Upload trained H100 optimized model

.gitattributes

@@ -33,3 +33,5 @@ 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
+checkpoint-1250/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

chat_template.jinja

@@ -0,0 +1,331 @@
+{#-
+  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 -%}
+            {{- "{\n" }}
+            {%- 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 + "\n\n" }}
+    {{- "namespace " + namespace_name + " {\n\n" }}
+    {%- for tool in tools %}
+        {%- set tool = tool.function %}
+        {{- "// " + tool.description + "\n" }}
+        {{- "type "+ tool.name + " = " }}
+        {%- if tool.parameters and tool.parameters.properties %}
+            {{- "(_: {\n" }}
+            {%- for param_name, param_spec in tool.parameters.properties.items() %}
+                {%- if param_spec.description %}
+                    {{- "// " + param_spec.description + "\n" }}
+                {%- endif %}
+                {{- 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.enum %}
+                        {{- ", // default: " + param_spec.default }}
+                    {%- elif param_spec.oneOf %}
+                        {{- "// default: " + param_spec.default }}
+                    {%- else %}
+                        {{- ", // default: " + param_spec.default|tojson }}
+                    {%- endif -%}
+                {%- endif -%}
+                {%- if not loop.last %}
+                    {{- ",\n" }}
+                {%- else %}
+                    {{- ",\n" }}
+                {%- endif -%}
+            {%- endfor %}
+            {{- "}) => any;\n\n" }}
+        {%- else -%}
+            {{- "() => any;\n\n" }}
+        {%- endif -%}
+    {%- endfor %}
+    {{- "} // namespace " + namespace_name }}
+{%- endmacro -%}
+
+{%- macro render_builtin_tools(browser_tool, python_tool) -%}
+    {%- if browser_tool %}
+        {{- "## browser\n\n" }}
+        {{- "// Tool for browsing.\n" }}
+        {{- "// The `cursor` appears in brackets before each browsing display: `[{cursor}]`.\n" }}
+        {{- "// Cite information from the tool using the following format:\n" }}
+        {{- "// `【{cursor}†L{line_start}(-L{line_end})?】`, for example: `【6†L9-L11】` or `【8†L3】`.\n" }}
+        {{- "// Do not quote more than 10 words directly from the tool output.\n" }}
+        {{- "// sources=web (default: web)\n" }}
+        {{- "namespace browser {\n\n" }}
+        {{- "// Searches for information related to `query` and displays `topn` results.\n" }}
+        {{- "type search = (_: {\n" }}
+        {{- "query: string,\n" }}
+        {{- "topn?: number, // default: 10\n" }}
+        {{- "source?: string,\n" }}
+        {{- "}) => any;\n\n" }}
+        {{- "// Opens the link `id` from the page indicated by `cursor` starting at line number `loc`, showing `num_lines` lines.\n" }}
+        {{- "// Valid link ids are displayed with the formatting: `【{id}†.*】`.\n" }}
+        {{- "// If `cursor` is not provided, the most recent page is implied.\n" }}
+        {{- "// If `id` is a string, it is treated as a fully qualified URL associated with `source`.\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" }}
+        {{- "// Use this function without `id` to scroll to a new location of an opened page.\n" }}
+        {{- "type open = (_: {\n" }}
+        {{- "id?: number | string, // default: -1\n" }}
+        {{- "cursor?: number, // default: -1\n" }}
+        {{- "loc?: number, // default: -1\n" }}
+        {{- "num_lines?: number, // default: -1\n" }}
+        {{- "view_source?: boolean, // default: false\n" }}
+        {{- "source?: string,\n" }}
+        {{- "}) => any;\n\n" }}
+        {{- "// Finds exact matches of `pattern` in the current page, or the page given by `cursor`.\n" }}
+        {{- "type find = (_: {\n" }}
+        {{- "pattern: string,\n" }}
+        {{- "cursor?: number, // default: -1\n" }}
+        {{- "}) => any;\n\n" }}
+        {{- "} // namespace browser\n\n" }}
+    {%- endif -%}
+
+    {%- if python_tool %}
+        {{- "## python\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" }}
+        {{- "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" }}
+    {%- 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 + "\n" }}
+    {{- "Knowledge cutoff: 2024-06\n" }}
+    {{- "Current date: " + strftime_now("%Y-%m-%d") + "\n\n" }}
+    {%- if reasoning_effort is not defined %}
+        {%- set reasoning_effort = "medium" %}
+    {%- endif %}
+    {{- "Reasoning: " + reasoning_effort + "\n\n" }}
+    {%- if builtin_tools %}
+        {{- "# Tools\n\n" }}
+        {%- 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." }}
+    {%- if tools -%}
+        {{- "\nCalls to these tools must go to the commentary channel: 'functions'." }}
+    {%- endif -%}
+{%- 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\n\n" }}
+        {{- developer_message }}
+        {{- "\n\n" }}
+    {%- endif %}
+    {%- if tools -%}
+        {{- "# Tools\n\n" }}
+        {{- 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 need very careful handling here - we want to drop the tool call analysis message if the model #}
+            {#- has output a later <|final|> message, but otherwise we want to retain it. This is the only case #}
+            {#- when we render CoT/analysis messages in inference. #}
+            {%- set future_final_message = namespace(found=false) %}
+            {%- for future_message in loop_messages[loop.index:] %}
+                {%- if future_message.role == 'assistant' and "tool_calls" not in future_message %}
+                    {%- set future_final_message.found = true %}
+                {%- endif %}
+            {%- endfor %}
+            {#- 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 and not future_final_message.found %}
+                {{- "<|start|>assistant<|channel|>analysis<|message|>" + message.content + "<|end|>" }}
+            {%- elif message.thinking and not future_final_message.found %}
+                {{- "<|start|>assistant<|channel|>analysis<|message|>" + message.thinking + "<|end|>" }}
+            {%- endif %}
+            {{- "<|start|>assistant to=" }}
+            {{- "functions." + tool_call.name + "<|channel|>commentary " }}
+            {{- (tool_call.content_type if tool_call.content_type is defined else "json") + "<|message|>" }}
+            {{- tool_call.arguments|tojson }}
+            {{- "<|call|>" }}
+            {%- 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 -%}

checkpoint-1250/chat_template.jinja

@@ -0,0 +1,331 @@
+{#-
+  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 -%}
+            {{- "{\n" }}
+            {%- 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 + "\n\n" }}
+    {{- "namespace " + namespace_name + " {\n\n" }}
+    {%- for tool in tools %}
+        {%- set tool = tool.function %}
+        {{- "// " + tool.description + "\n" }}
+        {{- "type "+ tool.name + " = " }}
+        {%- if tool.parameters and tool.parameters.properties %}
+            {{- "(_: {\n" }}
+            {%- for param_name, param_spec in tool.parameters.properties.items() %}
+                {%- if param_spec.description %}
+                    {{- "// " + param_spec.description + "\n" }}
+                {%- endif %}
+                {{- 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.enum %}
+                        {{- ", // default: " + param_spec.default }}
+                    {%- elif param_spec.oneOf %}
+                        {{- "// default: " + param_spec.default }}
+                    {%- else %}
+                        {{- ", // default: " + param_spec.default|tojson }}
+                    {%- endif -%}
+                {%- endif -%}
+                {%- if not loop.last %}
+                    {{- ",\n" }}
+                {%- else %}
+                    {{- ",\n" }}
+                {%- endif -%}
+            {%- endfor %}
+            {{- "}) => any;\n\n" }}
+        {%- else -%}
+            {{- "() => any;\n\n" }}
+        {%- endif -%}
+    {%- endfor %}
+    {{- "} // namespace " + namespace_name }}
+{%- endmacro -%}
+
+{%- macro render_builtin_tools(browser_tool, python_tool) -%}
+    {%- if browser_tool %}
+        {{- "## browser\n\n" }}
+        {{- "// Tool for browsing.\n" }}
+        {{- "// The `cursor` appears in brackets before each browsing display: `[{cursor}]`.\n" }}
+        {{- "// Cite information from the tool using the following format:\n" }}
+        {{- "// `【{cursor}†L{line_start}(-L{line_end})?】`, for example: `【6†L9-L11】` or `【8†L3】`.\n" }}
+        {{- "// Do not quote more than 10 words directly from the tool output.\n" }}
+        {{- "// sources=web (default: web)\n" }}
+        {{- "namespace browser {\n\n" }}
+        {{- "// Searches for information related to `query` and displays `topn` results.\n" }}
+        {{- "type search = (_: {\n" }}
+        {{- "query: string,\n" }}
+        {{- "topn?: number, // default: 10\n" }}
+        {{- "source?: string,\n" }}
+        {{- "}) => any;\n\n" }}
+        {{- "// Opens the link `id` from the page indicated by `cursor` starting at line number `loc`, showing `num_lines` lines.\n" }}
+        {{- "// Valid link ids are displayed with the formatting: `【{id}†.*】`.\n" }}
+        {{- "// If `cursor` is not provided, the most recent page is implied.\n" }}
+        {{- "// If `id` is a string, it is treated as a fully qualified URL associated with `source`.\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" }}
+        {{- "// Use this function without `id` to scroll to a new location of an opened page.\n" }}
+        {{- "type open = (_: {\n" }}
+        {{- "id?: number | string, // default: -1\n" }}
+        {{- "cursor?: number, // default: -1\n" }}
+        {{- "loc?: number, // default: -1\n" }}
+        {{- "num_lines?: number, // default: -1\n" }}
+        {{- "view_source?: boolean, // default: false\n" }}
+        {{- "source?: string,\n" }}
+        {{- "}) => any;\n\n" }}
+        {{- "// Finds exact matches of `pattern` in the current page, or the page given by `cursor`.\n" }}
+        {{- "type find = (_: {\n" }}
+        {{- "pattern: string,\n" }}
+        {{- "cursor?: number, // default: -1\n" }}
+        {{- "}) => any;\n\n" }}
+        {{- "} // namespace browser\n\n" }}
+    {%- endif -%}
+
+    {%- if python_tool %}
+        {{- "## python\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" }}
+        {{- "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" }}
+    {%- 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 + "\n" }}
+    {{- "Knowledge cutoff: 2024-06\n" }}
+    {{- "Current date: " + strftime_now("%Y-%m-%d") + "\n\n" }}
+    {%- if reasoning_effort is not defined %}
+        {%- set reasoning_effort = "medium" %}
+    {%- endif %}
+    {{- "Reasoning: " + reasoning_effort + "\n\n" }}
+    {%- if builtin_tools %}
+        {{- "# Tools\n\n" }}
+        {%- 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." }}
+    {%- if tools -%}
+        {{- "\nCalls to these tools must go to the commentary channel: 'functions'." }}
+    {%- endif -%}
+{%- 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\n\n" }}
+        {{- developer_message }}
+        {{- "\n\n" }}
+    {%- endif %}
+    {%- if tools -%}
+        {{- "# Tools\n\n" }}
+        {{- 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 need very careful handling here - we want to drop the tool call analysis message if the model #}
+            {#- has output a later <|final|> message, but otherwise we want to retain it. This is the only case #}
+            {#- when we render CoT/analysis messages in inference. #}
+            {%- set future_final_message = namespace(found=false) %}
+            {%- for future_message in loop_messages[loop.index:] %}
+                {%- if future_message.role == 'assistant' and "tool_calls" not in future_message %}
+                    {%- set future_final_message.found = true %}
+                {%- endif %}
+            {%- endfor %}
+            {#- 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 and not future_final_message.found %}
+                {{- "<|start|>assistant<|channel|>analysis<|message|>" + message.content + "<|end|>" }}
+            {%- elif message.thinking and not future_final_message.found %}
+                {{- "<|start|>assistant<|channel|>analysis<|message|>" + message.thinking + "<|end|>" }}
+            {%- endif %}
+            {{- "<|start|>assistant to=" }}
+            {{- "functions." + tool_call.name + "<|channel|>commentary " }}
+            {{- (tool_call.content_type if tool_call.content_type is defined else "json") + "<|message|>" }}
+            {{- tool_call.arguments|tojson }}
+            {{- "<|call|>" }}
+            {%- 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 -%}

