Add files using upload-large-folder tool

.gitattributes

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

chat_template.jinja

@@ -0,0 +1,331 @@
+{#-
+  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 }}
+    {%- endif %}
+    {%- if tools -%}
+        {{- "\n\n" }}
+        {{- "# 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 -%}

config.json

@@ -0,0 +1,80 @@
+{
+  "architectures": [
+    "GptOssForCausalLM"
+  ],
+  "attention_bias": true,
+  "attention_dropout": 0.0,
+  "eos_token_id": 200002,
+  "experts_per_token": 4,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2880,
+  "initial_context_length": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 2880,
+  "layer_types": [
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 131072,
+  "model_type": "gpt_oss",
+  "num_attention_heads": 64,
+  "num_experts_per_tok": 4,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "num_local_experts": 128,
+  "output_router_logits": false,
+  "pad_token_id": 199999,
+  "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,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.55.2",
+  "use_cache": false,
+  "vocab_size": 201088
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "bos_token_id": 199998,
+  "do_sample": true,
+  "eos_token_id": [
+    200002,
+    199999
+  ],
+  "pad_token_id": 199999,
+  "transformers_version": "4.55.2"
+}

model-00001-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b637892fc052c69cabe5853086f5809dc9672e792d2a71042455397ebb7c4f47
+size 1212106064

model-00002-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88cb5c37b89e6ab5bd430cdbe52c6e947e1c29221dfa130d0b739b0d9c5afb13
+size 4248207640

model-00003-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c18a5a4e8d184f4d13d8afe17c461975cb75bc931d8c6c6907cae0d132883c91
+size 2177954736

model-00004-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:612d82e407beec185056f12c99cbca6166d284c592d9662a095a5d294e3069d4
+size 4248207640

model-00005-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:191fc1af4f5c58448f1c1683d959425a6d8bfeacd739f3d83585178bf465a3b9
+size 2177954736

model-00006-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2941ca2ff5b227fb1762866dd60de120f1800efa2cb6bb5a63b90ce3a21abd5e
+size 4248207640

model-00007-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2674c10d6f5cbb4635e1380df03768a461e28d6fb0ad1bda36571321b2809bc
+size 2177954736

model-00008-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8163980f1ba40724b7e2486a8a569968a770d1403986e361220804696cb0997
+size 4248207640

model-00009-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3528e140c13a021f20079d8092447d43f8d66d0e20af652f7230d321c186a8f
+size 2177954736

model-00010-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93e39d83df001e78560ec241f7e0575d07a4c5baa6e46627c1a90b630a58d290
+size 4248207640

model-00011-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cc6e4459a8ff42ef8028940d745a5bdf1e303ef2fbc1df57b78758dc955eab0
+size 2177954736

model-00012-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1ce951cc757cfed2c50fbe59df99f674a3a0d04ce8350ce62a6e414a77a99d4
+size 4248207640

model-00013-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:beeccc1212b9afddbaf7a19b72858b059cbde50689bcb7e69d7bfcfe3fe77521
+size 2177954736

model-00015-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b87e6b5619c7108f50025769109fe9c1f6d29bf35bbf81f19106fabd2e1095ba
+size 2177954736

model-00017-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3047c2dedc2f29fc484b412d8f78d5aeba7cb97e216f02886b6a1a0e546b5426
+size 2177954736

model-00019-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4050a6e2f9528296734e904869c7cecf9304ea2160b48f9aa91f1e12ecf0eed
+size 2177954736

model-00021-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:411e1ca65f8f3fd346d981cf9a5c24839225c4bb72dcc47b9421e2795747ec8f
+size 2177954688

model-00023-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc14c0a30eabcc78704fd40b2a67242be4d3ba3ee036615f2c5c5d5ea0179db0
+size 2177954752

model-00025-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aaaaca5f9931fe97c9510cd4cde61a4ccebb1fd7328838568448e9091f3f730c
+size 2177954752

model-00027-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6aafa832ed04a7a0ad261a27ac264240fb9bb68ffcd808738fa031ceb249008
+size 2177954752

model-00029-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45fbe448e7e1c1ec61c3445813b60c5123145939b9f6db96fc724750f66fea31
+size 2177954752

model-00031-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fef06650112bc23a56529425e615d284cf24ea9f50a8baa63803c70355e1931
+size 2177954752

model-00033-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:630d7ba901b2a75cc4ef7302b197cea636a7460ff388f698a0f08593bcaa743e
+size 2177954752

model-00035-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e32e74e3f76c2c47c846611ed859ec7c2529f9c9df440c24239b54ec06c70772
+size 2177954752

model-00037-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d866ce9171b4cd7e00a70510dd10ae1b7d90464b820be54f05bbda8ccc342d45
+size 2177954752

model-00039-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:023e9e47835efb0f61b38a3b6820096eb410cd635d37a5dd9b03e834b43530a4
+size 2177954752

model-00041-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3e35fc54377359fffb78e08cbada29b5988f71bd17926565d983c2ba4a483ed
+size 2177954752

model-00043-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7a2ae86c1c0a32ca99bcd08331d9636bdc9dcdd145b42171bc98a349491ba3e
+size 2177954752

model-00045-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f121bd962ef7ad72b25d627954d69bdd890023fb6bee49e48ac10eb271440bd0
+size 2177954752

model-00047-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d48c5b2e76a35084f83c9128e49464e3ada8354e19416a19b9405a7cd9f50d4
+size 2177954752

model-00049-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd147852baa24ab0f809f689c8e3aa0cecc32b87334edb50e46d37f90876289a
+size 2177954752

