Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

chat_template.jinja

@@ -0,0 +1,389 @@
+{#-
+  In addition to the normal inputs of `messages` and `tools`, this template also accepts the
+  following kwargs:
+  - "builtin_tools": A list, can contain "browser" and/or "python".
+  - "model_identity": A string that optionally describes the model identity.
+  - "reasoning_effort": A string that describes the reasoning effort, defaults to "medium".
+ #}
+
+{#- Tool Definition Rendering ============================================== #}
+{%- macro render_typescript_type(param_spec, required_params, is_nullable=false) -%}
+    {%- if param_spec.type == "array" -%}
+        {%- if param_spec['items'] -%}
+            {%- if param_spec['items']['type'] == "string" -%}
+                {{- "string[]" }}
+            {%- elif param_spec['items']['type'] == "number" -%}
+                {{- "number[]" }}
+            {%- elif param_spec['items']['type'] == "integer" -%}
+                {{- "number[]" }}
+            {%- elif param_spec['items']['type'] == "boolean" -%}
+                {{- "boolean[]" }}
+            {%- else -%}
+                {%- set inner_type = render_typescript_type(param_spec['items'], required_params) -%}
+                {%- if inner_type == "object | object" or inner_type|length > 50 -%}
+                    {{- "any[]" }}
+                {%- else -%}
+                    {{- inner_type + "[]" }}
+                {%- endif -%}
+            {%- endif -%}
+            {%- if param_spec.nullable -%}
+                {{- " | null" }}
+            {%- endif -%}
+        {%- else -%}
+            {{- "any[]" }}
+            {%- if param_spec.nullable -%}
+                {{- " | null" }}
+            {%- endif -%}
+        {%- endif -%}
+    {%- elif param_spec.type is defined and param_spec.type is iterable and param_spec.type is not string and param_spec.type is not mapping and param_spec.type[0] is defined -%}
+        {#- Handle array of types like ["object", "object"] from Union[dict, list] #}
+        {%- if param_spec.type | length > 1 -%}
+            {{- param_spec.type | join(" | ") }}
+        {%- else -%}
+            {{- param_spec.type[0] }}
+        {%- endif -%}
+    {%- elif param_spec.oneOf -%}
+        {#- Handle oneOf schemas - check for complex unions and fallback to any #}
+        {%- set has_object_variants = false -%}
+        {%- for variant in param_spec.oneOf -%}
+            {%- if variant.type == "object" -%}
+                {%- set has_object_variants = true -%}
+            {%- endif -%}
+        {%- endfor -%}
+        {%- if has_object_variants and param_spec.oneOf|length > 1 -%}
+            {{- "any" }}
+        {%- else -%}
+            {%- for variant in param_spec.oneOf -%}
+                {{- render_typescript_type(variant, required_params) -}}
+                {%- if variant.description %}
+                    {{- "// " + variant.description }}
+                {%- endif -%}
+                {%- if variant.default is defined %}
+                    {{ "// default: " + variant.default|tojson }}
+                {%- endif -%}
+                {%- if not loop.last %}
+                    {{- " | " }}
+                {% endif -%}
+            {%- endfor -%}
+        {%- endif -%}
+    {%- elif param_spec.type == "string" -%}
+        {%- if param_spec.enum -%}
+            {{- '"' + param_spec.enum|join('" | "') + '"' -}}
+        {%- else -%}
+            {{- "string" }}
+            {%- if param_spec.nullable %}
+                {{- " | null" }}
+            {%- endif -%}
+        {%- endif -%}
+    {%- elif param_spec.type == "number" -%}
+        {{- "number" }}
+    {%- elif param_spec.type == "integer" -%}
+        {{- "number" }}
+    {%- elif param_spec.type == "boolean" -%}
+        {{- "boolean" }}
+
+    {%- elif param_spec.type == "object" -%}
+        {%- if param_spec.properties -%}
+            {{- "{
+" }}
+            {%- for prop_name, prop_spec in param_spec.properties.items() -%}
+                {{- prop_name -}}
+                {%- if prop_name not in (param_spec.required or []) -%}
+                    {{- "?" }}
+                {%- endif -%}
+                {{- ": " }}
+                {{ render_typescript_type(prop_spec, param_spec.required or []) }}
+                {%- if not loop.last -%}
+                    {{-", " }}
+                {%- endif -%}
+            {%- endfor -%}
+            {{- "}" }}
+        {%- else -%}
+            {{- "object" }}
+        {%- endif -%}
+    {%- else -%}
+        {{- "any" }}
+    {%- endif -%}
+{%- endmacro -%}
+
+{%- macro render_tool_namespace(namespace_name, tools) -%}
+    {{- "## " + namespace_name + "
+
+" }}
+    {{- "namespace " + namespace_name + " {
+
+" }}
+    {%- for tool in tools %}
+        {%- set tool = tool.function %}
+        {{- "// " + tool.description + "
+" }}
+        {{- "type "+ tool.name + " = (" }}
+        {%- if tool.parameters and tool.parameters.properties -%}
+            {{- "_: " }}
+            {{- "{
+" }}
+            {%- for param_name, param_spec in tool.parameters.properties.items() %}
+                {{- "// " + param_spec.description + "
+" }}
+                {{- param_name }}
+                {%- if param_name not in (tool.parameters.required or []) -%}
+                    {{- "?" }}
+                {%- endif -%}
+                {{- ": " }}
+                {{- render_typescript_type(param_spec, tool.parameters.required or []) }}
+                {%- if param_spec.default is defined -%}
+                    {%- if param_spec.oneOf %}
+                        {{- "// default: " + param_spec.default }}
+                    {%- else %}
+                        {{- ", // default: " + param_spec.default|tojson }}
+                    {%- endif -%}
+                {%- endif -%}
+                {%- if not loop.last %}
+                    {{- ",
+" }}
+                {%- endif -%}
+            {%- endfor %}
+            {{- ",
+}) => any;
+" }}
+        {%- else -%}
+            {{- "
+}) => any;
+" }}
+        {%- endif -%}
+    {%- endfor %}
+    {{- "
+} // namespace " + namespace_name }}
+{%- endmacro -%}
+
+{%- macro render_builtin_tools(browser_tool, python_tool) -%}
+    {%- if browser_tool %}
+        {{- "## browser
+
+" }}
+        {{- "// Tool for browsing.
+" }}
+        {{- "// The `cursor` appears in brackets before each browsing display: `[{cursor}]`.
+" }}
+        {{- "// Cite information from the tool using the following format:
+" }}
+        {{- "// `【{cursor}†L{line_start}(-L{line_end})?】`, for example: `【6†L9-L11】` or `【8†L3】`.
+" }}
+        {{- "// Do not quote more than 10 words directly from the tool output.
+" }}
+        {{- "// sources=web (default: web)
+" }}
+        {{- "namespace browser {
+
+" }}
+        {{- "// Searches for information related to `query` and displays `topn` results.
+" }}
+        {{- "type search = (_: {
+" }}
+        {{- "query: string,
+" }}
+        {{- "topn?: number, // default: 10
+" }}
+        {{- "source?: string,
+" }}
+        {{- "}) => any;
+
+" }}
+        {{- "// Opens the link `id` from the page indicated by `cursor` starting at line number `loc`, showing `num_lines` lines.
+" }}
+        {{- "// Valid link ids are displayed with the formatting: `【{id}†.*】`.
+" }}
+        {{- "// If `cursor` is not provided, the most recent page is implied.
+" }}
+        {{- "// If `id` is a string, it is treated as a fully qualified URL associated with `source`.
+" }}
+        {{- "// 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.
+" }}
+        {{- "// Use this function without `id` to scroll to a new location of an opened page.
+" }}
+        {{- "type open = (_: {
+" }}
+        {{- "id?: number | string, // default: -1
+" }}
+        {{- "cursor?: number, // default: -1
+" }}
+        {{- "loc?: number, // default: -1
+" }}
+        {{- "num_lines?: number, // default: -1
+" }}
+        {{- "view_source?: boolean, // default: false
+" }}
+        {{- "source?: string,
+" }}
+        {{- "}) => any;
+
+" }}
+        {{- "// Finds exact matches of `pattern` in the current page, or the page given by `cursor`.
+" }}
+        {{- "type find = (_: {
+" }}
+        {{- "pattern: string,
+" }}
+        {{- "cursor?: number, // default: -1
+" }}
+        {{- "}) => any;
+
+" }}
+        {{- "} // namespace browser
+
+" }}
+    {%- endif -%}
+
+    {%- if python_tool %}
+        {{- "## python
+
+" }}
+        {{- "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).
+
+" }}
+        {{- "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.
+
+" }}
+    {%- endif -%}
+{%- endmacro -%}
+
+{#- System Message Construction ============================================ #}
+{%- macro build_system_message() -%}
+    {%- if model_identity is not defined %}
+        {%- set model_identity = "You are ChatGPT, a large language model trained by OpenAI." %}
+    {%- endif %}
+    {{- model_identity + "
+" }}
+    {{- "Knowledge cutoff: 2024-06
+" }}
+    {{- "Current date: " + strftime_now("%Y-%m-%d") + "
+
+" }}
+    {%- if reasoning_effort is not defined %}
+        {%- set reasoning_effort = "medium" %}
+    {%- endif %}
+    {{- "Reasoning: " + reasoning_effort + "
+
+" }}
+    {%- if builtin_tools %}
+        {{- "# Tools
+
+" }}
+        {%- set available_builtin_tools = namespace(browser=false, python=false) %}
+        {%- for tool in builtin_tools %}
+            {%- if tool == "browser" %}
+                {%- set available_builtin_tools.browser = true %}
+            {%- elif tool == "python" %}
+                {%- set available_builtin_tools.python = true %}
+            {%- endif %}
+        {%- endfor %}
+        {{- render_builtin_tools(available_builtin_tools.browser, available_builtin_tools.python) }}
+    {%- endif -%}
+    {{- "# Valid channels: analysis, commentary, final. Channel must be included for every message.
+" }}
+    {{- "Calls to these tools must go to the commentary channel: 'functions'." }}
+{%- endmacro -%}
+
+{#- Main Template Logic ================================================= #}
+{#- Set defaults #}
+
+{#- Render system message #}
+{{- "<|start|>system<|message|>" }}
+{{- build_system_message() }}
+{{- "<|end|>" }}
+
+{#- Extract developer message #}
+{%- if messages[0].role == "developer" or messages[0].role == "system" %}
+    {%- set developer_message = messages[0].content %}
+    {%- set loop_messages = messages[1:] %}
+{%- else %}
+    {%- set developer_message = "" %}
+    {%- set loop_messages = messages %}
+{%- endif %}
+
+{#- Render developer message #}
+{%- if developer_message or tools %}
+    {{- "<|start|>developer<|message|>" }}
+    {%- if developer_message %}
+        {{- "# Instructions
+
+" }}
+        {{- developer_message }}
+    {%- endif %}
+    {%- if tools -%}
+        {{- "
+
+" }}
+        {{- "# Tools
+
+" }}
+        {{- render_tool_namespace("functions", tools) }}
+    {%- endif -%}
+    {{- "<|end|>" }}
+{%- endif %}
+
+{#- Render messages #}
+{%- set last_tool_call = namespace(name=none) %}
+{%- for message in loop_messages -%}
+    {#- At this point only assistant/user/tool messages should remain #}
+    {%- if message.role == 'assistant' -%}
+        {#- Checks to ensure the messages are being passed in the format we expect #}
+        {%- if "content" in message %}
+            {%- if "<|channel|>analysis<|message|>" in message.content or "<|channel|>final<|message|>" in message.content %}
+                {{- raise_exception("You have passed a message containing <|channel|> tags in the content field. Instead of doing this, you should pass analysis messages (the string between '<|message|>' and '<|end|>') in the 'thinking' field, and final messages (the string between '<|message|>' and '<|end|>') in the 'content' field.") }}
+            {%- endif %}
+        {%- endif %}
+        {%- if "thinking" in message %}
+            {%- if "<|channel|>analysis<|message|>" in message.thinking or "<|channel|>final<|message|>" in message.thinking %}
+                {{- raise_exception("You have passed a message containing <|channel|> tags in the thinking field. Instead of doing this, you should pass analysis messages (the string between '<|message|>' and '<|end|>') in the 'thinking' field, and final messages (the string between '<|message|>' and '<|end|>') in the 'content' field.") }}
+            {%- endif %}
+        {%- endif %}
+        {%- if "tool_calls" in message %}
+            {#- We assume max 1 tool call per message, and so we infer the tool call name #}
+            {#- in "tool" messages from the most recent assistant tool call name #}
+            {%- set tool_call = message.tool_calls[0] %}
+            {%- if tool_call.function %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {%- if message.content and message.thinking %}
+                {{- 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.") }}
+            {%- elif message.content %}
+                {{- "<|start|>assistant<|channel|>analysis<|message|>" + message.content + "<|end|>" }}
+            {%- elif message.thinking %}
+                {{- "<|start|>assistant<|channel|>analysis<|message|>" + message.thinking + "<|end|>" }}
+            {%- endif %}
+            {{- "<|start|>assistant to=" }}
+            {{- "functions." + tool_call.name + "<|channel|>commentary json<|message|>" }}
+            {{- tool_call.arguments|tojson }}
+            {{- "<|end|>" }}
+            {%- set last_tool_call.name = tool_call.name %}
+        {%- elif loop.last and not add_generation_prompt %}
+            {#- Only render the CoT if the final turn is an assistant turn and add_generation_prompt is false #}
+            {#- This is a situation that should only occur in training, never in inference. #}
+            {%- if "thinking" in message %}
+                {{- "<|start|>assistant<|channel|>analysis<|message|>" + message.thinking + "<|end|>" }}
+            {%- endif %}
+            {#- <|return|> indicates the end of generation, but <|end|> does not #}
+            {#- <|return|> should never be an input to the model, but we include it as the final token #}
+            {#- when training, so the model learns to emit it. #}
+            {{- "<|start|>assistant<|channel|>final<|message|>" + message.content + "<|return|>" }}
+        {%- else %}
+            {#- CoT is dropped during all previous turns, so we never render it for inference #}
+            {{- "<|start|>assistant<|channel|>final<|message|>" + message.content + "<|end|>" }}
+            {%- set last_tool_call.name = none %}
+        {%- endif %}
+    {%- elif message.role == 'tool' -%}
+        {%- if last_tool_call.name is none %}
+            {{- raise_exception("Message has tool role, but there was no previous assistant message with a tool call!") }}
+        {%- endif %}
+        {{- "<|start|>functions." + last_tool_call.name }}
+        {{- " to=assistant<|channel|>commentary<|message|>" + message.content|tojson + "<|end|>" }}
+    {%- elif message.role == 'user' -%}
+        {{- "<|start|>user<|message|>" + message.content + "<|end|>" }}
+    {%- endif -%}
+{%- endfor -%}
+
+{#- Generation prompt #}
+{%- if add_generation_prompt -%}
+<|start|>assistant
+{%- endif -%}

