diff --git a/.gitattributes b/.gitattributes
index a6344aac8c09253b3b630fb776ae94478aa0275b..52373fe24473b1aa44333d318f578ae6bf04b49b 100644
--- a/.gitattributes
+++ b/.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
diff --git a/chat_template.jinja b/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..8762a2669af9875fde0a424b7036dfecea14d0ee
--- /dev/null
+++ b/chat_template.jinja
@@ -0,0 +1,397 @@
+{#-
+  In addition to the normal inputs of `messages` and `tools`, this template also accepts the
+  following kwargs:
+  - "builtin_tools": A list, can contain "browser" and/or "python".
+  - "model_identity": A string that optionally describes the model identity.
+  - "reasoning_effort": A string that describes the reasoning effort, defaults to "medium".
+ #}
+
+{#- Tool Definition Rendering ============================================== #}
+{%- macro render_typescript_type(param_spec, required_params, is_nullable=false) -%}
+    {%- if param_spec.type == "array" -%}
+        {%- if param_spec['items'] -%}
+            {%- if param_spec['items']['type'] == "string" -%}
+                {{- "string[]" }}
+            {%- elif param_spec['items']['type'] == "number" -%}
+                {{- "number[]" }}
+            {%- elif param_spec['items']['type'] == "integer" -%}
+                {{- "number[]" }}
+            {%- elif param_spec['items']['type'] == "boolean" -%}
+                {{- "boolean[]" }}
+            {%- else -%}
+                {%- set inner_type = render_typescript_type(param_spec['items'], required_params) -%}
+                {%- if inner_type == "object | object" or inner_type|length > 50 -%}
+                    {{- "any[]" }}
+                {%- else -%}
+                    {{- inner_type + "[]" }}
+                {%- endif -%}
+            {%- endif -%}
+            {%- if param_spec.nullable -%}
+                {{- " | null" }}
+            {%- endif -%}
+        {%- else -%}
+            {{- "any[]" }}
+            {%- if param_spec.nullable -%}
+                {{- " | null" }}
+            {%- endif -%}
+        {%- endif -%}
+    {%- elif param_spec.type is defined and param_spec.type is iterable and param_spec.type is not string and param_spec.type is not mapping and param_spec.type[0] is defined -%}
+        {#- Handle array of types like ["object", "object"] from Union[dict, list] #}
+        {%- if param_spec.type | length > 1 -%}
+            {{- param_spec.type | join(" | ") }}
+        {%- else -%}
+            {{- param_spec.type[0] }}
+        {%- endif -%}
+    {%- elif param_spec.oneOf -%}
+        {#- Handle oneOf schemas - check for complex unions and fallback to any #}
+        {%- set has_object_variants = false -%}
+        {%- for variant in param_spec.oneOf -%}
+            {%- if variant.type == "object" -%}
+                {%- set has_object_variants = true -%}
+            {%- endif -%}
+        {%- endfor -%}
+        {%- if has_object_variants and param_spec.oneOf|length > 1 -%}
+            {{- "any" }}
+        {%- else -%}
+            {%- for variant in param_spec.oneOf -%}
+                {{- render_typescript_type(variant, required_params) -}}
+                {%- if variant.description %}
+                    {{- "// " + variant.description }}
+                {%- endif -%}
+                {%- if variant.default is defined %}
+                    {{ "// default: " + variant.default|tojson }}
+                {%- endif -%}
+                {%- if not loop.last %}
+                    {{- " | " }}
+                {% endif -%}
+            {%- endfor -%}
+        {%- endif -%}
+    {%- elif param_spec.type == "string" -%}
+        {%- if param_spec.enum -%}
+            {{- '"' + param_spec.enum|join('" | "') + '"' -}}
+        {%- else -%}
+            {{- "string" }}
+            {%- if param_spec.nullable %}
+                {{- " | null" }}
+            {%- endif -%}
+        {%- endif -%}
+    {%- elif param_spec.type == "number" -%}
+        {{- "number" }}
+    {%- elif param_spec.type == "integer" -%}
+        {{- "number" }}
+    {%- elif param_spec.type == "boolean" -%}
+        {{- "boolean" }}
+
+    {%- elif param_spec.type == "object" -%}
+        {%- if param_spec.properties -%}
+            {{- "{
+" }}
+            {%- for prop_name, prop_spec in param_spec.properties.items() -%}
+                {{- prop_name -}}
+                {%- if prop_name not in (param_spec.required or []) -%}
+                    {{- "?" }}
+                {%- endif -%}
+                {{- ": " }}
+                {{ render_typescript_type(prop_spec, param_spec.required or []) }}
+                {%- if not loop.last -%}
+                    {{-", " }}
+                {%- endif -%}
+            {%- endfor -%}
+            {{- "}" }}
+        {%- else -%}
+            {{- "object" }}
+        {%- endif -%}
+    {%- else -%}
+        {{- "any" }}
+    {%- endif -%}
+{%- endmacro -%}
+
+{%- macro render_tool_namespace(namespace_name, tools) -%}
+    {{- "## " + namespace_name + "
+
+" }}
+    {{- "namespace " + namespace_name + " {
+
+" }}
+    {%- for tool in tools %}
+        {%- set tool = tool.function %}
+        {{- "// " + tool.description + "
+" }}
+        {{- "type "+ tool.name + " = " }}
+        {%- if tool.parameters and tool.parameters.properties %}
+            {{- "(_: {
+" }}
+            {%- for param_name, param_spec in tool.parameters.properties.items() %}
+                {%- if param_spec.description %}
+                    {{- "// " + param_spec.description + "
+" }}
+                {%- 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 %}
+                    {{- ",
+" }}
+                {%- else %}
+                    {{- "
+" }}
+                {%- endif -%}
+            {%- endfor %}
+            {{- "}) => any;
+
+" }}
+        {%- else -%}
+            {{- "() => any;
+
+" }}
+        {%- endif -%}
+    {%- endfor %}
+    {{- "} // namespace " + namespace_name }}
+{%- endmacro -%}
+
+{%- macro render_builtin_tools(browser_tool, python_tool) -%}
+    {%- if browser_tool %}
+        {{- "## browser
+
+" }}
+        {{- "// Tool for browsing.
+" }}
+        {{- "// The `cursor` appears in brackets before each browsing display: `[{cursor}]`.
+" }}
+        {{- "// Cite information from the tool using the following format:
+" }}
+        {{- "// `【{cursor}†L{line_start}(-L{line_end})?】`, for example: `【6†L9-L11】` or `【8†L3】`.
+" }}
+        {{- "// Do not quote more than 10 words directly from the tool output.
+" }}
+        {{- "// sources=web (default: web)
+" }}
+        {{- "namespace browser {
+
+" }}
+        {{- "// Searches for information related to `query` and displays `topn` results.
+" }}
+        {{- "type search = (_: {
+" }}
+        {{- "query: string,
+" }}
+        {{- "topn?: number, // default: 10
+" }}
+        {{- "source?: string,
+" }}
+        {{- "}) => any;
+
+" }}
+        {{- "// Opens the link `id` from the page indicated by `cursor` starting at line number `loc`, showing `num_lines` lines.
+" }}
+        {{- "// Valid link ids are displayed with the formatting: `【{id}†.*】`.
+" }}
+        {{- "// If `cursor` is not provided, the most recent page is implied.
+" }}
+        {{- "// If `id` is a string, it is treated as a fully qualified URL associated with `source`.
+" }}
+        {{- "// If `loc` is not provided, the viewport will be positioned at the beginning of the document or centered on the most relevant passage, if available.
+" }}
+        {{- "// Use this function without `id` to scroll to a new location of an opened page.
+" }}
+        {{- "type open = (_: {
+" }}
+        {{- "id?: number | string, // default: -1
+" }}
+        {{- "cursor?: number, // default: -1
+" }}
+        {{- "loc?: number, // default: -1
+" }}
+        {{- "num_lines?: number, // default: -1
+" }}
+        {{- "view_source?: boolean, // default: false
+" }}
+        {{- "source?: string,
+" }}
+        {{- "}) => any;
+
+" }}
+        {{- "// Finds exact matches of `pattern` in the current page, or the page given by `cursor`.
+" }}
+        {{- "type find = (_: {
+" }}
+        {{- "pattern: string,
+" }}
+        {{- "cursor?: number, // default: -1
+" }}
+        {{- "}) => any;
+
+" }}
+        {{- "} // namespace browser
+
+" }}
+    {%- endif -%}
+
+    {%- if python_tool %}
+        {{- "## python
+
+" }}
+        {{- "Use this tool to execute Python code in your chain of thought. The code will not be shown to the user. This tool should be used for internal reasoning, but not for code that is intended to be visible to the user (e.g. when creating plots, tables, or files).
+
+" }}
+        {{- "When you send a message containing Python code to python, it will be executed in a stateful Jupyter notebook environment. python will respond with the output of the execution or time out after 120.0 seconds. The drive at '/mnt/data' can be used to save and persist user files. Internet access for this session is UNKNOWN. Depends on the cluster.