model-00051-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eae8c1d40ca531f4ae67437a90ae1018689d93c49c10e5ff3adb96654e526377
+size 2177954752

model-00053-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdeffa5f88834ed0ada066730e7afe9ac1e32e3c904d8cd61bead9dfab2b26bb
+size 2177954752

model-00055-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cca6954fe079a5597708f6750bcc09502a5f3172a77b323af3bf62b963ba0b4
+size 2177954752

model-00057-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3845a31052f37cde3f3c5fa9905b5ab3beac96521b245e5fa16bc69d055d60a4
+size 2177954752

model-00059-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f59c99306815a8d9240e7699600eb39e2ec05b66c5a29a6a4013e38944085b0
+size 2177954752

model-00061-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aaa91bf8e5e7cad53aa7b07a9de78eb44bc93f39e5ca5b3763f00790b63c804b
+size 2177954752

model-00063-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:539b5c1c4ea319442ffe45662f877e8a4aee59f62c14bb5926cf8e6adf4cf71f
+size 2177954752

model-00065-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b84e934a06a3ab664132d962596d3454ee817cfb873eb4227e730eb603c41d2
+size 2177954752

model-00067-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33499655063ce6a491fd158f7e9ab970f0aff22338fbb9491f26a485ccfb27ac
+size 2177954752

model-00069-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac2d0bc8cfaa08a10bca4257daa1411f74f75f37acd5d1136f2d8ece87a386d0
+size 2177954752

model-00071-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecc960733576fe281ca082b2f384a1e4e349a234760a2cdf822082782fe12a81
+size 2177954752

model-00073-of-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5606a0b61d517a7baeb81d2aa7edd92952271c82bb8fc57456595dac32408ef1
+size 3282388536