chat_template.json

@@ -0,0 +1,3 @@
+{
+  "chat_template": "{#-\n  In addition to the normal inputs of `messages` and `tools`, this template also accepts the\n  following kwargs:\n  - \"builtin_tools\": A list, can contain \"browser\" and/or \"python\".\n  - \"model_identity\": A string that optionally describes the model identity.\n  - \"reasoning_effort\": A string that describes the reasoning effort, defaults to \"medium\".\n #}\n\n{#- Tool Definition Rendering ============================================== #}\n{%- macro render_typescript_type(param_spec, required_params, is_nullable=false) -%}\n    {%- if param_spec.type == \"array\" -%}\n        {%- if param_spec['items'] -%}\n            {%- if param_spec['items']['type'] == \"string\" -%}\n                {{- \"string[]\" }}\n            {%- elif param_spec['items']['type'] == \"number\" -%}\n                {{- \"number[]\" }}\n            {%- elif param_spec['items']['type'] == \"integer\" -%}\n                {{- \"number[]\" }}\n            {%- elif param_spec['items']['type'] == \"boolean\" -%}\n                {{- \"boolean[]\" }}\n            {%- else -%}\n                {%- set inner_type = render_typescript_type(param_spec['items'], required_params) -%}\n                {%- if inner_type == \"object | object\" or inner_type|length > 50 -%}\n                    {{- \"any[]\" }}\n                {%- else -%}\n                    {{- inner_type + \"[]\" }}\n                {%- endif -%}\n            {%- endif -%}\n            {%- if param_spec.nullable -%}\n                {{- \" | null\" }}\n            {%- endif -%}\n        {%- else -%}\n            {{- \"any[]\" }}\n            {%- if param_spec.nullable -%}\n                {{- \" | null\" }}\n            {%- endif -%}\n        {%- endif -%}\n    {%- elif param_spec.type is defined and param_spec.type is iterable and param_spec.type is not string and param_spec.type is not mapping and param_spec.type[0] is defined -%}\n        {#- Handle array of types like [\"object\", \"object\"] from Union[dict, list] #}\n        {%- if param_spec.type | length > 1 -%}\n            {{- param_spec.type | join(\" | \") }}\n        {%- else -%}\n            {{- param_spec.type[0] }}\n        {%- endif -%}\n    {%- elif param_spec.oneOf -%}\n        {#- Handle oneOf schemas - check for complex unions and fallback to any #}\n        {%- set has_object_variants = false -%}\n        {%- for variant in param_spec.oneOf -%}\n            {%- if variant.type == \"object\" -%}\n                {%- set has_object_variants = true -%}\n            {%- endif -%}\n        {%- endfor -%}\n        {%- if has_object_variants and param_spec.oneOf|length > 1 -%}\n            {{- \"any\" }}\n        {%- else -%}\n            {%- for variant in param_spec.oneOf -%}\n                {{- render_typescript_type(variant, required_params) -}}\n                {%- if variant.description %}\n                    {{- \"// \" + variant.description }}\n                {%- endif -%}\n                {%- if variant.default is defined %}\n                    {{ \"// default: \" + variant.default|tojson }}\n                {%- endif -%}\n                {%- if not loop.last %}\n                    {{- \" | \" }}\n                {% endif -%}\n            {%- endfor -%}\n        {%- endif -%}\n    {%- elif param_spec.type == \"string\" -%}\n        {%- if param_spec.enum -%}\n            {{- '\"' + param_spec.enum|join('\" | \"') + '\"' -}}\n        {%- else -%}\n            {{- \"string\" }}\n            {%- if param_spec.nullable %}\n                {{- \" | null\" }}\n            {%- endif -%}\n        {%- endif -%}\n    {%- elif param_spec.type == \"number\" -%}\n        {{- \"number\" }}\n    {%- elif param_spec.type == \"integer\" -%}\n        {{- \"number\" }}\n    {%- elif param_spec.type == \"boolean\" -%}\n        {{- \"boolean\" }}\n\n    {%- elif param_spec.type == \"object\" -%}\n        {%- if param_spec.properties -%}\n            {{- \"{\n\" }}\n            {%- for prop_name, prop_spec in param_spec.properties.items() -%}\n                {{- prop_name -}}\n                {%- if prop_name not in (param_spec.required or []) -%}\n                    {{- \"?\" }}\n                {%- endif -%}\n                {{- \": \" }}\n                {{ render_typescript_type(prop_spec, param_spec.required or []) }}\n                {%- if not loop.last -%}\n                    {{-\", \" }}\n                {%- endif -%}\n            {%- endfor -%}\n            {{- \"}\" }}\n        {%- else -%}\n            {{- \"object\" }}\n        {%- endif -%}\n    {%- else -%}\n        {{- \"any\" }}\n    {%- endif -%}\n{%- endmacro -%}\n\n{%- macro render_tool_namespace(namespace_name, tools) -%}\n    {{- \"## \" + namespace_name + \"\n\n\" }}\n    {{- \"namespace \" + namespace_name + \" {\n\n\" }}\n    {%- for tool in tools %}\n        {%- set tool = tool.function %}\n        {{- \"// \" + tool.description + \"\n\" }}\n        {{- \"type \"+ tool.name + \" = (\" }}\n        {%- if tool.parameters and tool.parameters.properties -%}\n            {{- \"_: \" }}\n            {{- \"{\n\" }}\n            {%- for param_name, param_spec in tool.parameters.properties.items() %}\n                {{- \"// \" + param_spec.description + \"\n\" }}\n                {{- param_name }}\n                {%- if param_name not in (tool.parameters.required or []) -%}\n                    {{- \"?\" }}\n                {%- endif -%}\n                {{- \": \" }}\n                {{- render_typescript_type(param_spec, tool.parameters.required or []) }}\n                {%- if param_spec.default is defined -%}\n                    {%- if param_spec.oneOf %}\n                        {{- \"// default: \" + param_spec.default }}\n                    {%- else %}\n                        {{- \", // default: \" + param_spec.default|tojson }}\n                    {%- endif -%}\n                {%- endif -%}\n                {%- if not loop.last %}\n                    {{- \",\n\" }}\n                {%- endif -%}\n            {%- endfor %}\n            {{- \",\n}) => any;\n\" }}\n        {%- else -%}\n            {{- \"\n}) => any;\n\" }}\n        {%- endif -%}\n    {%- endfor %}\n    {{- \"\n} // namespace \" + namespace_name }}\n{%- endmacro -%}\n\n{%- macro render_builtin_tools(browser_tool, python_tool) -%}\n    {%- if browser_tool %}\n        {{- \"## browser\n\n\" }}\n        {{- \"// Tool for browsing.\n\" }}\n        {{- \"// The `cursor` appears in brackets before each browsing display: `[{cursor}]`.\n\" }}\n        {{- \"// Cite information from the tool using the following format:\n\" }}\n        {{- \"// `\u3010{cursor}\u2020L{line_start}(-L{line_end})?\u3011`, for example: `\u30106\u2020L9-L11\u3011` or `\u30108\u2020L3\u3011`.\n\" }}\n        {{- \"// Do not quote more than 10 words directly from the tool output.\n\" }}\n        {{- \"// sources=web (default: web)\n\" }}\n        {{- \"namespace browser {\n\n\" }}\n        {{- \"// Searches for information related to `query` and displays `topn` results.\n\" }}\n        {{- \"type search = (_: {\n\" }}\n        {{- \"query: string,\n\" }}\n        {{- \"topn?: number, // default: 10\n\" }}\n        {{- \"source?: string,\n\" }}\n        {{- \"}) => any;\n\n\" }}\n        {{- \"// Opens the link `id` from the page indicated by `cursor` starting at line number `loc`, showing `num_lines` lines.\n\" }}\n        {{- \"// Valid link ids are displayed with the formatting: `\u3010{id}\u2020.*\u3011`.\n\" }}\n        {{- \"// If `cursor` is not provided, the most recent page is implied.\n\" }}\n        {{- \"// If `id` is a string, it is treated as a fully qualified URL associated with `source`.\n\" }}\n        {{- \"// 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\" }}\n        {{- \"// Use this function without `id` to scroll to a new location of an opened page.\n\" }}\n        {{- \"type open = (_: {\n\" }}\n        {{- \"id?: number | string, // default: -1\n\" }}\n        {{- \"cursor?: number, // default: -1\n\" }}\n        {{- \"loc?: number, // default: -1\n\" }}\n        {{- \"num_lines?: number, // default: -1\n\" }}\n        {{- \"view_source?: boolean, // default: false\n\" }}\n        {{- \"source?: string,\n\" }}\n        {{- \"}) => any;\n\n\" }}\n        {{- \"// Finds exact matches of `pattern` in the current page, or the page given by `cursor`.\n\" }}\n        {{- \"type find = (_: {\n\" }}\n        {{- \"pattern: string,\n\" }}\n        {{- \"cursor?: number, // default: -1\n\" }}\n        {{- \"}) => any;\n\n\" }}\n        {{- \"} // namespace browser\n\n\" }}\n    {%- endif -%}\n\n    {%- if python_tool %}\n        {{- \"## python\n\n\" }}\n        {{- \"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\" }}\n        {{- \"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\" }}\n    {%- endif -%}\n{%- endmacro -%}\n\n{#- System Message Construction ============================================ #}\n{%- macro build_system_message() -%}\n    {%- if model_identity is not defined %}\n        {%- set model_identity = \"You are ChatGPT, a large language model trained by OpenAI.\" %}\n    {%- endif %}\n    {{- model_identity + \"\n\" }}\n    {{- \"Knowledge cutoff: 2024-06\n\" }}\n    {{- \"Current date: \" + strftime_now(\"%Y-%m-%d\") + \"\n\n\" }}\n    {%- if reasoning_effort is not defined %}\n        {%- set reasoning_effort = \"medium\" %}\n    {%- endif %}\n    {{- \"Reasoning: \" + reasoning_effort + \"\n\n\" }}\n    {%- if builtin_tools %}\n        {{- \"# Tools\n\n\" }}\n        {%- set available_builtin_tools = namespace(browser=false, python=false) %}\n        {%- for tool in builtin_tools %}\n            {%- if tool == \"browser\" %}\n                {%- set available_builtin_tools.browser = true %}\n            {%- elif tool == \"python\" %}\n                {%- set available_builtin_tools.python = true %}\n            {%- endif %}\n        {%- endfor %}\n        {{- render_builtin_tools(available_builtin_tools.browser, available_builtin_tools.python) }}\n    {%- endif -%}\n    {{- \"# Valid channels: analysis, commentary, final. Channel must be included for every message.\n\" }}\n    {{- \"Calls to these tools must go to the commentary channel: 'functions'.\" }}\n{%- endmacro -%}\n\n{#- Main Template Logic ================================================= #}\n{#- Set defaults #}\n\n{#- Render system message #}\n{{- \"<|start|>system<|message|>\" }}\n{{- build_system_message() }}\n{{- \"<|end|>\" }}\n\n{#- Extract developer message #}\n{%- if messages[0].role == \"developer\" or messages[0].role == \"system\" %}\n    {%- set developer_message = messages[0].content %}\n    {%- set loop_messages = messages[1:] %}\n{%- else %}\n    {%- set developer_message = \"\" %}\n    {%- set loop_messages = messages %}\n{%- endif %}\n\n{#- Render developer message #}\n{%- if developer_message or tools %}\n    {{- \"<|start|>developer<|message|>\" }}\n    {%- if developer_message %}\n        {{- \"# Instructions\n\n\" }}\n        {{- developer_message }}\n    {%- endif %}\n    {%- if tools -%}\n        {{- \"\n\n\" }}\n        {{- \"# Tools\n\n\" }}\n        {{- render_tool_namespace(\"functions\", tools) }}\n    {%- endif -%}\n    {{- \"<|end|>\" }}\n{%- endif %}\n\n{#- Render messages #}\n{%- set last_tool_call = namespace(name=none) %}\n{%- for message in loop_messages -%}\n    {#- At this point only assistant/user/tool messages should remain #}\n    {%- if message.role == 'assistant' -%}\n        {#- Checks to ensure the messages are being passed in the format we expect #}\n        {%- if \"content\" in message %}\n            {%- if \"<|channel|>analysis<|message|>\" in message.content or \"<|channel|>final<|message|>\" in message.content %}\n                {{- raise_exception(\"You have passed a message containing <|channel|> tags in the content field. Instead of doing this, you should pass analysis messages (the string between '<|message|>' and '<|end|>') in the 'thinking' field, and final messages (the string between '<|message|>' and '<|end|>') in the 'content' field.\") }}\n            {%- endif %}\n        {%- endif %}\n        {%- if \"thinking\" in message %}\n            {%- if \"<|channel|>analysis<|message|>\" in message.thinking or \"<|channel|>final<|message|>\" in message.thinking %}\n                {{- raise_exception(\"You have passed a message containing <|channel|> tags in the thinking field. Instead of doing this, you should pass analysis messages (the string between '<|message|>' and '<|end|>') in the 'thinking' field, and final messages (the string between '<|message|>' and '<|end|>') in the 'content' field.\") }}\n            {%- endif %}\n        {%- endif %}\n        {%- if \"tool_calls\" in message %}\n            {#- We assume max 1 tool call per message, and so we infer the tool call name #}\n            {#- in \"tool\" messages from the most recent assistant tool call name #}\n            {%- set tool_call = message.tool_calls[0] %}\n            {%- if tool_call.function %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {%- if message.content and message.thinking %}\n                {{- 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.\") }}\n            {%- elif message.content %}\n                {{- \"<|start|>assistant<|channel|>analysis<|message|>\" + message.content + \"<|end|>\" }}\n            {%- elif message.thinking %}\n                {{- \"<|start|>assistant<|channel|>analysis<|message|>\" + message.thinking + \"<|end|>\" }}\n            {%- endif %}\n            {{- \"<|start|>assistant to=\" }}\n            {{- \"functions.\" + tool_call.name + \"<|channel|>commentary json<|message|>\" }}\n            {{- tool_call.arguments|tojson }}\n            {{- \"<|end|>\" }}\n            {%- set last_tool_call.name = tool_call.name %}\n        {%- elif loop.last and not add_generation_prompt %}\n            {#- Only render the CoT if the final turn is an assistant turn and add_generation_prompt is false #}\n            {#- This is a situation that should only occur in training, never in inference. #}\n            {%- if \"thinking\" in message %}\n                {{- \"<|start|>assistant<|channel|>analysis<|message|>\" + message.thinking + \"<|end|>\" }}\n            {%- endif %}\n            {#- <|return|> indicates the end of generation, but <|end|> does not #}\n            {#- <|return|> should never be an input to the model, but we include it as the final token #}\n            {#- when training, so the model learns to emit it. #}\n            {{- \"<|start|>assistant<|channel|>final<|message|>\" + message.content + \"<|return|>\" }}\n        {%- else %}\n            {#- CoT is dropped during all previous turns, so we never render it for inference #}\n            {{- \"<|start|>assistant<|channel|>final<|message|>\" + message.content + \"<|end|>\" }}\n            {%- set last_tool_call.name = none %}\n        {%- endif %}\n    {%- elif message.role == 'tool' -%}\n        {%- if last_tool_call.name is none %}\n            {{- raise_exception(\"Message has tool role, but there was no previous assistant message with a tool call!\") }}\n        {%- endif %}\n        {{- \"<|start|>functions.\" + last_tool_call.name }}\n        {{- \" to=assistant<|channel|>commentary<|message|>\" + message.content|tojson + \"<|end|>\" }}\n    {%- elif message.role == 'user' -%}\n        {{- \"<|start|>user<|message|>\" + message.content + \"<|end|>\" }}\n    {%- endif -%}\n{%- endfor -%}\n\n{#- Generation prompt #}\n{%- if add_generation_prompt -%}\n<|start|>assistant\n{%- endif -%}"
+}

config.json

@@ -0,0 +1,88 @@
+{
+  "architectures": [
+    "GptOssForCausalLM"
+  ],
+  "attention_bias": true,
+  "attention_dropout": 0.0,
+  "eos_token_id": 200002,
+  "experts_per_token": 4,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2880,
+  "initial_context_length": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 2880,
+  "layer_types": [
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 131072,
+  "model_type": "gpt_oss",
+  "num_attention_heads": 64,
+  "num_experts_per_tok": 4,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "num_local_experts": 128,
+  "output_router_logits": false,
+  "pad_token_id": 199999,
+  "quantization_config": {
+    "modules_to_not_convert": [
+      "model.layers.*.self_attn",
+      "model.layers.*.mlp.router",
+      "model.embed_tokens",
+      "lm_head"
+    ],
+    "quant_method": "mxfp4"
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "beta_fast": 32.0,
+    "beta_slow": 1.0,
+    "factor": 32.0,
+    "original_max_position_embeddings": 4096,
+    "rope_type": "yarn",
+    "truncate": false
+  },
+  "rope_theta": 150000,
+  "router_aux_loss_coef": 0.9,
+  "sliding_window": 128,
+  "swiglu_limit": 7.0,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.55.0.dev0",
+  "use_cache": true,
+  "vocab_size": 201088
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "bos_token_id": 199998,
+  "do_sample": true,
+  "eos_token_id": [
+    200002,
+    199999
+  ],
+  "pad_token_id": 199999,
+  "transformers_version": "4.55.0.dev0"
+}

metal/model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f3d5b8a213f146ec29296dad5c3370844d95ba9d21e8dc49f7e61e6e9ee9042
+size 65238253568

model-00000-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:695218884684c611fe08a74751ee443f971e9bd9bc062edba822da3fe45969b7
+size 4625017896

model-00001-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a881aa5f561b26a22b14a8262aa61849ace349ffd73d74769e030ac90a1fcf8a
+size 4115586736

model-00002-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:022478dd04398c5bdb545a5be0a6437ecc2eb53d1dbd29edafcfff4b3ddf0a41
+size 4625017888

model-00003-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47aee9e7b9d5bedb215042c01ccededd9bd9c30b0dddea862dc2506b9d6c74de
+size 4115586752

model-00004-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6c2752acda607b1d5ca52df9e75c1b9b2761e6875ff10c9bd6ddac473c0262e
+size 4625017896

model-00005-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c8dd401544c31cb93b8459eee7da20ea2a07626a59455d7d92b85257df9b46c
+size 4115586696

model-00006-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28d839f2e027985a8b14e45f2323798862eddb7770ee9800ea6b7c803abee489
+size 4625017856

model-00007-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8958c5f183c04f6ea959cfd90562b5128124154b2bbf979b8a22b9405b30ed8
+size 4060267176

model-00008-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf1f2a88868ffc37d520dcf77d26f0e823710b5e682d473ff10f6974fa3b7517
+size 4625017896

model-00009-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f72d34a4004241b45c332b61f8ffa124e9a913bc1ab442b66e717d3e94e741ce
+size 4170906304

model-00010-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f48c867c2cb0a44bfc2f8768cb98e4aec9a350946fceacfebdcad5d32ad4a471
+size 4625017896

model-00011-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a06851b2cfd35f48722f823bc1ab8f7bcb4a878a5b8e975f4d3544f230454eeb
+size 4115586752

model-00012-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3af33667c307e20ae2a7648ea52653de46dd0171601ec5c696e47a2f5d5bf1e4
+size 4064660808

model-00013-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcbcb74b043e071d1e05471d500d74dcf661175e00878ed302ccdf1801a75aef
+size 4625017896

model-00014-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54b1be1609696c307cc5ca117b1fa54feaddebffa04e9c2db117652a01964230
+size 4115586736