+
+" }}
+    {%- endif -%}
+{%- endmacro -%}
+
+{#- System Message Construction ============================================ #}
+{%- macro build_system_message() -%}
+    {%- if model_identity is not defined %}
+        {%- set model_identity = "You are ChatGPT, a large language model trained by OpenAI." %}
+    {%- endif %}
+    {{- model_identity + "
+" }}
+    {{- "Knowledge cutoff: 2024-06
+" }}
+    {{- "Current date: " + strftime_now("%Y-%m-%d") + "
+
+" }}
+    {%- if reasoning_effort is not defined %}
+        {%- set reasoning_effort = "medium" %}
+    {%- endif %}
+    {{- "Reasoning: " + reasoning_effort + "
+
+" }}
+    {%- if builtin_tools %}
+        {{- "# Tools
+
+" }}
+        {%- set available_builtin_tools = namespace(browser=false, python=false) %}
+        {%- for tool in builtin_tools %}
+            {%- if tool == "browser" %}
+                {%- set available_builtin_tools.browser = true %}
+            {%- elif tool == "python" %}
+                {%- set available_builtin_tools.python = true %}
+            {%- endif %}
+        {%- endfor %}
+        {{- render_builtin_tools(available_builtin_tools.browser, available_builtin_tools.python) }}
+    {%- endif -%}
+    {{- "# Valid channels: analysis, commentary, final. Channel must be included for every message." }}
+    {%- if tools -%}
+        {{- "
+Calls 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
+
+" }}
+        {{- developer_message }}
+    {%- endif %}
+    {%- if tools -%}
+        {{- "
+
+" }}
+        {{- "# Tools
+
+" }}
+        {{- render_tool_namespace("functions", tools) }}
+    {%- endif -%}
+    {{- "<|end|>" }}
+{%- endif %}
+
+{#- Render messages #}
+{%- set last_tool_call = namespace(name=none) %}
+{%- for message in loop_messages -%}
+    {#- At this point only assistant/user/tool messages should remain #}
+    {%- if message.role == 'assistant' -%}
+        {#- Checks to ensure the messages are being passed in the format we expect #}
+        {%- if "content" in message %}
+            {%- if "<|channel|>analysis<|message|>" in message.content or "<|channel|>final<|message|>" in message.content %}
+                {{- raise_exception("You have passed a message containing <|channel|> tags in the content field. Instead of doing this, you should pass analysis messages (the string between '<|message|>' and '<|end|>') in the 'thinking' field, and final messages (the string between '<|message|>' and '<|end|>') in the 'content' field.") }}
+            {%- endif %}
+        {%- endif %}
+        {%- if "thinking" in message %}
+            {%- if "<|channel|>analysis<|message|>" in message.thinking or "<|channel|>final<|message|>" in message.thinking %}
+                {{- raise_exception("You have passed a message containing <|channel|> tags in the thinking field. Instead of doing this, you should pass analysis messages (the string between '<|message|>' and '<|end|>') in the 'thinking' field, and final messages (the string between '<|message|>' and '<|end|>') in the 'content' field.") }}
+            {%- endif %}
+        {%- endif %}
+        {%- if "tool_calls" in message %}
+            {#- We assume max 1 tool call per message, and so we infer the tool call name #}
+            {#- in "tool" messages from the most recent assistant tool call name #}
+            {%- set tool_call = message.tool_calls[0] %}
+            {%- if tool_call.function %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {%- if message.content and message.thinking %}
+                {{- raise_exception("Cannot pass both content and thinking in an assistant message with tool calls! Put the analysis message in one or the other, but not both.") }}
+            {%- elif message.content %}
+                {{- "<|start|>assistant<|channel|>analysis<|message|>" + message.content + "<|end|>" }}
+            {%- elif message.thinking %}
+                {{- "<|start|>assistant<|channel|>analysis<|message|>" + message.thinking + "<|end|>" }}
+            {%- endif %}
+            {{- "<|start|>assistant to=" }}
+            {{- "functions." + tool_call.name + "<|channel|>commentary " }}
+            {{- (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 -%}
\ No newline at end of file
diff --git a/config.json b/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..f50da59dc4e07568a206806352a1385d17f95ca5
--- /dev/null
+++ b/config.json
@@ -0,0 +1,95 @@
+{
+  "architectures": [
+    "GptOssForCausalLM"
+  ],
+  "attention_bias": true,
+  "attention_dropout": 0.0,
+  "eos_token_id": 200002,
+  "experts_per_token": 4,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2880,
+  "initial_context_length": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 2880,
+  "layer_types": [
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 131072,
+  "model_type": "gpt_oss",
+  "num_attention_heads": 64,
+  "num_experts_per_tok": 4,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "num_local_experts": 128,
+  "output_router_logits": false,
+  "pad_token_id": 199999,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "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": "4.56.0.dev0",
+  "use_cache": true,
+  "vocab_size": 201088
+}
diff --git a/generation_config.json b/generation_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..78317cfc44866df4ad74d80917d2de9ec763d414
--- /dev/null
+++ b/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": "4.56.0.dev0"
+}
diff --git a/model-00002-of-00073.safetensors b/model-00002-of-00073.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..ffc0cdeabd7728fd42611ee0398fa4b6378779da
--- /dev/null
+++ b/model-00002-of-00073.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66f8d893fc4fbd27a07d2454114d5cc84821fa18d7575b625aa184b31ef0a572
+size 4248207640
diff --git a/model-00003-of-00073.safetensors b/model-00003-of-00073.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..09044e898f17de40644f9dffc9adeb821b79fbb2
--- /dev/null
+++ b/model-00003-of-00073.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5dac486466d29442dea478d2c32e08e732574058ca0d9490e266b78eb0ea26a6
+size 2138581743
diff --git a/model-00004-of-00073.safetensors b/model-00004-of-00073.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..83f6cf600c5f0c8b103e33df6643999950836fb8
--- /dev/null
+++ b/model-00004-of-00073.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dda6a71a050e68fe98ddfc12c0e3e86234b29d2ee5a6ba9083cabcc9e173563f
+size 4248207640
diff --git a/model-00006-of-00073.safetensors b/model-00006-of-00073.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..4826abbdd222efc4dd73a42a68a3767db186b184
--- /dev/null
+++ b/model-00006-of-00073.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01b81738668bce7b58ec8cef5e8c25b1e2b7afafcd1af7913da2788838263bd0
+size 4248207640
diff --git a/model-00007-of-00073.safetensors b/model-00007-of-00073.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..67d32270db7513e0de3326b4a1599c6736f7ee1d
--- /dev/null
+++ b/model-00007-of-00073.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb18bc8ef6173f2b20de8f6823ff9902420fcf1c7b984b9564a425cbf32788dd
+size 2138581741
diff --git a/model-00008-of-00073.safetensors b/model-00008-of-00073.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..2420db70e716e40cceab702078683d15ae2a9c77
--- /dev/null
+++ b/model-00008-of-00073.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b43d83c403e92882c79cdfbeb8b80e30d0d7fe58329ab8d3a8a13db0c1d7c5d
+size 4248207640
diff --git a/model-00009-of-00073.safetensors b/model-00009-of-00073.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..61f09e739b2042cf71b63801731b7cb52c0610a2
--- /dev/null
+++ b/model-00009-of-00073.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e86efab9a378f573a65e720b436136d7210e3207ba65ff4bde911a2def608aa
+size 2138581743
diff --git a/model-00010-of-00073.safetensors b/model-00010-of-00073.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..e60d1990f00f619edf4f6cd8d8c70146e442bea3
--- /dev/null
+++ b/model-00010-of-00073.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3dc516fd1e058767eb5d566b81f2619fc9319aed76409628d94b9fda5e4994a0
+size 4248207640
diff --git a/model-00012-of-00073.safetensors b/model-00012-of-00073.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..972054b5252c2a5dfab20c4eac58bd0309ac6975
--- /dev/null
+++ b/model-00012-of-00073.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39b2a45ac61f5b5d44e5a2df4b88643f8c7d57545b06c60121d954a9598599c1
+size 4248207640
diff --git a/model-00013-of-00073.safetensors b/model-00013-of-00073.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..f83cd9557afa376122424aa3848049520840e387
--- /dev/null
+++ b/model-00013-of-00073.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01f7b4e8220fb96dd1a529d7491876964cf2be03c4327e9934519d3aba4d308c
+size 2138581743
diff --git a/model-00014-of-00073.safetensors b/model-00014-of-00073.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..b8fb665708d218c8c30bf3b87cbf7e0911c014c5
--- /dev/null
+++ b/model-00014-of-00073.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a4ba78d4b340e08bcdb3fbfb48c26cc57abd581046b6a2a6620b9c63cca14aa
+size 4248207640
diff --git a/model-00017-of-00073.safetensors b/model-00017-of-00073.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..f3f7b7db28a1e43f1f18aade62ae4f09ff9ab5a1
--- /dev/null
+++ b/model-00017-of-00073.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1d1ba4374a77cb60b31a55f2c418a6d1b00bd557efd4f1f4798c2472444412b
+size 2138581741
diff --git a/model-00018-of-00073.safetensors b/model-00018-of-00073.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..284f05e627e9326343342712706cf4d4af78b817
--- /dev/null
+++ b/model-00018-of-00073.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f52b5fe061cefc784b2fb5a09ce6f30fe1fa6641103a141a5b8722df2a48aff8
+size 4248207640
diff --git a/model-00024-of-00073.safetensors b/model-00024-of-00073.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..cf61bb785574a6ebca04b516a646503ebc931f8c
--- /dev/null
+++ b/model-00024-of-00073.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f75eeb2761915a28fd12ae35d2fa13b6b984d9c6829184dc6a81bb778d1811c2
+size 4248207640
diff --git a/model-00025-of-00073.safetensors b/model-00025-of-00073.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..182d01406a81087377e6dad544642f4b10af38b9
--- /dev/null
+++ b/model-00025-of-00073.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9537389cb195cb1ee2e0528893f3f519a14c35d27d434d10a21580ea83363fbf
+size 2138581774
diff --git a/model-00026-of-00073.safetensors b/model-00026-of-00073.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..c0878898b2bbee01fece50654f41f0c4ce2ebba0
--- /dev/null
+++ b/model-00026-of-00073.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78d69f06e29de3eeb3e8df6353d418cfca5a6abb432f90b95c750252e5d3b7e1
+size 4248207640
diff --git a/model-00027-of-00073.safetensors b/model-00027-of-00073.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..c8a4b64a41789d142d016738b2526abfb6963f9b
--- /dev/null
+++ b/model-00027-of-00073.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6da56d16866ad461201388a498303bfb7b4d957103d626d5fcfd98e552906f66
+size 2138581775
diff --git a/model-00028-of-00073.safetensors b/model-00028-of-00073.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..15e444843fc91d96ca903cb006caf5d99846de73
--- /dev/null
+++ b/model-00028-of-00073.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2301da5402b74812725f99d892af657a421d7d3ff1fedf3309c28aa0fa0e4353
+size 4248207640
diff --git a/model-00029-of-00073.safetensors b/model-00029-of-00073.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..3c1875e161cdea117d810ad98940a9bdf5bf1ae6
--- /dev/null
+++ b/model-00029-of-00073.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1336384b3506f6bf09173b86f3a890bb3fcdb20193d932819a968a2fd265c3a4
+size 2138581776
diff --git a/model-00032-of-00073.safetensors b/model-00032-of-00073.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..3cc323a0b5cf83aeb072e6aeee414ddbb742a8e3
--- /dev/null
+++ b/model-00032-of-00073.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a9dc8df6da9507d6f99547ed7b6ab17793cbcd5a81c0c2f3439ff8f6c1d10c9
+size 4248207640
diff --git a/model-00034-of-00073.safetensors b/model-00034-of-00073.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..088d89c3ce46312b5fb168b42c9b138975af0fdd
--- /dev/null
+++ b/model-00034-of-00073.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2278f08494e6ef08a3e4b5794fc650970b01bb6652502c3bf861d9ee39024d52
+size 4248207640
diff --git a/model-00036-of-00073.safetensors b/model-00036-of-00073.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..a8e95409219a417441b9a780689e1c0c90bf0d3c
--- /dev/null
+++ b/model-00036-of-00073.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d28428c507c8b4e042c656f2db6c30fc9db7dd6f6c0157dcda930c2a3ea4d11c
+size 4248207640
