Upload folder using huggingface_hub

.gitattributes

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

README.md

@@ -0,0 +1,57 @@
+---
+license: apache-2.0
+language:
+- ja
+- en
+- de
+- fr
+- it
+base_model: swiss-ai/Apertus-v1.5-8B
+library_name: mlx
+pipeline_tag: text-generation
+tags:
+- mlx
+- apertus
+- multilingual
+- quantized
+---
+
+# Apertus-v1.5-8B (MLX 8bit, text LM, verified)
+
+スイスAIイニシアチブの [Apertus-v1.5-8B](https://huggingface.co/swiss-ai/Apertus-v1.5-8B)（Apache-2.0・多言語・xIELU活性/QK-norm/llama3型RoPEスケーリングの独自アーキテクチャ）から**テキストLM部分を抽出してMLX変換**したものです（8bit量子化・group size 64・実効8.5bpw）。品質と速度のバランスが良い**推奨版**です。
+
+**このMLX版の価値**: 上流モデルはリリース版transformers/vLLMでは動かず、[swiss-ai専用フォーク](https://github.com/swiss-ai/transformers/tree/3797303dda74844e3d1f8977ff5518bb91f818b4)が必要ですが、この変換は**mlx-lm標準でそのまま動きます**（`pip install mlx-lm`のみ）。
+
+**スコープ**: 元モデルは画像・音声入力対応のomniモデルですが、本repoは**テキスト専用**の抽出です（vision/audioトークナイザは含みません。埋め込みはテキスト出力語彙131,072行に切り詰め済み — テキスト対話のトークンIDはすべてこの範囲内であることを確認しています）。
+
+## 使い方
+
+```bash
+pip install mlx-lm
+python -m mlx_lm generate --model tokimoa/apertus-v1.5-8b-mlx-8bit   --prompt "富士山の標高を教えてください。" --max-tokens 200 --temp 0.0
+```
+
+**Deliberation（思考モード）に注意**: chat templateに思考モードのフラグがあり、mlx-lm経由の既定では**有効**（`<|inner_prefix|>`で内部推論を出力してから回答）、Hugging Face transformersの既定では無効になります。無効にしたい場合は`apply_chat_template`に`enable_thinking=False`を渡してください。
+
+## 変換品質の検証（tokimoa）
+
+transformers公式実装（swiss-aiフォーク・**CPU** bf16）との突き合わせ検証:
+
+- **同一入力でのprefillロジット比較: 日本語ビジネスプローブ5種すべてでtop-1トークン一致**（cos類似度0.9992〜0.9997・top-10重複9〜10/10 = 量子化劣化ほぼなし）
+- bf16版は反復実行で出力完全一致（決定論的）
+- 検証時の発見: 参照フォークは**MPS上では出力が破綻**します（縮退ループ）。参照はCPUで実行しました（変換品質とは無関係の上流問題）
+
+## 実測速度（M4 Max 36GB）
+
+- 生成: 約44 tok/s / ピークメモリ: 8.7GB（重み8.0GB）
+
+## 変換情報
+
+- 変換元: `swiss-ai/Apertus-v1.5-8B`（公式BF16、commit a411d83）からテキストLM抽出（`model.language_model.*`→`model.*`・lm_head保持・embed切り詰め）
+- 変換: `mlx-lm 0.31.3` `convert -q --q-bits 8`（group size 64 affine、実効8.5bpw）
+- 兄弟repo: [bf16](https://huggingface.co/tokimoa/apertus-v1.5-8b-mlx-bf16)（参照一致検証の基準）/ [4bit](https://huggingface.co/tokimoa/apertus-v1.5-8b-mlx-4bit)（4.3GB・約75 tok/s）
+- 変換者: [tokimoa](https://tokimoa.jp)
+
+## ライセンス
+
+Apache-2.0（元モデルに準拠）。上流の[利用ポリシー（AUP）](https://github.com/swiss-ai/apertus-legal/blob/main/apertus_1.5/USAGE_POLICY.pdf)も参照してください。

chat_template.jinja

@@ -0,0 +1,365 @@
+{%- macro render_typescript_type(param_spec, required_params, is_nullable=false) -%}
+    {%- if param_spec.type == "array" -%}
+        {%- if param_spec['items'] -%}
+            {%- if param_spec['items']['type'] == "string" -%}
+                {{- "string[]" }}
+            {%- elif param_spec['items']['type'] == "number" -%}
+                {{- "number[]" }}
+            {%- elif param_spec['items']['type'] == "integer" -%}
+                {{- "number[]" }}
+            {%- elif param_spec['items']['type'] == "boolean" -%}
+                {{- "boolean[]" }}
+            {%- else -%}
+                {%- set inner_type = render_typescript_type(param_spec['items'], required_params) -%}
+                {%- if inner_type == "object | object" or inner_type|length > 50 -%}
+                    {{- "any[]" }}
+                {%- else -%}
+                    {{- inner_type + "[]" }}
+                {%- endif -%}
+            {%- endif -%}
+            {%- if param_spec.nullable -%}
+                {{- " | null" }}
+            {%- endif -%}
+        {%- else -%}
+            {{- "any[]" }}
+            {%- if param_spec.nullable -%}
+                {{- " | null" }}
+            {%- endif -%}
+        {%- endif -%}
+    {%- elif param_spec.type is defined and param_spec.type is iterable and param_spec.type is not string and param_spec.type is not mapping and param_spec.type[0] is defined -%}
+        {#- Handle array of types like ["object", "object"] from Union[dict, list] #}
+        {%- if param_spec.type | length > 1 -%}
+            {{- param_spec.type | join(" | ") }}
+        {%- else -%}
+            {{- param_spec.type[0] }}
+        {%- endif -%}
+    {%- elif param_spec.oneOf -%}
+        {#- Handle oneOf schemas - check for complex unions and fallback to any #}
+        {%- set has_object_variants = false -%}
+        {%- for variant in param_spec.oneOf -%}
+            {%- if variant.type == "object" -%}
+                {%- set has_object_variants = true -%}
+            {%- endif -%}
+        {%- endfor -%}
+        {%- if has_object_variants and param_spec.oneOf|length > 1 -%}
+            {{- "any" }}
+        {%- else -%}
+            {%- for variant in param_spec.oneOf -%}
+                {{- render_typescript_type(variant, required_params) -}}
+                {%- if variant.description %}
+                    {{- "// " + variant.description }}
+                {%- endif -%}