checkpoint-1250/config.json

@@ -0,0 +1,69 @@
+{
+  "architectures": [
+    "GptOssForCausalLM"
+  ],
+  "attention_bias": true,
+  "attention_dropout": 0.0,
+  "bos_token_id": 199998,
+  "dtype": "bfloat16",
+  "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"
+  ],
+  "max_position_embeddings": 131072,
+  "model_type": "gpt_oss",
+  "num_attention_heads": 64,
+  "num_experts_per_tok": 4,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 8,
+  "num_local_experts": 32,
+  "output_router_logits": false,
+  "pad_token_id": 199999,
+  "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": "4.57.1",
+  "use_cache": false,
+  "vocab_size": 201088
+}

checkpoint-1250/generation_config.json

@@ -0,0 +1,11 @@
+{
+  "bos_token_id": 199998,
+  "do_sample": true,
+  "eos_token_id": [
+    200002,
+    199999,
+    200012
+  ],
+  "pad_token_id": 199999,
+  "transformers_version": "4.57.1"
+}

checkpoint-1250/model-00001-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc729189133161b61e287dd7bdec06afc2b7f77ed1820ca53eda0553fa742230
+size 4504304664

checkpoint-1250/model-00002-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4708b3da84cd7d559f5cd2eb9d0d13466ae1ccd90fdee8295d9ec3d8748582c
+size 4939127656

checkpoint-1250/model-00003-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96031fa4efe1e880b2f17ac4352c3a2d251129d8140d122b9e8649a2d45c51d2
+size 4939127656

checkpoint-1250/model-00004-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46e221c089ddcbacd6f4495a2dfccea2206cb8b21795ea868415125e9fb8139e
+size 4939127680

checkpoint-1250/model-00005-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f223ae981c1c8f4925334b8e0954ce78a613b0602d3eba28ea73f0146c9d73f3
+size 4939127704

checkpoint-1250/model-00006-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf0e3a0ccf931369e3ebe77f1f6d0a1781d739d6cb1dfed7c54fedda3f94fe18
+size 4939127704

checkpoint-1250/model-00007-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51a3ad356e1a0d63de63f78975caf1a129d7d29bc00a7614de652aff7a4c57b0
+size 4939127704

checkpoint-1250/model-00008-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07a2d79388f1f6f1bebac3d03216b6ac47c2bf498640ab54ac8c15beb629847f
+size 4939127704

checkpoint-1250/model-00009-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2eda29cdc86d75937066cde98574795f08a96ebe34b22e126e1cb252ec494df4
+size 2751362856