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"total_size": 65248815744}, "weight_map": {"model.layers.25.mlp.experts.gate_up_proj_blocks": "model-00000-of-00014.safetensors", "model.layers.25.mlp.experts.gate_up_proj_scales": "model-00000-of-00014.safetensors", "model.layers.25.mlp.experts.down_proj_bias": "model-00000-of-00014.safetensors", "model.layers.25.mlp.experts.down_proj_blocks": "model-00000-of-00014.safetensors", "model.layers.25.mlp.experts.down_proj_scales": "model-00000-of-00014.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00000-of-00014.safetensors", "model.layers.26.input_layernorm.weight": "model-00000-of-00014.safetensors", "model.layers.26.self_attn.o_proj.bias": "model-00000-of-00014.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00000-of-00014.safetensors", "model.layers.26.self_attn.q_proj.bias": "model-00000-of-00014.safetensors", "model.layers.26.self_attn.k_proj.bias": "model-00000-of-00014.safetensors", "model.layers.26.self_attn.v_proj.bias": "model-00000-of-00014.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00000-of-00014.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00000-of-00014.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00000-of-00014.safetensors", "model.layers.26.self_attn.sinks": "model-00000-of-00014.safetensors", "model.layers.26.mlp.router.bias": "model-00000-of-00014.safetensors", "model.layers.26.mlp.router.weight": "model-00000-of-00014.safetensors", "model.layers.26.mlp.experts.gate_up_proj_bias": "model-00000-of-00014.safetensors", "model.layers.26.mlp.experts.gate_up_proj_blocks": "model-00000-of-00014.safetensors", "model.layers.26.mlp.experts.gate_up_proj_scales": "model-00000-of-00014.safetensors", "model.layers.26.mlp.experts.down_proj_bias": "model-00000-of-00014.safetensors", "model.layers.26.mlp.experts.down_proj_blocks": "model-00000-of-00014.safetensors", "model.layers.26.mlp.experts.down_proj_scales": "model-00000-of-00014.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00000-of-00014.safetensors", "model.layers.27.input_layernorm.weight": "model-00000-of-00014.safetensors", "model.layers.27.self_attn.o_proj.bias": "model-00000-of-00014.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00000-of-00014.safetensors", "model.layers.27.self_attn.q_proj.bias": "model-00000-of-00014.safetensors", "model.layers.27.self_attn.k_proj.bias": "model-00000-of-00014.safetensors", "model.layers.27.self_attn.v_proj.bias": "model-00000-of-00014.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00000-of-00014.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00000-of-00014.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00000-of-00014.safetensors", "model.layers.27.self_attn.sinks": "model-00000-of-00014.safetensors", "model.layers.27.mlp.router.bias": "model-00000-of-00014.safetensors", "model.layers.27.mlp.router.weight": "model-00000-of-00014.safetensors", "model.layers.27.mlp.experts.gate_up_proj_bias": "model-00000-of-00014.safetensors", "model.layers.27.mlp.experts.gate_up_proj_blocks": "model-00000-of-00014.safetensors", "model.layers.27.mlp.experts.gate_up_proj_scales": "model-00000-of-00014.safetensors", "model.layers.27.mlp.experts.down_proj_bias": "model-00000-of-00014.safetensors", "model.layers.27.mlp.experts.down_proj_blocks": "model-00001-of-00014.safetensors", "model.layers.27.mlp.experts.down_proj_scales": "model-00001-of-00014.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.28.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.28.self_attn.o_proj.bias": "model-00001-of-00014.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00014.safetensors", "model.layers.28.self_attn.q_proj.bias": "model-00001-of-00014.safetensors", "model.layers.28.self_attn.k_proj.bias": "model-00001-of-00014.safetensors", "model.layers.28.self_attn.v_proj.bias": "model-00001-of-00014.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00014.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00014.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00014.safetensors", "model.layers.28.self_attn.sinks": "model-00001-of-00014.safetensors", "model.layers.28.mlp.router.bias": "model-00001-of-00014.safetensors", "model.layers.28.mlp.router.weight": "model-00001-of-00014.safetensors", "model.layers.28.mlp.experts.gate_up_proj_bias": "model-00001-of-00014.safetensors", "model.layers.28.mlp.experts.gate_up_proj_blocks": "model-00001-of-00014.safetensors", "model.layers.28.mlp.experts.gate_up_proj_scales": "model-00001-of-00014.safetensors", "model.layers.28.mlp.experts.down_proj_bias": "model-00001-of-00014.safetensors", "model.layers.28.mlp.experts.down_proj_blocks": "model-00001-of-00014.safetensors", "model.layers.28.mlp.experts.down_proj_scales": "model-00001-of-00014.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.29.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.29.self_attn.o_proj.bias": "model-00001-of-00014.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00014.safetensors", "model.layers.29.self_attn.q_proj.bias": "model-00001-of-00014.safetensors", "model.layers.29.self_attn.k_proj.bias": "model-00001-of-00014.safetensors", "model.layers.29.self_attn.v_proj.bias": "model-00001-of-00014.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00014.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00014.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00014.safetensors", "model.layers.29.self_attn.sinks": "model-00001-of-00014.safetensors", "model.layers.29.mlp.router.bias": "model-00001-of-00014.safetensors", "model.layers.29.mlp.router.weight": "model-00001-of-00014.safetensors", "model.layers.29.mlp.experts.gate_up_proj_bias": "model-00001-of-00014.safetensors", "model.layers.29.mlp.experts.gate_up_proj_blocks": "model-00001-of-00014.safetensors", "model.layers.29.mlp.experts.gate_up_proj_scales": "model-00001-of-00014.safetensors", "model.layers.29.mlp.experts.down_proj_bias": "model-00001-of-00014.safetensors", "model.layers.29.mlp.experts.down_proj_blocks": "model-00001-of-00014.safetensors", "model.layers.29.mlp.experts.down_proj_scales": "model-00001-of-00014.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.3.self_attn.o_proj.bias": "model-00001-of-00014.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00014.safetensors", "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00014.safetensors", "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00014.safetensors", "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00014.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00014.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00014.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00014.safetensors", "model.layers.3.self_attn.sinks": "model-00001-of-00014.safetensors", "model.layers.3.mlp.router.bias": "model-00001-of-00014.safetensors", "model.layers.3.mlp.router.weight": "model-00001-of-00014.safetensors", "model.layers.3.mlp.experts.gate_up_proj_bias": "model-00001-of-00014.safetensors", "model.layers.3.mlp.experts.gate_up_proj_blocks": "model-00002-of-00014.safetensors", "model.layers.3.mlp.experts.gate_up_proj_scales": "model-00002-of-00014.safetensors", "model.layers.3.mlp.experts.down_proj_bias": "model-00002-of-00014.safetensors", "model.layers.3.mlp.experts.down_proj_blocks": "model-00002-of-00014.safetensors", "model.layers.3.mlp.experts.down_proj_scales": "model-00002-of-00014.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.30.input_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.30.self_attn.o_proj.bias": "model-00002-of-00014.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", "model.layers.30.self_attn.q_proj.bias": "model-00002-of-00014.safetensors", "model.layers.30.self_attn.k_proj.bias": "model-00002-of-00014.safetensors", "model.layers.30.self_attn.v_proj.bias": "model-00002-of-00014.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", "model.layers.30.self_attn.sinks": "model-00002-of-00014.safetensors", "model.layers.30.mlp.router.bias": "model-00002-of-00014.safetensors", "model.layers.30.mlp.router.weight": "model-00002-of-00014.safetensors", "model.layers.30.mlp.experts.gate_up_proj_bias": "model-00002-of-00014.safetensors", "model.layers.2.mlp.experts.gate_up_proj_blocks": "model-00002-of-00014.safetensors", "model.layers.2.mlp.experts.gate_up_proj_scales": "model-00002-of-00014.safetensors", "model.layers.2.mlp.experts.down_proj_bias": "model-00002-of-00014.safetensors", "model.layers.2.mlp.experts.down_proj_blocks": "model-00002-of-00014.safetensors", "model.layers.2.mlp.experts.down_proj_scales": "model-00002-of-00014.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.20.input_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.20.self_attn.o_proj.bias": "model-00002-of-00014.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", "model.layers.20.self_attn.q_proj.bias": "model-00002-of-00014.safetensors", "model.layers.20.self_attn.k_proj.bias": "model-00002-of-00014.safetensors", "model.layers.20.self_attn.v_proj.bias": "model-00002-of-00014.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", "model.layers.20.self_attn.sinks": "model-00002-of-00014.safetensors", "model.layers.20.mlp.router.bias": "model-00002-of-00014.safetensors", "model.layers.20.mlp.router.weight": "model-00002-of-00014.safetensors", "model.layers.20.mlp.experts.gate_up_proj_bias": "model-00002-of-00014.safetensors", "model.layers.20.mlp.experts.gate_up_proj_blocks": "model-00002-of-00014.safetensors", "model.layers.20.mlp.experts.gate_up_proj_scales": "model-00002-of-00014.safetensors", "model.layers.20.mlp.experts.down_proj_bias": "model-00002-of-00014.safetensors", "model.layers.20.mlp.experts.down_proj_blocks": "model-00003-of-00014.safetensors", "model.layers.20.mlp.experts.down_proj_scales": "model-00003-of-00014.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.21.self_attn.o_proj.bias": "model-00003-of-00014.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00014.safetensors", "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00014.safetensors", "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00014.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", "model.layers.21.self_attn.sinks": "model-00003-of-00014.safetensors", "model.layers.21.mlp.router.bias": "model-00003-of-00014.safetensors", "model.layers.21.mlp.router.weight": "model-00003-of-00014.safetensors", "model.layers.21.mlp.experts.gate_up_proj_bias": "model-00003-of-00014.safetensors", "model.layers.21.mlp.experts.gate_up_proj_blocks": "model-00003-of-00014.safetensors", "model.layers.21.mlp.experts.gate_up_proj_scales": "model-00003-of-00014.safetensors", "model.layers.21.mlp.experts.down_proj_bias": "model-00003-of-00014.safetensors", "model.layers.21.mlp.experts.down_proj_blocks": "model-00003-of-00014.safetensors", "model.layers.21.mlp.experts.down_proj_scales": "model-00003-of-00014.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.22.self_attn.o_proj.bias": "model-00003-of-00014.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00014.safetensors", "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00014.safetensors", "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00014.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", "model.layers.22.self_attn.sinks": "model-00003-of-00014.safetensors", "model.layers.22.mlp.router.bias": "model-00003-of-00014.safetensors", "model.layers.22.mlp.router.weight": "model-00003-of-00014.safetensors", "model.layers.22.mlp.experts.gate_up_proj_bias": "model-00003-of-00014.safetensors", "model.layers.22.mlp.experts.gate_up_proj_blocks": "model-00003-of-00014.safetensors", "model.layers.22.mlp.experts.gate_up_proj_scales": "model-00003-of-00014.safetensors", "model.layers.22.mlp.experts.down_proj_bias": "model-00003-of-00014.safetensors", "model.layers.22.mlp.experts.down_proj_blocks": "model-00003-of-00014.safetensors", "model.layers.22.mlp.experts.down_proj_scales": "model-00003-of-00014.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.23.self_attn.o_proj.bias": "model-00003-of-00014.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00014.safetensors", "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00014.safetensors", "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00014.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", "model.layers.23.self_attn.sinks": "model-00003-of-00014.safetensors", "model.layers.23.mlp.router.bias": "model-00003-of-00014.safetensors", "model.layers.23.mlp.router.weight": "model-00003-of-00014.safetensors", "model.layers.23.mlp.experts.gate_up_proj_bias": "model-00003-of-00014.safetensors", "model.layers.23.mlp.experts.gate_up_proj_blocks": "model-00004-of-00014.safetensors", "model.layers.23.mlp.experts.gate_up_proj_scales": "model-00004-of-00014.safetensors", "model.layers.23.mlp.experts.down_proj_bias": "model-00004-of-00014.safetensors", "model.layers.23.mlp.experts.down_proj_blocks": "model-00004-of-00014.safetensors", "model.layers.23.mlp.experts.down_proj_scales": "model-00004-of-00014.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.24.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.24.self_attn.o_proj.bias": "model-00004-of-00014.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", "model.layers.24.self_attn.q_proj.bias": "model-00004-of-00014.safetensors", "model.layers.24.self_attn.k_proj.bias": "model-00004-of-00014.safetensors", "model.layers.24.self_attn.v_proj.bias": "model-00004-of-00014.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", "model.layers.24.self_attn.sinks": "model-00004-of-00014.safetensors", "model.layers.24.mlp.router.bias": "model-00004-of-00014.safetensors", "model.layers.24.mlp.router.weight": "model-00004-of-00014.safetensors", "model.layers.24.mlp.experts.gate_up_proj_bias": "model-00004-of-00014.safetensors", "model.layers.24.mlp.experts.gate_up_proj_blocks": "model-00004-of-00014.safetensors", "model.layers.24.mlp.experts.gate_up_proj_scales": "model-00004-of-00014.safetensors", "model.layers.24.mlp.experts.down_proj_bias": "model-00004-of-00014.safetensors", "model.layers.24.mlp.experts.down_proj_blocks": "model-00004-of-00014.safetensors", "model.layers.24.mlp.experts.down_proj_scales": "model-00004-of-00014.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.25.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.25.self_attn.o_proj.bias": "model-00004-of-00014.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", "model.layers.25.self_attn.q_proj.bias": "model-00004-of-00014.safetensors", "model.layers.25.self_attn.k_proj.bias": "model-00004-of-00014.safetensors", "model.layers.25.self_attn.v_proj.bias": "model-00004-of-00014.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", "model.layers.25.self_attn.sinks": "model-00004-of-00014.safetensors", "model.layers.25.mlp.router.bias": "model-00004-of-00014.safetensors", "model.layers.25.mlp.router.weight": "model-00004-of-00014.safetensors", "model.layers.25.mlp.experts.gate_up_proj_bias": "model-00004-of-00014.safetensors", "model.layers.4.mlp.experts.gate_up_proj_blocks": "model-00004-of-00014.safetensors", "model.layers.4.mlp.experts.gate_up_proj_scales": "model-00004-of-00014.safetensors", "model.layers.4.mlp.experts.down_proj_bias": "model-00004-of-00014.safetensors", "model.layers.4.mlp.experts.down_proj_blocks": "model-00005-of-00014.safetensors", "model.layers.4.mlp.experts.down_proj_scales": "model-00005-of-00014.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.5.input_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.5.self_attn.o_proj.bias": "model-00005-of-00014.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.5.self_attn.q_proj.bias": "model-00005-of-00014.safetensors", "model.layers.5.self_attn.k_proj.bias": "model-00005-of-00014.safetensors", "model.layers.5.self_attn.v_proj.bias": "model-00005-of-00014.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.5.self_attn.sinks": "model-00005-of-00014.safetensors", "model.layers.5.mlp.router.bias": "model-00005-of-00014.safetensors", "model.layers.5.mlp.router.weight": "model-00005-of-00014.safetensors", "model.layers.5.mlp.experts.gate_up_proj_bias": "model-00005-of-00014.safetensors", "model.layers.5.mlp.experts.gate_up_proj_blocks": "model-00005-of-00014.safetensors", "model.layers.5.mlp.experts.gate_up_proj_scales": "model-00005-of-00014.safetensors", "model.layers.5.mlp.experts.down_proj_bias": "model-00005-of-00014.safetensors", "model.layers.5.mlp.experts.down_proj_blocks": "model-00005-of-00014.safetensors", "model.layers.5.mlp.experts.down_proj_scales": "model-00005-of-00014.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.6.input_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.6.self_attn.o_proj.bias": "model-00005-of-00014.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.6.self_attn.q_proj.bias": "model-00005-of-00014.safetensors", "model.layers.6.self_attn.k_proj.bias": "model-00005-of-00014.safetensors", "model.layers.6.self_attn.v_proj.bias": "model-00005-of-00014.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.6.self_attn.sinks": "model-00005-of-00014.safetensors", "model.layers.6.mlp.router.bias": "model-00005-of-00014.safetensors", "model.layers.6.mlp.router.weight": "model-00005-of-00014.safetensors", "model.layers.6.mlp.experts.gate_up_proj_bias": "model-00005-of-00014.safetensors", "model.layers.6.mlp.experts.gate_up_proj_blocks": "model-00005-of-00014.safetensors", "model.layers.6.mlp.experts.gate_up_proj_scales": "model-00005-of-00014.safetensors", "model.layers.6.mlp.experts.down_proj_bias": "model-00005-of-00014.safetensors", "model.layers.6.mlp.experts.down_proj_blocks": "model-00005-of-00014.safetensors", "model.layers.6.mlp.experts.down_proj_scales": "model-00005-of-00014.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.7.input_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.7.self_attn.o_proj.bias": "model-00005-of-00014.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.7.self_attn.q_proj.bias": "model-00005-of-00014.safetensors", "model.layers.7.self_attn.k_proj.bias": "model-00005-of-00014.safetensors", "model.layers.7.self_attn.v_proj.bias": "model-00005-of-00014.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.7.self_attn.sinks": "model-00005-of-00014.safetensors", "model.layers.7.mlp.router.bias": "model-00005-of-00014.safetensors", "model.layers.7.mlp.router.weight": "model-00005-of-00014.safetensors", "model.layers.7.mlp.experts.gate_up_proj_bias": "model-00005-of-00014.safetensors", "model.layers.7.mlp.experts.gate_up_proj_blocks": "model-00006-of-00014.safetensors", "model.layers.7.mlp.experts.gate_up_proj_scales": "model-00006-of-00014.safetensors", "model.layers.7.mlp.experts.down_proj_bias": "model-00006-of-00014.safetensors", "model.layers.7.mlp.experts.down_proj_blocks": "model-00006-of-00014.safetensors", "model.layers.7.mlp.experts.down_proj_scales": "model-00006-of-00014.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.8.input_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.8.self_attn.o_proj.bias": "model-00006-of-00014.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", "model.layers.8.self_attn.q_proj.bias": "model-00006-of-00014.safetensors", "model.layers.8.self_attn.k_proj.bias": "model-00006-of-00014.safetensors", "model.layers.8.self_attn.v_proj.bias": "model-00006-of-00014.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", "model.layers.8.self_attn.sinks": "model-00006-of-00014.safetensors", "model.layers.8.mlp.router.bias": "model-00006-of-00014.safetensors", "model.layers.8.mlp.router.weight": "model-00006-of-00014.safetensors", "model.layers.8.mlp.experts.gate_up_proj_bias": "model-00006-of-00014.safetensors", "model.layers.8.mlp.experts.gate_up_proj_blocks": "model-00006-of-00014.safetensors", "model.layers.8.mlp.experts.gate_up_proj_scales": "model-00006-of-00014.safetensors", "model.layers.8.mlp.experts.down_proj_bias": "model-00006-of-00014.safetensors", "model.layers.8.mlp.experts.down_proj_blocks": "model-00006-of-00014.safetensors", "model.layers.8.mlp.experts.down_proj_scales": "model-00006-of-00014.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.9.input_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.9.self_attn.o_proj.bias": "model-00006-of-00014.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", "model.layers.9.self_attn.q_proj.bias": "model-00006-of-00014.safetensors", "model.layers.9.self_attn.k_proj.bias": "model-00006-of-00014.safetensors", "model.layers.9.self_attn.v_proj.bias": "model-00006-of-00014.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", "model.layers.9.self_attn.sinks": "model-00006-of-00014.safetensors", "model.layers.9.mlp.router.bias": "model-00006-of-00014.safetensors", "model.layers.9.mlp.router.weight": "model-00006-of-00014.safetensors", "model.layers.9.mlp.experts.gate_up_proj_bias": "model-00006-of-00014.safetensors", "model.layers.9.mlp.experts.gate_up_proj_blocks": "model-00006-of-00014.safetensors", "model.layers.9.mlp.experts.gate_up_proj_scales": "model-00006-of-00014.safetensors", "model.layers.9.mlp.experts.down_proj_bias": "model-00006-of-00014.safetensors", "model.layers.9.mlp.experts.down_proj_blocks": "model-00007-of-00014.safetensors", "model.layers.9.mlp.experts.down_proj_scales": "model-00007-of-00014.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.14.mlp.experts.gate_up_proj_blocks": "model-00007-of-00014.safetensors", "model.layers.14.mlp.experts.gate_up_proj_scales": "model-00007-of-00014.safetensors", "model.layers.14.mlp.experts.down_proj_bias": "model-00007-of-00014.safetensors", "model.layers.14.mlp.experts.down_proj_blocks": "model-00007-of-00014.safetensors", "model.layers.14.mlp.experts.down_proj_scales": "model-00007-of-00014.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.15.input_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.15.self_attn.o_proj.bias": "model-00007-of-00014.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", "model.layers.15.self_attn.q_proj.bias": "model-00007-of-00014.safetensors", "model.layers.15.self_attn.k_proj.bias": "model-00007-of-00014.safetensors", "model.layers.15.self_attn.v_proj.bias": "model-00007-of-00014.