+                {%- if variant.default is defined %}
+                    {{ "// default: " + variant.default|tojson }}
+                {%- endif -%}
+                {%- if not loop.last %}
+                    {{- " | " }}
+                {% endif -%}
+            {%- endfor -%}
+        {%- endif -%}
+    {%- elif param_spec.type == "string" -%}
+        {%- if param_spec.enum -%}
+            {{- '"' + param_spec.enum|join('" | "') + '"' -}}
+        {%- else -%}
+            {{- "string" }}
+            {%- if param_spec.nullable %}
+                {{- " | null" }}
+            {%- endif -%}
+        {%- endif -%}
+    {%- elif param_spec.type == "number" -%}
+        {{- "number" }}
+    {%- elif param_spec.type == "integer" -%}
+        {{- "number" }}
+    {%- elif param_spec.type == "boolean" -%}
+        {{- "boolean" }}
+    {%- elif param_spec.type == "object" -%}
+        {%- if param_spec.properties -%}
+            {{- "{\n" }}
+            {%- for prop_name, prop_spec in param_spec.properties.items() -%}
+                {{- prop_name -}}
+                {%- if prop_name not in (param_spec.required or []) -%}
+                    {{- "?" }}
+                {%- endif -%}
+                {{- ": " }}
+                {{ render_typescript_type(prop_spec, param_spec.required or []) }}
+                {%- if not loop.last -%}
+                    {{-", " }}
+                {%- endif -%}
+            {%- endfor -%}
+            {{- "}" }}
+        {%- else -%}
+            {{- "object" }}
+        {%- endif -%}
+    {%- else -%}
+        {{- "any" }}
+    {%- endif -%}
+{%- endmacro -%}
+
+{%- macro render_tools(tools) -%}
+    {%- for tool in tools %}
+        {%- if tool.function %}
+            {%- set tool = tool.function %}
+        {%- endif %}
+        {{- "// " + tool.description + "\n" }}
+        {{- "type "+ tool.name + " = " }}
+        {%- if tool.parameters and tool.parameters.properties %}
+            {{- "(_: {\n" }}
+            {%- for param_name, param_spec in tool.parameters.properties.items() %}
+                {%- if param_spec.description %}
+                    {{- "// " + param_spec.description + "\n" }}
+                {%- endif %}
+                {{- param_name }}
+                {%- if param_name not in (tool.parameters.required or []) -%}
+                    {{- "?" }}
+                {%- endif -%}
+                {{- ": " }}
+                {{- render_typescript_type(param_spec, tool.parameters.required or []) }}
+                {%- if param_spec.default is defined -%}
+                    {%- if param_spec.enum %}
+                        {{- ", // default: " + param_spec.default }}
+                    {%- elif param_spec.oneOf %}
+                        {{- "// default: " + param_spec.default }}
+                    {%- else %}
+                        {{- ", // default: " + param_spec.default|tojson }}
+                    {%- endif -%}
+                {%- endif -%}
+                {%- if not loop.last %}
+                    {{- ",\n" }}
+                {%- else %}
+                    {{- "\n" }}
+                {%- endif -%}
+            {%- endfor %}
+            {{- "}) => any;" }}
+        {%- else -%}
+            {{- "() => any;" }}
+        {%- endif -%}
+        {%- if not loop.last -%}
+            {{- "\n" }}
+        {%- endif -%}
+    {%- endfor %}
+{%- endmacro -%}
+
+{{ bos_token }}
+
+{%- set system_token = '<|system_start|>' -%}
+{%- set end_system_token = '<|system_end|>' -%}
+{%- set developer_token = '<|developer_start|>' -%}
+{%- set end_developer_token = '<|developer_end|>' -%}
+{%- set user_token = '<|user_start|>' -%}
+{%- set end_user_token = '<|user_end|>' -%}
+{%- set assistant_token = '<|assistant_start|>' -%}
+{%- set end_assistant_token = '<|assistant_end|>' -%}
+{%- set inner_token = '<|inner_prefix|>' -%}
+{%- set outer_token = '<|inner_suffix|>' -%}
+{%- set tool_calls_token = '<|tools_prefix|>' -%}
+{%- set end_tool_calls_token = '<|tools_suffix|>' -%}
+{%- set tool_output_start_token = '<|tool_output_start|>' -%}
+{%- set tool_output_end_token = '<|tool_output_end|>' -%}
+{%- set image_token = '<|image|>' -%}
+{%- set audio_token = '<|audio|>' -%}
+
+{%- set ns = namespace(in_assistant=false, in_tool=false, in_inner=false, waiting_for_tool_outputs=false, assistant_format=none) -%}
+
+{%- if messages and messages[0].role == 'system' -%}
+    {%- if "content" in messages[0] -%}
+        {%- if messages[0].content is string -%}
+            {{ system_token + messages[0].content + end_system_token }}
+        {%- elif messages[0].content is mapping and "text" in messages[0].content -%}
+            {{ system_token + messages[0].content.text + end_system_token }}
+        {%- else -%}
+            {{- raise_exception("Invalid system message") -}}