checkpoint-1250/model.safetensors.index.json

@@ -0,0 +1,419 @@
+{
+  "metadata": {
+    "total_parameters": 20914757184,
+    "total_size": 41829514368
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00009-of-00009.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.mlp.experts.down_proj": "model-00001-of-00009.safetensors",
+    "model.layers.0.mlp.experts.down_proj_bias": "model-00001-of-00009.safetensors",
+    "model.layers.0.mlp.experts.gate_up_proj": "model-00001-of-00009.safetensors",
+    "model.layers.0.mlp.experts.gate_up_proj_bias": "model-00001-of-00009.safetensors",
+    "model.layers.0.mlp.router.bias": "model-00001-of-00009.safetensors",
+    "model.layers.0.mlp.router.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00009.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.self_attn.o_proj.bias": "model-00001-of-00009.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00009.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.self_attn.sinks": "model-00001-of-00009.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00009.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.mlp.experts.down_proj": "model-00001-of-00009.safetensors",
+    "model.layers.1.mlp.experts.down_proj_bias": "model-00001-of-00009.safetensors",
+    "model.layers.1.mlp.experts.gate_up_proj": "model-00001-of-00009.safetensors",
+    "model.layers.1.mlp.experts.gate_up_proj_bias": "model-00001-of-00009.safetensors",
+    "model.layers.1.mlp.router.bias": "model-00001-of-00009.safetensors",
+    "model.layers.1.mlp.router.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00009.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.self_attn.o_proj.bias": "model-00001-of-00009.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00009.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.self_attn.sinks": "model-00001-of-00009.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00009.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.10.mlp.experts.down_proj": "model-00004-of-00009.safetensors",
+    "model.layers.10.mlp.experts.down_proj_bias": "model-00004-of-00009.safetensors",
+    "model.layers.10.mlp.experts.gate_up_proj": "model-00004-of-00009.safetensors",
+    "model.layers.10.mlp.experts.gate_up_proj_bias": "model-00004-of-00009.safetensors",
+    "model.layers.10.mlp.router.bias": "model-00004-of-00009.safetensors",
+    "model.layers.10.mlp.router.weight": "model-00004-of-00009.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00004-of-00009.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.10.self_attn.o_proj.bias": "model-00004-of-00009.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00004-of-00009.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.10.self_attn.sinks": "model-00004-of-00009.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00004-of-00009.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.11.mlp.experts.down_proj": "model-00005-of-00009.safetensors",
+    "model.layers.11.mlp.experts.down_proj_bias": "model-00005-of-00009.safetensors",
+    "model.layers.11.mlp.experts.gate_up_proj": "model-00005-of-00009.safetensors",
+    "model.layers.11.mlp.experts.gate_up_proj_bias": "model-00005-of-00009.safetensors",
+    "model.layers.11.mlp.router.bias": "model-00004-of-00009.safetensors",
+    "model.layers.11.mlp.router.weight": "model-00004-of-00009.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00004-of-00009.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.11.self_attn.o_proj.bias": "model-00004-of-00009.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00004-of-00009.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.11.self_attn.sinks": "model-00004-of-00009.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00004-of-00009.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.12.mlp.experts.down_proj": "model-00005-of-00009.safetensors",
+    "model.layers.12.mlp.experts.down_proj_bias": "model-00005-of-00009.safetensors",
+    "model.layers.12.mlp.experts.gate_up_proj": "model-00005-of-00009.safetensors",
+    "model.layers.12.mlp.experts.gate_up_proj_bias": "model-00005-of-00009.safetensors",
+    "model.layers.12.mlp.router.bias": "model-00005-of-00009.safetensors",
+    "model.layers.12.mlp.router.weight": "model-00005-of-00009.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00005-of-00009.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.12.self_attn.o_proj.bias": "model-00005-of-00009.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00005-of-00009.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.12.self_attn.sinks": "model-00005-of-00009.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00005-of-00009.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.13.mlp.experts.down_proj": "model-00005-of-00009.safetensors",
+    "model.layers.13.mlp.experts.down_proj_bias": "model-00005-of-00009.safetensors",
+    "model.layers.13.mlp.experts.gate_up_proj": "model-00005-of-00009.safetensors",
+    "model.layers.13.mlp.experts.gate_up_proj_bias": "model-00005-of-00009.safetensors",
+    "model.layers.13.mlp.router.bias": "model-00005-of-00009.safetensors",
+    "model.layers.13.mlp.router.weight": "model-00005-of-00009.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00005-of-00009.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.13.self_attn.o_proj.bias": "model-00005-of-00009.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00005-of-00009.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.13.self_attn.sinks": "model-00005-of-00009.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00005-of-00009.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.14.mlp.experts.down_proj": "model-00006-of-00009.safetensors",
+    "model.layers.14.mlp.experts.down_proj_bias": "model-00006-of-00009.safetensors",
+    "model.layers.14.mlp.experts.gate_up_proj": "model-00006-of-00009.safetensors",
+    "model.layers.14.mlp.experts.gate_up_proj_bias": "model-00006-of-00009.safetensors",
+    "model.layers.14.mlp.router.bias": "model-00005-of-00009.safetensors",
+    "model.layers.14.mlp.router.weight": "model-00005-of-00009.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00005-of-00009.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.14.self_attn.o_proj.bias": "model-00005-of-00009.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00005-of-00009.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.14.self_attn.sinks": "model-00005-of-00009.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00005-of-00009.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.15.mlp.experts.down_proj": "model-00006-of-00009.safetensors",
+    "model.layers.15.mlp.experts.down_proj_bias": "model-00006-of-00009.safetensors",
+    "model.layers.15.mlp.experts.gate_up_proj": "model-00006-of-00009.safetensors",
+    "model.layers.15.mlp.experts.gate_up_proj_bias": "model-00006-of-00009.safetensors",
+    "model.layers.15.mlp.router.bias": "model-00006-of-00009.safetensors",
+    "model.layers.15.mlp.router.weight": "model-00006-of-00009.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00006-of-00009.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.15.self_attn.o_proj.bias": "model-00006-of-00009.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00006-of-00009.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.15.self_attn.sinks": "model-00006-of-00009.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00006-of-00009.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.16.mlp.experts.down_proj": "model-00006-of-00009.safetensors",
+    "model.layers.16.mlp.experts.down_proj_bias": "model-00006-of-00009.safetensors",
+    "model.layers.16.mlp.experts.gate_up_proj": "model-00006-of-00009.safetensors",
+    "model.layers.16.mlp.experts.gate_up_proj_bias": "model-00006-of-00009.safetensors",
+    "model.layers.16.mlp.router.bias": "model-00006-of-00009.safetensors",
+    "model.layers.16.mlp.router.weight": "model-00006-of-00009.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00006-of-00009.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.16.self_attn.o_proj.bias": "model-00006-of-00009.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00006-of-00009.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.16.self_attn.sinks": "model-00006-of-00009.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00006-of-00009.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.17.mlp.experts.down_proj": "model-00007-of-00009.safetensors",
+    "model.layers.17.mlp.experts.down_proj_bias": "model-00007-of-00009.safetensors",
+    "model.layers.17.mlp.experts.gate_up_proj": "model-00007-of-00009.safetensors",
+    "model.layers.17.mlp.experts.gate_up_proj_bias": "model-00007-of-00009.safetensors",
+    "model.layers.17.mlp.router.bias": "model-00006-of-00009.safetensors",
+    "model.layers.17.mlp.router.weight": "model-00006-of-00009.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00006-of-00009.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.17.self_attn.o_proj.bias": "model-00006-of-00009.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00006-of-00009.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.17.self_attn.sinks": "model-00006-of-00009.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00006-of-00009.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.18.mlp.experts.down_proj": "model-00007-of-00009.safetensors",
+    "model.layers.18.mlp.experts.down_proj_bias": "model-00007-of-00009.safetensors",
+    "model.layers.18.mlp.experts.gate_up_proj": "model-00007-of-00009.safetensors",
+    "model.layers.18.mlp.experts.gate_up_proj_bias": "model-00007-of-00009.safetensors",
+    "model.layers.18.mlp.router.bias": "model-00007-of-00009.safetensors",
+    "model.layers.18.mlp.router.weight": "model-00007-of-00009.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00007-of-00009.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.18.self_attn.o_proj.bias": "model-00007-of-00009.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00007-of-00009.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.18.self_attn.sinks": "model-00007-of-00009.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00007-of-00009.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.19.mlp.experts.down_proj": "model-00007-of-00009.safetensors",
+    "model.layers.19.mlp.experts.down_proj_bias": "model-00007-of-00009.safetensors",
+    "model.layers.19.mlp.experts.gate_up_proj": "model-00007-of-00009.safetensors",
+    "model.layers.19.mlp.experts.gate_up_proj_bias": "model-00007-of-00009.safetensors",
+    "model.layers.19.mlp.router.bias": "model-00007-of-00009.safetensors",
+    "model.layers.19.mlp.router.weight": "model-00007-of-00009.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00007-of-00009.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.19.self_attn.o_proj.bias": "model-00007-of-00009.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00007-of-00009.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.19.self_attn.sinks": "model-00007-of-00009.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00007-of-00009.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.2.mlp.experts.down_proj": "model-00002-of-00009.safetensors",
+    "model.layers.2.mlp.experts.down_proj_bias": "model-00002-of-00009.safetensors",
+    "model.layers.2.mlp.experts.gate_up_proj": "model-00002-of-00009.safetensors",
+    "model.layers.2.mlp.experts.gate_up_proj_bias": "model-00002-of-00009.safetensors",
+    "model.layers.2.mlp.router.bias": "model-00001-of-00009.safetensors",
+    "model.layers.2.mlp.router.weight": "model-00001-of-00009.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00009.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.2.self_attn.o_proj.bias": "model-00001-of-00009.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00009.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.2.self_attn.sinks": "model-00001-of-00009.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00009.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.20.mlp.experts.down_proj": "model-00008-of-00009.safetensors",
+    "model.layers.20.mlp.experts.down_proj_bias": "model-00008-of-00009.safetensors",
+    "model.layers.20.mlp.experts.gate_up_proj": "model-00008-of-00009.safetensors",
+    "model.layers.20.mlp.experts.gate_up_proj_bias": "model-00008-of-00009.safetensors",
+    "model.layers.20.mlp.router.bias": "model-00007-of-00009.safetensors",
+    "model.layers.20.mlp.router.weight": "model-00007-of-00009.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00007-of-00009.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.20.self_attn.o_proj.bias": "model-00007-of-00009.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00007-of-00009.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.20.self_attn.sinks": "model-00007-of-00009.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00007-of-00009.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.21.mlp.experts.down_proj": "model-00008-of-00009.safetensors",
+    "model.layers.21.mlp.experts.down_proj_bias": "model-00008-of-00009.safetensors",
+    "model.layers.21.mlp.experts.gate_up_proj": "model-00008-of-00009.safetensors",
+    "model.layers.21.mlp.experts.gate_up_proj_bias": "model-00008-of-00009.safetensors",
+    "model.layers.21.mlp.router.bias": "model-00008-of-00009.safetensors",
+    "model.layers.21.mlp.router.weight": "model-00008-of-00009.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00008-of-00009.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.21.self_attn.o_proj.bias": "model-00008-of-00009.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00008-of-00009.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.21.self_attn.sinks": "model-00008-of-00009.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00008-of-00009.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.22.mlp.experts.down_proj": "model-00008-of-00009.safetensors",
+    "model.layers.22.mlp.experts.down_proj_bias": "model-00008-of-00009.safetensors",
+    "model.layers.22.mlp.experts.gate_up_proj": "model-00008-of-00009.safetensors",
+    "model.layers.22.mlp.experts.gate_up_proj_bias": "model-00008-of-00009.safetensors",
+    "model.layers.22.mlp.router.bias": "model-00008-of-00009.safetensors",
+    "model.layers.22.mlp.router.weight": "model-00008-of-00009.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00008-of-00009.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.22.self_attn.o_proj.bias": "model-00008-of-00009.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00008-of-00009.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.22.self_attn.sinks": "model-00008-of-00009.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00008-of-00009.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00009-of-00009.safetensors",
+    "model.layers.23.mlp.experts.down_proj": "model-00009-of-00009.safetensors",
+    "model.layers.23.mlp.experts.down_proj_bias": "model-00009-of-00009.safetensors",
+    "model.layers.23.mlp.experts.gate_up_proj": "model-00009-of-00009.safetensors",
+    "model.layers.23.mlp.experts.gate_up_proj_bias": "model-00009-of-00009.safetensors",
+    "model.layers.23.mlp.router.bias": "model-00008-of-00009.safetensors",
+    "model.layers.23.mlp.router.weight": "model-00008-of-00009.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00008-of-00009.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.23.self_attn.o_proj.bias": "model-00008-of-00009.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00008-of-00009.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.23.self_attn.sinks": "model-00008-of-00009.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00008-of-00009.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.3.mlp.experts.down_proj": "model-00002-of-00009.safetensors",
+    "model.layers.3.mlp.experts.down_proj_bias": "model-00002-of-00009.safetensors",
+    "model.layers.3.mlp.experts.gate_up_proj": "model-00002-of-00009.safetensors",
+    "model.layers.3.mlp.experts.gate_up_proj_bias": "model-00002-of-00009.safetensors",
+    "model.layers.3.mlp.router.bias": "model-00002-of-00009.safetensors",
+    "model.layers.3.mlp.router.weight": "model-00002-of-00009.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00002-of-00009.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.3.self_attn.o_proj.bias": "model-00002-of-00009.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00002-of-00009.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.3.self_attn.sinks": "model-00002-of-00009.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00002-of-00009.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.4.mlp.experts.down_proj": "model-00002-of-00009.safetensors",
+    "model.layers.4.mlp.experts.down_proj_bias": "model-00002-of-00009.safetensors",
+    "model.layers.4.mlp.experts.gate_up_proj": "model-00002-of-00009.safetensors",
+    "model.layers.4.mlp.experts.gate_up_proj_bias": "model-00002-of-00009.safetensors",
+    "model.layers.4.mlp.router.bias": "model-00002-of-00009.safetensors",
+    "model.layers.4.mlp.router.weight": "model-00002-of-00009.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00009.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.4.self_attn.o_proj.bias": "model-00002-of-00009.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00009.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.4.self_attn.sinks": "model-00002-of-00009.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00009.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.5.mlp.experts.down_proj": "model-00003-of-00009.safetensors",
+    "model.layers.5.mlp.experts.down_proj_bias": "model-00003-of-00009.safetensors",
+    "model.layers.5.mlp.experts.gate_up_proj": "model-00003-of-00009.safetensors",
+    "model.layers.5.mlp.experts.gate_up_proj_bias": "model-00003-of-00009.safetensors",
+    "model.layers.5.mlp.router.bias": "model-00002-of-00009.safetensors",
+    "model.layers.5.mlp.router.weight": "model-00002-of-00009.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00009.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.5.self_attn.o_proj.bias": "model-00002-of-00009.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00009.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.5.self_attn.sinks": "model-00002-of-00009.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00009.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.6.mlp.experts.down_proj": "model-00003-of-00009.safetensors",
+    "model.layers.6.mlp.experts.down_proj_bias": "model-00003-of-00009.safetensors",
+    "model.layers.6.mlp.experts.gate_up_proj": "model-00003-of-00009.safetensors",
+    "model.layers.6.mlp.experts.gate_up_proj_bias": "model-00003-of-00009.safetensors",
+    "model.layers.6.mlp.router.bias": "model-00003-of-00009.safetensors",
+    "model.layers.6.mlp.router.weight": "model-00003-of-00009.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00003-of-00009.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.6.self_attn.o_proj.bias": "model-00003-of-00009.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00003-of-00009.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.6.self_attn.sinks": "model-00003-of-00009.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00003-of-00009.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.7.mlp.experts.down_proj": "model-00003-of-00009.safetensors",
+    "model.layers.7.mlp.experts.down_proj_bias": "model-00003-of-00009.safetensors",
+    "model.layers.7.mlp.experts.gate_up_proj": "model-00003-of-00009.safetensors",
+    "model.layers.7.mlp.experts.gate_up_proj_bias": "model-00003-of-00009.safetensors",
+    "model.layers.7.mlp.router.bias": "model-00003-of-00009.safetensors",
+    "model.layers.7.mlp.router.weight": "model-00003-of-00009.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00003-of-00009.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.7.self_attn.o_proj.bias": "model-00003-of-00009.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00003-of-00009.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.7.self_attn.sinks": "model-00003-of-00009.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00003-of-00009.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.8.mlp.experts.down_proj": "model-00004-of-00009.safetensors",
+    "model.layers.8.mlp.experts.down_proj_bias": "model-00004-of-00009.safetensors",
+    "model.layers.8.mlp.experts.gate_up_proj": "model-00004-of-00009.safetensors",
+    "model.layers.8.mlp.experts.gate_up_proj_bias": "model-00004-of-00009.safetensors",
+    "model.layers.8.mlp.router.bias": "model-00003-of-00009.safetensors",
+    "model.layers.8.mlp.router.weight": "model-00003-of-00009.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00003-of-00009.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.8.self_attn.o_proj.bias": "model-00003-of-00009.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00003-of-00009.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.8.self_attn.sinks": "model-00003-of-00009.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00003-of-00009.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.9.mlp.experts.down_proj": "model-00004-of-00009.safetensors",
+    "model.layers.9.mlp.experts.down_proj_bias": "model-00004-of-00009.safetensors",
+    "model.layers.9.mlp.experts.gate_up_proj": "model-00004-of-00009.safetensors",
+    "model.layers.9.mlp.experts.gate_up_proj_bias": "model-00004-of-00009.safetensors",
+    "model.layers.9.mlp.router.bias": "model-00004-of-00009.safetensors",
+    "model.layers.9.mlp.router.weight": "model-00004-of-00009.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00004-of-00009.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.9.self_attn.o_proj.bias": "model-00004-of-00009.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00004-of-00009.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.9.self_attn.sinks": "model-00004-of-00009.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00004-of-00009.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.norm.weight": "model-00009-of-00009.safetensors"
+  }
+}