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", "model.layers.15.self_attn.sinks": "model-00007-of-00014.safetensors", "model.layers.15.mlp.router.bias": "model-00007-of-00014.safetensors", "model.layers.15.mlp.router.weight": "model-00007-of-00014.safetensors", "model.layers.15.mlp.experts.gate_up_proj_bias": "model-00007-of-00014.safetensors", "model.layers.15.mlp.experts.gate_up_proj_blocks": "model-00007-of-00014.safetensors", "model.layers.15.mlp.experts.gate_up_proj_scales": "model-00007-of-00014.safetensors", "model.layers.15.mlp.experts.down_proj_bias": "model-00007-of-00014.safetensors", "model.layers.15.mlp.experts.down_proj_blocks": "model-00007-of-00014.safetensors", "model.layers.15.mlp.experts.down_proj_scales": "model-00007-of-00014.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.16.input_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.16.self_attn.o_proj.bias": "model-00007-of-00014.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", "model.layers.16.self_attn.q_proj.bias": "model-00007-of-00014.safetensors", "model.layers.16.self_attn.k_proj.bias": "model-00007-of-00014.safetensors", "model.layers.16.self_attn.v_proj.bias": "model-00007-of-00014.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", "model.layers.16.self_attn.sinks": "model-00007-of-00014.safetensors", "model.layers.16.mlp.router.bias": "model-00007-of-00014.safetensors", "model.layers.16.mlp.router.weight": "model-00007-of-00014.safetensors", "model.layers.16.mlp.experts.gate_up_proj_bias": "model-00007-of-00014.safetensors", "model.layers.16.mlp.experts.gate_up_proj_blocks": "model-00008-of-00014.safetensors", "model.layers.16.mlp.experts.gate_up_proj_scales": "model-00008-of-00014.safetensors", "model.layers.16.mlp.experts.down_proj_bias": "model-00008-of-00014.safetensors", "model.layers.16.mlp.experts.down_proj_blocks": "model-00008-of-00014.safetensors", "model.layers.16.mlp.experts.down_proj_scales": "model-00008-of-00014.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.17.input_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.17.self_attn.o_proj.bias": "model-00008-of-00014.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.17.self_attn.q_proj.bias": "model-00008-of-00014.safetensors", "model.layers.17.self_attn.k_proj.bias": "model-00008-of-00014.safetensors", "model.layers.17.self_attn.v_proj.bias": "model-00008-of-00014.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", "model.layers.17.self_attn.sinks": "model-00008-of-00014.safetensors", "model.layers.17.mlp.router.bias": "model-00008-of-00014.safetensors", "model.layers.17.mlp.router.weight": "model-00008-of-00014.safetensors", "model.layers.17.mlp.experts.gate_up_proj_bias": "model-00008-of-00014.safetensors", "model.layers.17.mlp.experts.gate_up_proj_blocks": "model-00008-of-00014.safetensors", "model.layers.17.mlp.experts.gate_up_proj_scales": "model-00008-of-00014.safetensors", "model.layers.17.mlp.experts.down_proj_bias": "model-00008-of-00014.safetensors", "model.layers.17.mlp.experts.down_proj_blocks": "model-00008-of-00014.safetensors", "model.layers.17.mlp.experts.down_proj_scales": "model-00008-of-00014.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.18.input_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.18.self_attn.o_proj.bias": "model-00008-of-00014.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.18.self_attn.q_proj.bias": "model-00008-of-00014.safetensors", "model.layers.18.self_attn.k_proj.bias": "model-00008-of-00014.safetensors", "model.layers.18.self_attn.v_proj.bias": "model-00008-of-00014.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", "model.layers.18.self_attn.sinks": "model-00008-of-00014.safetensors", "model.layers.18.mlp.router.bias": "model-00008-of-00014.safetensors", "model.layers.18.mlp.router.weight": "model-00008-of-00014.safetensors", "model.layers.18.mlp.experts.gate_up_proj_bias": "model-00008-of-00014.safetensors", "model.layers.18.mlp.experts.gate_up_proj_blocks": "model-00008-of-00014.safetensors", "model.layers.18.mlp.experts.gate_up_proj_scales": "model-00008-of-00014.safetensors", "model.layers.18.mlp.experts.down_proj_bias": "model-00008-of-00014.safetensors", "model.layers.18.mlp.experts.down_proj_blocks": "model-00009-of-00014.safetensors", "model.layers.18.mlp.experts.down_proj_scales": "model-00009-of-00014.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.19.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.19.self_attn.o_proj.bias": "model-00009-of-00014.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.19.self_attn.q_proj.bias": "model-00009-of-00014.safetensors", "model.layers.19.self_attn.k_proj.bias": "model-00009-of-00014.safetensors", "model.layers.19.self_attn.v_proj.bias": "model-00009-of-00014.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.19.self_attn.sinks": "model-00009-of-00014.safetensors", "model.layers.19.mlp.router.bias": "model-00009-of-00014.safetensors", "model.layers.19.mlp.router.weight": "model-00009-of-00014.safetensors", "model.layers.19.mlp.experts.gate_up_proj_bias": "model-00009-of-00014.safetensors", "model.layers.19.mlp.experts.gate_up_proj_blocks": "model-00009-of-00014.safetensors", "model.layers.19.mlp.experts.gate_up_proj_scales": "model-00009-of-00014.safetensors", "model.layers.19.mlp.experts.down_proj_bias": "model-00009-of-00014.safetensors", "model.layers.19.mlp.experts.down_proj_blocks": "model-00009-of-00014.safetensors", "model.layers.19.mlp.experts.down_proj_scales": "model-00009-of-00014.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.2.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.2.self_attn.o_proj.bias": "model-00009-of-00014.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.2.self_attn.q_proj.bias": "model-00009-of-00014.safetensors", "model.layers.2.self_attn.k_proj.bias": "model-00009-of-00014.safetensors", "model.layers.2.self_attn.v_proj.bias": "model-00009-of-00014.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.2.self_attn.sinks": "model-00009-of-00014.safetensors", "model.layers.2.mlp.router.bias": "model-00009-of-00014.safetensors", "model.layers.2.mlp.router.weight": "model-00009-of-00014.safetensors", "model.layers.2.mlp.experts.gate_up_proj_bias": "model-00009-of-00014.safetensors", "model.layers.0.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.0.self_attn.o_proj.bias": "model-00009-of-00014.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.0.self_attn.q_proj.bias": "model-00009-of-00014.safetensors", "model.layers.0.self_attn.k_proj.bias": "model-00009-of-00014.safetensors", "model.layers.0.self_attn.v_proj.bias": "model-00009-of-00014.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.0.self_attn.sinks": "model-00009-of-00014.safetensors", "model.layers.0.mlp.router.bias": "model-00009-of-00014.safetensors", "model.layers.0.mlp.router.weight": "model-00009-of-00014.safetensors", "model.layers.0.mlp.experts.gate_up_proj_bias": "model-00009-of-00014.safetensors", "model.layers.0.mlp.experts.gate_up_proj_blocks": "model-00009-of-00014.safetensors", "model.layers.0.mlp.experts.gate_up_proj_scales": "model-00009-of-00014.safetensors", "model.layers.0.mlp.experts.down_proj_bias": "model-00009-of-00014.safetensors", "model.layers.0.mlp.experts.down_proj_blocks": "model-00009-of-00014.safetensors", "model.layers.0.mlp.experts.down_proj_scales": "model-00009-of-00014.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.1.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.1.self_attn.o_proj.bias": "model-00009-of-00014.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.1.self_attn.q_proj.bias": "model-00009-of-00014.safetensors", "model.layers.1.self_attn.k_proj.bias": "model-00009-of-00014.safetensors", "model.layers.1.self_attn.v_proj.bias": "model-00009-of-00014.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.1.self_attn.sinks": "model-00009-of-00014.safetensors", "model.layers.1.mlp.router.bias": "model-00009-of-00014.safetensors", "model.layers.1.mlp.router.weight": "model-00009-of-00014.safetensors", "model.layers.1.mlp.experts.gate_up_proj_bias": "model-00009-of-00014.safetensors", "model.layers.1.mlp.experts.gate_up_proj_blocks": "model-00010-of-00014.safetensors", "model.layers.1.mlp.experts.gate_up_proj_scales": "model-00010-of-00014.safetensors", "model.layers.1.mlp.experts.down_proj_bias": "model-00010-of-00014.safetensors", "model.layers.1.mlp.experts.down_proj_blocks": "model-00010-of-00014.safetensors", "model.layers.1.mlp.experts.down_proj_scales": "model-00010-of-00014.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.10.input_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.10.self_attn.o_proj.bias": "model-00010-of-00014.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", "model.layers.10.self_attn.q_proj.bias": "model-00010-of-00014.safetensors", "model.layers.10.self_attn.k_proj.bias": "model-00010-of-00014.safetensors", "model.layers.10.self_attn.v_proj.bias": "model-00010-of-00014.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", "model.layers.10.self_attn.sinks": "model-00010-of-00014.safetensors", "model.layers.10.mlp.router.bias": "model-00010-of-00014.safetensors", "model.layers.10.mlp.router.weight": "model-00010-of-00014.safetensors", "model.layers.10.mlp.experts.gate_up_proj_bias": "model-00010-of-00014.safetensors", "model.layers.10.mlp.experts.gate_up_proj_blocks": "model-00010-of-00014.safetensors", "model.layers.10.mlp.experts.gate_up_proj_scales": "model-00010-of-00014.safetensors", "model.layers.10.mlp.experts.down_proj_bias": "model-00010-of-00014.safetensors", "model.layers.10.mlp.experts.down_proj_blocks": "model-00010-of-00014.safetensors", "model.layers.10.mlp.experts.down_proj_scales": "model-00010-of-00014.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.11.input_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.11.self_attn.o_proj.bias": "model-00010-of-00014.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", "model.layers.11.self_attn.q_proj.bias": "model-00010-of-00014.safetensors", "model.layers.11.self_attn.k_proj.bias": "model-00010-of-00014.safetensors", "model.layers.11.self_attn.v_proj.bias": "model-00010-of-00014.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", "model.layers.11.self_attn.sinks": "model-00010-of-00014.safetensors", "model.layers.11.mlp.router.bias": "model-00010-of-00014.safetensors", "model.layers.11.mlp.router.weight": "model-00010-of-00014.safetensors", "model.layers.11.mlp.experts.gate_up_proj_bias": "model-00010-of-00014.safetensors", "model.layers.11.mlp.experts.gate_up_proj_blocks": "model-00010-of-00014.safetensors", "model.layers.11.mlp.experts.gate_up_proj_scales": "model-00010-of-00014.safetensors", "model.layers.11.mlp.experts.down_proj_bias": "model-00010-of-00014.safetensors", "model.layers.11.mlp.experts.down_proj_blocks": "model-00011-of-00014.safetensors", "model.layers.11.mlp.experts.down_proj_scales": "model-00011-of-00014.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.12.input_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.12.self_attn.o_proj.bias": "model-00011-of-00014.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.12.self_attn.q_proj.bias": "model-00011-of-00014.safetensors", "model.layers.12.self_attn.k_proj.bias": "model-00011-of-00014.safetensors", "model.layers.12.self_attn.v_proj.bias": "model-00011-of-00014.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", "model.layers.12.self_attn.sinks": "model-00011-of-00014.safetensors", "model.layers.12.mlp.router.bias": "model-00011-of-00014.safetensors", "model.layers.12.mlp.router.weight": "model-00011-of-00014.safetensors", "model.layers.12.mlp.experts.gate_up_proj_bias": "model-00011-of-00014.safetensors", "model.layers.12.mlp.experts.gate_up_proj_blocks": "model-00011-of-00014.safetensors", "model.layers.12.mlp.experts.gate_up_proj_scales": "model-00011-of-00014.safetensors", "model.layers.12.mlp.experts.down_proj_bias": "model-00011-of-00014.safetensors", "model.layers.12.mlp.experts.down_proj_blocks": "model-00011-of-00014.safetensors", "model.layers.12.mlp.experts.down_proj_scales": "model-00011-of-00014.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.13.input_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.13.self_attn.o_proj.bias": "model-00011-of-00014.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.13.self_attn.q_proj.bias": "model-00011-of-00014.safetensors", "model.layers.13.self_attn.k_proj.bias": "model-00011-of-00014.safetensors", "model.layers.13.self_attn.v_proj.bias": "model-00011-of-00014.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", "model.layers.13.self_attn.sinks": "model-00011-of-00014.safetensors", "model.layers.13.mlp.router.bias": "model-00011-of-00014.safetensors", "model.layers.13.mlp.router.weight": "model-00011-of-00014.safetensors", "model.layers.13.mlp.experts.gate_up_proj_bias": "model-00011-of-00014.safetensors", "model.layers.13.mlp.experts.gate_up_proj_blocks": "model-00011-of-00014.safetensors", "model.layers.13.mlp.experts.gate_up_proj_scales": "model-00011-of-00014.safetensors", "model.layers.13.mlp.experts.down_proj_bias": "model-00011-of-00014.safetensors", "model.layers.13.mlp.experts.down_proj_blocks": "model-00011-of-00014.safetensors", "model.layers.13.mlp.experts.down_proj_scales": "model-00011-of-00014.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.14.input_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.14.self_attn.o_proj.bias": "model-00011-of-00014.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.14.self_attn.q_proj.bias": "model-00011-of-00014.safetensors", "model.layers.14.self_attn.k_proj.bias": "model-00011-of-00014.safetensors", "model.layers.14.self_attn.v_proj.bias": "model-00011-of-00014.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", "model.layers.14.self_attn.sinks": "model-00011-of-00014.safetensors", "model.layers.14.mlp.router.bias": "model-00011-of-00014.safetensors", "model.layers.14.mlp.router.weight": "model-00011-of-00014.safetensors", "model.layers.14.mlp.experts.gate_up_proj_bias": "model-00011-of-00014.safetensors", "model.embed_tokens.weight": "model-00012-of-00014.safetensors", "model.norm.weight": "model-00012-of-00014.safetensors", "lm_head.weight": "model-00012-of-00014.safetensors", "model.layers.30.mlp.experts.gate_up_proj_blocks": "model-00012-of-00014.safetensors", "model.layers.30.mlp.experts.gate_up_proj_scales": "model-00012-of-00014.safetensors", "model.layers.30.mlp.experts.down_proj_bias": "model-00012-of-00014.safetensors", "model.layers.30.mlp.experts.down_proj_blocks": "model-00012-of-00014.safetensors", "model.layers.30.mlp.experts.down_proj_scales": "model-00012-of-00014.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.31.input_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.31.self_attn.o_proj.bias": "model-00012-of-00014.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", "model.layers.31.self_attn.q_proj.bias": "model-00012-of-00014.safetensors", "model.layers.31.self_attn.k_proj.bias": "model-00012-of-00014.safetensors", "model.layers.31.self_attn.v_proj.bias": "model-00012-of-00014.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", "model.layers.31.self_attn.sinks": "model-00012-of-00014.safetensors", "model.layers.31.mlp.router.bias": "model-00012-of-00014.safetensors", "model.layers.31.mlp.router.weight": "model-00012-of-00014.safetensors", "model.layers.31.mlp.experts.gate_up_proj_bias": "model-00012-of-00014.safetensors", "model.layers.31.mlp.experts.gate_up_proj_blocks": "model-00013-of-00014.safetensors", "model.layers.31.mlp.experts.gate_up_proj_scales": "model-00013-of-00014.safetensors", "model.layers.31.mlp.experts.down_proj_bias": "model-00013-of-00014.safetensors", "model.layers.31.mlp.experts.down_proj_blocks": "model-00013-of-00014.safetensors", "model.layers.31.mlp.experts.down_proj_scales": "model-00013-of-00014.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.32.input_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.32.self_attn.o_proj.bias": "model-00013-of-00014.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.32.self_attn.q_proj.bias": "model-00013-of-00014.safetensors", "model.layers.32.self_attn.k_proj.bias": "model-00013-of-00014.safetensors", "model.layers.32.self_attn.v_proj.bias": "model-00013-of-00014.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.32.self_attn.sinks": "model-00013-of-00014.safetensors", "model.layers.32.mlp.router.bias": "model-00013-of-00014.safetensors", "model.layers.32.mlp.router.weight": "model-00013-of-00014.safetensors", "model.layers.32.mlp.experts.gate_up_proj_bias": "model-00013-of-00014.safetensors", "model.layers.32.mlp.experts.gate_up_proj_blocks": "model-00013-of-00014.safetensors", "model.layers.32.mlp.experts.gate_up_proj_scales": "model-00013-of-00014.safetensors", "model.layers.32.mlp.experts.down_proj_bias": "model-00013-of-00014.safetensors", "model.layers.32.mlp.experts.down_proj_blocks": "model-00013-of-00014.safetensors", "model.layers.32.mlp.experts.down_proj_scales": "model-00013-of-00014.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.33.input_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.33.self_attn.o_proj.bias": "model-00013-of-00014.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.33.self_attn.q_proj.bias": "model-00013-of-00014.safetensors", "model.layers.33.self_attn.k_proj.bias": "model-00013-of-00014.safetensors", "model.layers.33.self_attn.v_proj.bias": "model-00013-of-00014.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.33.self_attn.sinks": "model-00013-of-00014.safetensors", "model.layers.33.mlp.router.bias": "model-00013-of-00014.safetensors", "model.layers.33.mlp.router.weight": "model-00013-of-00014.safetensors", "model.layers.33.mlp.experts.gate_up_proj_bias": "model-00013-of-00014.safetensors", "model.layers.33.mlp.experts.gate_up_proj_blocks": "model-00013-of-00014.safetensors", "model.layers.33.mlp.experts.gate_up_proj_scales": "model-00013-of-00014.safetensors", "model.layers.33.mlp.experts.down_proj_bias": "model-00013-of-00014.safetensors", "model.layers.33.mlp.experts.down_proj_blocks": "model-00014-of-00014.safetensors", "model.layers.33.mlp.experts.down_proj_scales": "model-00014-of-00014.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.34.input_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.34.self_attn.o_proj.bias": "model-00014-of-00014.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00014-of-00014.safetensors", "model.layers.34.self_attn.q_proj.bias": "model-00014-of-00014.safetensors", "model.layers.34.self_attn.k_proj.bias": "model-00014-of-00014.safetensors", "model.layers.34.self_attn.v_proj.bias": "model-00014-of-00014.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00014-of-00014.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00014-of-00014.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00014-of-00014.safetensors", "model.layers.34.self_attn.sinks": "model-00014-of-00014.safetensors", "model.layers.34.mlp.router.bias": "model-00014-of-00014.safetensors", "model.layers.34.mlp.router.weight": "model-00014-of-00014.safetensors", "model.layers.34.mlp.experts.gate_up_proj_bias": "model-00014-of-00014.safetensors", "model.layers.34.mlp.experts.gate_up_proj_blocks": "model-00014-of-00014.safetensors", "model.layers.34.mlp.experts.gate_up_proj_scales": "model-00014-of-00014.safetensors", "model.layers.34.mlp.experts.down_proj_bias": "model-00014-of-00014.safetensors", "model.layers.34.mlp.experts.down_proj_blocks": "model-00014-of-00014.safetensors", "model.layers.34.mlp.experts.down_proj_scales": "model-00014-of-00014.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.35.input_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.35.self_attn.o_proj.bias": "model-00014-of-00014.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00014-of-00014.safetensors", "model.layers.35.self_attn.q_proj.bias": "model-00014-of-00014.safetensors", "model.layers.35.self_attn.k_proj.bias": "model-00014-of-00014.safetensors", "model.layers.35.self_attn.v_proj.bias": "model-00014-of-00014.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00014-of-00014.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00014-of-00014.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00014-of-00014.safetensors", "model.layers.35.self_attn.sinks": "model-00014-of-00014.safetensors", "model.layers.35.mlp.router.bias": "model-00014-of-00014.safetensors", "model.layers.35.mlp.router.weight": "model-00014-of-00014.safetensors", "model.layers.35.mlp.experts.gate_up_proj_bias": "model-00014-of-00014.safetensors", "model.layers.35.mlp.experts.gate_up_proj_blocks": "model-00014-of-00014.safetensors", "model.layers.35.mlp.experts.gate_up_proj_scales": "model-00014-of-00014.safetensors", "model.layers.35.mlp.experts.down_proj_bias": "model-00014-of-00014.safetensors", "model.layers.35.mlp.experts.down_proj_blocks": "model-00014-of-00014.safetensors", "model.layers.35.mlp.experts.down_proj_scales": "model-00014-of-00014.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.4.input_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.4.self_attn.o_proj.bias": "model-00014-of-00014.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00014-of-00014.safetensors", "model.layers.4.self_attn.q_proj.bias": "model-00014-of-00014.safetensors", "model.layers.4.self_attn.k_proj.bias": "model-00014-of-00014.safetensors", "model.layers.4.self_attn.v_proj.bias": "model-00014-of-00014.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00014-of-00014.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00014-of-00014.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00014-of-00014.safetensors", "model.layers.4.self_attn.sinks": "model-00014-of-00014.safetensors", "model.layers.4.mlp.router.bias": "model-00014-of-00014.safetensors", "model.layers.4.mlp.router.weight": "model-00014-of-00014.safetensors", "model.layers.4.mlp.experts.gate_up_proj_bias": "model-00014-of-00014.safetensors"}}