model.safetensors.index.json

@@ -0,0 +1,623 @@
+{
+  "metadata": {
+    "total_parameters": 116829156672,
+    "total_size": 233658313344
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00073-of-00073.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00073.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00003-of-00073.safetensors",
+    "model.layers.0.mlp.experts.down_proj": "model-00003-of-00073.safetensors",
+    "model.layers.0.mlp.experts.down_proj_bias": "model-00003-of-00073.safetensors",
+    "model.layers.0.mlp.experts.gate_up_proj": "model-00002-of-00073.safetensors",
+    "model.layers.0.mlp.experts.gate_up_proj_bias": "model-00002-of-00073.safetensors",
+    "model.layers.0.mlp.router.bias": "model-00001-of-00073.safetensors",
+    "model.layers.0.mlp.router.weight": "model-00001-of-00073.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00073.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00073.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00073.safetensors",
+    "model.layers.0.self_attn.o_proj.bias": "model-00001-of-00073.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00073.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00073.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00073.safetensors",
+    "model.layers.0.self_attn.sinks": "model-00001-of-00073.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00073.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00073.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00005-of-00073.safetensors",
+    "model.layers.1.mlp.experts.down_proj": "model-00005-of-00073.safetensors",
+    "model.layers.1.mlp.experts.down_proj_bias": "model-00005-of-00073.safetensors",
+    "model.layers.1.mlp.experts.gate_up_proj": "model-00004-of-00073.safetensors",
+    "model.layers.1.mlp.experts.gate_up_proj_bias": "model-00004-of-00073.safetensors",
+    "model.layers.1.mlp.router.bias": "model-00003-of-00073.safetensors",
+    "model.layers.1.mlp.router.weight": "model-00003-of-00073.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00005-of-00073.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00003-of-00073.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00003-of-00073.safetensors",
+    "model.layers.1.self_attn.o_proj.bias": "model-00003-of-00073.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00003-of-00073.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00003-of-00073.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00003-of-00073.safetensors",
+    "model.layers.1.self_attn.sinks": "model-00003-of-00073.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00003-of-00073.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00003-of-00073.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00023-of-00073.safetensors",
+    "model.layers.10.mlp.experts.down_proj": "model-00023-of-00073.safetensors",
+    "model.layers.10.mlp.experts.down_proj_bias": "model-00023-of-00073.safetensors",
+    "model.layers.10.mlp.experts.gate_up_proj": "model-00022-of-00073.safetensors",
+    "model.layers.10.mlp.experts.gate_up_proj_bias": "model-00022-of-00073.safetensors",
+    "model.layers.10.mlp.router.bias": "model-00021-of-00073.safetensors",
+    "model.layers.10.mlp.router.weight": "model-00021-of-00073.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00023-of-00073.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00021-of-00073.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00021-of-00073.safetensors",
+    "model.layers.10.self_attn.o_proj.bias": "model-00021-of-00073.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00021-of-00073.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00021-of-00073.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00021-of-00073.safetensors",
+    "model.layers.10.self_attn.sinks": "model-00021-of-00073.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00021-of-00073.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00021-of-00073.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00025-of-00073.safetensors",
+    "model.layers.11.mlp.experts.down_proj": "model-00025-of-00073.safetensors",
+    "model.layers.11.mlp.experts.down_proj_bias": "model-00025-of-00073.safetensors",
+    "model.layers.11.mlp.experts.gate_up_proj": "model-00024-of-00073.safetensors",
+    "model.layers.11.mlp.experts.gate_up_proj_bias": "model-00024-of-00073.safetensors",
+    "model.layers.11.mlp.router.bias": "model-00023-of-00073.safetensors",
+    "model.layers.11.mlp.router.weight": "model-00023-of-00073.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00025-of-00073.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00023-of-00073.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00023-of-00073.safetensors",
+    "model.layers.11.self_attn.o_proj.bias": "model-00023-of-00073.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00023-of-00073.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00023-of-00073.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00023-of-00073.safetensors",
+    "model.layers.11.self_attn.sinks": "model-00023-of-00073.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00023-of-00073.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00023-of-00073.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00027-of-00073.safetensors",
+    "model.layers.12.mlp.experts.down_proj": "model-00027-of-00073.safetensors",
+    "model.layers.12.mlp.experts.down_proj_bias": "model-00027-of-00073.safetensors",
+    "model.layers.12.mlp.experts.gate_up_proj": "model-00026-of-00073.safetensors",
+    "model.layers.12.mlp.experts.gate_up_proj_bias": "model-00026-of-00073.safetensors",
+    "model.layers.12.mlp.router.bias": "model-00025-of-00073.safetensors",
+    "model.layers.12.mlp.router.weight": "model-00025-of-00073.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00027-of-00073.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00025-of-00073.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00025-of-00073.safetensors",
+    "model.layers.12.self_attn.o_proj.bias": "model-00025-of-00073.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00025-of-00073.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00025-of-00073.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00025-of-00073.safetensors",
+    "model.layers.12.self_attn.sinks": "model-00025-of-00073.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00025-of-00073.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00025-of-00073.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00029-of-00073.safetensors",
+    "model.layers.13.mlp.experts.down_proj": "model-00029-of-00073.safetensors",
+    "model.layers.13.mlp.experts.down_proj_bias": "model-00029-of-00073.safetensors",
+    "model.layers.13.mlp.experts.gate_up_proj": "model-00028-of-00073.safetensors",
+    "model.layers.13.mlp.experts.gate_up_proj_bias": "model-00028-of-00073.safetensors",
+    "model.layers.13.mlp.router.bias": "model-00027-of-00073.safetensors",
+    "model.layers.13.mlp.router.weight": "model-00027-of-00073.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00029-of-00073.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00027-of-00073.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00027-of-00073.safetensors",
+    "model.layers.13.self_attn.o_proj.bias": "model-00027-of-00073.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00027-of-00073.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00027-of-00073.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00027-of-00073.safetensors",