+        {%- endif -%}
+    {%- else -%}
+        {{- raise_exception("Invalid system message") -}}
+    {%- endif -%}
+    {%- set loop_messages = messages[1:] -%}
+{%- else -%}
+    {{ system_token + 'You are Apertus 1.5 Omni, a multimodal assistant developed by the Swiss AI Initiative. Extended from Apertus 1 via continued pretraining, you understand images and audio and respond in text.' + end_system_token }}
+    {%- set loop_messages = messages -%}
+{%- endif -%}
+
+{{ developer_token + 'Deliberation: ' }}
+{%- if enable_thinking is defined and enable_thinking -%}
+    {{ 'enabled\n' }}
+{%- else -%}
+    {{ 'disabled\n' }}
+{%- endif -%}
+{%- if tools is defined and tools -%}
+    {{ 'Tool Capabilities:\n' + render_tools(tools) }}
+{%- else -%}
+    {{ 'Tool Capabilities: disabled' }}
+{%- endif -%}
+{{ end_developer_token }}
+
+{%- for message in loop_messages -%}
+    {%- if message.role == 'user' -%}
+        {%- set ns.in_inner = false -%}
+        {%- if ns.in_tool -%}
+            {{ tool_output_end_token }}
+            {%- set ns.in_tool = false -%}
+        {%- endif -%}
+        {%- if ns.in_assistant -%}
+            {{ end_assistant_token }}
+            {%- set ns.in_assistant = false -%}
+        {%- endif -%}
+        {%- if "content" in message -%}
+            {{ user_token }}
+            {%- if message.content is string -%}
+                {{ message.content }}
+            {%- elif message.content is mapping and "parts" in message.content -%}
+                {%- set parts = message.content.parts -%}
+                {%- for part in parts -%}
+                    {%- if part.type == "text" -%}
+                        {{ part.text }}
+                    {%- elif part.type == "image" or part.type == "image_url" or part.type == "input_image" -%}
+                        {{ image_token }}
+                    {%- elif part.type == "audio" or part.type == "audio_url" or part.type == "input_audio" -%}
+                        {{ audio_token }}
+                    {%- else -%}
+                        {{- raise_exception("Invalid user part: " + part.type) -}}
+                    {%- endif -%}
+                {%- endfor -%}
+            {%- elif message.content is not string and message.content is not mapping and message.content is iterable -%}
+                {%- for part in message.content -%}
+                    {%- if part.type == "text" -%}
+                        {{ part.text }}
+                    {%- elif part.type == "image" or part.type == "image_url" or part.type == "input_image" -%}
+                        {{ image_token }}
+                    {%- elif part.type == "audio" or part.type == "audio_url" or part.type == "input_audio" -%}
+                        {{ audio_token }}
+                    {%- else -%}
+                        {{- raise_exception("Invalid user part: " + part.type) -}}
+                    {%- endif -%}
+                {%- endfor -%}
+            {%- else -%}
+                {{- raise_exception("Invalid user message: " + message.role) -}}
+            {%- endif -%}
+            {{ end_user_token }}
+        {%- endif -%}
+    {%- elif message.role == 'assistant' -%}
+        {%- if not ns.in_assistant -%}
+            {{ assistant_token }}
+            {%- set ns.in_assistant = true -%}
+        {%- endif -%}
+        {%- if "content" in message -%}
+            {%- if message.content is string and (ns.assistant_format is none or ns.assistant_format == "string") -%}
+                {%- if ns.in_tool -%}
+                    {{ tool_output_end_token }}
+                    {%- set ns.in_tool = false -%}
+                {%- endif -%}
+                {%- set ns.assistant_format = "string" -%}
+                {{ message.content }}
+            {%- elif message.content is mapping and "blocks" in message.content and (ns.assistant_format is none or ns.assistant_format == "mapping") -%}
+                {%- set ns.assistant_format = "mapping" -%}
+                {%- set blocks = message.content.blocks -%}
+                {%- for block in blocks -%}
+                    {%- if block.type == 'thoughts' -%}
+                        {%- if ns.in_tool -%}
+                            {{ tool_output_end_token }}
+                            {%- set ns.in_tool = false -%}
+                        {%- endif -%}
+                        {%- if not ns.in_inner -%}
+                            {%- set ns.in_inner = true -%}
+                            {{ inner_token }}
+                        {%- endif -%}
+                        {{ block.text }}
+                    {%- elif block.type == 'tool_calls' -%}
+                        {%- if ns.in_tool -%}
+                            {{ tool_output_end_token }}
