003-of-00013.safetensors",
|
| 1009 |
"model.layers.5.mlp.experts.gate_proj.bias": "model-00002-of-00013.safetensors",
|
|
|
|
| 1010 |
"model.layers.5.mlp.experts.gate_proj.scales": "model-00002-of-00013.safetensors",
|
| 1011 |
"model.layers.5.mlp.experts.gate_proj.weight": "model-00002-of-00013.safetensors",
|
| 1012 |
+
"model.layers.5.mlp.experts.up_proj.bias": "model-00002-of-00013.safetensors",
|
| 1013 |
+
"model.layers.5.mlp.experts.up_proj.scales": "model-00002-of-00013.safetensors",
|
|
|
|
| 1014 |
"model.layers.5.mlp.experts.up_proj.weight": "model-00002-of-00013.safetensors",
|
| 1015 |
"model.layers.5.mlp.router.bias": "model-00003-of-00013.safetensors",
|
| 1016 |
"model.layers.5.mlp.router.biases": "model-00003-of-00013.safetensors",
|
|
|
|
| 1036 |
"model.layers.5.self_attn.v_proj.weight": "model-00002-of-00013.safetensors",
|
| 1037 |
"model.layers.6.input_layernorm.weight": "model-00003-of-00013.safetensors",
|
| 1038 |
"model.layers.6.mlp.experts.down_proj.bias": "model-00003-of-00013.safetensors",
|
|
|
|
| 1039 |
"model.layers.6.mlp.experts.down_proj.scales": "model-00003-of-00013.safetensors",
|
| 1040 |
"model.layers.6.mlp.experts.down_proj.weight": "model-00003-of-00013.safetensors",
|
| 1041 |
"model.layers.6.mlp.experts.gate_proj.bias": "model-00003-of-00013.safetensors",
|
|
|
|
| 1042 |
"model.layers.6.mlp.experts.gate_proj.scales": "model-00003-of-00013.safetensors",
|
| 1043 |
"model.layers.6.mlp.experts.gate_proj.weight": "model-00003-of-00013.safetensors",
|
| 1044 |
"model.layers.6.mlp.experts.up_proj.bias": "model-00003-of-00013.safetensors",
|
|
|
|
| 1045 |
"model.layers.6.mlp.experts.up_proj.scales": "model-00003-of-00013.safetensors",
|
| 1046 |
"model.layers.6.mlp.experts.up_proj.weight": "model-00003-of-00013.safetensors",
|
| 1047 |
"model.layers.6.mlp.router.bias": "model-00003-of-00013.safetensors",
|
|
|
|
| 1068 |
"model.layers.6.self_attn.v_proj.weight": "model-00003-of-00013.safetensors",
|
| 1069 |
"model.layers.7.input_layernorm.weight": "model-00003-of-00013.safetensors",
|
| 1070 |
"model.layers.7.mlp.experts.down_proj.bias": "model-00003-of-00013.safetensors",
|
|
|
|
| 1071 |
"model.layers.7.mlp.experts.down_proj.scales": "model-00003-of-00013.safetensors",
|
| 1072 |
"model.layers.7.mlp.experts.down_proj.weight": "model-00003-of-00013.safetensors",
|
| 1073 |
"model.layers.7.mlp.experts.gate_proj.bias": "model-00003-of-00013.safetensors",
|
|
|
|
| 1074 |
"model.layers.7.mlp.experts.gate_proj.scales": "model-00003-of-00013.safetensors",
|
| 1075 |
"model.layers.7.mlp.experts.gate_proj.weight": "model-00003-of-00013.safetensors",
|
| 1076 |
"model.layers.7.mlp.experts.up_proj.bias": "model-00003-of-00013.safetensors",
|
|
|
|
| 1077 |
"model.layers.7.mlp.experts.up_proj.scales": "model-00003-of-00013.safetensors",
|
| 1078 |
"model.layers.7.mlp.experts.up_proj.weight": "model-00003-of-00013.safetensors",
|
| 1079 |
"model.layers.7.mlp.router.bias": "model-00003-of-00013.safetensors",
|
|
|
|
| 1100 |
"model.layers.7.self_attn.v_proj.weight": "model-00003-of-00013.safetensors",
|
| 1101 |
"model.layers.8.input_layernorm.weight": "model-00004-of-00013.safetensors",
|
| 1102 |
"model.layers.8.mlp.experts.down_proj.bias": "model-00004-of-00013.safetensors",
|
|
|
|
| 1103 |
"model.layers.8.mlp.experts.down_proj.scales": "model-00004-of-00013.safetensors",
|
| 1104 |
"model.layers.8.mlp.experts.down_proj.weight": "model-00004-of-00013.safetensors",
|
| 1105 |
"model.layers.8.mlp.experts.gate_proj.bias": "model-00003-of-00013.safetensors",
|
|
|
|
| 1106 |
"model.layers.8.mlp.experts.gate_proj.scales": "model-00003-of-00013.safetensors",
|
| 1107 |
"model.layers.8.mlp.experts.gate_proj.weight": "model-00003-of-00013.safetensors",
|
| 1108 |
+
"model.layers.8.mlp.experts.up_proj.bias": "model-00003-of-00013.safetensors",
|
| 1109 |
+
"model.layers.8.mlp.experts.up_proj.scales": "model-00003-of-00013.safetensors",
|
| 1110 |
+
"model.layers.8.mlp.experts.up_proj.weight": "model-00003-of-00013.safetensors",
|
|
|
|
| 1111 |
"model.layers.8.mlp.router.bias": "model-00004-of-00013.safetensors",
|
| 1112 |
"model.layers.8.mlp.router.biases": "model-00004-of-00013.safetensors",
|
| 1113 |
"model.layers.8.mlp.router.scales": "model-00004-of-00013.safetensors",
|
|
|
|
| 1132 |
"model.layers.8.self_attn.v_proj.weight": "model-00003-of-00013.safetensors",
|
| 1133 |
"model.layers.9.input_layernorm.weight": "model-00004-of-00013.safetensors",
|
| 1134 |
"model.layers.9.mlp.experts.down_proj.bias": "model-00004-of-00013.safetensors",
|
|
|
|
| 1135 |
"model.layers.9.mlp.experts.down_proj.scales": "model-00004-of-00013.safetensors",
|
| 1136 |
"model.layers.9.mlp.experts.down_proj.weight": "model-00004-of-00013.safetensors",
|
| 1137 |
"model.layers.9.mlp.experts.gate_proj.bias": "model-00004-of-00013.safetensors",
|
|
|
|
| 1138 |
"model.layers.9.mlp.experts.gate_proj.scales": "model-00004-of-00013.safetensors",
|
| 1139 |
"model.layers.9.mlp.experts.gate_proj.weight": "model-00004-of-00013.safetensors",
|
| 1140 |
"model.layers.9.mlp.experts.up_proj.bias": "model-00004-of-00013.safetensors",
|
|
|
|
| 1141 |
"model.layers.9.mlp.experts.up_proj.scales": "model-00004-of-00013.safetensors",
|
| 1142 |
"model.layers.9.mlp.experts.up_proj.weight": "model-00004-of-00013.safetensors",
|
| 1143 |
"model.layers.9.mlp.router.bias": "model-00004-of-00013.safetensors",
|