original/config.json

@@ -0,0 +1 @@
+{"num_hidden_layers": 36, "num_experts": 128, "experts_per_token": 4, "vocab_size": 201088, "hidden_size": 2880, "intermediate_size": 2880, "swiglu_limit": 7.0, "head_dim": 64, "num_attention_heads": 64, "num_key_value_heads": 8, "sliding_window": 128, "initial_context_length": 4096, "rope_theta": 150000, "rope_scaling_factor": 32.0, "rope_ntk_alpha": 1, "rope_ntk_beta": 32}

original/dtypes.json

@@ -0,0 +1 @@
+{"embedding.weight": "BF16", "block.0.attn.norm.scale": "BF16", "block.0.attn.qkv.weight": "BF16", "block.0.attn.qkv.bias": "BF16", "block.0.attn.sinks": "BF16", "block.0.attn.out.weight": "BF16", "block.0.attn.out.bias": "BF16", "block.0.mlp.norm.scale": "BF16", "block.0.mlp.gate.weight": "BF16", "block.0.mlp.gate.bias": "BF16", "block.0.mlp.mlp1_weight.blocks": "FP4", "block.0.mlp.mlp1_weight.scales": "UE8", "block.0.mlp.mlp1_bias": "BF16", "block.0.mlp.mlp2_weight.blocks": "FP4", "block.0.mlp.mlp2_weight.scales": "UE8", "block.0.mlp.mlp2_bias": "BF16", "block.1.attn.norm.scale": "BF16", "block.1.attn.qkv.weight": "BF16", "block.1.attn.qkv.bias": "BF16", "block.1.attn.sinks": "BF16", "block.1.attn.out.weight": "BF16", "block.1.attn.out.bias": "BF16", "block.1.mlp.norm.scale": "BF16", "block.1.mlp.gate.weight": "BF16", "block.1.mlp.gate.bias": "BF16", "block.1.mlp.mlp1_weight.blocks": "FP4", "block.1.mlp.mlp1_weight.scales": "UE8", "block.1.mlp.mlp1_bias": "BF16", "block.1.mlp.mlp2_weight.blocks": "FP4", "block.1.mlp.mlp2_weight.scales": "UE8", "block.1.mlp.mlp2_bias": "BF16", "block.2.attn.norm.scale": "BF16", "block.2.attn.qkv.weight": "BF16", "block.2.attn.qkv.bias": "BF16", "block.2.attn.sinks": "BF16", "block.2.attn.out.weight": "BF16", "block.2.attn.out.bias": "BF16", "block.2.mlp.norm.scale": "BF16", "block.2.mlp.gate.weight": "BF16", "block.2.mlp.gate.bias": "BF16", "block.2.mlp.mlp1_weight.blocks": "FP4", "block.2.mlp.mlp1_weight.scales": "UE8", "block.2.mlp.mlp1_bias": "BF16", "block.2.mlp.mlp2_weight.blocks": "FP4", "block.2.mlp.mlp2_weight.scales": "UE8", "block.2.mlp.mlp2_bias": "BF16", "block.3.attn.norm.scale": "BF16", "block.3.attn.qkv.weight": "BF16", "block.3.attn.qkv.bias": "BF16", "block.3.attn.sinks": "BF16", "block.3.attn.out.weight": "BF16", "block.3.attn.out.bias": "BF16", "block.3.mlp.norm.scale": "BF16", "block.3.mlp.gate.weight": "BF16", "block.3.mlp.gate.bias": "BF16", "block.3.mlp.mlp1_weight.blocks": "FP4", "block.3.mlp.mlp1_weight.scales": "UE8", "block.3.mlp.mlp1_bias": "BF16", "block.3.mlp.mlp2_weight.blocks": "FP4", "block.3.mlp.mlp2_weight.scales": "UE8", "block.3.mlp.mlp2_bias": "BF16", "block.4.attn.norm.scale": "BF16", "block.4.attn.qkv.weight": "BF16", "block.4.attn.qkv.bias": "BF16", "block.4.attn.sinks": "BF16", "block.4.attn.out.weight": "BF16", "block.4.attn.out.bias": "BF16", "block.4.mlp.norm.scale": "BF16", "block.4.mlp.gate.weight": "BF16", "block.4.mlp.gate.bias": "BF16", "block.4.mlp.mlp1_weight.blocks": "FP4", "block.4.mlp.mlp1_weight.scales": "UE8", "block.4.mlp.mlp1_bias": "BF16", "block.4.mlp.mlp2_weight.blocks": "FP4", "block.4.mlp.mlp2_weight.scales": "UE8", "block.4.mlp.mlp2_bias": "BF16", "block.5.attn.norm.scale": "BF16", "block.5.attn.qkv.weight": "BF16", "block.5.attn.qkv.bias": "BF16", "block.5.attn.sinks": "BF16", "block.5.attn.out.weight": "BF16", "block.5.attn.out.bias": "BF16", "block.5.mlp.norm.scale": "BF16", "block.5.mlp.gate.weight": "BF16", "block.5.mlp.gate.bias": "BF16", "block.5.mlp.mlp1_weight.blocks": "FP4", "block.5.mlp.mlp1_weight.scales": "UE8", "block.5.mlp.mlp1_bias": "BF16", "block.5.mlp.mlp2_weight.blocks": "FP4", "block.5.mlp.mlp2_weight.scales": "UE8", "block.5.mlp.mlp2_bias": "BF16", "block.6.attn.norm.scale": "BF16", "block.6.attn.qkv.weight": "BF16", "block.6.attn.qkv.bias": "BF16", "block.6.attn.sinks": "BF16", "block.6.attn.out.weight": "BF16", "block.6.attn.out.bias": "BF16", "block.6.mlp.norm.scale": "BF16", "block.6.mlp.gate.weight": "BF16", "block.6.mlp.gate.bias": "BF16", "block.6.mlp.mlp1_weight.blocks": "FP4", "block.6.mlp.mlp1_weight.scales": "UE8", "block.6.mlp.mlp1_bias": "BF16", "block.6.mlp.mlp2_weight.blocks": "FP4", "block.6.mlp.mlp2_weight.scales": "UE8", "block.6.mlp.mlp2_bias": "BF16", "block.7.attn.norm.scale": "BF16", "block.7.attn.qkv.weight": "BF16", "block.7.attn.qkv.bias": "BF16", "block.7.attn.sinks": "BF16", "block.7.attn.out.weight": "BF16", "block.7.attn.out.bias": "BF16", "block.7.mlp.norm.scale": "BF16", "block.7.mlp.gate.weight": "BF16", "block.7.mlp.gate.bias": "BF16", "block.7.mlp.mlp1_weight.blocks": "FP4", "block.7.mlp.mlp1_weight.scales": "UE8", "block.7.mlp.mlp1_bias": "BF16", "block.7.mlp.mlp2_weight.blocks": "FP4", "block.7.mlp.mlp2_weight.scales": "UE8", "block.7.mlp.mlp2_bias": "BF16", "block.8.attn.norm.scale": "BF16", "block.8.attn.qkv.weight": "BF16", "block.8.attn.qkv.bias": "BF16", "block.8.attn.sinks": "BF16", "block.8.attn.out.weight": "BF16", "block.8.attn.out.bias": "BF16", "block.8.mlp.norm.scale": "BF16", "block.8.mlp.gate.weight": "BF16", "block.8.mlp.gate.bias": "BF16", "block.8.mlp.mlp1_weight.blocks": "FP4", "block.8.mlp.mlp1_weight.scales": "UE8", "block.8.mlp.mlp1_bias": "BF16", "block.8.mlp.mlp2_weight.blocks": "FP4", "block.8.mlp.mlp2_weight.scales": "UE8", "block.8.mlp.mlp2_bias": "BF16", "block.9.attn.norm.scale": "BF16", "block.9.attn.qkv.weight": "BF16", "block.9.attn.qkv.bias": "BF16", "block.9.attn.sinks": "BF16", "block.9.attn.out.weight": "BF16", "block.9.attn.out.bias": "BF16", "block.9.mlp.norm.scale": "BF16", "block.9.mlp.gate.weight": "BF16", "block.9.mlp.gate.bias": "BF16", "block.9.mlp.mlp1_weight.blocks": "FP4", "block.9.mlp.mlp1_weight.scales": "UE8", "block.9.mlp.mlp1_bias": "BF16", "block.9.mlp.mlp2_weight.blocks": "FP4", "block.9.mlp.mlp2_weight.scales": "UE8", "block.9.mlp.mlp2_bias": "BF16", "block.10.attn.norm.scale": "BF16", "block.10.attn.qkv.weight": "BF16", "block.10.attn.qkv.bias": "BF16", "block.10.attn.sinks": "BF16", "block.10.attn.out.weight": "BF16", "block.10.attn.out.bias": "BF16", "block.10.mlp.norm.scale": "BF16", "block.10.mlp.gate.weight": "BF16", "block.10.mlp.gate.bias": "BF16", "block.10.mlp.mlp1_weight.blocks": "FP4", "block.10.mlp.mlp1_weight.scales": "UE8", "block.10.mlp.mlp1_bias": "BF16", "block.10.mlp.mlp2_weight.blocks": "FP4", "block.10.mlp.mlp2_weight.scales": "UE8", "block.10.mlp.mlp2_bias": "BF16", "block.11.attn.norm.scale": "BF16", "block.11.attn.qkv.weight": "BF16", "block.11.attn.qkv.bias": "BF16", "block.11.attn.sinks": "BF16", "block.11.attn.out.weight": "BF16", "block.11.attn.out.bias": "BF16", "block.11.mlp.norm.scale": "BF16", "block.11.mlp.gate.weight": "BF16", "block.11.mlp.gate.bias": "BF16", "block.11.mlp.mlp1_weight.blocks": "FP4", "block.11.mlp.mlp1_weight.scales": "UE8", "block.11.mlp.mlp1_bias": "BF16", "block.11.mlp.mlp2_weight.blocks": "FP4", "block.11.mlp.mlp2_weight.scales": "UE8", "block.11.mlp.mlp2_bias": "BF16", "block.12.attn.norm.scale": "BF16", "block.12.attn.qkv.weight": "BF16", "block.12.attn.qkv.bias": "BF16", "block.12.attn.sinks": "BF16", "block.12.attn.out.weight": "BF16", "block.12.attn.out.bias": "BF16", "block.12.mlp.norm.scale": "BF16", "block.12.mlp.gate.weight": "BF16", "block.12.mlp.gate.bias": "BF16", "block.12.mlp.mlp1_weight.blocks": "FP4", "block.12.mlp.mlp1_weight.scales": "UE8", "block.12.mlp.mlp1_bias": "BF16", "block.12.mlp.mlp2_weight.blocks": "FP4", "block.12.mlp.mlp2_weight.scales": "UE8", "block.12.mlp.mlp2_bias": "BF16", "block.13.attn.norm.scale": "BF16", "block.13.attn.qkv.weight": "BF16", "block.13.attn.qkv.bias": "BF16", "block.13.attn.sinks": "BF16", "block.13.attn.out.weight": "BF16", "block.13.attn.out.bias": "BF16", "block.13.mlp.norm.scale": "BF16", "block.13.mlp.gate.weight": "BF16", "block.13.mlp.gate.bias": "BF16", "block.13.mlp.mlp1_weight.blocks": "FP4", "block.13.mlp.mlp1_weight.scales": "UE8", "block.13.mlp.mlp1_bias": "BF16", "block.13.mlp.mlp2_weight.blocks": "FP4", "block.13.mlp.mlp2_weight.scales": "UE8", "block.13.mlp.mlp2_bias": "BF16", "block.14.attn.norm.scale": "BF16", "block.14.attn.qkv.weight": "BF16", "block.14.attn.qkv.bias": "BF16", "block.14.attn.sinks": "BF16", "block.14.attn.out.weight": "BF16", "block.14.attn.out.bias": "BF16", "block.14.mlp.norm.scale": "BF16", "block.14.mlp.gate.weight": "BF16", "block.14.mlp.gate.bias": "BF16", "block.14.mlp.mlp1_weight.blocks": "FP4", "block.14.mlp.mlp1_weight.scales": "UE8", "block.14.mlp.mlp1_bias": "BF16", "block.14.mlp.mlp2_weight.blocks": "FP4", "block.14.mlp.mlp2_weight.scales": "UE8", "block.14.mlp.mlp2_bias": "BF16", "block.15.attn.norm.scale": "BF16", "block.15.attn.qkv.weight": "BF16", "block.15.attn.qkv.bias": "BF16", "block.15.attn.sinks": "BF16", "block.15.attn.out.weight": "BF16", "block.15.attn.out.bias": "BF16", "block.15.mlp.norm.scale": "BF16", "block.15.mlp.gate.weight": "BF16", "block.15.mlp.gate.bias": "BF16", "block.15.mlp.mlp1_weight.blocks": "FP4", "block.15.mlp.mlp1_weight.scales": "UE8", "block.15.mlp.mlp1_bias": "BF16", "block.15.mlp.mlp2_weight.blocks": "FP4", "block.15.mlp.mlp2_weight.scales": "UE8", "block.15.mlp.mlp2_bias": "BF16", "block.16.attn.norm.scale": "BF16", "block.16.attn.qkv.weight": "BF16", "block.16.attn.qkv.bias": "BF16", "block.16.attn.sinks": "BF16", "block.16.attn.out.weight": "BF16", "block.16.attn.out.bias": "BF16", "block.16.mlp.norm.scale": "BF16", "block.16.mlp.gate.weight": "BF16", "block.16.mlp.gate.bias": "BF16", "block.16.mlp.mlp1_weight.blocks": "FP4", "block.16.mlp.mlp1_weight.scales": "UE8", "block.16.mlp.mlp1_bias": "BF16", "block.16.mlp.mlp2_weight.blocks": "FP4", "block.16.mlp.mlp2_weight.scales": "UE8", "block.16.mlp.mlp2_bias": "BF16", "block.17.attn.norm.scale": "BF16", "block.17.attn.qkv.weight": "BF16", "block.17.attn.qkv.bias": "BF16", "block.17.attn.sinks": "BF16", "block.17.attn.out.weight": "BF16", "block.17.attn.out.bias": "BF16", "block.17.mlp.norm.scale": "BF16", "block.17.mlp.gate.weight": "BF16", "block.17.mlp.gate.bias": "BF16", "block.17.mlp.mlp1_weight.blocks": "FP4", "block.17.mlp.mlp1_weight.scales": "UE8", "block.17.mlp.mlp1_bias": "BF16", "block.17.mlp.mlp2_weight.blocks": "FP4", "block.17.mlp.mlp2_weight.scales": "UE8", "block.17.mlp.mlp2_bias": "BF16", "block.18.attn.norm.scale": "BF16", "block.18.attn.qkv.weight": "BF16", "block.18.attn.qkv.bias": "BF16", "block.18.attn.sinks": "BF16", "block.18.attn.out.weight": "BF16", "block.18.attn.out.bias": "BF16", "block.18.mlp.norm.scale": "BF16", "block.18.mlp.gate.weight": "BF16", "block.18.mlp.gate.bias": "BF16", "block.18.mlp.mlp1_weight.blocks": "FP4", "block.18.mlp.mlp1_weight.scales": "UE8", "block.18.mlp.mlp1_bias": "BF16", "block.18.mlp.mlp2_weight.blocks": "FP4", "block.18.mlp.mlp2_weight.scales": "UE8", "block.18.mlp.mlp2_bias": "BF16", "block.19.attn.norm.scale": "BF16", "block.19.attn.qkv.weight": "BF16", "block.19.attn.qkv.bias": "BF16", "block.19.attn.sinks": "BF16", "block.19.attn.out.weight": "BF16", "block.19.attn.out.bias": "BF16", "block.19.mlp.norm.scale": "BF16", "block.19.mlp.gate.weight": "BF16", "block.19.mlp.gate.bias": "BF16", "block.19.mlp.mlp1_weight.blocks": "FP4", "block.19.mlp.mlp1_weight.scales": "UE8", "block.19.mlp.mlp1_bias": "BF16", "block.19.mlp.mlp2_weight.blocks": "FP4", "block.19.mlp.mlp2_weight.scales": "UE8", "block.19.mlp.mlp2_bias": "BF16", "block.20.attn.norm.scale": "BF16", "block.20.attn.qkv.weight": "BF16", "block.20.attn.qkv.bias": "BF16", "block.20.attn.sinks": "BF16", "block.20.attn.out.weight": "BF16", "block.20.attn.out.bias": "BF16", "block.20.mlp.norm.scale": "BF16", "block.20.mlp.gate.weight": "BF16", "block.20.mlp.gate.bias": "BF16", "block.20.mlp.mlp1_weight.blocks": "FP4", "block.20.mlp.mlp1_weight.scales": "UE8", "block.20.mlp.mlp1_bias": "BF16", "block.20.mlp.mlp2_weight.blocks": "FP4", "block.20.mlp.mlp2_weight.scales": "UE8", "block.20.mlp.mlp2_bias": "BF16", "block.21.attn.norm.scale": "BF16", "block.21.attn.qkv.weight": "BF16", "block.21.attn.qkv.bias": "BF16", "block.21.attn.sinks": "BF16", "block.21.attn.out.weight": "BF16", "block.21.attn.out.bias": "BF16", "block.21.mlp.norm.scale": "BF16", "block.21.mlp.gate.weight": "BF16", "block.21.mlp.gate.bias": "BF16", "block.21.mlp.mlp1_weight.blocks": "FP4", "block.21.mlp.mlp1_weight.scales": "UE8", "block.21.mlp.mlp1_bias": "BF16", "block.21.mlp.mlp2_weight.blocks": "FP4", "block.21.mlp.mlp2_weight.scales": "UE8", "block.21.mlp.mlp2_bias": "BF16", "block.22.attn.norm.scale": "BF16", "block.22.attn.qkv.weight": "BF16", "block.22.attn.qkv.bias": "BF16", "block.22.attn.sinks": "BF16", "block.22.attn.out.weight": "BF16", "block.22.attn.out.bias": "BF16", "block.22.mlp.norm.scale": "BF16", "block.22.mlp.gate.weight": "BF16", "block.22.mlp.gate.bias": "BF16", "block.22.mlp.mlp1_weight.blocks": "FP4", "block.22.mlp.mlp1_weight.scales": "UE8", "block.22.mlp.mlp1_bias": "BF16", "block.22.mlp.mlp2_weight.blocks": "FP4", "block.22.mlp.mlp2_weight.scales": "UE8", "block.22.mlp.mlp2_bias": "BF16", "block.23.attn.norm.scale": "BF16", "block.23.attn.qkv.weight": "BF16", "block.23.attn.qkv.bias": "BF16", "block.23.attn.sinks": "BF16", "block.23.attn.out.weight": "BF16", "block.23.attn.out.bias": "BF16", "block.23.mlp.norm.scale": "BF16", "block.23.mlp.gate.weight": "BF16", "block.23.mlp.gate.bias": "BF16", "block.23.mlp.mlp1_weight.blocks": "FP4", "block.23.mlp.mlp1_weight.scales": "UE8", "block.23.mlp.mlp1_bias": "BF16", "block.23.mlp.mlp2_weight.blocks": "FP4", "block.23.mlp.mlp2_weight.scales": "UE8", "block.23.mlp.mlp2_bias": "BF16", "block.24.attn.norm.scale": "BF16", "block.24.attn.qkv.weight": "BF16", "block.24.attn.qkv.bias": "BF16", "block.24.attn.sinks": "BF16", "block.24.attn.out.weight": "BF16", "block.24.attn.out.bias": "BF16", "block.24.mlp.norm.scale": "BF16", "block.24.mlp.gate.weight": "BF16", "block.24.mlp.gate.bias": "BF16", "block.24.mlp.mlp1_weight.blocks": "FP4", "block.24.mlp.mlp1_weight.scales": "UE8", "block.24.mlp.mlp1_bias": "BF16", "block.24.mlp.mlp2_weight.blocks": "FP4", "block.24.mlp.mlp2_weight.scales": "UE8", "block.24.mlp.mlp2_bias": "BF16", "block.25.attn.norm.scale": "BF16", "block.25.attn.qkv.weight": "BF16", "block.25.attn.qkv.bias": "BF16", "block.25.attn.sinks": "BF16", "block.25.attn.out.weight": "BF16", "block.25.attn.out.bias": "BF16", "block.25.mlp.norm.scale": "BF16", "block.25.mlp.gate.weight": "BF16", "block.25.mlp.gate.bias": "BF16", "block.25.mlp.mlp1_weight.blocks": "FP4", "block.25.mlp.mlp1_weight.scales": "UE8", "block.25.mlp.mlp1_bias": "BF16", "block.25.mlp.mlp2_weight.blocks": "FP4", "block.25.mlp.mlp2_weight.scales": "UE8", "block.25.mlp.mlp2_bias": "BF16", "block.26.attn.norm.scale": "BF16", "block.26.attn.qkv.weight": "BF16", "block.26.attn.qkv.bias": "BF16", "block.26.attn.sinks": "BF16", "block.26.attn.out.weight": "BF16", "block.26.attn.out.bias": "BF16", "block.26.mlp.norm.scale": "BF16", "block.26.mlp.gate.weight": "BF16", "block.26.mlp.gate.bias": "BF16", "block.26.mlp.mlp1_weight.blocks": "FP4", "block.26.mlp.mlp1_weight.scales": "UE8", "block.26.mlp.mlp1_bias": "BF16", "block.26.mlp.mlp2_weight.blocks": "FP4", "block.26.mlp.mlp2_weight.scales": "UE8", "block.26.mlp.mlp2_bias": "BF16", "block.27.attn.norm.scale": "BF16", "block.27.attn.qkv.weight": "BF16", "block.27.attn.qkv.bias": "BF16", "block.27.attn.sinks": "BF16", "block.27.attn.out.weight": "BF16", "block.27.attn.out.bias": "BF16", "block.27.mlp.norm.scale": "BF16", "block.27.mlp.gate.weight": "BF16", "block.27.mlp.gate.bias": "BF16", "block.27.mlp.mlp1_weight.blocks": "FP4", "block.27.mlp.mlp1_weight.scales": "UE8", "block.27.mlp.mlp1_bias": "BF16", "block.27.mlp.mlp2_weight.blocks": "FP4", "block.27.mlp.mlp2_weight.scales": "UE8", "block.27.mlp.mlp2_bias": "BF16", "block.28.attn.norm.scale": "BF16", "block.28.attn.qkv.weight": "BF16", "block.28.attn.qkv.bias": "BF16", "block.28.attn.sinks": "BF16", "block.28.attn.out.weight": "BF16", "block.28.attn.out.bias": "BF16", "block.28.mlp.norm.scale": "BF16", "block.28.mlp.gate.weight": "BF16", "block.28.mlp.gate.bias": "BF16", "block.28.mlp.mlp1_weight.blocks": "FP4", "block.28.mlp.mlp1_weight.scales": "UE8", "block.28.mlp.mlp1_bias": "BF16", "block.28.mlp.mlp2_weight.blocks": "FP4", "block.28.mlp.mlp2_weight.scales": "UE8", "block.28.mlp.mlp2_bias": "BF16", "block.29.attn.norm.scale": "BF16", "block.29.attn.qkv.weight": "BF16", "block.29.attn.qkv.bias": "BF16", "block.29.attn.sinks": "BF16", "block.29.attn.out.weight": "BF16", "block.29.attn.out.bias": "BF16", "block.29.mlp.norm.scale": "BF16", "block.29.mlp.gate.weight": "BF16", "block.29.mlp.gate.bias": "BF16", "block.29.mlp.mlp1_weight.blocks": "FP4", "block.29.mlp.mlp1_weight.scales": "UE8", "block.29.mlp.mlp1_bias": "BF16", "block.29.mlp.mlp2_weight.blocks": "FP4", "block.29.mlp.mlp2_weight.scales": "UE8", "block.29.mlp.mlp2_bias": "BF16", "block.30.attn.norm.scale": "BF16", "block.30.attn.qkv.weight": "BF16", "block.30.attn.qkv.bias": "BF16", "block.30.attn.sinks": "BF16", "block.30.attn.out.weight": "BF16", "block.30.attn.out.bias": "BF16", "block.30.mlp.norm.scale": "BF16", "block.30.mlp.gate.weight": "BF16", "block.30.mlp.gate.bias": "BF16", "block.30.mlp.mlp1_weight.blocks": "FP4", "block.30.mlp.mlp1_weight.scales": "UE8", "block.30.mlp.mlp1_bias": "BF16", "block.30.mlp.mlp2_weight.blocks": "FP4", "block.30.mlp.mlp2_weight.scales": "UE8", "block.30.mlp.mlp2_bias": "BF16", "block.31.attn.norm.scale": "BF16", "block.31.attn.qkv.weight": "BF16", "block.31.attn.qkv.bias": "BF16", "block.31.attn.sinks": "BF16", "block.31.attn.out.weight": "BF16", "block.31.attn.out.bias": "BF16", "block.31.mlp.norm.scale": "BF16", "block.31.mlp.gate.weight": "BF16", "block.31.mlp.gate.bias": "BF16", "block.31.mlp.mlp1_weight.blocks": "FP4", "block.31.mlp.mlp1_weight.scales": "UE8", "block.31.mlp.mlp1_bias": "BF16", "block.31.mlp.mlp2_weight.blocks": "FP4", "block.31.mlp.mlp2_weight.scales": "UE8", "block.31.mlp.mlp2_bias": "BF16", "block.32.attn.norm.scale": "BF16", "block.32.attn.qkv.weight": "BF16", "block.32.attn.qkv.bias": "BF16", "block.32.attn.sinks": "BF16", "block.32.attn.out.weight": "BF16", "block.32.attn.out.bias": "BF16", "block.32.mlp.norm.scale": "BF16", "block.32.mlp.gate.weight": "BF16", "block.32.mlp.gate.bias": "BF16", "block.32.mlp.mlp1_weight.blocks": "FP4", "block.32.mlp.mlp1_weight.scales": "UE8", "block.32.mlp.mlp1_bias": "BF16", "block.32.mlp.mlp2_weight.blocks": "FP4", "block.32.mlp.mlp2_weight.scales": "UE8", "block.32.mlp.mlp2_bias": "BF16", "block.33.attn.norm.scale": "BF16", "block.33.attn.qkv.weight": "BF16", "block.33.attn.qkv.bias": "BF16", "block.33.attn.sinks": "BF16", "block.33.attn.out.weight": "BF16", "block.33.attn.out.bias": "BF16", "block.33.mlp.norm.scale": "BF16", "block.33.mlp.gate.weight": "BF16", "block.33.mlp.gate.bias": "BF16", "block.33.mlp.mlp1_weight.blocks": "FP4", "block.33.mlp.mlp1_weight.scales": "UE8", "block.33.mlp.mlp1_bias": "BF16", "block.33.mlp.mlp2_weight.blocks": "FP4", "block.33.mlp.mlp2_weight.scales": "UE8", "block.33.mlp.mlp2_bias": "BF16", "block.34.attn.norm.scale": "BF16", "block.34.attn.qkv.weight": "BF16", "block.34.attn.qkv.bias": "BF16", "block.34.attn.sinks": "BF16", "block.34.attn.out.weight": "BF16", "block.34.attn.out.bias": "BF16", "block.34.mlp.norm.scale": "BF16", "block.34.mlp.gate.weight": "BF16", "block.34.mlp.gate.bias": "BF16", "block.34.mlp.mlp1_weight.blocks": "FP4", "block.34.mlp.mlp1_weight.scales": "UE8", "block.34.mlp.mlp1_bias": "BF16", "block.34.mlp.mlp2_weight.blocks": "FP4", "block.34.mlp.mlp2_weight.scales": "UE8", "block.34.mlp.mlp2_bias": "BF16", "block.35.attn.norm.scale": "BF16", "block.35.attn.qkv.weight": "BF16", "block.35.attn.qkv.bias": "BF16", "block.35.attn.sinks": "BF16", "block.35.attn.out.weight": "BF16", "block.35.attn.out.bias": "BF16", "block.35.mlp.norm.scale": "BF16", "block.35.mlp.gate.weight": "BF16", "block.35.mlp.gate.bias": "BF16", "block.35.mlp.mlp1_weight.blocks": "FP4", "block.35.mlp.mlp1_weight.scales": "UE8", "block.35.mlp.mlp1_bias": "BF16", "block.35.mlp.mlp2_weight.blocks": "FP4", "block.35.mlp.mlp2_weight.scales": "UE8", "block.35.mlp.mlp2_bias": "BF16", "norm.scale": "BF16", "unembedding.weight": "BF16"}