+    "model.layers.13.self_attn.sinks": "model-00027-of-00073.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00027-of-00073.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00027-of-00073.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00031-of-00073.safetensors",
+    "model.layers.14.mlp.experts.down_proj": "model-00031-of-00073.safetensors",
+    "model.layers.14.mlp.experts.down_proj_bias": "model-00031-of-00073.safetensors",
+    "model.layers.14.mlp.experts.gate_up_proj": "model-00030-of-00073.safetensors",
+    "model.layers.14.mlp.experts.gate_up_proj_bias": "model-00030-of-00073.safetensors",
+    "model.layers.14.mlp.router.bias": "model-00029-of-00073.safetensors",
+    "model.layers.14.mlp.router.weight": "model-00029-of-00073.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00031-of-00073.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00029-of-00073.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00029-of-00073.safetensors",
+    "model.layers.14.self_attn.o_proj.bias": "model-00029-of-00073.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00029-of-00073.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00029-of-00073.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00029-of-00073.safetensors",
+    "model.layers.14.self_attn.sinks": "model-00029-of-00073.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00029-of-00073.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00029-of-00073.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00033-of-00073.safetensors",
+    "model.layers.15.mlp.experts.down_proj": "model-00033-of-00073.safetensors",
+    "model.layers.15.mlp.experts.down_proj_bias": "model-00033-of-00073.safetensors",
+    "model.layers.15.mlp.experts.gate_up_proj": "model-00032-of-00073.safetensors",
+    "model.layers.15.mlp.experts.gate_up_proj_bias": "model-00032-of-00073.safetensors",
+    "model.layers.15.mlp.router.bias": "model-00031-of-00073.safetensors",
+    "model.layers.15.mlp.router.weight": "model-00031-of-00073.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00033-of-00073.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00031-of-00073.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00031-of-00073.safetensors",
+    "model.layers.15.self_attn.o_proj.bias": "model-00031-of-00073.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00031-of-00073.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00031-of-00073.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00031-of-00073.safetensors",
+    "model.layers.15.self_attn.sinks": "model-00031-of-00073.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00031-of-00073.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00031-of-00073.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00035-of-00073.safetensors",
+    "model.layers.16.mlp.experts.down_proj": "model-00035-of-00073.safetensors",
+    "model.layers.16.mlp.experts.down_proj_bias": "model-00035-of-00073.safetensors",
+    "model.layers.16.mlp.experts.gate_up_proj": "model-00034-of-00073.safetensors",
+    "model.layers.16.mlp.experts.gate_up_proj_bias": "model-00034-of-00073.safetensors",
+    "model.layers.16.mlp.router.bias": "model-00033-of-00073.safetensors",
+    "model.layers.16.mlp.router.weight": "model-00033-of-00073.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00035-of-00073.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00033-of-00073.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00033-of-00073.safetensors",
+    "model.layers.16.self_attn.o_proj.bias": "model-00033-of-00073.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00033-of-00073.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00033-of-00073.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00033-of-00073.safetensors",
+    "model.layers.16.self_attn.sinks": "model-00033-of-00073.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00033-of-00073.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00033-of-00073.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00037-of-00073.safetensors",
+    "model.layers.17.mlp.experts.down_proj": "model-00037-of-00073.safetensors",
+    "model.layers.17.mlp.experts.down_proj_bias": "model-00037-of-00073.safetensors",
+    "model.layers.17.mlp.experts.gate_up_proj": "model-00036-of-00073.safetensors",
+    "model.layers.17.mlp.experts.gate_up_proj_bias": "model-00036-of-00073.safetensors",
+    "model.layers.17.mlp.router.bias": "model-00035-of-00073.safetensors",
+    "model.layers.17.mlp.router.weight": "model-00035-of-00073.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00037-of-00073.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00035-of-00073.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00035-of-00073.safetensors",
+    "model.layers.17.self_attn.o_proj.bias": "model-00035-of-00073.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00035-of-00073.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00035-of-00073.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00035-of-00073.safetensors",
+    "model.layers.17.self_attn.sinks": "model-00035-of-00073.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00035-of-00073.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00035-of-00073.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00039-of-00073.safetensors",
+    "model.layers.18.mlp.experts.down_proj": "model-00039-of-00073.safetensors",
+    "model.layers.18.mlp.experts.down_proj_bias": "model-00039-of-00073.safetensors",
+    "model.layers.18.mlp.experts.gate_up_proj": "model-00038-of-00073.safetensors",
+    "model.layers.18.mlp.experts.gate_up_proj_bias": "model-00038-of-00073.safetensors",
+    "model.layers.18.mlp.router.bias": "model-00037-of-00073.safetensors",
+    "model.layers.18.mlp.router.weight": "model-00037-of-00073.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00039-of-00073.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00037-of-00073.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00037-of-00073.safetensors",
+    "model.layers.18.self_attn.o_proj.bias": "model-00037-of-00073.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00037-of-00073.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00037-of-00073.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00037-of-00073.safetensors",
+    "model.layers.18.self_attn.sinks": "model-00037-of-00073.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00037-of-00073.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00037-of-00073.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00041-of-00073.safetensors",
+    "model.layers.19.mlp.experts.down_proj": "model-00041-of-00073.safetensors",
+    "model.layers.19.mlp.experts.down_proj_bias": "model-00041-of-00073.safetensors",
+    "model.layers.19.mlp.experts.gate_up_proj": "model-00040-of-00073.safetensors",
+    "model.layers.19.mlp.experts.gate_up_proj_bias": "model-00040-of-00073.safetensors",
+    "model.layers.19.mlp.router.bias": "model-00039-of-00073.safetensors",
+    "model.layers.19.mlp.router.weight": "model-00039-of-00073.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00041-of-00073.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00039-of-00073.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00039-of-00073.safetensors",
+    "model.layers.19.self_attn.o_proj.bias": "model-00039-of-00073.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00039-of-00073.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00039-of-00073.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00039-of-00073.safetensors",
+    "model.layers.19.self_attn.sinks": "model-00039-of-00073.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00039-of-00073.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00039-of-00073.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00007-of-00073.safetensors",