+                            {%- set ns.in_tool = false -%}
+                        {%- endif -%}
+                        {%- if ns.in_inner and not loop.first and block.calls|length == 1 and block.calls[0].name == 'display_answers' -%}
+                            {%- set ns.in_inner = false -%}
+                            {{ outer_token }}
+                        {%- endif -%}
+                        {{ tool_calls_token + '[' }}
+                        {%- for tool_call in block.calls -%}
+                            {%- if tool_call.function %}
+                                {%- set tool_call = tool_call.function %}
+                            {%- endif %}
+                            {{- '{"' + tool_call.name + '": ' + (tool_call.arguments if tool_call.arguments is string else tool_call.arguments | tojson) + '}' }}
+                            {%- if not loop.last -%}
+                                {{- ", " }}
+                            {%- endif -%}
+                        {%- endfor -%}
+                        {{ ']' + end_tool_calls_token }}
+                        {%- set ns.waiting_for_tool_outputs = true -%}
+                    {%- elif block.type == 'tool_outputs' -%}
+                        {%- if ns.in_tool -%}
+                            {{- raise_exception("Cannot have both tool outputs as separate messages and tool outputs as blocks") -}}
+                        {%- endif -%}
+                        {{ tool_output_start_token }}
+                        {%- for tool_output in block.outputs -%}
+                            {{- tool_output.output }}
+                            {%- if not loop.last -%}
+                                {{- ", " }}
+                            {%- endif -%}
+                        {%- endfor -%}
+                        {{- tool_output_end_token }}
+                        {%- set ns.waiting_for_tool_outputs = false -%}
+                    {%- elif block.type == 'response' -%}
+                        {%- if ns.in_tool -%}
+                            {{ tool_output_end_token }}
+                            {%- set ns.in_tool = false -%}
+                        {%- endif -%}
+                        {%- if (not loop.first and ns.in_inner) or (ns.in_assistant and ns.in_inner) -%}
+                            {%- set ns.in_inner = false -%}
+                            {{ outer_token }}
+                        {%- endif -%}
+                        {{ block.text }}
+                    {%- else -%}
+                        {{- raise_exception("Invalid assistant block type: " + block.type) -}}
+                    {%- endif -%}
+                {%- endfor -%}
+            {%- else -%}
+                {{- raise_exception("Invalid assistant content") -}}
+            {%- endif -%}
+        {%- else -%}
+            {{- raise_exception("Invalid assistant message") -}}
+        {%- endif -%}
+        {%- if "tool_calls" in message and message.tool_calls -%}
+            {{ tool_calls_token + '[' }}
+            {%- for tool_call in message.tool_calls -%}
+                {%- if tool_call.type is defined and tool_call.type != 'function' -%}
+                    {{- raise_exception("Invalid tool call type: " + tool_call.type) -}}
+                {%- endif -%}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {%- if tool_call.name and tool_call.arguments -%}
+                    {{- '{"' + tool_call.name + '": ' + (tool_call.arguments if tool_call.arguments is string else tool_call.arguments | tojson) + '}' }}
+                    {%- if not loop.last -%}
+                        {{- ", " }}
+                    {%- endif -%}
+                {%- else -%}
+                    {{- raise_exception("Invalid tool call") -}}
+                {%- endif -%}
+            {%- endfor -%}
+            {{ ']' + end_tool_calls_token }}
+            {%- set ns.waiting_for_tool_outputs = true -%}
+        {%- endif -%}
+    {%- elif message.role == 'tool' -%}
+        {%- if not ns.in_assistant -%}
+            {{- raise_exception("Tool message outside of assistant") -}}
+        {%- endif -%}
+        {%- if not ns.in_tool -%}
+            {{ tool_output_start_token }}
+            {%- set ns.in_tool = true -%}
+        {%- else -%}
+            {{ ", "}}
+        {%- endif -%}
+        {{ message.content }}
+        {%- set ns.waiting_for_tool_outputs = false -%}
+    {%- else -%}
+        {{- raise_exception("Invalid message role") -}}
+    {%- endif -%}
+{%- endfor -%}
+{%- if ns.in_tool -%}
+    {{ tool_output_end_token }}
+{%- endif -%}
+{%- if ns.in_assistant and not (continue_assistant_message is defined and continue_assistant_message) and not ns.waiting_for_tool_outputs -%}
+    {{ end_assistant_token }}
+{%- endif -%}
+{%- if add_generation_prompt -%}
+    {{ assistant_token }}