original/model--00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68a8dc1f8e2e5996cb702f14332a25ddf3463daeab2df68e21ca09ef181203c3
+size 10544040680

original/model--00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19b8f0d5c7dc3195c61a711d08384a1f85624f018186da541585c0f97ac61020
+size 10488721680

original/model--00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0dbccd746d50e9543e8016d0a43ab4487c7f86d72349b1ef17abdfec509d0701
+size 10488721688

original/model--00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcc73cf6d18f96a2e62428758463157cc12768f410873152a50d3929a64cd049
+size 10488721672

original/model--00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15fd69843e9cc6fdf2db0efe0cf0979b49a6ba84b3a38169b2fabc5479d04a7d
+size 10488721680

original/model--00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3aedef2ee0a5a78a003b3f74fd6883033946b80097bf41e4f4715d95066f0588
+size 10433402600

original/model--00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20d5dfcad1ed6c50aa3c0da7d3f08828dba72b5f58686a987bf3a8f01659cda6
+size 2316539800

original/model.safetensors.index.json

@@ -0,0 +1,550 @@
+{
+  "metadata": {
+    "total_size": 65248815744
+  },
+  "weight_map": {
+    "block.0.attn.norm.scale": "model--00001-of-00007.safetensors",
+    "block.0.attn.out.bias": "model--00001-of-00007.safetensors",
+    "block.0.attn.out.weight": "model--00001-of-00007.safetensors",
+    "block.0.attn.qkv.bias": "model--00001-of-00007.safetensors",
+    "block.0.attn.qkv.weight": "model--00001-of-00007.safetensors",
+    "block.0.attn.sinks": "model--00001-of-00007.safetensors",
+    "block.0.mlp.gate.bias": "model--00001-of-00007.safetensors",
+    "block.0.mlp.gate.weight": "model--00001-of-00007.safetensors",
+    "block.0.mlp.mlp1_bias": "model--00001-of-00007.safetensors",
+    "block.0.mlp.mlp1_weight.blocks": "model--00001-of-00007.safetensors",
+    "block.0.mlp.mlp1_weight.scales": "model--00001-of-00007.safetensors",
+    "block.0.mlp.mlp2_bias": "model--00001-of-00007.safetensors",
+    "block.0.mlp.mlp2_weight.blocks": "model--00001-of-00007.safetensors",
+    "block.0.mlp.mlp2_weight.scales": "model--00001-of-00007.safetensors",
+    "block.0.mlp.norm.scale": "model--00001-of-00007.safetensors",
+    "block.1.attn.norm.scale": "model--00001-of-00007.safetensors",
+    "block.1.attn.out.bias": "model--00001-of-00007.safetensors",
+    "block.1.attn.out.weight": "model--00001-of-00007.safetensors",
+    "block.1.attn.qkv.bias": "model--00001-of-00007.safetensors",
+    "block.1.attn.qkv.weight": "model--00001-of-00007.safetensors",
+    "block.1.attn.sinks": "model--00001-of-00007.safetensors",
+    "block.1.mlp.gate.bias": "model--00001-of-00007.safetensors",
+    "block.1.mlp.gate.weight": "model--00001-of-00007.safetensors",
+    "block.1.mlp.mlp1_bias": "model--00001-of-00007.safetensors",
+    "block.1.mlp.mlp1_weight.blocks": "model--00001-of-00007.safetensors",
+    "block.1.mlp.mlp1_weight.scales": "model--00001-of-00007.safetensors",
+    "block.1.mlp.mlp2_bias": "model--00001-of-00007.safetensors",
+    "block.1.mlp.mlp2_weight.blocks": "model--00001-of-00007.safetensors",
+    "block.1.mlp.mlp2_weight.scales": "model--00001-of-00007.safetensors",
+    "block.1.mlp.norm.scale": "model--00001-of-00007.safetensors",
+    "block.10.attn.norm.scale": "model--00001-of-00007.safetensors",
+    "block.10.attn.out.bias": "model--00001-of-00007.safetensors",
+    "block.10.attn.out.weight": "model--00001-of-00007.safetensors",
+    "block.10.attn.qkv.bias": "model--00001-of-00007.safetensors",
+    "block.10.attn.qkv.weight": "model--00001-of-00007.safetensors",
+    "block.10.attn.sinks": "model--00001-of-00007.safetensors",
+    "block.10.mlp.gate.bias": "model--00001-of-00007.safetensors",
+    "block.10.mlp.gate.weight": "model--00001-of-00007.safetensors",
+    "block.10.mlp.mlp1_bias": "model--00001-of-00007.safetensors",
+    "block.10.mlp.mlp1_weight.blocks": "model--00001-of-00007.safetensors",
+    "block.10.mlp.mlp1_weight.scales": "model--00001-of-00007.safetensors",
+    "block.10.mlp.mlp2_bias": "model--00001-of-00007.safetensors",
+    "block.10.mlp.mlp2_weight.blocks": "model--00001-of-00007.safetensors",
+    "block.10.mlp.mlp2_weight.scales": "model--00001-of-00007.safetensors",
+    "block.10.mlp.norm.scale": "model--00001-of-00007.safetensors",
+    "block.11.attn.norm.scale": "model--00001-of-00007.safetensors",
+    "block.11.attn.out.bias": "model--00001-of-00007.safetensors",
+    "block.11.attn.out.weight": "model--00001-of-00007.safetensors",
+    "block.11.attn.qkv.bias": "model--00001-of-00007.safetensors",
+    "block.11.attn.qkv.weight": "model--00001-of-00007.safetensors",
+    "block.11.attn.sinks": "model--00001-of-00007.safetensors",
+    "block.11.mlp.gate.bias": "model--00001-of-00007.safetensors",
+    "block.11.mlp.gate.weight": "model--00001-of-00007.safetensors",
+    "block.11.mlp.mlp1_bias": "model--00001-of-00007.safetensors",
+    "block.11.mlp.mlp1_weight.blocks": "model--00001-of-00007.safetensors",
+    "block.11.mlp.mlp1_weight.scales": "model--00001-of-00007.safetensors",
+    "block.11.mlp.mlp2_bias": "model--00001-of-00007.safetensors",
+    "block.11.mlp.mlp2_weight.blocks": "model--00001-of-00007.safetensors",
+    "block.11.mlp.mlp2_weight.scales": "model--00001-of-00007.safetensors",
+    "block.11.mlp.norm.scale": "model--00001-of-00007.safetensors",
+    "block.12.attn.norm.scale": "model--00001-of-00007.safetensors",
+    "block.12.attn.out.bias": "model--00001-of-00007.safetensors",
+    "block.12.attn.out.weight": "model--00001-of-00007.safetensors",
+    "block.12.attn.qkv.bias": "model--00001-of-00007.safetensors",
+    "block.12.attn.qkv.weight": "model--00001-of-00007.safetensors",
+    "block.12.attn.sinks": "model--00001-of-00007.safetensors",
+    "block.12.mlp.gate.bias": "model--00001-of-00007.safetensors",
+    "block.12.mlp.gate.weight": "model--00001-of-00007.safetensors",
+    "block.12.mlp.mlp1_bias": "model--00001-of-00007.safetensors",
+    "block.12.mlp.mlp1_weight.blocks": "model--00001-of-00007.safetensors",
+    "block.12.mlp.mlp1_weight.scales": "model--00001-of-00007.safetensors",
+    "block.12.mlp.mlp2_bias": "model--00001-of-00007.safetensors",
+    "block.12.mlp.mlp2_weight.blocks": "model--00001-of-00007.safetensors",
+    "block.12.mlp.mlp2_weight.scales": "model--00001-of-00007.safetensors",
+    "block.12.mlp.norm.scale": "model--00001-of-00007.safetensors",
+    "block.13.attn.norm.scale": "model--00001-of-00007.safetensors",
+    "block.13.attn.out.bias": "model--00001-of-00007.safetensors",
+    "block.13.attn.out.weight": "model--00001-of-00007.safetensors",
+    "block.13.attn.qkv.bias": "model--00001-of-00007.safetensors",
+    "block.13.attn.qkv.weight": "model--00001-of-00007.safetensors",
+    "block.13.attn.sinks": "model--00001-of-00007.safetensors",
+    "block.13.mlp.gate.bias": "model--00001-of-00007.safetensors",
+    "block.13.mlp.gate.weight": "model--00001-of-00007.safetensors",
+    "block.13.mlp.mlp1_bias": "model--00001-of-00007.safetensors",
+    "block.13.mlp.mlp1_weight.blocks": "model--00001-of-00007.safetensors",
+    "block.13.mlp.mlp1_weight.scales": "model--00001-of-00007.safetensors",
+    "block.13.mlp.mlp2_bias": "model--00001-of-00007.safetensors",
+    "block.13.mlp.mlp2_weight.blocks": "model--00001-of-00007.safetensors",
+    "block.13.mlp.mlp2_weight.scales": "model--00001-of-00007.safetensors",
+    "block.13.mlp.norm.scale": "model--00001-of-00007.safetensors",
+    "block.14.attn.norm.scale": "model--00001-of-00007.safetensors",
+    "block.14.attn.out.bias": "model--00001-of-00007.safetensors",
+    "block.14.attn.out.weight": "model--00001-of-00007.safetensors",
+    "block.14.attn.qkv.bias": "model--00001-of-00007.safetensors",
+    "block.14.attn.qkv.weight": "model--00001-of-00007.safetensors",
+    "block.14.attn.sinks": "model--00001-of-00007.safetensors",
+    "block.14.mlp.gate.bias": "model--00001-of-00007.safetensors",
+    "block.14.mlp.gate.weight": "model--00001-of-00007.safetensors",
+    "block.14.mlp.mlp1_bias": "model--00001-of-00007.safetensors",
+    "block.14.mlp.mlp1_weight.blocks": "model--00002-of-00007.safetensors",
+    "block.14.mlp.mlp1_weight.scales": "model--00002-of-00007.safetensors",
+    "block.14.mlp.mlp2_bias": "model--00002-of-00007.safetensors",
+    "block.14.mlp.mlp2_weight.blocks": "model--00002-of-00007.safetensors",
+    "block.14.mlp.mlp2_weight.scales": "model--00002-of-00007.safetensors",
+    "block.14.mlp.norm.scale": "model--00002-of-00007.safetensors",
+    "block.15.attn.norm.scale": "model--00002-of-00007.safetensors",
+    "block.15.attn.out.bias": "model--00002-of-00007.safetensors",
+    "block.15.attn.out.weight": "model--00002-of-00007.safetensors",
+    "block.15.attn.qkv.bias": "model--00002-of-00007.safetensors",
+    "block.15.attn.qkv.weight": "model--00002-of-00007.safetensors",
+    "block.15.attn.sinks": "model--00002-of-00007.safetensors",
+    "block.15.mlp.gate.bias": "model--00002-of-00007.safetensors",
+    "block.15.mlp.gate.weight": "model--00002-of-00007.safetensors",
+    "block.15.mlp.mlp1_bias": "model--00002-of-00007.safetensors",
+    "block.15.mlp.mlp1_weight.blocks": "model--00002-of-00007.safetensors",
+    "block.15.mlp.mlp1_weight.scales": "model--00002-of-00007.safetensors",
+    "block.15.mlp.mlp2_bias": "model--00002-of-00007.safetensors",
+    "block.15.mlp.mlp2_weight.blocks": "model--00002-of-00007.safetensors",
+    "block.15.mlp.mlp2_weight.scales": "model--00002-of-00007.safetensors",
+    "block.15.mlp.norm.scale": "model--00002-of-00007.safetensors",
+    "block.16.attn.norm.scale": "model--00002-of-00007.safetensors",
+    "block.16.attn.out.bias": "model--00002-of-00007.safetensors",
+    "block.16.attn.out.weight": "model--00002-of-00007.safetensors",
+    "block.16.attn.qkv.bias": "model--00002-of-00007.safetensors",
+    "block.16.attn.qkv.weight": "model--00002-of-00007.safetensors",
+    "block.16.attn.sinks": "model--00002-of-00007.safetensors",
+    "block.16.mlp.gate.bias": "model--00002-of-00007.safetensors",
+    "block.16.mlp.gate.weight": "model--00002-of-00007.safetensors",
+    "block.16.mlp.mlp1_bias": "model--00002-of-00007.safetensors",
+    "block.16.mlp.mlp1_weight.blocks": "model--00002-of-00007.safetensors",
+    "block.16.mlp.mlp1_weight.scales": "model--00002-of-00007.safetensors",
+    "block.16.mlp.mlp2_bias": "model--00002-of-00007.safetensors",
+    "block.16.mlp.mlp2_weight.blocks": "model--00002-of-00007.safetensors",
+    "block.16.mlp.mlp2_weight.scales": "model--00002-of-00007.safetensors",
+    "block.16.mlp.norm.scale": "model--00002-of-00007.safetensors",
+    "block.17.attn.norm.scale": "model--00002-of-00007.safetensors",
+    "block.17.attn.out.bias": "model--00002-of-00007.safetensors",
+    "block.17.attn.out.weight": "model--00002-of-00007.safetensors",
+    "block.17.attn.qkv.bias": "model--00002-of-00007.safetensors",
+    "block.17.attn.qkv.weight": "model--00002-of-00007.safetensors",
+    "block.17.attn.sinks": "model--00002-of-00007.safetensors",
+    "block.17.mlp.gate.bias": "model--00002-of-00007.safetensors",
+    "block.17.mlp.gate.weight": "model--00002-of-00007.safetensors",
+    "block.17.mlp.mlp1_bias": "model--00002-of-00007.safetensors",
+    "block.17.mlp.mlp1_weight.blocks": "model--00002-of-00007.safetensors",
+    "block.17.mlp.mlp1_weight.scales": "model--00002-of-00007.safetensors",
+    "block.17.mlp.mlp2_bias": "model--00002-of-00007.safetensors",
+    "block.17.mlp.mlp2_weight.blocks": "model--00002-of-00007.safetensors",
+    "block.17.mlp.mlp2_weight.scales": "model--00002-of-00007.safetensors",
+    "block.17.mlp.norm.scale": "model--00002-of-00007.safetensors",
+    "block.18.attn.norm.scale": "model--00002-of-00007.safetensors",
+    "block.18.attn.out.bias": "model--00002-of-00007.safetensors",
+    "block.18.attn.out.weight": "model--00002-of-00007.safetensors",
+    "block.18.attn.qkv.bias": "model--00002-of-00007.safetensors",
+    "block.18.attn.qkv.weight": "model--00002-of-00007.safetensors",
+    "block.18.attn.sinks": "model--00002-of-00007.safetensors",
+    "block.18.mlp.gate.bias": "model--00002-of-00007.safetensors",
+    "block.18.mlp.gate.weight": "model--00002-of-00007.safetensors",
+    "block.18.mlp.mlp1_bias": "model--00002-of-00007.safetensors",
+    "block.18.mlp.mlp1_weight.blocks": "model--00002-of-00007.safetensors",
+    "block.18.mlp.mlp1_weight.scales": "model--00002-of-00007.safetensors",
+    "block.18.mlp.mlp2_bias": "model--00002-of-00007.safetensors",
+    "block.18.mlp.mlp2_weight.blocks": "model--00002-of-00007.safetensors",
+    "block.18.mlp.mlp2_weight.scales": "model--00002-of-00007.safetensors",
+    "block.18.mlp.norm.scale": "model--00002-of-00007.safetensors",
+    "block.19.attn.norm.scale": "model--00002-of-00007.safetensors",
+    "block.19.attn.out.bias": "model--00002-of-00007.safetensors",
+    "block.19.attn.out.weight": "model--00002-of-00007.safetensors",
+    "block.19.attn.qkv.bias": "model--00002-of-00007.safetensors",
+    "block.19.attn.qkv.weight": "model--00002-of-00007.safetensors",
+    "block.19.attn.sinks": "model--00002-of-00007.safetensors",
+    "block.19.mlp.gate.bias": "model--00002-of-00007.safetensors",
+    "block.19.mlp.gate.weight": "model--00002-of-00007.safetensors",
+    "block.19.mlp.mlp1_bias": "model--00002-of-00007.safetensors",
+    "block.19.mlp.mlp1_weight.blocks": "model--00002-of-00007.safetensors",
+    "block.19.mlp.mlp1_weight.scales": "model--00002-of-00007.safetensors",
+    "block.19.mlp.mlp2_bias": "model--00002-of-00007.safetensors",
+    "block.19.mlp.mlp2_weight.blocks": "model--00002-of-00007.safetensors",
+    "block.19.mlp.mlp2_weight.scales": "model--00002-of-00007.safetensors",
+    "block.19.mlp.norm.scale": "model--00002-of-00007.safetensors",