diff --git a/model-00038-of-00073.safetensors b/model-00038-of-00073.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..849397898f8f12af6c3f25eb4035ca339cbf60ca
--- /dev/null
+++ b/model-00038-of-00073.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9704e3b5209e51b7310530e1da1e31b4aafb290a21b1957990b59ee98c08312f
+size 4248207640
diff --git a/model-00040-of-00073.safetensors b/model-00040-of-00073.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..87db2650c968dc085ff0badeaee1c644084e9842
--- /dev/null
+++ b/model-00040-of-00073.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63132593ac1bd4883db66340d38ef61685065e53db5ac40276bbfc1d83fb8bb8
+size 4248207640
diff --git a/model-00041-of-00073.safetensors b/model-00041-of-00073.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..87194a7338a9895e77bbb3fb87643a856f799ca5
--- /dev/null
+++ b/model-00041-of-00073.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b62d21c43f0bf7a17f868846bc1421907464a4782d8f85265bce5ca6a5e880c6
+size 2138581773
diff --git a/model-00042-of-00073.safetensors b/model-00042-of-00073.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..e077fbf39e8f59fb092cad7e9beb0f11a35d88a2
--- /dev/null
+++ b/model-00042-of-00073.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e39c7084ce12ee967b6dd15c8e1849fa550d50fd8e7d123064c3b3b5a233118a
+size 4248207640
diff --git a/model-00045-of-00073.safetensors b/model-00045-of-00073.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..c199d66fd82970e9efbbefe69828ab6fa8ed38ac
--- /dev/null
+++ b/model-00045-of-00073.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d6ceee23f5a2e781ae1990d1c03d3417160f64aa07a893a7c29da3b48fa809e
+size 2138581773
diff --git a/model-00046-of-00073.safetensors b/model-00046-of-00073.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..0f594f984ea46eff3d7723c171a02dd4f2378589
--- /dev/null
+++ b/model-00046-of-00073.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1939048181675b836a1f11862169988e54ecf788d4b74421f664052d565c07a
+size 4248207640
diff --git a/model-00050-of-00073.safetensors b/model-00050-of-00073.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..ec92fb99018bb46f07247e1d0cb26ae87e64ccce
--- /dev/null
+++ b/model-00050-of-00073.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65373fb48bed15e6db585aec180e53098ef5d59368265be9aa54da55f9ae0e05
+size 4248207640
diff --git a/model-00051-of-00073.safetensors b/model-00051-of-00073.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..9c447cb9e29859ea9d3bead0c7122239498a4fdf
--- /dev/null
+++ b/model-00051-of-00073.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcb2a8a97ab2d3b1d49c9138fd428cd75ffa5c079744072874e94429af4f3203
+size 2138581772
diff --git a/model-00052-of-00073.safetensors b/model-00052-of-00073.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..19291c6fd6b13eefbf7b721a2bf67b482efd69c6
--- /dev/null
+++ b/model-00052-of-00073.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa3fbc51fb6592d3a61b1769c06c2a922fbe396432626191e2b036de3e507d80
+size 4248207640
diff --git a/model-00054-of-00073.safetensors b/model-00054-of-00073.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..d93e6623a9cb4e3de6bf754dc568c3d43496a8c0
--- /dev/null
+++ b/model-00054-of-00073.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0531a970dd6c5d8e7cbae562255f6a3a9436546c311a29602e0fcc0fd8a84e3
+size 4248207640
diff --git a/model-00056-of-00073.safetensors b/model-00056-of-00073.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..1e7113d9e7d57947433e98a77c58c13231e34c68
--- /dev/null
+++ b/model-00056-of-00073.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b05fa63d01ec993405b2926e45798aea2b185200c2f008aeeaea68d0a6945c98
+size 4248207640
diff --git a/model-00057-of-00073.safetensors b/model-00057-of-00073.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..c4acc756a466c0ccdc8044b390ffd03d549ac928
--- /dev/null
+++ b/model-00057-of-00073.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8eaf2af70f7c97f15d53dec3f58f4a8e41b949555ecefeb7b802bcadc587ba2a
+size 2138581774
diff --git a/model-00058-of-00073.safetensors b/model-00058-of-00073.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..6bad9865380e13fc1ab55d7135f68a43edfa0b21
--- /dev/null
+++ b/model-00058-of-00073.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b8641d3b84630260b190480647bc640fd122dbe24a6dd465b6812a17ba73989
+size 4248207640
diff --git a/model-00060-of-00073.safetensors b/model-00060-of-00073.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..ff2ead735964c12ba27e21fd67e94edcc02baedc
--- /dev/null
+++ b/model-00060-of-00073.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e2351f41533aec995d9780f0c6a4b47279ab381e02709b46fe618487503602a
+size 4248207640
diff --git a/model-00061-of-00073.safetensors b/model-00061-of-00073.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..8ea49411931c2ac0ad79ea5d2ac822dd7aedea70
--- /dev/null
+++ b/model-00061-of-00073.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6b387735d686048c9c46bed56c60c86948a75f96234ff48d303fa760429de9d
+size 2138581771
diff --git a/model-00062-of-00073.safetensors b/model-00062-of-00073.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..c2d3cf4ccf45a0fc5ac5dae3961e74f5c2493d3d
--- /dev/null
+++ b/model-00062-of-00073.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d21973e03b03ac1b40821ecfe3e5c184ad04e6ef527e0b0a44a2f1879414f3ef
+size 4248207640
diff --git a/model-00063-of-00073.safetensors b/model-00063-of-00073.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..6f746e296fc37f41c5aed2997706197270d70446
--- /dev/null
+++ b/model-00063-of-00073.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:360af365e01dbc56645d37210ffd5c4e92d53f6a909aea3d39d4c8d5b5a6bfb3
+size 2138581772
diff --git a/model-00065-of-00073.safetensors b/model-00065-of-00073.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..a8819ba59b75eef9cb946ea3a485e797d569da38
--- /dev/null
+++ b/model-00065-of-00073.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61ab20c7484c82a2f37b8e48867629beeb7a05c4a8175dab203801589a362b72
+size 2138581774
diff --git a/model-00067-of-00073.safetensors b/model-00067-of-00073.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..723b27877b077fb23206b44af05ef835b56a8e74
--- /dev/null
+++ b/model-00067-of-00073.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25c10d3f1c499ddf6e77bc584c5c6c0969758df03e392bd3c80b616b35fd56b2
+size 2138581773
diff --git a/model-00069-of-00073.safetensors b/model-00069-of-00073.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..9e4968cd0e0615bf6f8e94c0666895e10a05fea5
--- /dev/null
+++ b/model-00069-of-00073.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12dfc9aa6ed931d6d0183cd5dcc4b78f67f2ad2dac336327806838d7f031642e
+size 2138581774
diff --git a/model-00070-of-00073.safetensors b/model-00070-of-00073.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..12f4adbd05ea78a9774d4fb7818c600e720e62e5
--- /dev/null
+++ b/model-00070-of-00073.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:964669a60753219bb8f516f22d2985b609743436f665afa55dc9c95c40f0dd06
+size 4248207640
diff --git a/model.safetensors.index.json b/model.safetensors.index.json
new file mode 100644
index 0000000000000000000000000000000000000000..08756f49f89f64027abb3c281874fa14d385e4b7
--- /dev/null
+++ b/model.safetensors.index.json
@@ -0,0 +1,1343 @@
+{
+  "metadata": {
+    "total_parameters": 116829156672,
+    "total_size": 232240806057
+  },
+  "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.k_proj.weight.absmax": "model-00001-of-00073.safetensors",
+    "model.layers.0.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00073.safetensors",
+    "model.layers.0.self_attn.k_proj.weight.nested_quant_map": "model-00001-of-00073.safetensors",
+    "model.layers.0.self_attn.k_proj.weight.quant_map": "model-00001-of-00073.safetensors",
+    "model.layers.0.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "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.o_proj.weight.absmax": "model-00001-of-00073.safetensors",
+    "model.layers.0.self_attn.o_proj.weight.nested_absmax": "model-00001-of-00073.safetensors",
+    "model.layers.0.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00073.safetensors",
+    "model.layers.0.self_attn.o_proj.weight.quant_map": "model-00001-of-00073.safetensors",
+    "model.layers.0.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "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.q_proj.weight.absmax": "model-00001-of-00073.safetensors",
+    "model.layers.0.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00073.safetensors",
+    "model.layers.0.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00073.safetensors",
+    "model.layers.0.self_attn.q_proj.weight.quant_map": "model-00001-of-00073.safetensors",
+    "model.layers.0.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "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.0.self_attn.v_proj.weight.absmax": "model-00001-of-00073.safetensors",
+    "model.layers.0.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00073.safetensors",
+    "model.layers.0.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00073.safetensors",
+    "model.layers.0.self_attn.v_proj.weight.quant_map": "model-00001-of-00073.safetensors",
+    "model.layers.0.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "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.k_proj.weight.absmax": "model-00003-of-00073.safetensors",
+    "model.layers.1.self_attn.k_proj.weight.nested_absmax": "model-00003-of-00073.safetensors",
+    "model.layers.1.self_attn.k_proj.weight.nested_quant_map": "model-00003-of-00073.safetensors",
+    "model.layers.1.self_attn.k_proj.weight.quant_map": "model-00003-of-00073.safetensors",
+    "model.layers.1.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "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.o_proj.weight.absmax": "model-00003-of-00073.safetensors",
+    "model.layers.1.self_attn.o_proj.weight.nested_absmax": "model-00003-of-00073.safetensors",
+    "model.layers.1.self_attn.o_proj.weight.nested_quant_map": "model-00003-of-00073.safetensors",
+    "model.layers.1.self_attn.o_proj.weight.quant_map": "model-00003-of-00073.safetensors",
+    "model.layers.1.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "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.q_proj.weight.absmax": "model-00003-of-00073.safetensors",
+    "model.layers.1.self_attn.q_proj.weight.nested_absmax": "model-00003-of-00073.safetensors",
+    "model.layers.1.self_attn.q_proj.weight.nested_quant_map": "model-00003-of-00073.safetensors",
+    "model.layers.1.self_attn.q_proj.weight.quant_map": "model-00003-of-00073.safetensors",
+    "model.layers.1.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "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.1.self_attn.v_proj.weight.absmax": "model-00003-of-00073.safetensors",
+    "model.layers.1.self_attn.v_proj.weight.nested_absmax": "model-00003-of-00073.safetensors",
+    "model.layers.1.self_attn.v_proj.weight.nested_quant_map": "model-00003-of-00073.safetensors",
+    "model.layers.1.self_attn.v_proj.weight.quant_map": "model-00003-of-00073.safetensors",
+    "model.layers.1.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "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.k_proj.weight.absmax": "model-00021-of-00073.safetensors",
+    "model.layers.10.self_attn.k_proj.weight.nested_absmax": "model-00021-of-00073.safetensors",
+    "model.layers.10.self_attn.k_proj.weight.nested_quant_map": "model-00021-of-00073.safetensors",
+    "model.layers.10.self_attn.k_proj.weight.quant_map": "model-00021-of-00073.safetensors",
+    "model.layers.10.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "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.o_proj.weight.absmax": "model-00021-of-00073.safetensors",
+    "model.layers.10.self_attn.o_proj.weight.nested_absmax": "model-00021-of-00073.safetensors",
+    "model.layers.10.self_attn.o_proj.weight.nested_quant_map": "model-00021-of-00073.safetensors",
+    "model.layers.10.self_attn.o_proj.weight.quant_map": "model-00021-of-00073.safetensors",
+    "model.layers.10.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "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.q_proj.weight.absmax": "model-00021-of-00073.safetensors",
+    "model.layers.10.self_attn.q_proj.weight.nested_absmax": "model-00021-of-00073.safetensors",
+    "model.layers.10.self_attn.q_proj.weight.nested_quant_map": "model-00021-of-00073.safetensors",
+    "model.layers.10.self_attn.q_proj.weight.quant_map": "model-00021-of-00073.safetensors",
+    "model.layers.10.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "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.10.self_attn.v_proj.weight.absmax": "model-00021-of-00073.safetensors",
+    "model.layers.10.self_attn.v_proj.weight.nested_absmax": "model-00021-of-00073.safetensors",