+{%- endif -%}

config.json

@@ -0,0 +1,47 @@
+{
+    "architectures": [
+        "ApertusForCausalLM"
+    ],
+    "attention_bias": false,
+    "bos_token_id": 1,
+    "dtype": "bfloat16",
+    "eos_token_id": [
+        2,
+        68,
+        72
+    ],
+    "hidden_act": "xielu",
+    "hidden_size": 4096,
+    "intermediate_size": 21504,
+    "max_position_embeddings": 262144,
+    "mlp_bias": false,
+    "model_type": "apertus",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 32,
+    "num_key_value_heads": 8,
+    "pad_token_id": 3,
+    "post_norm": false,
+    "qk_norm": true,
+    "quantization": {
+        "group_size": 64,
+        "bits": 8,
+        "mode": "affine"
+    },
+    "quantization_config": {
+        "group_size": 64,
+        "bits": 8,
+        "mode": "affine"
+    },
+    "rms_norm_eps": 1e-05,
+    "rope_scaling": {
+        "factor": 32.0,
+        "high_freq_factor": 4.0,
+        "low_freq_factor": 1.0,
+        "original_max_position_embeddings": 8192,
+        "rope_theta": 4000000,
+        "rope_type": "llama3"
+    },
+    "rope_theta": 4000000,
+    "tie_word_embeddings": false,
+    "vocab_size": 131072
+}

generation_config.json

@@ -0,0 +1,11 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": [
+    2,
+    68,
+    72
+  ],
+  "pad_token_id": 3,
+  "transformers_version": "5.3.0"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4918e26c83a24a73d97370a04f717bcae546a78c1da35d2362a9e8347dc2fb8
+size 5343680334

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b12da8d063a53c29c1aa0dec7dcf2b5a504b22ec9cc301a083480dd423c3d180
+size 3213343088

model.safetensors.index.json

@@ -0,0 +1,847 @@
+{
+    "metadata": {
+        "total_size": 8556929280,
+        "total_parameters": 8053338240
+    },
+    "weight_map": {
+        "lm_head.biases": "model-00002-of-00002.safetensors",
+        "lm_head.scales": "model-00002-of-00002.safetensors",
+        "lm_head.weight": "model-00002-of-00002.safetensors",
+        "model.embed_tokens.biases": "model-00001-of-00002.safetensors",
+        "model.embed_tokens.scales": "model-00001-of-00002.safetensors",
+        "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.mlp.act_fn.alpha_n": "model-00001-of-00002.safetensors",
+        "model.layers.0.mlp.act_fn.alpha_p": "model-00001-of-00002.safetensors",
+        "model.layers.0.mlp.act_fn.beta": "model-00001-of-00002.safetensors",
+        "model.layers.0.mlp.act_fn.eps": "model-00001-of-00002.safetensors",
+        "model.layers.0.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.0.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.0.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.mlp.act_fn.alpha_n": "model-00001-of-00002.safetensors",
+        "model.layers.1.mlp.act_fn.alpha_p": "model-00001-of-00002.safetensors",
+        "model.layers.1.mlp.act_fn.beta": "model-00001-of-00002.safetensors",
+        "model.layers.1.mlp.act_fn.eps": "model-00001-of-00002.safetensors",
+        "model.layers.1.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.1.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.1.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.mlp.act_fn.alpha_n": "model-00001-of-00002.safetensors",
+        "model.layers.10.mlp.act_fn.alpha_p": "model-00001-of-00002.safetensors",
+        "model.layers.10.mlp.act_fn.beta": "model-00001-of-00002.safetensors",
+        "model.layers.10.mlp.act_fn.eps": "model-00001-of-00002.safetensors",
+        "model.layers.10.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.10.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.10.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.mlp.act_fn.alpha_n": "model-00001-of-00002.safetensors",
+        "model.layers.11.mlp.act_fn.alpha_p": "model-00001-of-00002.safetensors",
+        "model.layers.11.mlp.act_fn.beta": "model-00001-of-00002.safetensors",
+        "model.layers.11.mlp.act_fn.eps": "model-00001-of-00002.safetensors",
+        "model.layers.11.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.11.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.11.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.mlp.act_fn.alpha_n": "model-00001-of-00002.safetensors",
+        "model.layers.12.mlp.act_fn.alpha_p": "model-00001-of-00002.safetensors",
+        "model.layers.12.mlp.act_fn.beta": "model-00001-of-00002.safetensors",
+        "model.layers.12.mlp.act_fn.eps": "model-00001-of-00002.safetensors",
+        "model.layers.12.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.12.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.12.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.mlp.act_fn.alpha_n": "model-00001-of-00002.safetensors",
+        "model.layers.13.mlp.act_fn.alpha_p": "model-00001-of-00002.safetensors",