+    "block.2.attn.norm.scale": "model--00002-of-00007.safetensors",
+    "block.2.attn.out.bias": "model--00002-of-00007.safetensors",
+    "block.2.attn.out.weight": "model--00002-of-00007.safetensors",
+    "block.2.attn.qkv.bias": "model--00002-of-00007.safetensors",
+    "block.2.attn.qkv.weight": "model--00002-of-00007.safetensors",
+    "block.2.attn.sinks": "model--00002-of-00007.safetensors",
+    "block.2.mlp.gate.bias": "model--00002-of-00007.safetensors",
+    "block.2.mlp.gate.weight": "model--00002-of-00007.safetensors",
+    "block.2.mlp.mlp1_bias": "model--00002-of-00007.safetensors",
+    "block.2.mlp.mlp1_weight.blocks": "model--00003-of-00007.safetensors",
+    "block.2.mlp.mlp1_weight.scales": "model--00003-of-00007.safetensors",
+    "block.2.mlp.mlp2_bias": "model--00003-of-00007.safetensors",
+    "block.2.mlp.mlp2_weight.blocks": "model--00003-of-00007.safetensors",
+    "block.2.mlp.mlp2_weight.scales": "model--00003-of-00007.safetensors",
+    "block.2.mlp.norm.scale": "model--00003-of-00007.safetensors",
+    "block.20.attn.norm.scale": "model--00003-of-00007.safetensors",
+    "block.20.attn.out.bias": "model--00003-of-00007.safetensors",
+    "block.20.attn.out.weight": "model--00003-of-00007.safetensors",
+    "block.20.attn.qkv.bias": "model--00003-of-00007.safetensors",
+    "block.20.attn.qkv.weight": "model--00003-of-00007.safetensors",
+    "block.20.attn.sinks": "model--00003-of-00007.safetensors",
+    "block.20.mlp.gate.bias": "model--00003-of-00007.safetensors",
+    "block.20.mlp.gate.weight": "model--00003-of-00007.safetensors",
+    "block.20.mlp.mlp1_bias": "model--00003-of-00007.safetensors",
+    "block.20.mlp.mlp1_weight.blocks": "model--00003-of-00007.safetensors",
+    "block.20.mlp.mlp1_weight.scales": "model--00003-of-00007.safetensors",
+    "block.20.mlp.mlp2_bias": "model--00003-of-00007.safetensors",
+    "block.20.mlp.mlp2_weight.blocks": "model--00003-of-00007.safetensors",
+    "block.20.mlp.mlp2_weight.scales": "model--00003-of-00007.safetensors",
+    "block.20.mlp.norm.scale": "model--00003-of-00007.safetensors",
+    "block.21.attn.norm.scale": "model--00003-of-00007.safetensors",
+    "block.21.attn.out.bias": "model--00003-of-00007.safetensors",
+    "block.21.attn.out.weight": "model--00003-of-00007.safetensors",
+    "block.21.attn.qkv.bias": "model--00003-of-00007.safetensors",
+    "block.21.attn.qkv.weight": "model--00003-of-00007.safetensors",
+    "block.21.attn.sinks": "model--00003-of-00007.safetensors",
+    "block.21.mlp.gate.bias": "model--00003-of-00007.safetensors",
+    "block.21.mlp.gate.weight": "model--00003-of-00007.safetensors",
+    "block.21.mlp.mlp1_bias": "model--00003-of-00007.safetensors",
+    "block.21.mlp.mlp1_weight.blocks": "model--00003-of-00007.safetensors",
+    "block.21.mlp.mlp1_weight.scales": "model--00003-of-00007.safetensors",
+    "block.21.mlp.mlp2_bias": "model--00003-of-00007.safetensors",
+    "block.21.mlp.mlp2_weight.blocks": "model--00003-of-00007.safetensors",
+    "block.21.mlp.mlp2_weight.scales": "model--00003-of-00007.safetensors",
+    "block.21.mlp.norm.scale": "model--00003-of-00007.safetensors",
+    "block.22.attn.norm.scale": "model--00003-of-00007.safetensors",
+    "block.22.attn.out.bias": "model--00003-of-00007.safetensors",
+    "block.22.attn.out.weight": "model--00003-of-00007.safetensors",
+    "block.22.attn.qkv.bias": "model--00003-of-00007.safetensors",
+    "block.22.attn.qkv.weight": "model--00003-of-00007.safetensors",
+    "block.22.attn.sinks": "model--00003-of-00007.safetensors",
+    "block.22.mlp.gate.bias": "model--00003-of-00007.safetensors",
+    "block.22.mlp.gate.weight": "model--00003-of-00007.safetensors",
+    "block.22.mlp.mlp1_bias": "model--00003-of-00007.safetensors",
+    "block.22.mlp.mlp1_weight.blocks": "model--00003-of-00007.safetensors",
+    "block.22.mlp.mlp1_weight.scales": "model--00003-of-00007.safetensors",
+    "block.22.mlp.mlp2_bias": "model--00003-of-00007.safetensors",
+    "block.22.mlp.mlp2_weight.blocks": "model--00003-of-00007.safetensors",
+    "block.22.mlp.mlp2_weight.scales": "model--00003-of-00007.safetensors",
+    "block.22.mlp.norm.scale": "model--00003-of-00007.safetensors",
+    "block.23.attn.norm.scale": "model--00003-of-00007.safetensors",
+    "block.23.attn.out.bias": "model--00003-of-00007.safetensors",
+    "block.23.attn.out.weight": "model--00003-of-00007.safetensors",
+    "block.23.attn.qkv.bias": "model--00003-of-00007.safetensors",
+    "block.23.attn.qkv.weight": "model--00003-of-00007.safetensors",
+    "block.23.attn.sinks": "model--00003-of-00007.safetensors",
+    "block.23.mlp.gate.bias": "model--00003-of-00007.safetensors",
+    "block.23.mlp.gate.weight": "model--00003-of-00007.safetensors",
+    "block.23.mlp.mlp1_bias": "model--00003-of-00007.safetensors",
+    "block.23.mlp.mlp1_weight.blocks": "model--00003-of-00007.safetensors",
+    "block.23.mlp.mlp1_weight.scales": "model--00003-of-00007.safetensors",
+    "block.23.mlp.mlp2_bias": "model--00003-of-00007.safetensors",
+    "block.23.mlp.mlp2_weight.blocks": "model--00003-of-00007.safetensors",
+    "block.23.mlp.mlp2_weight.scales": "model--00003-of-00007.safetensors",
+    "block.23.mlp.norm.scale": "model--00003-of-00007.safetensors",
+    "block.24.attn.norm.scale": "model--00003-of-00007.safetensors",
+    "block.24.attn.out.bias": "model--00003-of-00007.safetensors",
+    "block.24.attn.out.weight": "model--00003-of-00007.safetensors",
+    "block.24.attn.qkv.bias": "model--00003-of-00007.safetensors",
+    "block.24.attn.qkv.weight": "model--00003-of-00007.safetensors",
+    "block.24.attn.sinks": "model--00003-of-00007.safetensors",
+    "block.24.mlp.gate.bias": "model--00003-of-00007.safetensors",
+    "block.24.mlp.gate.weight": "model--00003-of-00007.safetensors",
+    "block.24.mlp.mlp1_bias": "model--00003-of-00007.safetensors",
+    "block.24.mlp.mlp1_weight.blocks": "model--00003-of-00007.safetensors",
+    "block.24.mlp.mlp1_weight.scales": "model--00003-of-00007.safetensors",
+    "block.24.mlp.mlp2_bias": "model--00003-of-00007.safetensors",
+    "block.24.mlp.mlp2_weight.blocks": "model--00003-of-00007.safetensors",
+    "block.24.mlp.mlp2_weight.scales": "model--00003-of-00007.safetensors",
+    "block.24.mlp.norm.scale": "model--00003-of-00007.safetensors",
+    "block.25.attn.norm.scale": "model--00003-of-00007.safetensors",
+    "block.25.attn.out.bias": "model--00003-of-00007.safetensors",
+    "block.25.attn.out.weight": "model--00003-of-00007.safetensors",
+    "block.25.attn.qkv.bias": "model--00003-of-00007.safetensors",
+    "block.25.attn.qkv.weight": "model--00003-of-00007.safetensors",
+    "block.25.attn.sinks": "model--00003-of-00007.safetensors",
+    "block.25.mlp.gate.bias": "model--00003-of-00007.safetensors",
+    "block.25.mlp.gate.weight": "model--00003-of-00007.safetensors",
+    "block.25.mlp.mlp1_bias": "model--00003-of-00007.safetensors",
+    "block.25.mlp.mlp1_weight.blocks": "model--00004-of-00007.safetensors",
+    "block.25.mlp.mlp1_weight.scales": "model--00004-of-00007.safetensors",
+    "block.25.mlp.mlp2_bias": "model--00004-of-00007.safetensors",
+    "block.25.mlp.mlp2_weight.blocks": "model--00004-of-00007.safetensors",
+    "block.25.mlp.mlp2_weight.scales": "model--00004-of-00007.safetensors",
+    "block.25.mlp.norm.scale": "model--00004-of-00007.safetensors",
+    "block.26.attn.norm.scale": "model--00004-of-00007.safetensors",
+    "block.26.attn.out.bias": "model--00004-of-00007.safetensors",
+    "block.26.attn.out.weight": "model--00004-of-00007.safetensors",
+    "block.26.attn.qkv.bias": "model--00004-of-00007.safetensors",
+    "block.26.attn.qkv.weight": "model--00004-of-00007.safetensors",
+    "block.26.attn.sinks": "model--00004-of-00007.safetensors",
+    "block.26.mlp.gate.bias": "model--00004-of-00007.safetensors",
+    "block.26.mlp.gate.weight": "model--00004-of-00007.safetensors",
+    "block.26.mlp.mlp1_bias": "model--00004-of-00007.safetensors",
+    "block.26.mlp.mlp1_weight.blocks": "model--00004-of-00007.safetensors",
+    "block.26.mlp.mlp1_weight.scales": "model--00004-of-00007.safetensors",
+    "block.26.mlp.mlp2_bias": "model--00004-of-00007.safetensors",
+    "block.26.mlp.mlp2_weight.blocks": "model--00004-of-00007.safetensors",
+    "block.26.mlp.mlp2_weight.scales": "model--00004-of-00007.safetensors",
+    "block.26.mlp.norm.scale": "model--00004-of-00007.safetensors",
+    "block.27.attn.norm.scale": "model--00004-of-00007.safetensors",
+    "block.27.attn.out.bias": "model--00004-of-00007.safetensors",
+    "block.27.attn.out.weight": "model--00004-of-00007.safetensors",
+    "block.27.attn.qkv.bias": "model--00004-of-00007.safetensors",
+    "block.27.attn.qkv.weight": "model--00004-of-00007.safetensors",
+    "block.27.attn.sinks": "model--00004-of-00007.safetensors",
+    "block.27.mlp.gate.bias": "model--00004-of-00007.safetensors",
+    "block.27.mlp.gate.weight": "model--00004-of-00007.safetensors",
+    "block.27.mlp.mlp1_bias": "model--00004-of-00007.safetensors",
+    "block.27.mlp.mlp1_weight.blocks": "model--00004-of-00007.safetensors",
+    "block.27.mlp.mlp1_weight.scales": "model--00004-of-00007.safetensors",
+    "block.27.mlp.mlp2_bias": "model--00004-of-00007.safetensors",
+    "block.27.mlp.mlp2_weight.blocks": "model--00004-of-00007.safetensors",
+    "block.27.mlp.mlp2_weight.scales": "model--00004-of-00007.safetensors",
+    "block.27.mlp.norm.scale": "model--00004-of-00007.safetensors",
+    "block.28.attn.norm.scale": "model--00004-of-00007.safetensors",
+    "block.28.attn.out.bias": "model--00004-of-00007.safetensors",
+    "block.28.attn.out.weight": "model--00004-of-00007.safetensors",
+    "block.28.attn.qkv.bias": "model--00004-of-00007.safetensors",
+    "block.28.attn.qkv.weight": "model--00004-of-00007.safetensors",
+    "block.28.attn.sinks": "model--00004-of-00007.safetensors",
+    "block.28.mlp.gate.bias": "model--00004-of-00007.safetensors",
+    "block.28.mlp.gate.weight": "model--00004-of-00007.safetensors",
+    "block.28.mlp.mlp1_bias": "model--00004-of-00007.safetensors",
+    "block.28.mlp.mlp1_weight.blocks": "model--00004-of-00007.safetensors",
+    "block.28.mlp.mlp1_weight.scales": "model--00004-of-00007.safetensors",
+    "block.28.mlp.mlp2_bias": "model--00004-of-00007.safetensors",
+    "block.28.mlp.mlp2_weight.blocks": "model--00004-of-00007.safetensors",
+    "block.28.mlp.mlp2_weight.scales": "model--00004-of-00007.safetensors",
+    "block.28.mlp.norm.scale": "model--00004-of-00007.safetensors",
+    "block.29.attn.norm.scale": "model--00004-of-00007.safetensors",
+    "block.29.attn.out.bias": "model--00004-of-00007.safetensors",
+    "block.29.attn.out.weight": "model--00004-of-00007.safetensors",
+    "block.29.attn.qkv.bias": "model--00004-of-00007.safetensors",
+    "block.29.attn.qkv.weight": "model--00004-of-00007.safetensors",
+    "block.29.attn.sinks": "model--00004-of-00007.safetensors",
+    "block.29.mlp.gate.bias": "model--00004-of-00007.safetensors",
+    "block.29.mlp.gate.weight": "model--00004-of-00007.safetensors",
+    "block.29.mlp.mlp1_bias": "model--00004-of-00007.safetensors",
+    "block.29.mlp.mlp1_weight.blocks": "model--00004-of-00007.safetensors",
+    "block.29.mlp.mlp1_weight.scales": "model--00004-of-00007.safetensors",
+    "block.29.mlp.mlp2_bias": "model--00004-of-00007.safetensors",
+    "block.29.mlp.mlp2_weight.blocks": "model--00004-of-00007.safetensors",
+    "block.29.mlp.mlp2_weight.scales": "model--00004-of-00007.safetensors",
+    "block.29.mlp.norm.scale": "model--00004-of-00007.safetensors",
+    "block.3.attn.norm.scale": "model--00004-of-00007.safetensors",
+    "block.3.attn.out.bias": "model--00004-of-00007.safetensors",
+    "block.3.attn.out.weight": "model--00004-of-00007.safetensors",
+    "block.3.attn.qkv.bias": "model--00004-of-00007.safetensors",
+    "block.3.attn.qkv.weight": "model--00004-of-00007.safetensors",
+    "block.3.attn.sinks": "model--00004-of-00007.safetensors",
+    "block.3.mlp.gate.bias": "model--00004-of-00007.safetensors",
+    "block.3.mlp.gate.weight": "model--00004-of-00007.safetensors",
+    "block.3.mlp.mlp1_bias": "model--00004-of-00007.safetensors",
+    "block.3.mlp.mlp1_weight.blocks": "model--00004-of-00007.safetensors",
+    "block.3.mlp.mlp1_weight.scales": "model--00004-of-00007.safetensors",
+    "block.3.mlp.mlp2_bias": "model--00004-of-00007.safetensors",
+    "block.3.mlp.mlp2_weight.blocks": "model--00004-of-00007.safetensors",
+    "block.3.mlp.mlp2_weight.scales": "model--00004-of-00007.safetensors",
+    "block.3.mlp.norm.scale": "model--00004-of-00007.safetensors",
+    "block.30.attn.norm.scale": "model--00004-of-00007.safetensors",
+    "block.30.attn.out.bias": "model--00004-of-00007.safetensors",
+    "block.30.attn.out.weight": "model--00004-of-00007.safetensors",
+    "block.30.attn.qkv.bias": "model--00004-of-00007.safetensors",
+    "block.30.attn.qkv.weight": "model--00004-of-00007.safetensors",
+    "block.30.attn.sinks": "model--00004-of-00007.safetensors",
+    "block.30.mlp.gate.bias": "model--00004-of-00007.safetensors",
+    "block.30.mlp.gate.weight": "model--00004-of-00007.safetensors",
+    "block.30.mlp.mlp1_bias": "model--00004-of-00007.safetensors",
+    "block.30.mlp.mlp1_weight.blocks": "model--00005-of-00007.safetensors",
+    "block.30.mlp.mlp1_weight.scales": "model--00005-of-00007.safetensors",
+    "block.30.mlp.mlp2_bias": "model--00005-of-00007.safetensors",
+    "block.30.mlp.mlp2_weight.blocks": "model--00005-of-00007.safetensors",
+    "block.30.mlp.mlp2_weight.scales": "model--00005-of-00007.safetensors",
+    "block.30.mlp.norm.scale": "model--00005-of-00007.safetensors",
+    "block.31.attn.norm.scale": "model--00005-of-00007.safetensors",
+    "block.31.attn.out.bias": "model--00005-of-00007.safetensors",
+    "block.31.attn.out.weight": "model--00005-of-00007.safetensors",