+    "model.layers.10.self_attn.v_proj.weight.nested_quant_map": "model-00021-of-00073.safetensors",
+    "model.layers.10.self_attn.v_proj.weight.quant_map": "model-00021-of-00073.safetensors",
+    "model.layers.10.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "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.k_proj.weight.absmax": "model-00023-of-00073.safetensors",
+    "model.layers.11.self_attn.k_proj.weight.nested_absmax": "model-00023-of-00073.safetensors",
+    "model.layers.11.self_attn.k_proj.weight.nested_quant_map": "model-00023-of-00073.safetensors",
+    "model.layers.11.self_attn.k_proj.weight.quant_map": "model-00023-of-00073.safetensors",
+    "model.layers.11.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "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.o_proj.weight.absmax": "model-00023-of-00073.safetensors",
+    "model.layers.11.self_attn.o_proj.weight.nested_absmax": "model-00023-of-00073.safetensors",
+    "model.layers.11.self_attn.o_proj.weight.nested_quant_map": "model-00023-of-00073.safetensors",
+    "model.layers.11.self_attn.o_proj.weight.quant_map": "model-00023-of-00073.safetensors",
+    "model.layers.11.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "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.q_proj.weight.absmax": "model-00023-of-00073.safetensors",
+    "model.layers.11.self_attn.q_proj.weight.nested_absmax": "model-00023-of-00073.safetensors",
+    "model.layers.11.self_attn.q_proj.weight.nested_quant_map": "model-00023-of-00073.safetensors",
+    "model.layers.11.self_attn.q_proj.weight.quant_map": "model-00023-of-00073.safetensors",
+    "model.layers.11.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "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.11.self_attn.v_proj.weight.absmax": "model-00023-of-00073.safetensors",
+    "model.layers.11.self_attn.v_proj.weight.nested_absmax": "model-00023-of-00073.safetensors",
+    "model.layers.11.self_attn.v_proj.weight.nested_quant_map": "model-00023-of-00073.safetensors",
+    "model.layers.11.self_attn.v_proj.weight.quant_map": "model-00023-of-00073.safetensors",
+    "model.layers.11.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "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.k_proj.weight.absmax": "model-00025-of-00073.safetensors",
+    "model.layers.12.self_attn.k_proj.weight.nested_absmax": "model-00025-of-00073.safetensors",
+    "model.layers.12.self_attn.k_proj.weight.nested_quant_map": "model-00025-of-00073.safetensors",
+    "model.layers.12.self_attn.k_proj.weight.quant_map": "model-00025-of-00073.safetensors",
+    "model.layers.12.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "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.o_proj.weight.absmax": "model-00025-of-00073.safetensors",
+    "model.layers.12.self_attn.o_proj.weight.nested_absmax": "model-00025-of-00073.safetensors",
+    "model.layers.12.self_attn.o_proj.weight.nested_quant_map": "model-00025-of-00073.safetensors",
+    "model.layers.12.self_attn.o_proj.weight.quant_map": "model-00025-of-00073.safetensors",
+    "model.layers.12.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "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.q_proj.weight.absmax": "model-00025-of-00073.safetensors",
+    "model.layers.12.self_attn.q_proj.weight.nested_absmax": "model-00025-of-00073.safetensors",
+    "model.layers.12.self_attn.q_proj.weight.nested_quant_map": "model-00025-of-00073.safetensors",
+    "model.layers.12.self_attn.q_proj.weight.quant_map": "model-00025-of-00073.safetensors",
+    "model.layers.12.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "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.12.self_attn.v_proj.weight.absmax": "model-00025-of-00073.safetensors",
+    "model.layers.12.self_attn.v_proj.weight.nested_absmax": "model-00025-of-00073.safetensors",
+    "model.layers.12.self_attn.v_proj.weight.nested_quant_map": "model-00025-of-00073.safetensors",
+    "model.layers.12.self_attn.v_proj.weight.quant_map": "model-00025-of-00073.safetensors",
+    "model.layers.12.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "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.k_proj.weight.absmax": "model-00027-of-00073.safetensors",
+    "model.layers.13.self_attn.k_proj.weight.nested_absmax": "model-00027-of-00073.safetensors",
+    "model.layers.13.self_attn.k_proj.weight.nested_quant_map": "model-00027-of-00073.safetensors",
+    "model.layers.13.self_attn.k_proj.weight.quant_map": "model-00027-of-00073.safetensors",
+    "model.layers.13.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "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.o_proj.weight.absmax": "model-00027-of-00073.safetensors",
+    "model.layers.13.self_attn.o_proj.weight.nested_absmax": "model-00027-of-00073.safetensors",
+    "model.layers.13.self_attn.o_proj.weight.nested_quant_map": "model-00027-of-00073.safetensors",
+    "model.layers.13.self_attn.o_proj.weight.quant_map": "model-00027-of-00073.safetensors",
+    "model.layers.13.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "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.q_proj.weight.absmax": "model-00027-of-00073.safetensors",
+    "model.layers.13.self_attn.q_proj.weight.nested_absmax": "model-00027-of-00073.safetensors",
+    "model.layers.13.self_attn.q_proj.weight.nested_quant_map": "model-00027-of-00073.safetensors",
+    "model.layers.13.self_attn.q_proj.weight.quant_map": "model-00027-of-00073.safetensors",
+    "model.layers.13.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "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.13.self_attn.v_proj.weight.absmax": "model-00027-of-00073.safetensors",
+    "model.layers.13.self_attn.v_proj.weight.nested_absmax": "model-00027-of-00073.safetensors",
+    "model.layers.13.self_attn.v_proj.weight.nested_quant_map": "model-00027-of-00073.safetensors",
+    "model.layers.13.self_attn.v_proj.weight.quant_map": "model-00027-of-00073.safetensors",
+    "model.layers.13.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "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.k_proj.weight.absmax": "model-00029-of-00073.safetensors",
+    "model.layers.14.self_attn.k_proj.weight.nested_absmax": "model-00029-of-00073.safetensors",
+    "model.layers.14.self_attn.k_proj.weight.nested_quant_map": "model-00029-of-00073.safetensors",
+    "model.layers.14.self_attn.k_proj.weight.quant_map": "model-00029-of-00073.safetensors",
+    "model.layers.14.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "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.o_proj.weight.absmax": "model-00029-of-00073.safetensors",
+    "model.layers.14.self_attn.o_proj.weight.nested_absmax": "model-00029-of-00073.safetensors",
+    "model.layers.14.self_attn.o_proj.weight.nested_quant_map": "model-00029-of-00073.safetensors",
+    "model.layers.14.self_attn.o_proj.weight.quant_map": "model-00029-of-00073.safetensors",
+    "model.layers.14.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "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.q_proj.weight.absmax": "model-00029-of-00073.safetensors",
+    "model.layers.14.self_attn.q_proj.weight.nested_absmax": "model-00029-of-00073.safetensors",
+    "model.layers.14.self_attn.q_proj.weight.nested_quant_map": "model-00029-of-00073.safetensors",
+    "model.layers.14.self_attn.q_proj.weight.quant_map": "model-00029-of-00073.safetensors",
+    "model.layers.14.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "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.14.self_attn.v_proj.weight.absmax": "model-00029-of-00073.safetensors",
+    "model.layers.14.self_attn.v_proj.weight.nested_absmax": "model-00029-of-00073.safetensors",
+    "model.layers.14.self_attn.v_proj.weight.nested_quant_map": "model-00029-of-00073.safetensors",
+    "model.layers.14.self_attn.v_proj.weight.quant_map": "model-00029-of-00073.safetensors",
+    "model.layers.14.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "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.k_proj.weight.absmax": "model-00031-of-00073.safetensors",
+    "model.layers.15.self_attn.k_proj.weight.nested_absmax": "model-00031-of-00073.safetensors",
+    "model.layers.15.self_attn.k_proj.weight.nested_quant_map": "model-00031-of-00073.safetensors",
+    "model.layers.15.self_attn.k_proj.weight.quant_map": "model-00031-of-00073.safetensors",
+    "model.layers.15.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "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.o_proj.weight.absmax": "model-00031-of-00073.safetensors",
+    "model.layers.15.self_attn.o_proj.weight.nested_absmax": "model-00031-of-00073.safetensors",
+    "model.layers.15.self_attn.o_proj.weight.nested_quant_map": "model-00031-of-00073.safetensors",
+    "model.layers.15.self_attn.o_proj.weight.quant_map": "model-00031-of-00073.safetensors",
+    "model.layers.15.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "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.q_proj.weight.absmax": "model-00031-of-00073.safetensors",
+    "model.layers.15.self_attn.q_proj.weight.nested_absmax": "model-00031-of-00073.safetensors",
+    "model.layers.15.self_attn.q_proj.weight.nested_quant_map": "model-00031-of-00073.safetensors",
+    "model.layers.15.self_attn.q_proj.weight.quant_map": "model-00031-of-00073.safetensors",
+    "model.layers.15.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "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.15.self_attn.v_proj.weight.absmax": "model-00031-of-00073.safetensors",
+    "model.layers.15.self_attn.v_proj.weight.nested_absmax": "model-00031-of-00073.safetensors",
+    "model.layers.15.self_attn.v_proj.weight.nested_quant_map": "model-00031-of-00073.safetensors",
+    "model.layers.15.self_attn.v_proj.weight.quant_map": "model-00031-of-00073.safetensors",
+    "model.layers.15.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "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.k_proj.weight.absmax": "model-00033-of-00073.safetensors",
+    "model.layers.16.self_attn.k_proj.weight.nested_absmax": "model-00033-of-00073.safetensors",
+    "model.layers.16.self_attn.k_proj.weight.nested_quant_map": "model-00033-of-00073.safetensors",
+    "model.layers.16.self_attn.k_proj.weight.quant_map": "model-00033-of-00073.safetensors",
+    "model.layers.16.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "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.o_proj.weight.absmax": "model-00033-of-00073.safetensors",
+    "model.layers.16.self_attn.o_proj.weight.nested_absmax": "model-00033-of-00073.safetensors",
+    "model.layers.16.self_attn.o_proj.weight.nested_quant_map": "model-00033-of-00073.safetensors",
+    "model.layers.16.self_attn.o_proj.weight.quant_map": "model-00033-of-00073.safetensors",
+    "model.layers.16.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "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.q_proj.weight.absmax": "model-00033-of-00073.safetensors",
+    "model.layers.16.self_attn.q_proj.weight.nested_absmax": "model-00033-of-00073.safetensors",
+    "model.layers.16.self_attn.q_proj.weight.nested_quant_map": "model-00033-of-00073.safetensors",
+    "model.layers.16.self_attn.q_proj.weight.quant_map": "model-00033-of-00073.safetensors",
+    "model.layers.16.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "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.16.self_attn.v_proj.weight.absmax": "model-00033-of-00073.safetensors",
+    "model.layers.16.self_attn.v_proj.weight.nested_absmax": "model-00033-of-00073.safetensors",
+    "model.layers.16.self_attn.v_proj.weight.nested_quant_map": "model-00033-of-00073.safetensors",
+    "model.layers.16.self_attn.v_proj.weight.quant_map": "model-00033-of-00073.safetensors",
+    "model.layers.16.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "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.k_proj.weight.absmax": "model-00035-of-00073.safetensors",
+    "model.layers.17.self_attn.k_proj.weight.nested_absmax": "model-00035-of-00073.safetensors",
+    "model.layers.17.self_attn.k_proj.weight.nested_quant_map": "model-00035-of-00073.safetensors",
+    "model.layers.17.self_attn.k_proj.weight.quant_map": "model-00035-of-00073.safetensors",
+    "model.layers.17.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "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.o_proj.weight.absmax": "model-00035-of-00073.safetensors",
+    "model.layers.17.self_attn.o_proj.weight.nested_absmax": "model-00035-of-00073.safetensors",
+    "model.layers.17.self_attn.o_proj.weight.nested_quant_map": "model-00035-of-00073.safetensors",
+    "model.layers.17.self_attn.o_proj.weight.quant_map": "model-00035-of-00073.safetensors",
+    "model.layers.17.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "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.q_proj.weight.absmax": "model-00035-of-00073.safetensors",