checkpoint-1250/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4466beaa56ab10637e9ff5d265e2d020747c591c11818d1acb0155aae394f7c
+size 2794414739

checkpoint-1250/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61c19bab1174704a4a4441475683bf1270277af15d2e2c95e964789128e482c4
+size 14645

checkpoint-1250/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ad1f24bf2246b019e5c4979ace691aa118b7de7cc84ddd0aa9224068c0079d8
+size 1465

checkpoint-1250/special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|return|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-1250/tokenizer.json

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

checkpoint-1250/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"
+}

checkpoint-1250/trainer_state.json

@@ -0,0 +1,916 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1250,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0008,
+      "grad_norm": 11.4375,
+      "learning_rate": 0.0,
+      "loss": 3.8345,
+      "step": 1
+    },
+    {
+      "epoch": 0.008,
+      "grad_norm": 11.125,
+      "learning_rate": 2.25e-06,
+      "loss": 3.3934,
+      "step": 10
+    },
+    {
+      "epoch": 0.016,
+      "grad_norm": 9.5,
+      "learning_rate": 4.75e-06,
+      "loss": 3.4002,
+      "step": 20
+    },
+    {
+      "epoch": 0.024,
+      "grad_norm": 9.4375,
+      "learning_rate": 7.25e-06,
+      "loss": 3.4003,
+      "step": 30
+    },
+    {
+      "epoch": 0.032,
+      "grad_norm": 11.1875,
+      "learning_rate": 9.750000000000002e-06,
+      "loss": 3.374,
+      "step": 40
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 10.625,
+      "learning_rate": 1.225e-05,
+      "loss": 3.4678,
+      "step": 50
+    },
+    {
+      "epoch": 0.048,
+      "grad_norm": 11.0,
+      "learning_rate": 1.475e-05,
+      "loss": 3.4331,
+      "step": 60
+    },
+    {
+      "epoch": 0.056,
+      "grad_norm": 10.6875,
+      "learning_rate": 1.725e-05,
+      "loss": 3.4722,
+      "step": 70
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 10.25,
+      "learning_rate": 1.9750000000000002e-05,
+      "loss": 3.2413,
+      "step": 80
+    },
+    {
+      "epoch": 0.072,
+      "grad_norm": 10.8125,
+      "learning_rate": 2.2250000000000002e-05,
+      "loss": 3.1804,
+      "step": 90
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 10.1875,
+      "learning_rate": 2.4750000000000002e-05,
+      "loss": 3.1778,
+      "step": 100
+    },
+    {
+      "epoch": 0.088,
+      "grad_norm": 8.4375,
+      "learning_rate": 2.725e-05,
+      "loss": 3.2479,
+      "step": 110
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 11.0,
+      "learning_rate": 2.975e-05,
+      "loss": 3.2259,
+      "step": 120
+    },
+    {
+      "epoch": 0.104,
+      "grad_norm": 9.5625,
+      "learning_rate": 3.2250000000000005e-05,
+      "loss": 3.0845,
+      "step": 130
+    },
+    {
+      "epoch": 0.112,
+      "grad_norm": 8.9375,
+      "learning_rate": 3.475e-05,
+      "loss": 3.1694,
+      "step": 140
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 8.4375,
+      "learning_rate": 3.7250000000000004e-05,
+      "loss": 3.1736,
+      "step": 150
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 9.5,
+      "learning_rate": 3.9750000000000004e-05,
+      "loss": 3.035,
+      "step": 160
+    },
+    {
+      "epoch": 0.136,
+      "grad_norm": 9.8125,
+      "learning_rate": 4.2250000000000004e-05,
+      "loss": 3.1456,
+      "step": 170
+    },
+    {
+      "epoch": 0.144,
+      "grad_norm": 9.25,
+      "learning_rate": 4.4750000000000004e-05,
+      "loss": 3.0917,
+      "step": 180
+    },
+    {
+      "epoch": 0.152,
+      "grad_norm": 9.1875,
+      "learning_rate": 4.7249999999999997e-05,
+      "loss": 2.9948,
+      "step": 190
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 8.5625,
+      "learning_rate": 4.975e-05,
+      "loss": 3.0667,
+      "step": 200
+    },
+    {
+      "epoch": 0.168,
+      "grad_norm": 8.125,
+      "learning_rate": 4.957142857142857e-05,
+      "loss": 2.9987,
+      "step": 210
+    },
+    {
+      "epoch": 0.176,
+      "grad_norm": 7.875,
+      "learning_rate": 4.90952380952381e-05,
+      "loss": 2.9686,
+      "step": 220
+    },
+    {
+      "epoch": 0.184,
+      "grad_norm": 9.1875,
+      "learning_rate": 4.861904761904762e-05,
+      "loss": 3.0708,
+      "step": 230
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 7.90625,
+      "learning_rate": 4.8142857142857147e-05,
+      "loss": 3.0676,
+      "step": 240
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 9.375,
+      "learning_rate": 4.766666666666667e-05,
+      "loss": 2.8833,
+      "step": 250
+    },
+    {
+      "epoch": 0.208,
+      "grad_norm": 8.75,
+      "learning_rate": 4.719047619047619e-05,
+      "loss": 3.0558,
+      "step": 260
+    },
+    {
+      "epoch": 0.216,
+      "grad_norm": 9.375,
+      "learning_rate": 4.671428571428571e-05,
+      "loss": 3.0003,
+      "step": 270
+    },
+    {
+      "epoch": 0.224,
+      "grad_norm": 8.25,
+      "learning_rate": 4.623809523809524e-05,
+      "loss": 2.9514,
+      "step": 280
+    },
+    {
+      "epoch": 0.232,
+      "grad_norm": 7.15625,
+      "learning_rate": 4.5761904761904765e-05,
+      "loss": 2.984,
+      "step": 290
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 8.625,
+      "learning_rate": 4.528571428571429e-05,
+      "loss": 3.0273,
+      "step": 300
+    },
+    {
+      "epoch": 0.248,
+      "grad_norm": 7.75,
+      "learning_rate": 4.480952380952381e-05,
+      "loss": 2.9437,
+      "step": 310
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 9.1875,
+      "learning_rate": 4.433333333333334e-05,
+      "loss": 3.0913,
+      "step": 320
+    },
+    {
+      "epoch": 0.264,
+      "grad_norm": 8.5625,
+      "learning_rate": 4.385714285714286e-05,
+      "loss": 2.9659,
+      "step": 330
+    },
+    {
+      "epoch": 0.272,
+      "grad_norm": 8.0625,
+      "learning_rate": 4.338095238095238e-05,
+      "loss": 2.854,
+      "step": 340
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 7.0,
+      "learning_rate": 4.290476190476191e-05,
+      "loss": 2.8936,
+      "step": 350
+    },
+    {
+      "epoch": 0.288,
+      "grad_norm": 8.125,
+      "learning_rate": 4.242857142857143e-05,
+      "loss": 2.9805,
+      "step": 360
+    },
+    {
+      "epoch": 0.296,
+      "grad_norm": 8.5,
+      "learning_rate": 4.1952380952380956e-05,
+      "loss": 2.9814,
+      "step": 370
+    },
+    {
+      "epoch": 0.304,
+      "grad_norm": 7.25,
+      "learning_rate": 4.147619047619048e-05,
+      "loss": 2.8731,
+      "step": 380
+    },
+    {
+      "epoch": 0.312,
+      "grad_norm": 7.4375,
+      "learning_rate": 4.1e-05,
+      "loss": 2.8186,
+      "step": 390
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 8.0,
+      "learning_rate": 4.052380952380952e-05,
+      "loss": 3.048,
+      "step": 400
+    },
+    {
+      "epoch": 0.328,
+      "grad_norm": 8.5,
+      "learning_rate": 4.004761904761905e-05,
+      "loss": 2.8923,
+      "step": 410
+    },
+    {
+      "epoch": 0.336,
+      "grad_norm": 7.96875,
+      "learning_rate": 3.9571428571428574e-05,
+      "loss": 2.8443,
+      "step": 420
+    },
+    {
+      "epoch": 0.344,
+      "grad_norm": 7.75,
+      "learning_rate": 3.9095238095238096e-05,
+      "loss": 3.0182,
+      "step": 430
+    },
+    {
+      "epoch": 0.352,
+      "grad_norm": 7.625,
+      "learning_rate": 3.861904761904762e-05,
+      "loss": 2.849,
+      "step": 440
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 8.125,
+      "learning_rate": 3.814285714285715e-05,
+      "loss": 2.8413,
+      "step": 450
+    },
+    {
+      "epoch": 0.368,
+      "grad_norm": 7.6875,
+      "learning_rate": 3.766666666666667e-05,
+      "loss": 2.9321,
+      "step": 460
+    },
+    {
+      "epoch": 0.376,
+      "grad_norm": 7.15625,
+      "learning_rate": 3.719047619047619e-05,
+      "loss": 2.9628,
+      "step": 470
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": 8.0625,
+      "learning_rate": 3.671428571428572e-05,
+      "loss": 3.0175,
+      "step": 480
+    },
+    {
+      "epoch": 0.392,
+      "grad_norm": 7.375,
+      "learning_rate": 3.6238095238095236e-05,
+      "loss": 2.9446,
+      "step": 490
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 7.625,
+      "learning_rate": 3.5761904761904765e-05,
+      "loss": 2.8095,
+      "step": 500
+    },
+    {
+      "epoch": 0.408,
+      "grad_norm": 9.25,
+      "learning_rate": 3.528571428571429e-05,
+      "loss": 2.9347,
+      "step": 510
+    },
+    {
+      "epoch": 0.416,
+      "grad_norm": 7.875,
+      "learning_rate": 3.480952380952381e-05,
+      "loss": 2.7751,
+      "step": 520
+    },
+    {
+      "epoch": 0.424,
+      "grad_norm": 8.5625,
+      "learning_rate": 3.433333333333333e-05,
+      "loss": 2.8434,
+      "step": 530
+    },
+    {
+      "epoch": 0.432,
+      "grad_norm": 7.71875,
+      "learning_rate": 3.385714285714286e-05,
+      "loss": 2.869,
+      "step": 540
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 6.75,
+      "learning_rate": 3.338095238095238e-05,
+      "loss": 2.8466,
+      "step": 550
+    },
+    {
+      "epoch": 0.448,
+      "grad_norm": 7.4375,
+      "learning_rate": 3.2904761904761906e-05,
+      "loss": 2.7286,
+      "step": 560
+    },
+    {
+      "epoch": 0.456,
+      "grad_norm": 8.4375,
+      "learning_rate": 3.242857142857143e-05,
+      "loss": 2.9655,
+      "step": 570
+    },
+    {
+      "epoch": 0.464,
+      "grad_norm": 7.3125,
+      "learning_rate": 3.195238095238096e-05,
+      "loss": 2.7955,
+      "step": 580
+    },
+    {
+      "epoch": 0.472,
+      "grad_norm": 9.25,
+      "learning_rate": 3.147619047619048e-05,
+      "loss": 2.8469,
+      "step": 590
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 8.25,
+      "learning_rate": 3.1e-05,
+      "loss": 2.9423,
+      "step": 600
+    },
+    {
+      "epoch": 0.488,
+      "grad_norm": 8.0625,
+      "learning_rate": 3.0523809523809524e-05,
+      "loss": 2.9848,
+      "step": 610
+    },