+        "model.layers.13.mlp.act_fn.beta": "model-00001-of-00002.safetensors",
+        "model.layers.13.mlp.act_fn.eps": "model-00001-of-00002.safetensors",
+        "model.layers.13.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.13.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.13.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.mlp.act_fn.alpha_n": "model-00001-of-00002.safetensors",
+        "model.layers.14.mlp.act_fn.alpha_p": "model-00001-of-00002.safetensors",
+        "model.layers.14.mlp.act_fn.beta": "model-00001-of-00002.safetensors",
+        "model.layers.14.mlp.act_fn.eps": "model-00001-of-00002.safetensors",
+        "model.layers.14.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.14.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.14.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.mlp.act_fn.alpha_n": "model-00001-of-00002.safetensors",
+        "model.layers.15.mlp.act_fn.alpha_p": "model-00001-of-00002.safetensors",
+        "model.layers.15.mlp.act_fn.beta": "model-00001-of-00002.safetensors",
+        "model.layers.15.mlp.act_fn.eps": "model-00001-of-00002.safetensors",
+        "model.layers.15.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.15.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.15.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.mlp.act_fn.alpha_n": "model-00001-of-00002.safetensors",
+        "model.layers.16.mlp.act_fn.alpha_p": "model-00001-of-00002.safetensors",
+        "model.layers.16.mlp.act_fn.beta": "model-00001-of-00002.safetensors",
+        "model.layers.16.mlp.act_fn.eps": "model-00001-of-00002.safetensors",
+        "model.layers.16.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.16.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.16.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.17.attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.17.feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.17.mlp.act_fn.alpha_n": "model-00001-of-00002.safetensors",
+        "model.layers.17.mlp.act_fn.alpha_p": "model-00001-of-00002.safetensors",
+        "model.layers.17.mlp.act_fn.beta": "model-00001-of-00002.safetensors",
+        "model.layers.17.mlp.act_fn.eps": "model-00001-of-00002.safetensors",
+        "model.layers.17.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.17.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.17.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.17.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.18.attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.18.feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.18.mlp.act_fn.alpha_n": "model-00001-of-00002.safetensors",
+        "model.layers.18.mlp.act_fn.alpha_p": "model-00001-of-00002.safetensors",
+        "model.layers.18.mlp.act_fn.beta": "model-00001-of-00002.safetensors",
+        "model.layers.18.mlp.act_fn.eps": "model-00001-of-00002.safetensors",
+        "model.layers.18.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.18.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.18.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.18.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.19.attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.19.feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.19.mlp.act_fn.alpha_n": "model-00001-of-00002.safetensors",
+        "model.layers.19.mlp.act_fn.alpha_p": "model-00001-of-00002.safetensors",
+        "model.layers.19.mlp.act_fn.beta": "model-00001-of-00002.safetensors",
+        "model.layers.19.mlp.act_fn.eps": "model-00001-of-00002.safetensors",
+        "model.layers.19.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.19.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.19.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.19.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.mlp.act_fn.alpha_n": "model-00001-of-00002.safetensors",
+        "model.layers.2.mlp.act_fn.alpha_p": "model-00001-of-00002.safetensors",
+        "model.layers.2.mlp.act_fn.beta": "model-00001-of-00002.safetensors",
+        "model.layers.2.mlp.act_fn.eps": "model-00001-of-00002.safetensors",
+        "model.layers.2.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.2.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.2.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.20.attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.20.feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.20.mlp.act_fn.alpha_n": "model-00002-of-00002.safetensors",
+        "model.layers.20.mlp.act_fn.alpha_p": "model-00002-of-00002.safetensors",
+        "model.layers.20.mlp.act_fn.beta": "model-00002-of-00002.safetensors",
+        "model.layers.20.mlp.act_fn.eps": "model-00002-of-00002.safetensors",