+    "model.layers.17.self_attn.q_proj.weight.nested_absmax": "model-00035-of-00073.safetensors",
+    "model.layers.17.self_attn.q_proj.weight.nested_quant_map": "model-00035-of-00073.safetensors",
+    "model.layers.17.self_attn.q_proj.weight.quant_map": "model-00035-of-00073.safetensors",
+    "model.layers.17.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "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.17.self_attn.v_proj.weight.absmax": "model-00035-of-00073.safetensors",
+    "model.layers.17.self_attn.v_proj.weight.nested_absmax": "model-00035-of-00073.safetensors",
+    "model.layers.17.self_attn.v_proj.weight.nested_quant_map": "model-00035-of-00073.safetensors",
+    "model.layers.17.self_attn.v_proj.weight.quant_map": "model-00035-of-00073.safetensors",
+    "model.layers.17.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "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.k_proj.weight.absmax": "model-00037-of-00073.safetensors",
+    "model.layers.18.self_attn.k_proj.weight.nested_absmax": "model-00037-of-00073.safetensors",
+    "model.layers.18.self_attn.k_proj.weight.nested_quant_map": "model-00037-of-00073.safetensors",
+    "model.layers.18.self_attn.k_proj.weight.quant_map": "model-00037-of-00073.safetensors",
+    "model.layers.18.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "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.o_proj.weight.absmax": "model-00037-of-00073.safetensors",
+    "model.layers.18.self_attn.o_proj.weight.nested_absmax": "model-00037-of-00073.safetensors",
+    "model.layers.18.self_attn.o_proj.weight.nested_quant_map": "model-00037-of-00073.safetensors",
+    "model.layers.18.self_attn.o_proj.weight.quant_map": "model-00037-of-00073.safetensors",
+    "model.layers.18.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "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.q_proj.weight.absmax": "model-00037-of-00073.safetensors",
+    "model.layers.18.self_attn.q_proj.weight.nested_absmax": "model-00037-of-00073.safetensors",
+    "model.layers.18.self_attn.q_proj.weight.nested_quant_map": "model-00037-of-00073.safetensors",
+    "model.layers.18.self_attn.q_proj.weight.quant_map": "model-00037-of-00073.safetensors",
+    "model.layers.18.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "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.18.self_attn.v_proj.weight.absmax": "model-00037-of-00073.safetensors",
+    "model.layers.18.self_attn.v_proj.weight.nested_absmax": "model-00037-of-00073.safetensors",
+    "model.layers.18.self_attn.v_proj.weight.nested_quant_map": "model-00037-of-00073.safetensors",
+    "model.layers.18.self_attn.v_proj.weight.quant_map": "model-00037-of-00073.safetensors",
+    "model.layers.18.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "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.k_proj.weight.absmax": "model-00039-of-00073.safetensors",
+    "model.layers.19.self_attn.k_proj.weight.nested_absmax": "model-00039-of-00073.safetensors",
+    "model.layers.19.self_attn.k_proj.weight.nested_quant_map": "model-00039-of-00073.safetensors",
+    "model.layers.19.self_attn.k_proj.weight.quant_map": "model-00039-of-00073.safetensors",
+    "model.layers.19.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "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.o_proj.weight.absmax": "model-00039-of-00073.safetensors",
+    "model.layers.19.self_attn.o_proj.weight.nested_absmax": "model-00039-of-00073.safetensors",
+    "model.layers.19.self_attn.o_proj.weight.nested_quant_map": "model-00039-of-00073.safetensors",
+    "model.layers.19.self_attn.o_proj.weight.quant_map": "model-00039-of-00073.safetensors",
+    "model.layers.19.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "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.q_proj.weight.absmax": "model-00039-of-00073.safetensors",
+    "model.layers.19.self_attn.q_proj.weight.nested_absmax": "model-00039-of-00073.safetensors",
+    "model.layers.19.self_attn.q_proj.weight.nested_quant_map": "model-00039-of-00073.safetensors",
+    "model.layers.19.self_attn.q_proj.weight.quant_map": "model-00039-of-00073.safetensors",
+    "model.layers.19.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "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.19.self_attn.v_proj.weight.absmax": "model-00039-of-00073.safetensors",
+    "model.layers.19.self_attn.v_proj.weight.nested_absmax": "model-00039-of-00073.safetensors",
+    "model.layers.19.self_attn.v_proj.weight.nested_quant_map": "model-00039-of-00073.safetensors",
+    "model.layers.19.self_attn.v_proj.weight.quant_map": "model-00039-of-00073.safetensors",
+    "model.layers.19.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "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.k_proj.weight.absmax": "model-00005-of-00073.safetensors",
+    "model.layers.2.self_attn.k_proj.weight.nested_absmax": "model-00005-of-00073.safetensors",
+    "model.layers.2.self_attn.k_proj.weight.nested_quant_map": "model-00005-of-00073.safetensors",
+    "model.layers.2.self_attn.k_proj.weight.quant_map": "model-00005-of-00073.safetensors",
+    "model.layers.2.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "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.o_proj.weight.absmax": "model-00005-of-00073.safetensors",
+    "model.layers.2.self_attn.o_proj.weight.nested_absmax": "model-00005-of-00073.safetensors",
+    "model.layers.2.self_attn.o_proj.weight.nested_quant_map": "model-00005-of-00073.safetensors",
+    "model.layers.2.self_attn.o_proj.weight.quant_map": "model-00005-of-00073.safetensors",
+    "model.layers.2.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "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.q_proj.weight.absmax": "model-00005-of-00073.safetensors",
+    "model.layers.2.self_attn.q_proj.weight.nested_absmax": "model-00005-of-00073.safetensors",
+    "model.layers.2.self_attn.q_proj.weight.nested_quant_map": "model-00005-of-00073.safetensors",
+    "model.layers.2.self_attn.q_proj.weight.quant_map": "model-00005-of-00073.safetensors",
+    "model.layers.2.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "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.2.self_attn.v_proj.weight.absmax": "model-00005-of-00073.safetensors",
+    "model.layers.2.self_attn.v_proj.weight.nested_absmax": "model-00005-of-00073.safetensors",
+    "model.layers.2.self_attn.v_proj.weight.nested_quant_map": "model-00005-of-00073.safetensors",
+    "model.layers.2.self_attn.v_proj.weight.quant_map": "model-00005-of-00073.safetensors",
+    "model.layers.2.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "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.k_proj.weight.absmax": "model-00041-of-00073.safetensors",
+    "model.layers.20.self_attn.k_proj.weight.nested_absmax": "model-00041-of-00073.safetensors",
+    "model.layers.20.self_attn.k_proj.weight.nested_quant_map": "model-00041-of-00073.safetensors",
+    "model.layers.20.self_attn.k_proj.weight.quant_map": "model-00041-of-00073.safetensors",
+    "model.layers.20.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "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.o_proj.weight.absmax": "model-00041-of-00073.safetensors",
+    "model.layers.20.self_attn.o_proj.weight.nested_absmax": "model-00041-of-00073.safetensors",
+    "model.layers.20.self_attn.o_proj.weight.nested_quant_map": "model-00041-of-00073.safetensors",
+    "model.layers.20.self_attn.o_proj.weight.quant_map": "model-00041-of-00073.safetensors",
+    "model.layers.20.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "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.q_proj.weight.absmax": "model-00041-of-00073.safetensors",
+    "model.layers.20.self_attn.q_proj.weight.nested_absmax": "model-00041-of-00073.safetensors",
+    "model.layers.20.self_attn.q_proj.weight.nested_quant_map": "model-00041-of-00073.safetensors",
+    "model.layers.20.self_attn.q_proj.weight.quant_map": "model-00041-of-00073.safetensors",
+    "model.layers.20.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "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.20.self_attn.v_proj.weight.absmax": "model-00041-of-00073.safetensors",
+    "model.layers.20.self_attn.v_proj.weight.nested_absmax": "model-00041-of-00073.safetensors",
+    "model.layers.20.self_attn.v_proj.weight.nested_quant_map": "model-00041-of-00073.safetensors",
+    "model.layers.20.self_attn.v_proj.weight.quant_map": "model-00041-of-00073.safetensors",
+    "model.layers.20.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "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.k_proj.weight.absmax": "model-00043-of-00073.safetensors",
+    "model.layers.21.self_attn.k_proj.weight.nested_absmax": "model-00043-of-00073.safetensors",
+    "model.layers.21.self_attn.k_proj.weight.nested_quant_map": "model-00043-of-00073.safetensors",
+    "model.layers.21.self_attn.k_proj.weight.quant_map": "model-00043-of-00073.safetensors",
+    "model.layers.21.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "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.o_proj.weight.absmax": "model-00043-of-00073.safetensors",
+    "model.layers.21.self_attn.o_proj.weight.nested_absmax": "model-00043-of-00073.safetensors",
+    "model.layers.21.self_attn.o_proj.weight.nested_quant_map": "model-00043-of-00073.safetensors",
+    "model.layers.21.self_attn.o_proj.weight.quant_map": "model-00043-of-00073.safetensors",
+    "model.layers.21.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "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.q_proj.weight.absmax": "model-00043-of-00073.safetensors",
+    "model.layers.21.self_attn.q_proj.weight.nested_absmax": "model-00043-of-00073.safetensors",
+    "model.layers.21.self_attn.q_proj.weight.nested_quant_map": "model-00043-of-00073.safetensors",
+    "model.layers.21.self_attn.q_proj.weight.quant_map": "model-00043-of-00073.safetensors",
+    "model.layers.21.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "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.21.self_attn.v_proj.weight.absmax": "model-00043-of-00073.safetensors",
+    "model.layers.21.self_attn.v_proj.weight.nested_absmax": "model-00043-of-00073.safetensors",
+    "model.layers.21.self_attn.v_proj.weight.nested_quant_map": "model-00043-of-00073.safetensors",
+    "model.layers.21.self_attn.v_proj.weight.quant_map": "model-00043-of-00073.safetensors",
+    "model.layers.21.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "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.k_proj.weight.absmax": "model-00045-of-00073.safetensors",
+    "model.layers.22.self_attn.k_proj.weight.nested_absmax": "model-00045-of-00073.safetensors",
+    "model.layers.22.self_attn.k_proj.weight.nested_quant_map": "model-00045-of-00073.safetensors",
+    "model.layers.22.self_attn.k_proj.weight.quant_map": "model-00045-of-00073.safetensors",
+    "model.layers.22.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "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.o_proj.weight.absmax": "model-00045-of-00073.safetensors",
+    "model.layers.22.self_attn.o_proj.weight.nested_absmax": "model-00045-of-00073.safetensors",
+    "model.layers.22.self_attn.o_proj.weight.nested_quant_map": "model-00045-of-00073.safetensors",
+    "model.layers.22.self_attn.o_proj.weight.quant_map": "model-00045-of-00073.safetensors",
+    "model.layers.22.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "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.q_proj.weight.absmax": "model-00045-of-00073.safetensors",
+    "model.layers.22.self_attn.q_proj.weight.nested_absmax": "model-00045-of-00073.safetensors",
+    "model.layers.22.self_attn.q_proj.weight.nested_quant_map": "model-00045-of-00073.safetensors",
+    "model.layers.22.self_attn.q_proj.weight.quant_map": "model-00045-of-00073.safetensors",
+    "model.layers.22.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "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.22.self_attn.v_proj.weight.absmax": "model-00045-of-00073.safetensors",
+    "model.layers.22.self_attn.v_proj.weight.nested_absmax": "model-00045-of-00073.safetensors",
+    "model.layers.22.self_attn.v_proj.weight.nested_quant_map": "model-00045-of-00073.safetensors",
+    "model.layers.22.self_attn.v_proj.weight.quant_map": "model-00045-of-00073.safetensors",
+    "model.layers.22.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "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.k_proj.weight.absmax": "model-00047-of-00073.safetensors",
+    "model.layers.23.self_attn.k_proj.weight.nested_absmax": "model-00047-of-00073.safetensors",
+    "model.layers.23.self_attn.k_proj.weight.nested_quant_map": "model-00047-of-00073.safetensors",
+    "model.layers.23.self_attn.k_proj.weight.quant_map": "model-00047-of-00073.safetensors",
+    "model.layers.23.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "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.o_proj.weight.absmax": "model-00047-of-00073.safetensors",