+    {
+      "epoch": 0.496,
+      "grad_norm": 7.25,
+      "learning_rate": 3.0047619047619046e-05,
+      "loss": 2.8185,
+      "step": 620
+    },
+    {
+      "epoch": 0.504,
+      "grad_norm": 8.3125,
+      "learning_rate": 2.957142857142857e-05,
+      "loss": 2.7036,
+      "step": 630
+    },
+    {
+      "epoch": 0.512,
+      "grad_norm": 7.5625,
+      "learning_rate": 2.9095238095238097e-05,
+      "loss": 2.6809,
+      "step": 640
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 8.3125,
+      "learning_rate": 2.8619047619047623e-05,
+      "loss": 2.8011,
+      "step": 650
+    },
+    {
+      "epoch": 0.528,
+      "grad_norm": 7.40625,
+      "learning_rate": 2.814285714285714e-05,
+      "loss": 2.7213,
+      "step": 660
+    },
+    {
+      "epoch": 0.536,
+      "grad_norm": 7.15625,
+      "learning_rate": 2.7666666666666667e-05,
+      "loss": 2.8342,
+      "step": 670
+    },
+    {
+      "epoch": 0.544,
+      "grad_norm": 6.625,
+      "learning_rate": 2.7190476190476193e-05,
+      "loss": 2.7829,
+      "step": 680
+    },
+    {
+      "epoch": 0.552,
+      "grad_norm": 7.5625,
+      "learning_rate": 2.6714285714285715e-05,
+      "loss": 2.7949,
+      "step": 690
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 7.5625,
+      "learning_rate": 2.623809523809524e-05,
+      "loss": 2.7692,
+      "step": 700
+    },
+    {
+      "epoch": 0.568,
+      "grad_norm": 8.25,
+      "learning_rate": 2.5761904761904766e-05,
+      "loss": 2.8251,
+      "step": 710
+    },
+    {
+      "epoch": 0.576,
+      "grad_norm": 7.15625,
+      "learning_rate": 2.5285714285714285e-05,
+      "loss": 2.7056,
+      "step": 720
+    },
+    {
+      "epoch": 0.584,
+      "grad_norm": 8.8125,
+      "learning_rate": 2.480952380952381e-05,
+      "loss": 2.8116,
+      "step": 730
+    },
+    {
+      "epoch": 0.592,
+      "grad_norm": 8.125,
+      "learning_rate": 2.4333333333333336e-05,
+      "loss": 2.6844,
+      "step": 740
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 8.5625,
+      "learning_rate": 2.385714285714286e-05,
+      "loss": 2.7657,
+      "step": 750
+    },
+    {
+      "epoch": 0.608,
+      "grad_norm": 8.1875,
+      "learning_rate": 2.338095238095238e-05,
+      "loss": 2.8522,
+      "step": 760
+    },
+    {
+      "epoch": 0.616,
+      "grad_norm": 7.71875,
+      "learning_rate": 2.2904761904761906e-05,
+      "loss": 2.8368,
+      "step": 770
+    },
+    {
+      "epoch": 0.624,
+      "grad_norm": 7.71875,
+      "learning_rate": 2.242857142857143e-05,
+      "loss": 2.6978,
+      "step": 780
+    },
+    {
+      "epoch": 0.632,
+      "grad_norm": 7.25,
+      "learning_rate": 2.195238095238095e-05,
+      "loss": 2.8267,
+      "step": 790
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 8.1875,
+      "learning_rate": 2.1476190476190477e-05,
+      "loss": 2.7188,
+      "step": 800
+    },
+    {
+      "epoch": 0.648,
+      "grad_norm": 7.78125,
+      "learning_rate": 2.1e-05,
+      "loss": 2.8553,
+      "step": 810
+    },
+    {
+      "epoch": 0.656,
+      "grad_norm": 7.25,
+      "learning_rate": 2.0523809523809524e-05,
+      "loss": 2.675,
+      "step": 820
+    },
+    {
+      "epoch": 0.664,
+      "grad_norm": 6.9375,
+      "learning_rate": 2.004761904761905e-05,
+      "loss": 2.7901,
+      "step": 830
+    },
+    {
+      "epoch": 0.672,
+      "grad_norm": 8.4375,
+      "learning_rate": 1.9571428571428572e-05,
+      "loss": 2.6719,
+      "step": 840
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 7.8125,
+      "learning_rate": 1.9095238095238098e-05,
+      "loss": 2.6436,
+      "step": 850
+    },
+    {
+      "epoch": 0.688,
+      "grad_norm": 7.71875,
+      "learning_rate": 1.861904761904762e-05,
+      "loss": 2.8045,
+      "step": 860
+    },
+    {
+      "epoch": 0.696,
+      "grad_norm": 8.75,
+      "learning_rate": 1.8142857142857146e-05,
+      "loss": 2.802,
+      "step": 870
+    },
+    {
+      "epoch": 0.704,
+      "grad_norm": 8.0,
+      "learning_rate": 1.7666666666666668e-05,
+      "loss": 2.807,
+      "step": 880
+    },
+    {
+      "epoch": 0.712,
+      "grad_norm": 8.75,
+      "learning_rate": 1.719047619047619e-05,
+      "loss": 2.7425,
+      "step": 890
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 7.40625,
+      "learning_rate": 1.6714285714285716e-05,
+      "loss": 2.8515,
+      "step": 900
+    },
+    {
+      "epoch": 0.728,
+      "grad_norm": 7.0625,
+      "learning_rate": 1.6238095238095238e-05,
+      "loss": 2.7694,
+      "step": 910
+    },
+    {
+      "epoch": 0.736,
+      "grad_norm": 8.0,
+      "learning_rate": 1.5761904761904764e-05,
+      "loss": 2.6311,
+      "step": 920
+    },
+    {
+      "epoch": 0.744,
+      "grad_norm": 6.6875,
+      "learning_rate": 1.5285714285714286e-05,
+      "loss": 2.6884,
+      "step": 930
+    },
+    {
+      "epoch": 0.752,
+      "grad_norm": 6.9375,
+      "learning_rate": 1.480952380952381e-05,
+      "loss": 2.8331,
+      "step": 940
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 7.75,
+      "learning_rate": 1.4333333333333334e-05,
+      "loss": 2.7617,
+      "step": 950
+    },
+    {
+      "epoch": 0.768,
+      "grad_norm": 7.1875,
+      "learning_rate": 1.3857142857142858e-05,
+      "loss": 2.6287,
+      "step": 960
+    },
+    {
+      "epoch": 0.776,
+      "grad_norm": 7.71875,
+      "learning_rate": 1.3380952380952383e-05,
+      "loss": 2.8381,
+      "step": 970
+    },
+    {
+      "epoch": 0.784,
+      "grad_norm": 7.625,
+      "learning_rate": 1.2904761904761906e-05,
+      "loss": 2.6136,
+      "step": 980
+    },
+    {
+      "epoch": 0.792,
+      "grad_norm": 7.40625,
+      "learning_rate": 1.242857142857143e-05,
+      "loss": 2.7682,
+      "step": 990
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 7.71875,
+      "learning_rate": 1.1952380952380952e-05,
+      "loss": 2.6878,
+      "step": 1000
+    },
+    {
+      "epoch": 0.808,
+      "grad_norm": 8.0,
+      "learning_rate": 1.1476190476190476e-05,
+      "loss": 2.5709,
+      "step": 1010
+    },
+    {
+      "epoch": 0.816,
+      "grad_norm": 8.0625,
+      "learning_rate": 1.1000000000000001e-05,
+      "loss": 2.7941,
+      "step": 1020
+    },
+    {
+      "epoch": 0.824,
+      "grad_norm": 8.1875,
+      "learning_rate": 1.0523809523809525e-05,
+      "loss": 2.6739,
+      "step": 1030
+    },
+    {
+      "epoch": 0.832,
+      "grad_norm": 7.59375,
+      "learning_rate": 1.004761904761905e-05,
+      "loss": 2.6953,
+      "step": 1040
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 7.3125,
+      "learning_rate": 9.571428571428572e-06,
+      "loss": 2.6107,
+      "step": 1050
+    },
+    {
+      "epoch": 0.848,
+      "grad_norm": 7.59375,
+      "learning_rate": 9.095238095238095e-06,
+      "loss": 2.7805,
+      "step": 1060
+    },
+    {
+      "epoch": 0.856,
+      "grad_norm": 9.0625,
+      "learning_rate": 8.61904761904762e-06,
+      "loss": 2.7856,
+      "step": 1070
+    },
+    {
+      "epoch": 0.864,
+      "grad_norm": 7.75,
+      "learning_rate": 8.142857142857143e-06,
+      "loss": 2.6762,
+      "step": 1080
+    },
+    {
+      "epoch": 0.872,
+      "grad_norm": 7.625,
+      "learning_rate": 7.666666666666667e-06,
+      "loss": 2.7825,
+      "step": 1090
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 7.0,
+      "learning_rate": 7.19047619047619e-06,
+      "loss": 2.7893,
+      "step": 1100
+    },
+    {
+      "epoch": 0.888,
+      "grad_norm": 6.9375,
+      "learning_rate": 6.714285714285714e-06,
+      "loss": 2.7058,
+      "step": 1110
+    },
+    {
+      "epoch": 0.896,
+      "grad_norm": 7.03125,
+      "learning_rate": 6.238095238095239e-06,
+      "loss": 2.7899,
+      "step": 1120
+    },
+    {
+      "epoch": 0.904,
+      "grad_norm": 6.9375,
+      "learning_rate": 5.761904761904762e-06,
+      "loss": 2.6251,
+      "step": 1130
+    },
+    {
+      "epoch": 0.912,
+      "grad_norm": 6.84375,
+      "learning_rate": 5.285714285714286e-06,
+      "loss": 2.7011,
+      "step": 1140
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 6.78125,
+      "learning_rate": 4.80952380952381e-06,
+      "loss": 2.6375,
+      "step": 1150
+    },
+    {
+      "epoch": 0.928,
+      "grad_norm": 8.5625,
+      "learning_rate": 4.333333333333334e-06,
+      "loss": 2.7994,
+      "step": 1160
+    },
+    {
+      "epoch": 0.936,
+      "grad_norm": 6.59375,
+      "learning_rate": 3.857142857142857e-06,
+      "loss": 2.7145,
+      "step": 1170
+    },
+    {
+      "epoch": 0.944,
+      "grad_norm": 7.0625,
+      "learning_rate": 3.3809523809523814e-06,
+      "loss": 2.6465,
+      "step": 1180
+    },
+    {
+      "epoch": 0.952,
+      "grad_norm": 8.3125,
+      "learning_rate": 2.904761904761905e-06,
+      "loss": 2.7466,
+      "step": 1190
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 7.84375,
+      "learning_rate": 2.428571428571429e-06,
+      "loss": 2.76,
+      "step": 1200
+    },
+    {
+      "epoch": 0.968,
+      "grad_norm": 7.78125,
+      "learning_rate": 1.9523809523809523e-06,
+      "loss": 2.7507,
+      "step": 1210
+    },
+    {
+      "epoch": 0.976,
+      "grad_norm": 7.4375,
+      "learning_rate": 1.4761904761904762e-06,
+      "loss": 2.7197,
+      "step": 1220
+    },
+    {
+      "epoch": 0.984,
+      "grad_norm": 7.96875,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 2.7261,
+      "step": 1230
+    },
+    {
+      "epoch": 0.992,
+      "grad_norm": 5.90625,
+      "learning_rate": 5.238095238095238e-07,
+      "loss": 2.6812,
+      "step": 1240
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 8.125,
+      "learning_rate": 4.761904761904762e-08,
+      "loss": 2.6935,
+      "step": 1250
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1250,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.443927710242921e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1250/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7bfa58ce9748715a5711511426ed685dd546e89891028b84e29bedc4291ade9
+size 5841