+        "model.layers.20.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.20.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.20.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.20.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.21.attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.21.feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.21.mlp.act_fn.alpha_n": "model-00002-of-00002.safetensors",
+        "model.layers.21.mlp.act_fn.alpha_p": "model-00002-of-00002.safetensors",
+        "model.layers.21.mlp.act_fn.beta": "model-00002-of-00002.safetensors",
+        "model.layers.21.mlp.act_fn.eps": "model-00002-of-00002.safetensors",
+        "model.layers.21.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.21.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.21.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.21.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.21.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.21.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.21.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.21.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.21.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.21.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.21.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.21.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.22.attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.22.feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.22.mlp.act_fn.alpha_n": "model-00002-of-00002.safetensors",
+        "model.layers.22.mlp.act_fn.alpha_p": "model-00002-of-00002.safetensors",
+        "model.layers.22.mlp.act_fn.beta": "model-00002-of-00002.safetensors",
+        "model.layers.22.mlp.act_fn.eps": "model-00002-of-00002.safetensors",
+        "model.layers.22.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.22.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.22.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.22.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.22.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.22.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.22.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.22.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.22.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.22.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.22.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.22.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.23.attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.23.feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.23.mlp.act_fn.alpha_n": "model-00002-of-00002.safetensors",
+        "model.layers.23.mlp.act_fn.alpha_p": "model-00002-of-00002.safetensors",
+        "model.layers.23.mlp.act_fn.beta": "model-00002-of-00002.safetensors",
+        "model.layers.23.mlp.act_fn.eps": "model-00002-of-00002.safetensors",
+        "model.layers.23.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.23.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.23.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.23.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.23.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.23.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.23.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.23.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.23.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.23.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.23.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.23.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.24.attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.24.feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.24.mlp.act_fn.alpha_n": "model-00002-of-00002.safetensors",
+        "model.layers.24.mlp.act_fn.alpha_p": "model-00002-of-00002.safetensors",
+        "model.layers.24.mlp.act_fn.beta": "model-00002-of-00002.safetensors",
+        "model.layers.24.mlp.act_fn.eps": "model-00002-of-00002.safetensors",
+        "model.layers.24.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.24.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.24.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.24.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.24.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.24.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.24.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.24.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.24.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.24.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.24.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.24.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.25.attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.25.feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.25.mlp.act_fn.alpha_n": "model-00002-of-00002.safetensors",