+    "model.layers.23.self_attn.o_proj.weight.nested_absmax": "model-00047-of-00073.safetensors",
+    "model.layers.23.self_attn.o_proj.weight.nested_quant_map": "model-00047-of-00073.safetensors",
+    "model.layers.23.self_attn.o_proj.weight.quant_map": "model-00047-of-00073.safetensors",
+    "model.layers.23.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "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.q_proj.weight.absmax": "model-00047-of-00073.safetensors",
+    "model.layers.23.self_attn.q_proj.weight.nested_absmax": "model-00047-of-00073.safetensors",
+    "model.layers.23.self_attn.q_proj.weight.nested_quant_map": "model-00047-of-00073.safetensors",
+    "model.layers.23.self_attn.q_proj.weight.quant_map": "model-00047-of-00073.safetensors",
+    "model.layers.23.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "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.23.self_attn.v_proj.weight.absmax": "model-00047-of-00073.safetensors",
+    "model.layers.23.self_attn.v_proj.weight.nested_absmax": "model-00047-of-00073.safetensors",
+    "model.layers.23.self_attn.v_proj.weight.nested_quant_map": "model-00047-of-00073.safetensors",
+    "model.layers.23.self_attn.v_proj.weight.quant_map": "model-00047-of-00073.safetensors",
+    "model.layers.23.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "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.k_proj.weight.absmax": "model-00049-of-00073.safetensors",
+    "model.layers.24.self_attn.k_proj.weight.nested_absmax": "model-00049-of-00073.safetensors",
+    "model.layers.24.self_attn.k_proj.weight.nested_quant_map": "model-00049-of-00073.safetensors",
+    "model.layers.24.self_attn.k_proj.weight.quant_map": "model-00049-of-00073.safetensors",
+    "model.layers.24.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "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.o_proj.weight.absmax": "model-00049-of-00073.safetensors",
+    "model.layers.24.self_attn.o_proj.weight.nested_absmax": "model-00049-of-00073.safetensors",
+    "model.layers.24.self_attn.o_proj.weight.nested_quant_map": "model-00049-of-00073.safetensors",
+    "model.layers.24.self_attn.o_proj.weight.quant_map": "model-00049-of-00073.safetensors",
+    "model.layers.24.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "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.q_proj.weight.absmax": "model-00049-of-00073.safetensors",
+    "model.layers.24.self_attn.q_proj.weight.nested_absmax": "model-00049-of-00073.safetensors",
+    "model.layers.24.self_attn.q_proj.weight.nested_quant_map": "model-00049-of-00073.safetensors",
+    "model.layers.24.self_attn.q_proj.weight.quant_map": "model-00049-of-00073.safetensors",
+    "model.layers.24.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "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.24.self_attn.v_proj.weight.absmax": "model-00049-of-00073.safetensors",
+    "model.layers.24.self_attn.v_proj.weight.nested_absmax": "model-00049-of-00073.safetensors",
+    "model.layers.24.self_attn.v_proj.weight.nested_quant_map": "model-00049-of-00073.safetensors",
+    "model.layers.24.self_attn.v_proj.weight.quant_map": "model-00049-of-00073.safetensors",
+    "model.layers.24.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "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.k_proj.weight.absmax": "model-00051-of-00073.safetensors",
+    "model.layers.25.self_attn.k_proj.weight.nested_absmax": "model-00051-of-00073.safetensors",
+    "model.layers.25.self_attn.k_proj.weight.nested_quant_map": "model-00051-of-00073.safetensors",
+    "model.layers.25.self_attn.k_proj.weight.quant_map": "model-00051-of-00073.safetensors",
+    "model.layers.25.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "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.o_proj.weight.absmax": "model-00051-of-00073.safetensors",
+    "model.layers.25.self_attn.o_proj.weight.nested_absmax": "model-00051-of-00073.safetensors",
+    "model.layers.25.self_attn.o_proj.weight.nested_quant_map": "model-00051-of-00073.safetensors",
+    "model.layers.25.self_attn.o_proj.weight.quant_map": "model-00051-of-00073.safetensors",
+    "model.layers.25.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "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.q_proj.weight.absmax": "model-00051-of-00073.safetensors",
+    "model.layers.25.self_attn.q_proj.weight.nested_absmax": "model-00051-of-00073.safetensors",
+    "model.layers.25.self_attn.q_proj.weight.nested_quant_map": "model-00051-of-00073.safetensors",
+    "model.layers.25.self_attn.q_proj.weight.quant_map": "model-00051-of-00073.safetensors",
+    "model.layers.25.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "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.25.self_attn.v_proj.weight.absmax": "model-00051-of-00073.safetensors",
+    "model.layers.25.self_attn.v_proj.weight.nested_absmax": "model-00051-of-00073.safetensors",
+    "model.layers.25.self_attn.v_proj.weight.nested_quant_map": "model-00051-of-00073.safetensors",
+    "model.layers.25.self_attn.v_proj.weight.quant_map": "model-00051-of-00073.safetensors",
+    "model.layers.25.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "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.k_proj.weight.absmax": "model-00053-of-00073.safetensors",
+    "model.layers.26.self_attn.k_proj.weight.nested_absmax": "model-00053-of-00073.safetensors",
+    "model.layers.26.self_attn.k_proj.weight.nested_quant_map": "model-00053-of-00073.safetensors",
+    "model.layers.26.self_attn.k_proj.weight.quant_map": "model-00053-of-00073.safetensors",
+    "model.layers.26.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "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.o_proj.weight.absmax": "model-00053-of-00073.safetensors",
+    "model.layers.26.self_attn.o_proj.weight.nested_absmax": "model-00053-of-00073.safetensors",
+    "model.layers.26.self_attn.o_proj.weight.nested_quant_map": "model-00053-of-00073.safetensors",
+    "model.layers.26.self_attn.o_proj.weight.quant_map": "model-00053-of-00073.safetensors",
+    "model.layers.26.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "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.q_proj.weight.absmax": "model-00053-of-00073.safetensors",
+    "model.layers.26.self_attn.q_proj.weight.nested_absmax": "model-00053-of-00073.safetensors",
+    "model.layers.26.self_attn.q_proj.weight.nested_quant_map": "model-00053-of-00073.safetensors",
+    "model.layers.26.self_attn.q_proj.weight.quant_map": "model-00053-of-00073.safetensors",
+    "model.layers.26.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "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.26.self_attn.v_proj.weight.absmax": "model-00053-of-00073.safetensors",
+    "model.layers.26.self_attn.v_proj.weight.nested_absmax": "model-00053-of-00073.safetensors",
+    "model.layers.26.self_attn.v_proj.weight.nested_quant_map": "model-00053-of-00073.safetensors",
+    "model.layers.26.self_attn.v_proj.weight.quant_map": "model-00053-of-00073.safetensors",
+    "model.layers.26.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "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.k_proj.weight.absmax": "model-00055-of-00073.safetensors",
+    "model.layers.27.self_attn.k_proj.weight.nested_absmax": "model-00055-of-00073.safetensors",
+    "model.layers.27.self_attn.k_proj.weight.nested_quant_map": "model-00055-of-00073.safetensors",
+    "model.layers.27.self_attn.k_proj.weight.quant_map": "model-00055-of-00073.safetensors",
+    "model.layers.27.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "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.o_proj.weight.absmax": "model-00055-of-00073.safetensors",
+    "model.layers.27.self_attn.o_proj.weight.nested_absmax": "model-00055-of-00073.safetensors",
+    "model.layers.27.self_attn.o_proj.weight.nested_quant_map": "model-00055-of-00073.safetensors",
+    "model.layers.27.self_attn.o_proj.weight.quant_map": "model-00055-of-00073.safetensors",
+    "model.layers.27.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "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.q_proj.weight.absmax": "model-00055-of-00073.safetensors",
+    "model.layers.27.self_attn.q_proj.weight.nested_absmax": "model-00055-of-00073.safetensors",
+    "model.layers.27.self_attn.q_proj.weight.nested_quant_map": "model-00055-of-00073.safetensors",
+    "model.layers.27.self_attn.q_proj.weight.quant_map": "model-00055-of-00073.safetensors",
+    "model.layers.27.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "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.27.self_attn.v_proj.weight.absmax": "model-00055-of-00073.safetensors",
+    "model.layers.27.self_attn.v_proj.weight.nested_absmax": "model-00055-of-00073.safetensors",
+    "model.layers.27.self_attn.v_proj.weight.nested_quant_map": "model-00055-of-00073.safetensors",
+    "model.layers.27.self_attn.v_proj.weight.quant_map": "model-00055-of-00073.safetensors",
+    "model.layers.27.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "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.k_proj.weight.absmax": "model-00057-of-00073.safetensors",
+    "model.layers.28.self_attn.k_proj.weight.nested_absmax": "model-00057-of-00073.safetensors",
+    "model.layers.28.self_attn.k_proj.weight.nested_quant_map": "model-00057-of-00073.safetensors",
+    "model.layers.28.self_attn.k_proj.weight.quant_map": "model-00057-of-00073.safetensors",
+    "model.layers.28.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "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.o_proj.weight.absmax": "model-00057-of-00073.safetensors",
+    "model.layers.28.self_attn.o_proj.weight.nested_absmax": "model-00057-of-00073.safetensors",
+    "model.layers.28.self_attn.o_proj.weight.nested_quant_map": "model-00057-of-00073.safetensors",
+    "model.layers.28.self_attn.o_proj.weight.quant_map": "model-00057-of-00073.safetensors",
+    "model.layers.28.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "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.q_proj.weight.absmax": "model-00057-of-00073.safetensors",
+    "model.layers.28.self_attn.q_proj.weight.nested_absmax": "model-00057-of-00073.safetensors",
+    "model.layers.28.self_attn.q_proj.weight.nested_quant_map": "model-00057-of-00073.safetensors",
+    "model.layers.28.self_attn.q_proj.weight.quant_map": "model-00057-of-00073.safetensors",
+    "model.layers.28.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "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.28.self_attn.v_proj.weight.absmax": "model-00057-of-00073.safetensors",
+    "model.layers.28.self_attn.v_proj.weight.nested_absmax": "model-00057-of-00073.safetensors",
+    "model.layers.28.self_attn.v_proj.weight.nested_quant_map": "model-00057-of-00073.safetensors",
+    "model.layers.28.self_attn.v_proj.weight.quant_map": "model-00057-of-00073.safetensors",
+    "model.layers.28.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "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.k_proj.weight.absmax": "model-00059-of-00073.safetensors",
+    "model.layers.29.self_attn.k_proj.weight.nested_absmax": "model-00059-of-00073.safetensors",
+    "model.layers.29.self_attn.k_proj.weight.nested_quant_map": "model-00059-of-00073.safetensors",
+    "model.layers.29.self_attn.k_proj.weight.quant_map": "model-00059-of-00073.safetensors",
+    "model.layers.29.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "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.o_proj.weight.absmax": "model-00059-of-00073.safetensors",
+    "model.layers.29.self_attn.o_proj.weight.nested_absmax": "model-00059-of-00073.safetensors",
+    "model.layers.29.self_attn.o_proj.weight.nested_quant_map": "model-00059-of-00073.safetensors",
+    "model.layers.29.self_attn.o_proj.weight.quant_map": "model-00059-of-00073.safetensors",
+    "model.layers.29.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "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.q_proj.weight.absmax": "model-00059-of-00073.safetensors",
+    "model.layers.29.self_attn.q_proj.weight.nested_absmax": "model-00059-of-00073.safetensors",
+    "model.layers.29.self_attn.q_proj.weight.nested_quant_map": "model-00059-of-00073.safetensors",
+    "model.layers.29.self_attn.q_proj.weight.quant_map": "model-00059-of-00073.safetensors",
+    "model.layers.29.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "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.29.self_attn.v_proj.weight.absmax": "model-00059-of-00073.safetensors",
+    "model.layers.29.self_attn.v_proj.weight.nested_absmax": "model-00059-of-00073.safetensors",
+    "model.layers.29.self_attn.v_proj.weight.nested_quant_map": "model-00059-of-00073.safetensors",
+    "model.layers.29.self_attn.v_proj.weight.quant_map": "model-00059-of-00073.safetensors",