config.json

@@ -0,0 +1,69 @@
+{
+  "architectures": [
+    "GptOssForCausalLM"
+  ],
+  "attention_bias": true,
+  "attention_dropout": 0.0,
+  "bos_token_id": 199998,
+  "dtype": "bfloat16",
+  "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"
+  ],
+  "max_position_embeddings": 131072,
+  "model_type": "gpt_oss",
+  "num_attention_heads": 64,
+  "num_experts_per_tok": 4,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 8,
+  "num_local_experts": 32,
+  "output_router_logits": false,
+  "pad_token_id": 199999,
+  "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": "4.57.1",
+  "use_cache": false,
+  "vocab_size": 201088
+}

generation_config.json

@@ -0,0 +1,11 @@
+{
+  "bos_token_id": 199998,
+  "do_sample": true,
+  "eos_token_id": [
+    200002,
+    199999,
+    200012
+  ],
+  "pad_token_id": 199999,
+  "transformers_version": "4.57.1"
+}

logs/events.out.tfevents.1763377278.idealistic-pudu-from-uranus-fa7e.10674.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccf40292de8fef165b1991f4da308ccf49c0bf864d5bcb0f5725b6e7ed67955d
+size 5999

logs/events.out.tfevents.1763377589.idealistic-pudu-from-uranus-fa7e.11740.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d89dbdf99bc27167a894217e0a77b19fe1c893499fe9e3803a4602661a928cf
+size 5999

logs/events.out.tfevents.1763377820.idealistic-pudu-from-uranus-fa7e.12716.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e81f935854e495713952658a7b2cbbe0e60ba4d72d0ac25c1b6cb5465b315d66
+size 6000

logs/events.out.tfevents.1763377925.idealistic-pudu-from-uranus-fa7e.13187.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:992703685fa84a0079cdd95164b7dc3c47661631bee013f71313ec930f2fa9b1
+size 6207

logs/events.out.tfevents.1763378147.idealistic-pudu-from-uranus-fa7e.14024.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:665e62bf2af7ef70f55c4289454ca80d1fda2ae476f46a775fc72ee0286aa461
+size 6207

logs/events.out.tfevents.1763378228.idealistic-pudu-from-uranus-fa7e.14429.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71e605388bcafaf25ce434a0ceb99de7b3a37c10b4eb491f342db94047ae2965
+size 32888

model-00001-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc729189133161b61e287dd7bdec06afc2b7f77ed1820ca53eda0553fa742230
+size 4504304664