+    "model.layers.2.mlp.experts.down_proj": "model-00007-of-00073.safetensors",
+    "model.layers.2.mlp.experts.down_proj_bias": "model-00007-of-00073.safetensors",
+    "model.layers.2.mlp.experts.gate_up_proj": "model-00006-of-00073.safetensors",
+    "model.layers.2.mlp.experts.gate_up_proj_bias": "model-00006-of-00073.safetensors",
+    "model.layers.2.mlp.router.bias": "model-00005-of-00073.safetensors",
+    "model.layers.2.mlp.router.weight": "model-00005-of-00073.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00007-of-00073.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00005-of-00073.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00005-of-00073.safetensors",
+    "model.layers.2.self_attn.o_proj.bias": "model-00005-of-00073.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00005-of-00073.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00005-of-00073.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00005-of-00073.safetensors",
+    "model.layers.2.self_attn.sinks": "model-00005-of-00073.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00005-of-00073.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00005-of-00073.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00043-of-00073.safetensors",
+    "model.layers.20.mlp.experts.down_proj": "model-00043-of-00073.safetensors",
+    "model.layers.20.mlp.experts.down_proj_bias": "model-00043-of-00073.safetensors",
+    "model.layers.20.mlp.experts.gate_up_proj": "model-00042-of-00073.safetensors",
+    "model.layers.20.mlp.experts.gate_up_proj_bias": "model-00042-of-00073.safetensors",
+    "model.layers.20.mlp.router.bias": "model-00041-of-00073.safetensors",
+    "model.layers.20.mlp.router.weight": "model-00041-of-00073.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00043-of-00073.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00041-of-00073.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00041-of-00073.safetensors",
+    "model.layers.20.self_attn.o_proj.bias": "model-00041-of-00073.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00041-of-00073.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00041-of-00073.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00041-of-00073.safetensors",
+    "model.layers.20.self_attn.sinks": "model-00041-of-00073.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00041-of-00073.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00041-of-00073.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00045-of-00073.safetensors",
+    "model.layers.21.mlp.experts.down_proj": "model-00045-of-00073.safetensors",
+    "model.layers.21.mlp.experts.down_proj_bias": "model-00045-of-00073.safetensors",
+    "model.layers.21.mlp.experts.gate_up_proj": "model-00044-of-00073.safetensors",
+    "model.layers.21.mlp.experts.gate_up_proj_bias": "model-00044-of-00073.safetensors",
+    "model.layers.21.mlp.router.bias": "model-00043-of-00073.safetensors",
+    "model.layers.21.mlp.router.weight": "model-00043-of-00073.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00045-of-00073.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00043-of-00073.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00043-of-00073.safetensors",
+    "model.layers.21.self_attn.o_proj.bias": "model-00043-of-00073.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00043-of-00073.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00043-of-00073.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00043-of-00073.safetensors",
+    "model.layers.21.self_attn.sinks": "model-00043-of-00073.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00043-of-00073.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00043-of-00073.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00047-of-00073.safetensors",
+    "model.layers.22.mlp.experts.down_proj": "model-00047-of-00073.safetensors",
+    "model.layers.22.mlp.experts.down_proj_bias": "model-00047-of-00073.safetensors",
+    "model.layers.22.mlp.experts.gate_up_proj": "model-00046-of-00073.safetensors",
+    "model.layers.22.mlp.experts.gate_up_proj_bias": "model-00046-of-00073.safetensors",
+    "model.layers.22.mlp.router.bias": "model-00045-of-00073.safetensors",
+    "model.layers.22.mlp.router.weight": "model-00045-of-00073.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00047-of-00073.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00045-of-00073.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00045-of-00073.safetensors",
+    "model.layers.22.self_attn.o_proj.bias": "model-00045-of-00073.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00045-of-00073.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00045-of-00073.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00045-of-00073.safetensors",
+    "model.layers.22.self_attn.sinks": "model-00045-of-00073.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00045-of-00073.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00045-of-00073.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00049-of-00073.safetensors",
+    "model.layers.23.mlp.experts.down_proj": "model-00049-of-00073.safetensors",
+    "model.layers.23.mlp.experts.down_proj_bias": "model-00049-of-00073.safetensors",
+    "model.layers.23.mlp.experts.gate_up_proj": "model-00048-of-00073.safetensors",
+    "model.layers.23.mlp.experts.gate_up_proj_bias": "model-00048-of-00073.safetensors",
+    "model.layers.23.mlp.router.bias": "model-00047-of-00073.safetensors",
+    "model.layers.23.mlp.router.weight": "model-00047-of-00073.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00049-of-00073.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00047-of-00073.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00047-of-00073.safetensors",
+    "model.layers.23.self_attn.o_proj.bias": "model-00047-of-00073.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00047-of-00073.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00047-of-00073.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00047-of-00073.safetensors",
+    "model.layers.23.self_attn.sinks": "model-00047-of-00073.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00047-of-00073.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00047-of-00073.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00051-of-00073.safetensors",
+    "model.layers.24.mlp.experts.down_proj": "model-00051-of-00073.safetensors",
+    "model.layers.24.mlp.experts.down_proj_bias": "model-00051-of-00073.safetensors",
+    "model.layers.24.mlp.experts.gate_up_proj": "model-00050-of-00073.safetensors",
+    "model.layers.24.mlp.experts.gate_up_proj_bias": "model-00050-of-00073.safetensors",
+    "model.layers.24.mlp.router.bias": "model-00049-of-00073.safetensors",
+    "model.layers.24.mlp.router.weight": "model-00049-of-00073.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00051-of-00073.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00049-of-00073.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00049-of-00073.safetensors",
+    "model.layers.24.self_attn.o_proj.bias": "model-00049-of-00073.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00049-of-00073.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00049-of-00073.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00049-of-00073.safetensors",
+    "model.layers.24.self_attn.sinks": "model-00049-of-00073.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00049-of-00073.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00049-of-00073.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00053-of-00073.safetensors",