+    "model.layers.29.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "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.k_proj.weight.absmax": "model-00007-of-00073.safetensors",
+    "model.layers.3.self_attn.k_proj.weight.nested_absmax": "model-00007-of-00073.safetensors",
+    "model.layers.3.self_attn.k_proj.weight.nested_quant_map": "model-00007-of-00073.safetensors",
+    "model.layers.3.self_attn.k_proj.weight.quant_map": "model-00007-of-00073.safetensors",
+    "model.layers.3.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "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.o_proj.weight.absmax": "model-00007-of-00073.safetensors",
+    "model.layers.3.self_attn.o_proj.weight.nested_absmax": "model-00007-of-00073.safetensors",
+    "model.layers.3.self_attn.o_proj.weight.nested_quant_map": "model-00007-of-00073.safetensors",
+    "model.layers.3.self_attn.o_proj.weight.quant_map": "model-00007-of-00073.safetensors",
+    "model.layers.3.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "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.q_proj.weight.absmax": "model-00007-of-00073.safetensors",
+    "model.layers.3.self_attn.q_proj.weight.nested_absmax": "model-00007-of-00073.safetensors",
+    "model.layers.3.self_attn.q_proj.weight.nested_quant_map": "model-00007-of-00073.safetensors",
+    "model.layers.3.self_attn.q_proj.weight.quant_map": "model-00007-of-00073.safetensors",
+    "model.layers.3.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "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.3.self_attn.v_proj.weight.absmax": "model-00007-of-00073.safetensors",
+    "model.layers.3.self_attn.v_proj.weight.nested_absmax": "model-00007-of-00073.safetensors",
+    "model.layers.3.self_attn.v_proj.weight.nested_quant_map": "model-00007-of-00073.safetensors",
+    "model.layers.3.self_attn.v_proj.weight.quant_map": "model-00007-of-00073.safetensors",
+    "model.layers.3.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "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.k_proj.weight.absmax": "model-00061-of-00073.safetensors",
+    "model.layers.30.self_attn.k_proj.weight.nested_absmax": "model-00061-of-00073.safetensors",
+    "model.layers.30.self_attn.k_proj.weight.nested_quant_map": "model-00061-of-00073.safetensors",
+    "model.layers.30.self_attn.k_proj.weight.quant_map": "model-00061-of-00073.safetensors",
+    "model.layers.30.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "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.o_proj.weight.absmax": "model-00061-of-00073.safetensors",
+    "model.layers.30.self_attn.o_proj.weight.nested_absmax": "model-00061-of-00073.safetensors",
+    "model.layers.30.self_attn.o_proj.weight.nested_quant_map": "model-00061-of-00073.safetensors",
+    "model.layers.30.self_attn.o_proj.weight.quant_map": "model-00061-of-00073.safetensors",
+    "model.layers.30.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "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.q_proj.weight.absmax": "model-00061-of-00073.safetensors",
+    "model.layers.30.self_attn.q_proj.weight.nested_absmax": "model-00061-of-00073.safetensors",
+    "model.layers.30.self_attn.q_proj.weight.nested_quant_map": "model-00061-of-00073.safetensors",
+    "model.layers.30.self_attn.q_proj.weight.quant_map": "model-00061-of-00073.safetensors",
+    "model.layers.30.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "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.30.self_attn.v_proj.weight.absmax": "model-00061-of-00073.safetensors",
+    "model.layers.30.self_attn.v_proj.weight.nested_absmax": "model-00061-of-00073.safetensors",
+    "model.layers.30.self_attn.v_proj.weight.nested_quant_map": "model-00061-of-00073.safetensors",
+    "model.layers.30.self_attn.v_proj.weight.quant_map": "model-00061-of-00073.safetensors",
+    "model.layers.30.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "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.k_proj.weight.absmax": "model-00063-of-00073.safetensors",
+    "model.layers.31.self_attn.k_proj.weight.nested_absmax": "model-00063-of-00073.safetensors",
+    "model.layers.31.self_attn.k_proj.weight.nested_quant_map": "model-00063-of-00073.safetensors",
+    "model.layers.31.self_attn.k_proj.weight.quant_map": "model-00063-of-00073.safetensors",
+    "model.layers.31.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "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.o_proj.weight.absmax": "model-00063-of-00073.safetensors",
+    "model.layers.31.self_attn.o_proj.weight.nested_absmax": "model-00063-of-00073.safetensors",
+    "model.layers.31.self_attn.o_proj.weight.nested_quant_map": "model-00063-of-00073.safetensors",
+    "model.layers.31.self_attn.o_proj.weight.quant_map": "model-00063-of-00073.safetensors",
+    "model.layers.31.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "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.q_proj.weight.absmax": "model-00063-of-00073.safetensors",
+    "model.layers.31.self_attn.q_proj.weight.nested_absmax": "model-00063-of-00073.safetensors",
+    "model.layers.31.self_attn.q_proj.weight.nested_quant_map": "model-00063-of-00073.safetensors",
+    "model.layers.31.self_attn.q_proj.weight.quant_map": "model-00063-of-00073.safetensors",
+    "model.layers.31.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "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.31.self_attn.v_proj.weight.absmax": "model-00063-of-00073.safetensors",
+    "model.layers.31.self_attn.v_proj.weight.nested_absmax": "model-00063-of-00073.safetensors",
+    "model.layers.31.self_attn.v_proj.weight.nested_quant_map": "model-00063-of-00073.safetensors",
+    "model.layers.31.self_attn.v_proj.weight.quant_map": "model-00063-of-00073.safetensors",
+    "model.layers.31.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "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.k_proj.weight.absmax": "model-00065-of-00073.safetensors",
+    "model.layers.32.self_attn.k_proj.weight.nested_absmax": "model-00065-of-00073.safetensors",
+    "model.layers.32.self_attn.k_proj.weight.nested_quant_map": "model-00065-of-00073.safetensors",
+    "model.layers.32.self_attn.k_proj.weight.quant_map": "model-00065-of-00073.safetensors",
+    "model.layers.32.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "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.o_proj.weight.absmax": "model-00065-of-00073.safetensors",
+    "model.layers.32.self_attn.o_proj.weight.nested_absmax": "model-00065-of-00073.safetensors",
+    "model.layers.32.self_attn.o_proj.weight.nested_quant_map": "model-00065-of-00073.safetensors",
+    "model.layers.32.self_attn.o_proj.weight.quant_map": "model-00065-of-00073.safetensors",
+    "model.layers.32.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "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.q_proj.weight.absmax": "model-00065-of-00073.safetensors",
+    "model.layers.32.self_attn.q_proj.weight.nested_absmax": "model-00065-of-00073.safetensors",
+    "model.layers.32.self_attn.q_proj.weight.nested_quant_map": "model-00065-of-00073.safetensors",
+    "model.layers.32.self_attn.q_proj.weight.quant_map": "model-00065-of-00073.safetensors",
+    "model.layers.32.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "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.32.self_attn.v_proj.weight.absmax": "model-00065-of-00073.safetensors",
+    "model.layers.32.self_attn.v_proj.weight.nested_absmax": "model-00065-of-00073.safetensors",
+    "model.layers.32.self_attn.v_proj.weight.nested_quant_map": "model-00065-of-00073.safetensors",
+    "model.layers.32.self_attn.v_proj.weight.quant_map": "model-00065-of-00073.safetensors",
+    "model.layers.32.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "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.k_proj.weight.absmax": "model-00067-of-00073.safetensors",
+    "model.layers.33.self_attn.k_proj.weight.nested_absmax": "model-00067-of-00073.safetensors",
+    "model.layers.33.self_attn.k_proj.weight.nested_quant_map": "model-00067-of-00073.safetensors",
+    "model.layers.33.self_attn.k_proj.weight.quant_map": "model-00067-of-00073.safetensors",
+    "model.layers.33.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "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.o_proj.weight.absmax": "model-00067-of-00073.safetensors",
+    "model.layers.33.self_attn.o_proj.weight.nested_absmax": "model-00067-of-00073.safetensors",
+    "model.layers.33.self_attn.o_proj.weight.nested_quant_map": "model-00067-of-00073.safetensors",
+    "model.layers.33.self_attn.o_proj.weight.quant_map": "model-00067-of-00073.safetensors",
+    "model.layers.33.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "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.q_proj.weight.absmax": "model-00067-of-00073.safetensors",
+    "model.layers.33.self_attn.q_proj.weight.nested_absmax": "model-00067-of-00073.safetensors",
+    "model.layers.33.self_attn.q_proj.weight.nested_quant_map": "model-00067-of-00073.safetensors",
+    "model.layers.33.self_attn.q_proj.weight.quant_map": "model-00067-of-00073.safetensors",
+    "model.layers.33.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "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.33.self_attn.v_proj.weight.absmax": "model-00067-of-00073.safetensors",
+    "model.layers.33.self_attn.v_proj.weight.nested_absmax": "model-00067-of-00073.safetensors",
+    "model.layers.33.self_attn.v_proj.weight.nested_quant_map": "model-00067-of-00073.safetensors",
+    "model.layers.33.self_attn.v_proj.weight.quant_map": "model-00067-of-00073.safetensors",
+    "model.layers.33.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "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.k_proj.weight.absmax": "model-00069-of-00073.safetensors",
+    "model.layers.34.self_attn.k_proj.weight.nested_absmax": "model-00069-of-00073.safetensors",
+    "model.layers.34.self_attn.k_proj.weight.nested_quant_map": "model-00069-of-00073.safetensors",
+    "model.layers.34.self_attn.k_proj.weight.quant_map": "model-00069-of-00073.safetensors",
+    "model.layers.34.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "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.o_proj.weight.absmax": "model-00069-of-00073.safetensors",
+    "model.layers.34.self_attn.o_proj.weight.nested_absmax": "model-00069-of-00073.safetensors",
+    "model.layers.34.self_attn.o_proj.weight.nested_quant_map": "model-00069-of-00073.safetensors",
+    "model.layers.34.self_attn.o_proj.weight.quant_map": "model-00069-of-00073.safetensors",
+    "model.layers.34.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "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.q_proj.weight.absmax": "model-00069-of-00073.safetensors",
+    "model.layers.34.self_attn.q_proj.weight.nested_absmax": "model-00069-of-00073.safetensors",
+    "model.layers.34.self_attn.q_proj.weight.nested_quant_map": "model-00069-of-00073.safetensors",
+    "model.layers.34.self_attn.q_proj.weight.quant_map": "model-00069-of-00073.safetensors",
+    "model.layers.34.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "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.34.self_attn.v_proj.weight.absmax": "model-00069-of-00073.safetensors",
+    "model.layers.34.self_attn.v_proj.weight.nested_absmax": "model-00069-of-00073.safetensors",
+    "model.layers.34.self_attn.v_proj.weight.nested_quant_map": "model-00069-of-00073.safetensors",
+    "model.layers.34.self_attn.v_proj.weight.quant_map": "model-00069-of-00073.safetensors",
+    "model.layers.34.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "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.k_proj.weight.absmax": "model-00071-of-00073.safetensors",
+    "model.layers.35.self_attn.k_proj.weight.nested_absmax": "model-00071-of-00073.safetensors",
+    "model.layers.35.self_attn.k_proj.weight.nested_quant_map": "model-00071-of-00073.safetensors",
+    "model.layers.35.self_attn.k_proj.weight.quant_map": "model-00071-of-00073.safetensors",
+    "model.layers.35.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "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.o_proj.weight.absmax": "model-00071-of-00073.safetensors",
+    "model.layers.35.self_attn.o_proj.weight.nested_absmax": "model-00071-of-00073.safetensors",
+    "model.layers.35.self_attn.o_proj.weight.nested_quant_map": "model-00071-of-00073.safetensors",
+    "model.layers.35.self_attn.o_proj.weight.quant_map": "model-00071-of-00073.safetensors",
+    "model.layers.35.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "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.q_proj.weight.absmax": "model-00071-of-00073.safetensors",
+    "model.layers.35.self_attn.q_proj.weight.nested_absmax": "model-00071-of-00073.safetensors",
+    "model.layers.35.self_attn.q_proj.weight.nested_quant_map": "model-00071-of-00073.safetensors",