model-00002-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4708b3da84cd7d559f5cd2eb9d0d13466ae1ccd90fdee8295d9ec3d8748582c
+size 4939127656

model-00003-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96031fa4efe1e880b2f17ac4352c3a2d251129d8140d122b9e8649a2d45c51d2
+size 4939127656

model-00004-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46e221c089ddcbacd6f4495a2dfccea2206cb8b21795ea868415125e9fb8139e
+size 4939127680

model-00005-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f223ae981c1c8f4925334b8e0954ce78a613b0602d3eba28ea73f0146c9d73f3
+size 4939127704

model-00006-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf0e3a0ccf931369e3ebe77f1f6d0a1781d739d6cb1dfed7c54fedda3f94fe18
+size 4939127704

model-00007-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51a3ad356e1a0d63de63f78975caf1a129d7d29bc00a7614de652aff7a4c57b0
+size 4939127704

model-00008-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07a2d79388f1f6f1bebac3d03216b6ac47c2bf498640ab54ac8c15beb629847f
+size 4939127704

model-00009-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2eda29cdc86d75937066cde98574795f08a96ebe34b22e126e1cb252ec494df4
+size 2751362856

model.safetensors.index.json

@@ -0,0 +1,419 @@
+{
+  "metadata": {
+    "total_parameters": 20914757184,
+    "total_size": 41829514368
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00009-of-00009.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.mlp.experts.down_proj": "model-00001-of-00009.safetensors",
+    "model.layers.0.mlp.experts.down_proj_bias": "model-00001-of-00009.safetensors",
+    "model.layers.0.mlp.experts.gate_up_proj": "model-00001-of-00009.safetensors",
+    "model.layers.0.mlp.experts.gate_up_proj_bias": "model-00001-of-00009.safetensors",
+    "model.layers.0.mlp.router.bias": "model-00001-of-00009.safetensors",
+    "model.layers.0.mlp.router.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00009.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.self_attn.o_proj.bias": "model-00001-of-00009.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00009.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.self_attn.sinks": "model-00001-of-00009.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00009.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.mlp.experts.down_proj": "model-00001-of-00009.safetensors",
+    "model.layers.1.mlp.experts.down_proj_bias": "model-00001-of-00009.safetensors",
+    "model.layers.1.mlp.experts.gate_up_proj": "model-00001-of-00009.safetensors",
+    "model.layers.1.mlp.experts.gate_up_proj_bias": "model-00001-of-00009.safetensors",
+    "model.layers.1.mlp.router.bias": "model-00001-of-00009.safetensors",
+    "model.layers.1.mlp.router.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00009.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.self_attn.o_proj.bias": "model-00001-of-00009.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00009.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.self_attn.sinks": "model-00001-of-00009.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00009.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.10.mlp.experts.down_proj": "model-00004-of-00009.safetensors",
+    "model.layers.10.mlp.experts.down_proj_bias": "model-00004-of-00009.safetensors",
+    "model.layers.10.mlp.experts.gate_up_proj": "model-00004-of-00009.safetensors",
+    "model.layers.10.mlp.experts.gate_up_proj_bias": "model-00004-of-00009.safetensors",
+    "model.layers.10.mlp.router.bias": "model-00004-of-00009.safetensors",
+    "model.layers.10.mlp.router.weight": "model-00004-of-00009.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00004-of-00009.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.10.self_attn.o_proj.bias": "model-00004-of-00009.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00004-of-00009.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.10.self_attn.sinks": "model-00004-of-00009.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00004-of-00009.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.11.mlp.experts.down_proj": "model-00005-of-00009.safetensors",
+    "model.layers.11.mlp.experts.down_proj_bias": "model-00005-of-00009.safetensors",
+    "model.layers.11.mlp.experts.gate_up_proj": "model-00005-of-00009.safetensors",
+    "model.layers.11.mlp.experts.gate_up_proj_bias": "model-00005-of-00009.safetensors",
+    "model.layers.11.mlp.router.bias": "model-00004-of-00009.safetensors",
+    "model.layers.11.mlp.router.weight": "model-00004-of-00009.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00004-of-00009.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.11.self_attn.o_proj.bias": "model-00004-of-00009.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00004-of-00009.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.11.self_attn.sinks": "model-00004-of-00009.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00004-of-00009.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.12.mlp.experts.down_proj": "model-00005-of-00009.safetensors",
+    "model.layers.12.mlp.experts.down_proj_bias": "model-00005-of-00009.safetensors",
+    "model.layers.12.mlp.experts.gate_up_proj": "model-00005-of-00009.safetensors",
+    "model.layers.12.mlp.experts.gate_up_proj_bias": "model-00005-of-00009.safetensors",
+    "model.layers.12.mlp.router.bias": "model-00005-of-00009.safetensors",
+    "model.layers.12.mlp.router.weight": "model-00005-of-00009.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00005-of-00009.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.12.self_attn.o_proj.bias": "model-00005-of-00009.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00005-of-00009.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.12.self_attn.sinks": "model-00005-of-00009.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00005-of-00009.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.13.mlp.experts.down_proj": "model-00005-of-00009.safetensors",
+    "model.layers.13.mlp.experts.down_proj_bias": "model-00005-of-00009.safetensors",
+    "model.layers.13.mlp.experts.gate_up_proj": "model-00005-of-00009.safetensors",
+    "model.layers.13.mlp.experts.gate_up_proj_bias": "model-00005-of-00009.safetensors",
+    "model.layers.13.mlp.router.bias": "model-00005-of-00009.safetensors",
+    "model.layers.13.mlp.router.weight": "model-00005-of-00009.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00005-of-00009.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.13.self_attn.o_proj.bias": "model-00005-of-00009.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00005-of-00009.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.13.self_attn.sinks": "model-00005-of-00009.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00005-of-00009.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.14.mlp.experts.down_proj": "model-00006-of-00009.safetensors",
+    "model.layers.14.mlp.experts.down_proj_bias": "model-00006-of-00009.safetensors",
+    "model.layers.14.mlp.experts.gate_up_proj": "model-00006-of-00009.safetensors",
+    "model.layers.14.mlp.experts.gate_up_proj_bias": "model-00006-of-00009.safetensors",
+    "model.layers.14.mlp.router.bias": "model-00005-of-00009.safetensors",
+    "model.layers.14.mlp.router.weight": "model-00005-of-00009.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00005-of-00009.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.14.self_attn.o_proj.bias": "model-00005-of-00009.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00005-of-00009.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.14.self_attn.sinks": "model-00005-of-00009.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00005-of-00009.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.15.mlp.experts.down_proj": "model-00006-of-00009.safetensors",
+    "model.layers.15.mlp.experts.down_proj_bias": "model-00006-of-00009.safetensors",
+    "model.layers.15.mlp.experts.gate_up_proj": "model-00006-of-00009.safetensors",
+    "model.layers.15.mlp.experts.gate_up_proj_bias": "model-00006-of-00009.safetensors",
+    "model.layers.15.mlp.router.bias": "model-00006-of-00009.safetensors",
+    "model.layers.15.mlp.router.weight": "model-00006-of-00009.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00006-of-00009.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.15.self_attn.o_proj.bias": "model-00006-of-00009.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00006-of-00009.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.15.self_attn.sinks": "model-00006-of-00009.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00006-of-00009.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.16.mlp.experts.down_proj": "model-00006-of-00009.safetensors",
+    "model.layers.16.mlp.experts.down_proj_bias": "model-00006-of-00009.safetensors",
+    "model.layers.16.mlp.experts.gate_up_proj": "model-00006-of-00009.safetensors",
+    "model.layers.16.mlp.experts.gate_up_proj_bias": "model-00006-of-00009.safetensors",
+    "model.layers.16.mlp.router.bias": "model-00006-of-00009.safetensors",
+    "model.layers.16.mlp.router.weight": "model-00006-of-00009.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00006-of-00009.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.16.self_attn.o_proj.bias": "model-00006-of-00009.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00006-of-00009.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.16.self_attn.sinks": "model-00006-of-00009.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00006-of-00009.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.17.mlp.experts.down_proj": "model-00007-of-00009.safetensors",
+    "model.layers.17.mlp.experts.down_proj_bias": "model-00007-of-00009.safetensors",
+    "model.layers.17.mlp.experts.gate_up_proj": "model-00007-of-00009.safetensors",
+    "model.layers.17.mlp.experts.gate_up_proj_bias": "model-00007-of-00009.safetensors",
+    "model.layers.17.mlp.router.bias": "model-00006-of-00009.safetensors",
+    "model.layers.17.mlp.router.weight": "model-00006-of-00009.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00006-of-00009.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.17.self_attn.o_proj.bias": "model-00006-of-00009.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00006-of-00009.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.17.self_attn.sinks": "model-00006-of-00009.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00006-of-00009.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.18.mlp.experts.down_proj": "model-00007-of-00009.safetensors",
+    "model.layers.18.mlp.experts.down_proj_bias": "model-00007-of-00009.safetensors",
+    "model.layers.18.mlp.experts.gate_up_proj": "model-00007-of-00009.safetensors",
+    "model.layers.18.mlp.experts.gate_up_proj_bias": "model-00007-of-00009.safetensors",
+    "model.layers.18.mlp.router.bias": "model-00007-of-00009.safetensors",
+    "model.layers.18.mlp.router.weight": "model-00007-of-00009.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00007-of-00009.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.18.self_attn.o_proj.bias": "model-00007-of-00009.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00007-of-00009.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.18.self_attn.sinks": "model-00007-of-00009.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00007-of-00009.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.19.mlp.experts.down_proj": "model-00007-of-00009.safetensors",
+    "model.layers.19.mlp.experts.down_proj_bias": "model-00007-of-00009.safetensors",
+    "model.layers.19.mlp.experts.gate_up_proj": "model-00007-of-00009.safetensors",
+    "model.layers.19.mlp.experts.gate_up_proj_bias": "model-00007-of-00009.safetensors",
+    "model.layers.19.mlp.router.bias": "model-00007-of-00009.safetensors",