+    "model.layers.25.mlp.experts.down_proj": "model-00053-of-00073.safetensors",
+    "model.layers.25.mlp.experts.down_proj_bias": "model-00053-of-00073.safetensors",
+    "model.layers.25.mlp.experts.gate_up_proj": "model-00052-of-00073.safetensors",
+    "model.layers.25.mlp.experts.gate_up_proj_bias": "model-00052-of-00073.safetensors",
+    "model.layers.25.mlp.router.bias": "model-00051-of-00073.safetensors",
+    "model.layers.25.mlp.router.weight": "model-00051-of-00073.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00053-of-00073.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00051-of-00073.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00051-of-00073.safetensors",
+    "model.layers.25.self_attn.o_proj.bias": "model-00051-of-00073.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00051-of-00073.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00051-of-00073.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00051-of-00073.safetensors",
+    "model.layers.25.self_attn.sinks": "model-00051-of-00073.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00051-of-00073.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00051-of-00073.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00055-of-00073.safetensors",
+    "model.layers.26.mlp.experts.down_proj": "model-00055-of-00073.safetensors",
+    "model.layers.26.mlp.experts.down_proj_bias": "model-00055-of-00073.safetensors",
+    "model.layers.26.mlp.experts.gate_up_proj": "model-00054-of-00073.safetensors",
+    "model.layers.26.mlp.experts.gate_up_proj_bias": "model-00054-of-00073.safetensors",
+    "model.layers.26.mlp.router.bias": "model-00053-of-00073.safetensors",
+    "model.layers.26.mlp.router.weight": "model-00053-of-00073.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00055-of-00073.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00053-of-00073.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00053-of-00073.safetensors",
+    "model.layers.26.self_attn.o_proj.bias": "model-00053-of-00073.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00053-of-00073.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00053-of-00073.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00053-of-00073.safetensors",
+    "model.layers.26.self_attn.sinks": "model-00053-of-00073.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00053-of-00073.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00053-of-00073.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00057-of-00073.safetensors",
+    "model.layers.27.mlp.experts.down_proj": "model-00057-of-00073.safetensors",
+    "model.layers.27.mlp.experts.down_proj_bias": "model-00057-of-00073.safetensors",
+    "model.layers.27.mlp.experts.gate_up_proj": "model-00056-of-00073.safetensors",
+    "model.layers.27.mlp.experts.gate_up_proj_bias": "model-00056-of-00073.safetensors",
+    "model.layers.27.mlp.router.bias": "model-00055-of-00073.safetensors",
+    "model.layers.27.mlp.router.weight": "model-00055-of-00073.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00057-of-00073.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00055-of-00073.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00055-of-00073.safetensors",
+    "model.layers.27.self_attn.o_proj.bias": "model-00055-of-00073.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00055-of-00073.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00055-of-00073.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00055-of-00073.safetensors",
+    "model.layers.27.self_attn.sinks": "model-00055-of-00073.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00055-of-00073.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00055-of-00073.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00059-of-00073.safetensors",
+    "model.layers.28.mlp.experts.down_proj": "model-00059-of-00073.safetensors",
+    "model.layers.28.mlp.experts.down_proj_bias": "model-00059-of-00073.safetensors",
+    "model.layers.28.mlp.experts.gate_up_proj": "model-00058-of-00073.safetensors",
+    "model.layers.28.mlp.experts.gate_up_proj_bias": "model-00058-of-00073.safetensors",
+    "model.layers.28.mlp.router.bias": "model-00057-of-00073.safetensors",
+    "model.layers.28.mlp.router.weight": "model-00057-of-00073.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00059-of-00073.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00057-of-00073.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00057-of-00073.safetensors",
+    "model.layers.28.self_attn.o_proj.bias": "model-00057-of-00073.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00057-of-00073.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00057-of-00073.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00057-of-00073.safetensors",
+    "model.layers.28.self_attn.sinks": "model-00057-of-00073.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00057-of-00073.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00057-of-00073.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00061-of-00073.safetensors",
+    "model.layers.29.mlp.experts.down_proj": "model-00061-of-00073.safetensors",
+    "model.layers.29.mlp.experts.down_proj_bias": "model-00061-of-00073.safetensors",
+    "model.layers.29.mlp.experts.gate_up_proj": "model-00060-of-00073.safetensors",
+    "model.layers.29.mlp.experts.gate_up_proj_bias": "model-00060-of-00073.safetensors",
+    "model.layers.29.mlp.router.bias": "model-00059-of-00073.safetensors",
+    "model.layers.29.mlp.router.weight": "model-00059-of-00073.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00061-of-00073.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00059-of-00073.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00059-of-00073.safetensors",
+    "model.layers.29.self_attn.o_proj.bias": "model-00059-of-00073.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00059-of-00073.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00059-of-00073.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00059-of-00073.safetensors",
+    "model.layers.29.self_attn.sinks": "model-00059-of-00073.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00059-of-00073.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00059-of-00073.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00009-of-00073.safetensors",
+    "model.layers.3.mlp.experts.down_proj": "model-00009-of-00073.safetensors",
+    "model.layers.3.mlp.experts.down_proj_bias": "model-00009-of-00073.safetensors",
+    "model.layers.3.mlp.experts.gate_up_proj": "model-00008-of-00073.safetensors",
+    "model.layers.3.mlp.experts.gate_up_proj_bias": "model-00008-of-00073.safetensors",
+    "model.layers.3.mlp.router.bias": "model-00007-of-00073.safetensors",
+    "model.layers.3.mlp.router.weight": "model-00007-of-00073.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00009-of-00073.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00007-of-00073.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00007-of-00073.safetensors",
+    "model.layers.3.self_attn.o_proj.bias": "model-00007-of-00073.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00007-of-00073.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00007-of-00073.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00007-of-00073.safetensors",
+    "model.layers.3.self_attn.sinks": "model-00007-of-00073.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00007-of-00073.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00007-of-00073.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00063-of-00073.safetensors",