+    "model.layers.35.self_attn.q_proj.weight.quant_map": "model-00071-of-00073.safetensors",
+    "model.layers.35.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "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.35.self_attn.v_proj.weight.absmax": "model-00071-of-00073.safetensors",
+    "model.layers.35.self_attn.v_proj.weight.nested_absmax": "model-00071-of-00073.safetensors",
+    "model.layers.35.self_attn.v_proj.weight.nested_quant_map": "model-00071-of-00073.safetensors",
+    "model.layers.35.self_attn.v_proj.weight.quant_map": "model-00071-of-00073.safetensors",
+    "model.layers.35.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "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.k_proj.weight.absmax": "model-00009-of-00073.safetensors",
+    "model.layers.4.self_attn.k_proj.weight.nested_absmax": "model-00009-of-00073.safetensors",
+    "model.layers.4.self_attn.k_proj.weight.nested_quant_map": "model-00009-of-00073.safetensors",
+    "model.layers.4.self_attn.k_proj.weight.quant_map": "model-00009-of-00073.safetensors",
+    "model.layers.4.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "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.o_proj.weight.absmax": "model-00009-of-00073.safetensors",
+    "model.layers.4.self_attn.o_proj.weight.nested_absmax": "model-00009-of-00073.safetensors",
+    "model.layers.4.self_attn.o_proj.weight.nested_quant_map": "model-00009-of-00073.safetensors",
+    "model.layers.4.self_attn.o_proj.weight.quant_map": "model-00009-of-00073.safetensors",
+    "model.layers.4.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "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.q_proj.weight.absmax": "model-00009-of-00073.safetensors",
+    "model.layers.4.self_attn.q_proj.weight.nested_absmax": "model-00009-of-00073.safetensors",
+    "model.layers.4.self_attn.q_proj.weight.nested_quant_map": "model-00009-of-00073.safetensors",
+    "model.layers.4.self_attn.q_proj.weight.quant_map": "model-00009-of-00073.safetensors",
+    "model.layers.4.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "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.4.self_attn.v_proj.weight.absmax": "model-00009-of-00073.safetensors",
+    "model.layers.4.self_attn.v_proj.weight.nested_absmax": "model-00009-of-00073.safetensors",
+    "model.layers.4.self_attn.v_proj.weight.nested_quant_map": "model-00009-of-00073.safetensors",
+    "model.layers.4.self_attn.v_proj.weight.quant_map": "model-00009-of-00073.safetensors",
+    "model.layers.4.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "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.k_proj.weight.absmax": "model-00011-of-00073.safetensors",
+    "model.layers.5.self_attn.k_proj.weight.nested_absmax": "model-00011-of-00073.safetensors",
+    "model.layers.5.self_attn.k_proj.weight.nested_quant_map": "model-00011-of-00073.safetensors",
+    "model.layers.5.self_attn.k_proj.weight.quant_map": "model-00011-of-00073.safetensors",
+    "model.layers.5.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "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.o_proj.weight.absmax": "model-00011-of-00073.safetensors",
+    "model.layers.5.self_attn.o_proj.weight.nested_absmax": "model-00011-of-00073.safetensors",
+    "model.layers.5.self_attn.o_proj.weight.nested_quant_map": "model-00011-of-00073.safetensors",
+    "model.layers.5.self_attn.o_proj.weight.quant_map": "model-00011-of-00073.safetensors",
+    "model.layers.5.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "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.q_proj.weight.absmax": "model-00011-of-00073.safetensors",
+    "model.layers.5.self_attn.q_proj.weight.nested_absmax": "model-00011-of-00073.safetensors",
+    "model.layers.5.self_attn.q_proj.weight.nested_quant_map": "model-00011-of-00073.safetensors",
+    "model.layers.5.self_attn.q_proj.weight.quant_map": "model-00011-of-00073.safetensors",
+    "model.layers.5.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "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.5.self_attn.v_proj.weight.absmax": "model-00011-of-00073.safetensors",
+    "model.layers.5.self_attn.v_proj.weight.nested_absmax": "model-00011-of-00073.safetensors",
+    "model.layers.5.self_attn.v_proj.weight.nested_quant_map": "model-00011-of-00073.safetensors",
+    "model.layers.5.self_attn.v_proj.weight.quant_map": "model-00011-of-00073.safetensors",
+    "model.layers.5.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "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.k_proj.weight.absmax": "model-00013-of-00073.safetensors",
+    "model.layers.6.self_attn.k_proj.weight.nested_absmax": "model-00013-of-00073.safetensors",
+    "model.layers.6.self_attn.k_proj.weight.nested_quant_map": "model-00013-of-00073.safetensors",
+    "model.layers.6.self_attn.k_proj.weight.quant_map": "model-00013-of-00073.safetensors",
+    "model.layers.6.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "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.o_proj.weight.absmax": "model-00013-of-00073.safetensors",
+    "model.layers.6.self_attn.o_proj.weight.nested_absmax": "model-00013-of-00073.safetensors",
+    "model.layers.6.self_attn.o_proj.weight.nested_quant_map": "model-00013-of-00073.safetensors",
+    "model.layers.6.self_attn.o_proj.weight.quant_map": "model-00013-of-00073.safetensors",
+    "model.layers.6.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "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.q_proj.weight.absmax": "model-00013-of-00073.safetensors",
+    "model.layers.6.self_attn.q_proj.weight.nested_absmax": "model-00013-of-00073.safetensors",
+    "model.layers.6.self_attn.q_proj.weight.nested_quant_map": "model-00013-of-00073.safetensors",
+    "model.layers.6.self_attn.q_proj.weight.quant_map": "model-00013-of-00073.safetensors",
+    "model.layers.6.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "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.6.self_attn.v_proj.weight.absmax": "model-00013-of-00073.safetensors",
+    "model.layers.6.self_attn.v_proj.weight.nested_absmax": "model-00013-of-00073.safetensors",
+    "model.layers.6.self_attn.v_proj.weight.nested_quant_map": "model-00013-of-00073.safetensors",
+    "model.layers.6.self_attn.v_proj.weight.quant_map": "model-00013-of-00073.safetensors",
+    "model.layers.6.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "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.k_proj.weight.absmax": "model-00015-of-00073.safetensors",
+    "model.layers.7.self_attn.k_proj.weight.nested_absmax": "model-00015-of-00073.safetensors",
+    "model.layers.7.self_attn.k_proj.weight.nested_quant_map": "model-00015-of-00073.safetensors",
+    "model.layers.7.self_attn.k_proj.weight.quant_map": "model-00015-of-00073.safetensors",
+    "model.layers.7.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "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.o_proj.weight.absmax": "model-00015-of-00073.safetensors",
+    "model.layers.7.self_attn.o_proj.weight.nested_absmax": "model-00015-of-00073.safetensors",
+    "model.layers.7.self_attn.o_proj.weight.nested_quant_map": "model-00015-of-00073.safetensors",
+    "model.layers.7.self_attn.o_proj.weight.quant_map": "model-00015-of-00073.safetensors",
+    "model.layers.7.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "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.q_proj.weight.absmax": "model-00015-of-00073.safetensors",
+    "model.layers.7.self_attn.q_proj.weight.nested_absmax": "model-00015-of-00073.safetensors",
+    "model.layers.7.self_attn.q_proj.weight.nested_quant_map": "model-00015-of-00073.safetensors",
+    "model.layers.7.self_attn.q_proj.weight.quant_map": "model-00015-of-00073.safetensors",
+    "model.layers.7.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "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.7.self_attn.v_proj.weight.absmax": "model-00015-of-00073.safetensors",
+    "model.layers.7.self_attn.v_proj.weight.nested_absmax": "model-00015-of-00073.safetensors",
+    "model.layers.7.self_attn.v_proj.weight.nested_quant_map": "model-00015-of-00073.safetensors",
+    "model.layers.7.self_attn.v_proj.weight.quant_map": "model-00015-of-00073.safetensors",
+    "model.layers.7.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "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.k_proj.weight.absmax": "model-00017-of-00073.safetensors",
+    "model.layers.8.self_attn.k_proj.weight.nested_absmax": "model-00017-of-00073.safetensors",
+    "model.layers.8.self_attn.k_proj.weight.nested_quant_map": "model-00017-of-00073.safetensors",
+    "model.layers.8.self_attn.k_proj.weight.quant_map": "model-00017-of-00073.safetensors",
+    "model.layers.8.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "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.o_proj.weight.absmax": "model-00017-of-00073.safetensors",
+    "model.layers.8.self_attn.o_proj.weight.nested_absmax": "model-00017-of-00073.safetensors",
+    "model.layers.8.self_attn.o_proj.weight.nested_quant_map": "model-00017-of-00073.safetensors",
+    "model.layers.8.self_attn.o_proj.weight.quant_map": "model-00017-of-00073.safetensors",
+    "model.layers.8.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "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.q_proj.weight.absmax": "model-00017-of-00073.safetensors",
+    "model.layers.8.self_attn.q_proj.weight.nested_absmax": "model-00017-of-00073.safetensors",
+    "model.layers.8.self_attn.q_proj.weight.nested_quant_map": "model-00017-of-00073.safetensors",
+    "model.layers.8.self_attn.q_proj.weight.quant_map": "model-00017-of-00073.safetensors",
+    "model.layers.8.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "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.8.self_attn.v_proj.weight.absmax": "model-00017-of-00073.safetensors",
+    "model.layers.8.self_attn.v_proj.weight.nested_absmax": "model-00017-of-00073.safetensors",
+    "model.layers.8.self_attn.v_proj.weight.nested_quant_map": "model-00017-of-00073.safetensors",
+    "model.layers.8.self_attn.v_proj.weight.quant_map": "model-00017-of-00073.safetensors",
+    "model.layers.8.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "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.k_proj.weight.absmax": "model-00019-of-00073.safetensors",
+    "model.layers.9.self_attn.k_proj.weight.nested_absmax": "model-00019-of-00073.safetensors",
+    "model.layers.9.self_attn.k_proj.weight.nested_quant_map": "model-00019-of-00073.safetensors",
+    "model.layers.9.self_attn.k_proj.weight.quant_map": "model-00019-of-00073.safetensors",
+    "model.layers.9.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "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.o_proj.weight.absmax": "model-00019-of-00073.safetensors",
+    "model.layers.9.self_attn.o_proj.weight.nested_absmax": "model-00019-of-00073.safetensors",
+    "model.layers.9.self_attn.o_proj.weight.nested_quant_map": "model-00019-of-00073.safetensors",
+    "model.layers.9.self_attn.o_proj.weight.quant_map": "model-00019-of-00073.safetensors",
+    "model.layers.9.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "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.q_proj.weight.absmax": "model-00019-of-00073.safetensors",
+    "model.layers.9.self_attn.q_proj.weight.nested_absmax": "model-00019-of-00073.safetensors",
+    "model.layers.9.self_attn.q_proj.weight.nested_quant_map": "model-00019-of-00073.safetensors",
+    "model.layers.9.self_attn.q_proj.weight.quant_map": "model-00019-of-00073.safetensors",
+    "model.layers.9.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "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.layers.9.self_attn.v_proj.weight.absmax": "model-00019-of-00073.safetensors",
+    "model.layers.9.self_attn.v_proj.weight.nested_absmax": "model-00019-of-00073.safetensors",
+    "model.layers.9.self_attn.v_proj.weight.nested_quant_map": "model-00019-of-00073.safetensors",
+    "model.layers.9.self_attn.v_proj.weight.quant_map": "model-00019-of-00073.safetensors",
+    "model.layers.9.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00019-of-00073.safetensors",
+    "model.norm.weight": "model-00073-of-00073.safetensors"
+  }
+}
diff --git a/special_tokens_map.json b/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..6274cc1bd159aa75de771315558e5cac7dd8bea0
--- /dev/null
+++ b/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
+  }
+}
diff --git a/tokenizer.json b/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..6ec3ef1795cbbda6b7cb7d1f114919cbe3fdd647
--- /dev/null
+++ b/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0614fe83cadab421296e664e1f48f4261fa8fef6e03e63bb75c20f38e37d07d3
+size 27868174
diff --git a/tokenizer_config.json b/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c021cddb0a9dd35b1bf83a9f145be2d9b3757891
--- /dev/null
+++ b/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"
+}