+    "model.layers.19.mlp.router.weight": "model-00007-of-00009.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00007-of-00009.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.19.self_attn.o_proj.bias": "model-00007-of-00009.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00007-of-00009.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.19.self_attn.sinks": "model-00007-of-00009.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00007-of-00009.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.2.mlp.experts.down_proj": "model-00002-of-00009.safetensors",
+    "model.layers.2.mlp.experts.down_proj_bias": "model-00002-of-00009.safetensors",
+    "model.layers.2.mlp.experts.gate_up_proj": "model-00002-of-00009.safetensors",
+    "model.layers.2.mlp.experts.gate_up_proj_bias": "model-00002-of-00009.safetensors",
+    "model.layers.2.mlp.router.bias": "model-00001-of-00009.safetensors",
+    "model.layers.2.mlp.router.weight": "model-00001-of-00009.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00009.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.2.self_attn.o_proj.bias": "model-00001-of-00009.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00009.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.2.self_attn.sinks": "model-00001-of-00009.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00009.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.20.mlp.experts.down_proj": "model-00008-of-00009.safetensors",
+    "model.layers.20.mlp.experts.down_proj_bias": "model-00008-of-00009.safetensors",
+    "model.layers.20.mlp.experts.gate_up_proj": "model-00008-of-00009.safetensors",
+    "model.layers.20.mlp.experts.gate_up_proj_bias": "model-00008-of-00009.safetensors",
+    "model.layers.20.mlp.router.bias": "model-00007-of-00009.safetensors",
+    "model.layers.20.mlp.router.weight": "model-00007-of-00009.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00007-of-00009.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.20.self_attn.o_proj.bias": "model-00007-of-00009.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00007-of-00009.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.20.self_attn.sinks": "model-00007-of-00009.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00007-of-00009.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.21.mlp.experts.down_proj": "model-00008-of-00009.safetensors",
+    "model.layers.21.mlp.experts.down_proj_bias": "model-00008-of-00009.safetensors",
+    "model.layers.21.mlp.experts.gate_up_proj": "model-00008-of-00009.safetensors",
+    "model.layers.21.mlp.experts.gate_up_proj_bias": "model-00008-of-00009.safetensors",
+    "model.layers.21.mlp.router.bias": "model-00008-of-00009.safetensors",
+    "model.layers.21.mlp.router.weight": "model-00008-of-00009.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00008-of-00009.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.21.self_attn.o_proj.bias": "model-00008-of-00009.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00008-of-00009.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.21.self_attn.sinks": "model-00008-of-00009.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00008-of-00009.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.22.mlp.experts.down_proj": "model-00008-of-00009.safetensors",
+    "model.layers.22.mlp.experts.down_proj_bias": "model-00008-of-00009.safetensors",
+    "model.layers.22.mlp.experts.gate_up_proj": "model-00008-of-00009.safetensors",
+    "model.layers.22.mlp.experts.gate_up_proj_bias": "model-00008-of-00009.safetensors",
+    "model.layers.22.mlp.router.bias": "model-00008-of-00009.safetensors",
+    "model.layers.22.mlp.router.weight": "model-00008-of-00009.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00008-of-00009.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.22.self_attn.o_proj.bias": "model-00008-of-00009.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00008-of-00009.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.22.self_attn.sinks": "model-00008-of-00009.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00008-of-00009.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00009-of-00009.safetensors",
+    "model.layers.23.mlp.experts.down_proj": "model-00009-of-00009.safetensors",
+    "model.layers.23.mlp.experts.down_proj_bias": "model-00009-of-00009.safetensors",
+    "model.layers.23.mlp.experts.gate_up_proj": "model-00009-of-00009.safetensors",
+    "model.layers.23.mlp.experts.gate_up_proj_bias": "model-00009-of-00009.safetensors",
+    "model.layers.23.mlp.router.bias": "model-00008-of-00009.safetensors",
+    "model.layers.23.mlp.router.weight": "model-00008-of-00009.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00008-of-00009.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.23.self_attn.o_proj.bias": "model-00008-of-00009.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00008-of-00009.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.23.self_attn.sinks": "model-00008-of-00009.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00008-of-00009.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.3.mlp.experts.down_proj": "model-00002-of-00009.safetensors",
+    "model.layers.3.mlp.experts.down_proj_bias": "model-00002-of-00009.safetensors",
+    "model.layers.3.mlp.experts.gate_up_proj": "model-00002-of-00009.safetensors",
+    "model.layers.3.mlp.experts.gate_up_proj_bias": "model-00002-of-00009.safetensors",
+    "model.layers.3.mlp.router.bias": "model-00002-of-00009.safetensors",
+    "model.layers.3.mlp.router.weight": "model-00002-of-00009.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00002-of-00009.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.3.self_attn.o_proj.bias": "model-00002-of-00009.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00002-of-00009.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.3.self_attn.sinks": "model-00002-of-00009.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00002-of-00009.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.4.mlp.experts.down_proj": "model-00002-of-00009.safetensors",
+    "model.layers.4.mlp.experts.down_proj_bias": "model-00002-of-00009.safetensors",
+    "model.layers.4.mlp.experts.gate_up_proj": "model-00002-of-00009.safetensors",
+    "model.layers.4.mlp.experts.gate_up_proj_bias": "model-00002-of-00009.safetensors",
+    "model.layers.4.mlp.router.bias": "model-00002-of-00009.safetensors",
+    "model.layers.4.mlp.router.weight": "model-00002-of-00009.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00009.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.4.self_attn.o_proj.bias": "model-00002-of-00009.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00009.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.4.self_attn.sinks": "model-00002-of-00009.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00009.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.5.mlp.experts.down_proj": "model-00003-of-00009.safetensors",
+    "model.layers.5.mlp.experts.down_proj_bias": "model-00003-of-00009.safetensors",
+    "model.layers.5.mlp.experts.gate_up_proj": "model-00003-of-00009.safetensors",
+    "model.layers.5.mlp.experts.gate_up_proj_bias": "model-00003-of-00009.safetensors",
+    "model.layers.5.mlp.router.bias": "model-00002-of-00009.safetensors",
+    "model.layers.5.mlp.router.weight": "model-00002-of-00009.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00009.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.5.self_attn.o_proj.bias": "model-00002-of-00009.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00009.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.5.self_attn.sinks": "model-00002-of-00009.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00009.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.6.mlp.experts.down_proj": "model-00003-of-00009.safetensors",
+    "model.layers.6.mlp.experts.down_proj_bias": "model-00003-of-00009.safetensors",
+    "model.layers.6.mlp.experts.gate_up_proj": "model-00003-of-00009.safetensors",
+    "model.layers.6.mlp.experts.gate_up_proj_bias": "model-00003-of-00009.safetensors",
+    "model.layers.6.mlp.router.bias": "model-00003-of-00009.safetensors",
+    "model.layers.6.mlp.router.weight": "model-00003-of-00009.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00003-of-00009.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.6.self_attn.o_proj.bias": "model-00003-of-00009.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00003-of-00009.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.6.self_attn.sinks": "model-00003-of-00009.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00003-of-00009.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.7.mlp.experts.down_proj": "model-00003-of-00009.safetensors",
+    "model.layers.7.mlp.experts.down_proj_bias": "model-00003-of-00009.safetensors",
+    "model.layers.7.mlp.experts.gate_up_proj": "model-00003-of-00009.safetensors",
+    "model.layers.7.mlp.experts.gate_up_proj_bias": "model-00003-of-00009.safetensors",
+    "model.layers.7.mlp.router.bias": "model-00003-of-00009.safetensors",
+    "model.layers.7.mlp.router.weight": "model-00003-of-00009.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00003-of-00009.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.7.self_attn.o_proj.bias": "model-00003-of-00009.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00003-of-00009.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.7.self_attn.sinks": "model-00003-of-00009.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00003-of-00009.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.8.mlp.experts.down_proj": "model-00004-of-00009.safetensors",
+    "model.layers.8.mlp.experts.down_proj_bias": "model-00004-of-00009.safetensors",
+    "model.layers.8.mlp.experts.gate_up_proj": "model-00004-of-00009.safetensors",
+    "model.layers.8.mlp.experts.gate_up_proj_bias": "model-00004-of-00009.safetensors",
+    "model.layers.8.mlp.router.bias": "model-00003-of-00009.safetensors",
+    "model.layers.8.mlp.router.weight": "model-00003-of-00009.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00003-of-00009.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.8.self_attn.o_proj.bias": "model-00003-of-00009.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00003-of-00009.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.8.self_attn.sinks": "model-00003-of-00009.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00003-of-00009.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.9.mlp.experts.down_proj": "model-00004-of-00009.safetensors",
+    "model.layers.9.mlp.experts.down_proj_bias": "model-00004-of-00009.safetensors",
+    "model.layers.9.mlp.experts.gate_up_proj": "model-00004-of-00009.safetensors",
+    "model.layers.9.mlp.experts.gate_up_proj_bias": "model-00004-of-00009.safetensors",
+    "model.layers.9.mlp.router.bias": "model-00004-of-00009.safetensors",
+    "model.layers.9.mlp.router.weight": "model-00004-of-00009.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00004-of-00009.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.9.self_attn.o_proj.bias": "model-00004-of-00009.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00004-of-00009.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.9.self_attn.sinks": "model-00004-of-00009.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00004-of-00009.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.norm.weight": "model-00009-of-00009.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|return|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

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"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7bfa58ce9748715a5711511426ed685dd546e89891028b84e29bedc4291ade9
+size 5841