+    "block.31.attn.qkv.bias": "model--00005-of-00007.safetensors",
+    "block.31.attn.qkv.weight": "model--00005-of-00007.safetensors",
+    "block.31.attn.sinks": "model--00005-of-00007.safetensors",
+    "block.31.mlp.gate.bias": "model--00005-of-00007.safetensors",
+    "block.31.mlp.gate.weight": "model--00005-of-00007.safetensors",
+    "block.31.mlp.mlp1_bias": "model--00005-of-00007.safetensors",
+    "block.31.mlp.mlp1_weight.blocks": "model--00005-of-00007.safetensors",
+    "block.31.mlp.mlp1_weight.scales": "model--00005-of-00007.safetensors",
+    "block.31.mlp.mlp2_bias": "model--00005-of-00007.safetensors",
+    "block.31.mlp.mlp2_weight.blocks": "model--00005-of-00007.safetensors",
+    "block.31.mlp.mlp2_weight.scales": "model--00005-of-00007.safetensors",
+    "block.31.mlp.norm.scale": "model--00005-of-00007.safetensors",
+    "block.32.attn.norm.scale": "model--00005-of-00007.safetensors",
+    "block.32.attn.out.bias": "model--00005-of-00007.safetensors",
+    "block.32.attn.out.weight": "model--00005-of-00007.safetensors",
+    "block.32.attn.qkv.bias": "model--00005-of-00007.safetensors",
+    "block.32.attn.qkv.weight": "model--00005-of-00007.safetensors",
+    "block.32.attn.sinks": "model--00005-of-00007.safetensors",
+    "block.32.mlp.gate.bias": "model--00005-of-00007.safetensors",
+    "block.32.mlp.gate.weight": "model--00005-of-00007.safetensors",
+    "block.32.mlp.mlp1_bias": "model--00005-of-00007.safetensors",
+    "block.32.mlp.mlp1_weight.blocks": "model--00005-of-00007.safetensors",
+    "block.32.mlp.mlp1_weight.scales": "model--00005-of-00007.safetensors",
+    "block.32.mlp.mlp2_bias": "model--00005-of-00007.safetensors",
+    "block.32.mlp.mlp2_weight.blocks": "model--00005-of-00007.safetensors",
+    "block.32.mlp.mlp2_weight.scales": "model--00005-of-00007.safetensors",
+    "block.32.mlp.norm.scale": "model--00005-of-00007.safetensors",
+    "block.33.attn.norm.scale": "model--00005-of-00007.safetensors",
+    "block.33.attn.out.bias": "model--00005-of-00007.safetensors",
+    "block.33.attn.out.weight": "model--00005-of-00007.safetensors",
+    "block.33.attn.qkv.bias": "model--00005-of-00007.safetensors",
+    "block.33.attn.qkv.weight": "model--00005-of-00007.safetensors",
+    "block.33.attn.sinks": "model--00005-of-00007.safetensors",
+    "block.33.mlp.gate.bias": "model--00005-of-00007.safetensors",
+    "block.33.mlp.gate.weight": "model--00005-of-00007.safetensors",
+    "block.33.mlp.mlp1_bias": "model--00005-of-00007.safetensors",
+    "block.33.mlp.mlp1_weight.blocks": "model--00005-of-00007.safetensors",
+    "block.33.mlp.mlp1_weight.scales": "model--00005-of-00007.safetensors",
+    "block.33.mlp.mlp2_bias": "model--00005-of-00007.safetensors",
+    "block.33.mlp.mlp2_weight.blocks": "model--00005-of-00007.safetensors",
+    "block.33.mlp.mlp2_weight.scales": "model--00005-of-00007.safetensors",
+    "block.33.mlp.norm.scale": "model--00005-of-00007.safetensors",
+    "block.34.attn.norm.scale": "model--00005-of-00007.safetensors",
+    "block.34.attn.out.bias": "model--00005-of-00007.safetensors",
+    "block.34.attn.out.weight": "model--00005-of-00007.safetensors",
+    "block.34.attn.qkv.bias": "model--00005-of-00007.safetensors",
+    "block.34.attn.qkv.weight": "model--00005-of-00007.safetensors",
+    "block.34.attn.sinks": "model--00005-of-00007.safetensors",
+    "block.34.mlp.gate.bias": "model--00005-of-00007.safetensors",
+    "block.34.mlp.gate.weight": "model--00005-of-00007.safetensors",
+    "block.34.mlp.mlp1_bias": "model--00005-of-00007.safetensors",
+    "block.34.mlp.mlp1_weight.blocks": "model--00005-of-00007.safetensors",
+    "block.34.mlp.mlp1_weight.scales": "model--00005-of-00007.safetensors",
+    "block.34.mlp.mlp2_bias": "model--00005-of-00007.safetensors",
+    "block.34.mlp.mlp2_weight.blocks": "model--00005-of-00007.safetensors",
+    "block.34.mlp.mlp2_weight.scales": "model--00005-of-00007.safetensors",
+    "block.34.mlp.norm.scale": "model--00005-of-00007.safetensors",
+    "block.35.attn.norm.scale": "model--00005-of-00007.safetensors",
+    "block.35.attn.out.bias": "model--00005-of-00007.safetensors",
+    "block.35.attn.out.weight": "model--00005-of-00007.safetensors",
+    "block.35.attn.qkv.bias": "model--00005-of-00007.safetensors",
+    "block.35.attn.qkv.weight": "model--00005-of-00007.safetensors",
+    "block.35.attn.sinks": "model--00005-of-00007.safetensors",
+    "block.35.mlp.gate.bias": "model--00005-of-00007.safetensors",
+    "block.35.mlp.gate.weight": "model--00005-of-00007.safetensors",
+    "block.35.mlp.mlp1_bias": "model--00005-of-00007.safetensors",
+    "block.35.mlp.mlp1_weight.blocks": "model--00005-of-00007.safetensors",
+    "block.35.mlp.mlp1_weight.scales": "model--00005-of-00007.safetensors",
+    "block.35.mlp.mlp2_bias": "model--00005-of-00007.safetensors",
+    "block.35.mlp.mlp2_weight.blocks": "model--00005-of-00007.safetensors",
+    "block.35.mlp.mlp2_weight.scales": "model--00005-of-00007.safetensors",
+    "block.35.mlp.norm.scale": "model--00005-of-00007.safetensors",
+    "block.4.attn.norm.scale": "model--00005-of-00007.safetensors",
+    "block.4.attn.out.bias": "model--00005-of-00007.safetensors",
+    "block.4.attn.out.weight": "model--00005-of-00007.safetensors",
+    "block.4.attn.qkv.bias": "model--00005-of-00007.safetensors",
+    "block.4.attn.qkv.weight": "model--00005-of-00007.safetensors",
+    "block.4.attn.sinks": "model--00005-of-00007.safetensors",
+    "block.4.mlp.gate.bias": "model--00005-of-00007.safetensors",
+    "block.4.mlp.gate.weight": "model--00005-of-00007.safetensors",
+    "block.4.mlp.mlp1_bias": "model--00005-of-00007.safetensors",
+    "block.4.mlp.mlp1_weight.blocks": "model--00006-of-00007.safetensors",
+    "block.4.mlp.mlp1_weight.scales": "model--00006-of-00007.safetensors",
+    "block.4.mlp.mlp2_bias": "model--00006-of-00007.safetensors",
+    "block.4.mlp.mlp2_weight.blocks": "model--00006-of-00007.safetensors",
+    "block.4.mlp.mlp2_weight.scales": "model--00006-of-00007.safetensors",
+    "block.4.mlp.norm.scale": "model--00006-of-00007.safetensors",
+    "block.5.attn.norm.scale": "model--00006-of-00007.safetensors",
+    "block.5.attn.out.bias": "model--00006-of-00007.safetensors",
+    "block.5.attn.out.weight": "model--00006-of-00007.safetensors",
+    "block.5.attn.qkv.bias": "model--00006-of-00007.safetensors",
+    "block.5.attn.qkv.weight": "model--00006-of-00007.safetensors",
+    "block.5.attn.sinks": "model--00006-of-00007.safetensors",
+    "block.5.mlp.gate.bias": "model--00006-of-00007.safetensors",
+    "block.5.mlp.gate.weight": "model--00006-of-00007.safetensors",
+    "block.5.mlp.mlp1_bias": "model--00006-of-00007.safetensors",
+    "block.5.mlp.mlp1_weight.blocks": "model--00006-of-00007.safetensors",
+    "block.5.mlp.mlp1_weight.scales": "model--00006-of-00007.safetensors",
+    "block.5.mlp.mlp2_bias": "model--00006-of-00007.safetensors",
+    "block.5.mlp.mlp2_weight.blocks": "model--00006-of-00007.safetensors",
+    "block.5.mlp.mlp2_weight.scales": "model--00006-of-00007.safetensors",
+    "block.5.mlp.norm.scale": "model--00006-of-00007.safetensors",
+    "block.6.attn.norm.scale": "model--00006-of-00007.safetensors",
+    "block.6.attn.out.bias": "model--00006-of-00007.safetensors",
+    "block.6.attn.out.weight": "model--00006-of-00007.safetensors",
+    "block.6.attn.qkv.bias": "model--00006-of-00007.safetensors",
+    "block.6.attn.qkv.weight": "model--00006-of-00007.safetensors",
+    "block.6.attn.sinks": "model--00006-of-00007.safetensors",
+    "block.6.mlp.gate.bias": "model--00006-of-00007.safetensors",
+    "block.6.mlp.gate.weight": "model--00006-of-00007.safetensors",
+    "block.6.mlp.mlp1_bias": "model--00006-of-00007.safetensors",
+    "block.6.mlp.mlp1_weight.blocks": "model--00006-of-00007.safetensors",
+    "block.6.mlp.mlp1_weight.scales": "model--00006-of-00007.safetensors",
+    "block.6.mlp.mlp2_bias": "model--00006-of-00007.safetensors",
+    "block.6.mlp.mlp2_weight.blocks": "model--00006-of-00007.safetensors",
+    "block.6.mlp.mlp2_weight.scales": "model--00006-of-00007.safetensors",
+    "block.6.mlp.norm.scale": "model--00006-of-00007.safetensors",
+    "block.7.attn.norm.scale": "model--00006-of-00007.safetensors",
+    "block.7.attn.out.bias": "model--00006-of-00007.safetensors",
+    "block.7.attn.out.weight": "model--00006-of-00007.safetensors",
+    "block.7.attn.qkv.bias": "model--00006-of-00007.safetensors",
+    "block.7.attn.qkv.weight": "model--00006-of-00007.safetensors",
+    "block.7.attn.sinks": "model--00006-of-00007.safetensors",
+    "block.7.mlp.gate.bias": "model--00006-of-00007.safetensors",
+    "block.7.mlp.gate.weight": "model--00006-of-00007.safetensors",
+    "block.7.mlp.mlp1_bias": "model--00006-of-00007.safetensors",
+    "block.7.mlp.mlp1_weight.blocks": "model--00006-of-00007.safetensors",
+    "block.7.mlp.mlp1_weight.scales": "model--00006-of-00007.safetensors",
+    "block.7.mlp.mlp2_bias": "model--00006-of-00007.safetensors",
+    "block.7.mlp.mlp2_weight.blocks": "model--00006-of-00007.safetensors",
+    "block.7.mlp.mlp2_weight.scales": "model--00006-of-00007.safetensors",
+    "block.7.mlp.norm.scale": "model--00006-of-00007.safetensors",
+    "block.8.attn.norm.scale": "model--00006-of-00007.safetensors",
+    "block.8.attn.out.bias": "model--00006-of-00007.safetensors",
+    "block.8.attn.out.weight": "model--00006-of-00007.safetensors",
+    "block.8.attn.qkv.bias": "model--00006-of-00007.safetensors",
+    "block.8.attn.qkv.weight": "model--00006-of-00007.safetensors",
+    "block.8.attn.sinks": "model--00006-of-00007.safetensors",
+    "block.8.mlp.gate.bias": "model--00006-of-00007.safetensors",
+    "block.8.mlp.gate.weight": "model--00006-of-00007.safetensors",
+    "block.8.mlp.mlp1_bias": "model--00006-of-00007.safetensors",
+    "block.8.mlp.mlp1_weight.blocks": "model--00006-of-00007.safetensors",
+    "block.8.mlp.mlp1_weight.scales": "model--00006-of-00007.safetensors",
+    "block.8.mlp.mlp2_bias": "model--00006-of-00007.safetensors",
+    "block.8.mlp.mlp2_weight.blocks": "model--00006-of-00007.safetensors",
+    "block.8.mlp.mlp2_weight.scales": "model--00006-of-00007.safetensors",
+    "block.8.mlp.norm.scale": "model--00006-of-00007.safetensors",
+    "block.9.attn.norm.scale": "model--00006-of-00007.safetensors",
+    "block.9.attn.out.bias": "model--00006-of-00007.safetensors",
+    "block.9.attn.out.weight": "model--00006-of-00007.safetensors",
+    "block.9.attn.qkv.bias": "model--00006-of-00007.safetensors",
+    "block.9.attn.qkv.weight": "model--00006-of-00007.safetensors",
+    "block.9.attn.sinks": "model--00006-of-00007.safetensors",
+    "block.9.mlp.gate.bias": "model--00006-of-00007.safetensors",
+    "block.9.mlp.gate.weight": "model--00006-of-00007.safetensors",
+    "block.9.mlp.mlp1_bias": "model--00006-of-00007.safetensors",
+    "block.9.mlp.mlp1_weight.blocks": "model--00006-of-00007.safetensors",
+    "block.9.mlp.mlp1_weight.scales": "model--00006-of-00007.safetensors",
+    "block.9.mlp.mlp2_bias": "model--00006-of-00007.safetensors",
+    "block.9.mlp.mlp2_weight.blocks": "model--00006-of-00007.safetensors",
+    "block.9.mlp.mlp2_weight.scales": "model--00006-of-00007.safetensors",
+    "block.9.mlp.norm.scale": "model--00006-of-00007.safetensors",
+    "embedding.weight": "model--00007-of-00007.safetensors",
+    "norm.scale": "model--00007-of-00007.safetensors",
+    "unembedding.weight": "model--00007-of-00007.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "<|startoftext|>",
+  "eos_token": "<|return|>",
+  "pad_token": "<|endoftext|>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0614fe83cadab421296e664e1f48f4261fa8fef6e03e63bb75c20f38e37d07d3
+size 27868174

tokenizer_config.json

@@ -0,0 +1,183 @@
+{
+  "added_tokens_decoder": {
+    "199998": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "199999": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200000": {
+      "content": "<|reserved_200000|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200001": {
+      "content": "<|reserved_200001|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200002": {
+      "content": "<|return|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200003": {
+      "content": "<|constrain|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200004": {
+      "content": "<|reserved_200004|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200005": {
+      "content": "<|channel|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200006": {
+      "content": "<|start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200007": {
+      "content": "<|end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200008": {
+      "content": "<|message|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200009": {
+      "content": "<|reserved_200009|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200010": {
+      "content": "<|reserved_200010|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200011": {
+      "content": "<|reserved_200011|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200012": {
+      "content": "<|call|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200013": {
+      "content": "<|reserved_200013|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200014": {
+      "content": "<|reserved_200014|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200015": {
+      "content": "<|reserved_200015|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200016": {
+      "content": "<|reserved_200016|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200017": {
+      "content": "<|reserved_200017|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200018": {
+      "content": "<|endofprompt|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|return|>",
+  "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}