+    "model.layers.30.mlp.experts.down_proj": "model-00063-of-00073.safetensors",
+    "model.layers.30.mlp.experts.down_proj_bias": "model-00063-of-00073.safetensors",
+    "model.layers.30.mlp.experts.gate_up_proj": "model-00062-of-00073.safetensors",
+    "model.layers.30.mlp.experts.gate_up_proj_bias": "model-00062-of-00073.safetensors",
+    "model.layers.30.mlp.router.bias": "model-00061-of-00073.safetensors",
+    "model.layers.30.mlp.router.weight": "model-00061-of-00073.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00063-of-00073.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00061-of-00073.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00061-of-00073.safetensors",
+    "model.layers.30.self_attn.o_proj.bias": "model-00061-of-00073.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00061-of-00073.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00061-of-00073.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00061-of-00073.safetensors",
+    "model.layers.30.self_attn.sinks": "model-00061-of-00073.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00061-of-00073.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00061-of-00073.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00065-of-00073.safetensors",
+    "model.layers.31.mlp.experts.down_proj": "model-00065-of-00073.safetensors",
+    "model.layers.31.mlp.experts.down_proj_bias": "model-00065-of-00073.safetensors",
+    "model.layers.31.mlp.experts.gate_up_proj": "model-00064-of-00073.safetensors",
+    "model.layers.31.mlp.experts.gate_up_proj_bias": "model-00064-of-00073.safetensors",
+    "model.layers.31.mlp.router.bias": "model-00063-of-00073.safetensors",
+    "model.layers.31.mlp.router.weight": "model-00063-of-00073.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00065-of-00073.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00063-of-00073.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00063-of-00073.safetensors",
+    "model.layers.31.self_attn.o_proj.bias": "model-00063-of-00073.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00063-of-00073.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00063-of-00073.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00063-of-00073.safetensors",
+    "model.layers.31.self_attn.sinks": "model-00063-of-00073.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00063-of-00073.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00063-of-00073.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00067-of-00073.safetensors",
+    "model.layers.32.mlp.experts.down_proj": "model-00067-of-00073.safetensors",
+    "model.layers.32.mlp.experts.down_proj_bias": "model-00067-of-00073.safetensors",
+    "model.layers.32.mlp.experts.gate_up_proj": "model-00066-of-00073.safetensors",
+    "model.layers.32.mlp.experts.gate_up_proj_bias": "model-00066-of-00073.safetensors",
+    "model.layers.32.mlp.router.bias": "model-00065-of-00073.safetensors",
+    "model.layers.32.mlp.router.weight": "model-00065-of-00073.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00067-of-00073.safetensors",
+    "model.layers.32.self_attn.k_proj.bias": "model-00065-of-00073.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00065-of-00073.safetensors",
+    "model.layers.32.self_attn.o_proj.bias": "model-00065-of-00073.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00065-of-00073.safetensors",
+    "model.layers.32.self_attn.q_proj.bias": "model-00065-of-00073.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00065-of-00073.safetensors",
+    "model.layers.32.self_attn.sinks": "model-00065-of-00073.safetensors",
+    "model.layers.32.self_attn.v_proj.bias": "model-00065-of-00073.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00065-of-00073.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00069-of-00073.safetensors",
+    "model.layers.33.mlp.experts.down_proj": "model-00069-of-00073.safetensors",
+    "model.layers.33.mlp.experts.down_proj_bias": "model-00069-of-00073.safetensors",
+    "model.layers.33.mlp.experts.gate_up_proj": "model-00068-of-00073.safetensors",
+    "model.layers.33.mlp.experts.gate_up_proj_bias": "model-00068-of-00073.safetensors",
+    "model.layers.33.mlp.router.bias": "model-00067-of-00073.safetensors",
+    "model.layers.33.mlp.router.weight": "model-00067-of-00073.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00069-of-00073.safetensors",
+    "model.layers.33.self_attn.k_proj.bias": "model-00067-of-00073.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00067-of-00073.safetensors",
+    "model.layers.33.self_attn.o_proj.bias": "model-00067-of-00073.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00067-of-00073.safetensors",
+    "model.layers.33.self_attn.q_proj.bias": "model-00067-of-00073.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00067-of-00073.safetensors",
+    "model.layers.33.self_attn.sinks": "model-00067-of-00073.safetensors",
+    "model.layers.33.self_attn.v_proj.bias": "model-00067-of-00073.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00067-of-00073.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00071-of-00073.safetensors",
+    "model.layers.34.mlp.experts.down_proj": "model-00071-of-00073.safetensors",
+    "model.layers.34.mlp.experts.down_proj_bias": "model-00071-of-00073.safetensors",
+    "model.layers.34.mlp.experts.gate_up_proj": "model-00070-of-00073.safetensors",
+    "model.layers.34.mlp.experts.gate_up_proj_bias": "model-00070-of-00073.safetensors",
+    "model.layers.34.mlp.router.bias": "model-00069-of-00073.safetensors",
+    "model.layers.34.mlp.router.weight": "model-00069-of-00073.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00071-of-00073.safetensors",
+    "model.layers.34.self_attn.k_proj.bias": "model-00069-of-00073.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00069-of-00073.safetensors",
+    "model.layers.34.self_attn.o_proj.bias": "model-00069-of-00073.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00069-of-00073.safetensors",
+    "model.layers.34.self_attn.q_proj.bias": "model-00069-of-00073.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00069-of-00073.safetensors",
+    "model.layers.34.self_attn.sinks": "model-00069-of-00073.safetensors",
+    "model.layers.34.self_attn.v_proj.bias": "model-00069-of-00073.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00069-of-00073.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00073-of-00073.safetensors",
+    "model.layers.35.mlp.experts.down_proj": "model-00073-of-00073.safetensors",
+    "model.layers.35.mlp.experts.down_proj_bias": "model-00073-of-00073.safetensors",
+    "model.layers.35.mlp.experts.gate_up_proj": "model-00072-of-00073.safetensors",
+    "model.layers.35.mlp.experts.gate_up_proj_bias": "model-00072-of-00073.safetensors",
+    "model.layers.35.mlp.router.bias": "model-00071-of-00073.safetensors",
+    "model.layers.35.mlp.router.weight": "model-00071-of-00073.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00073-of-00073.safetensors",
+    "model.layers.35.self_attn.k_proj.bias": "model-00071-of-00073.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00071-of-00073.safetensors",
+    "model.layers.35.self_attn.o_proj.bias": "model-00071-of-00073.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00071-of-00073.safetensors",
+    "model.layers.35.self_attn.q_proj.bias": "model-00071-of-00073.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00071-of-00073.safetensors",
+    "model.layers.35.self_attn.sinks": "model-00071-of-00073.safetensors",
+    "model.layers.35.self_attn.v_proj.bias": "model-00071-of-00073.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00071-of-00073.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00011-of-00073.safetensors",
+    "model.layers.4.mlp.experts.down_proj": "model-00011-of-00073.safetensors",
+    "model.layers.4.mlp.experts.down_proj_bias": "model-00011-of-00073.safetensors",
+    "model.layers.4.mlp.experts.gate_up_proj": "model-00010-of-00073.safetensors",
+    "model.layers.4.mlp.experts.gate_up_proj_bias": "model-00010-of-00073.safetensors",
+    "model.layers.4.mlp.router.bias": "model-00009-of-00073.safetensors",
+    "model.layers.4.mlp.router.weight": "model-00009-of-00073.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00011-of-00073.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00009-of-00073.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00009-of-00073.safetensors",
+    "model.layers.4.self_attn.o_proj.bias": "model-00009-of-00073.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00009-of-00073.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00009-of-00073.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00009-of-00073.safetensors",
+    "model.layers.4.self_attn.sinks": "model-00009-of-00073.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00009-of-00073.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00009-of-00073.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00013-of-00073.safetensors",
+    "model.layers.5.mlp.experts.down_proj": "model-00013-of-00073.safetensors",
+    "model.layers.5.mlp.experts.down_proj_bias": "model-00013-of-00073.safetensors",
+    "model.layers.5.mlp.experts.gate_up_proj": "model-00012-of-00073.safetensors",
+    "model.layers.5.mlp.experts.gate_up_proj_bias": "model-00012-of-00073.safetensors",
+    "model.layers.5.mlp.router.bias": "model-00011-of-00073.safetensors",
+    "model.layers.5.mlp.router.weight": "model-00011-of-00073.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00013-of-00073.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00011-of-00073.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00011-of-00073.safetensors",
+    "model.layers.5.self_attn.o_proj.bias": "model-00011-of-00073.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00011-of-00073.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00011-of-00073.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00011-of-00073.safetensors",
+    "model.layers.5.self_attn.sinks": "model-00011-of-00073.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00011-of-00073.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00011-of-00073.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00015-of-00073.safetensors",
+    "model.layers.6.mlp.experts.down_proj": "model-00015-of-00073.safetensors",
+    "model.layers.6.mlp.experts.down_proj_bias": "model-00015-of-00073.safetensors",
+    "model.layers.6.mlp.experts.gate_up_proj": "model-00014-of-00073.safetensors",
+    "model.layers.6.mlp.experts.gate_up_proj_bias": "model-00014-of-00073.safetensors",
+    "model.layers.6.mlp.router.bias": "model-00013-of-00073.safetensors",
+    "model.layers.6.mlp.router.weight": "model-00013-of-00073.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00015-of-00073.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00013-of-00073.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00013-of-00073.safetensors",
+    "model.layers.6.self_attn.o_proj.bias": "model-00013-of-00073.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00013-of-00073.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00013-of-00073.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00013-of-00073.safetensors",
+    "model.layers.6.self_attn.sinks": "model-00013-of-00073.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00013-of-00073.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00013-of-00073.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00017-of-00073.safetensors",
+    "model.layers.7.mlp.experts.down_proj": "model-00017-of-00073.safetensors",
+    "model.layers.7.mlp.experts.down_proj_bias": "model-00017-of-00073.safetensors",
+    "model.layers.7.mlp.experts.gate_up_proj": "model-00016-of-00073.safetensors",
+    "model.layers.7.mlp.experts.gate_up_proj_bias": "model-00016-of-00073.safetensors",
+    "model.layers.7.mlp.router.bias": "model-00015-of-00073.safetensors",
+    "model.layers.7.mlp.router.weight": "model-00015-of-00073.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00017-of-00073.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00015-of-00073.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00015-of-00073.safetensors",
+    "model.layers.7.self_attn.o_proj.bias": "model-00015-of-00073.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00015-of-00073.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00015-of-00073.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00015-of-00073.safetensors",
+    "model.layers.7.self_attn.sinks": "model-00015-of-00073.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00015-of-00073.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00015-of-00073.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00019-of-00073.safetensors",
+    "model.layers.8.mlp.experts.down_proj": "model-00019-of-00073.safetensors",
+    "model.layers.8.mlp.experts.down_proj_bias": "model-00019-of-00073.safetensors",
+    "model.layers.8.mlp.experts.gate_up_proj": "model-00018-of-00073.safetensors",
+    "model.layers.8.mlp.experts.gate_up_proj_bias": "model-00018-of-00073.safetensors",
+    "model.layers.8.mlp.router.bias": "model-00017-of-00073.safetensors",
+    "model.layers.8.mlp.router.weight": "model-00017-of-00073.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00019-of-00073.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00017-of-00073.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00017-of-00073.safetensors",
+    "model.layers.8.self_attn.o_proj.bias": "model-00017-of-00073.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00017-of-00073.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00017-of-00073.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00017-of-00073.safetensors",
+    "model.layers.8.self_attn.sinks": "model-00017-of-00073.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00017-of-00073.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00017-of-00073.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00021-of-00073.safetensors",
+    "model.layers.9.mlp.experts.down_proj": "model-00021-of-00073.safetensors",
+    "model.layers.9.mlp.experts.down_proj_bias": "model-00021-of-00073.safetensors",
+    "model.layers.9.mlp.experts.gate_up_proj": "model-00020-of-00073.safetensors",
+    "model.layers.9.mlp.experts.gate_up_proj_bias": "model-00020-of-00073.safetensors",
+    "model.layers.9.mlp.router.bias": "model-00019-of-00073.safetensors",
+    "model.layers.9.mlp.router.weight": "model-00019-of-00073.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00021-of-00073.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00019-of-00073.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00019-of-00073.safetensors",
+    "model.layers.9.self_attn.o_proj.bias": "model-00019-of-00073.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00019-of-00073.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00019-of-00073.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00019-of-00073.safetensors",
+    "model.layers.9.self_attn.sinks": "model-00019-of-00073.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00019-of-00073.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00019-of-00073.safetensors",
+    "model.norm.weight": "model-00073-of-00073.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