+        "model.layers.25.mlp.act_fn.alpha_p": "model-00002-of-00002.safetensors",
+        "model.layers.25.mlp.act_fn.beta": "model-00002-of-00002.safetensors",
+        "model.layers.25.mlp.act_fn.eps": "model-00002-of-00002.safetensors",
+        "model.layers.25.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.25.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.25.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.25.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.25.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.25.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.25.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.25.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.25.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.25.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.25.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.25.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.26.attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.26.feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.26.mlp.act_fn.alpha_n": "model-00002-of-00002.safetensors",
+        "model.layers.26.mlp.act_fn.alpha_p": "model-00002-of-00002.safetensors",
+        "model.layers.26.mlp.act_fn.beta": "model-00002-of-00002.safetensors",
+        "model.layers.26.mlp.act_fn.eps": "model-00002-of-00002.safetensors",
+        "model.layers.26.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.26.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.26.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.26.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.26.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.26.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.26.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.26.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.26.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.26.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.26.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.26.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.27.attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.27.feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.27.mlp.act_fn.alpha_n": "model-00002-of-00002.safetensors",
+        "model.layers.27.mlp.act_fn.alpha_p": "model-00002-of-00002.safetensors",
+        "model.layers.27.mlp.act_fn.beta": "model-00002-of-00002.safetensors",
+        "model.layers.27.mlp.act_fn.eps": "model-00002-of-00002.safetensors",
+        "model.layers.27.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.27.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.27.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.27.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.27.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.27.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.27.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.27.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.27.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.27.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.27.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.27.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.28.attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.28.feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.28.mlp.act_fn.alpha_n": "model-00002-of-00002.safetensors",
+        "model.layers.28.mlp.act_fn.alpha_p": "model-00002-of-00002.safetensors",
+        "model.layers.28.mlp.act_fn.beta": "model-00002-of-00002.safetensors",
+        "model.layers.28.mlp.act_fn.eps": "model-00002-of-00002.safetensors",
+        "model.layers.28.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.28.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.28.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.28.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.28.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.28.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.28.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.28.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.28.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.28.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.28.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.28.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.29.attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.29.feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.29.mlp.act_fn.alpha_n": "model-00002-of-00002.safetensors",
+        "model.layers.29.mlp.act_fn.alpha_p": "model-00002-of-00002.safetensors",
+        "model.layers.29.mlp.act_fn.beta": "model-00002-of-00002.safetensors",
+        "model.layers.29.mlp.act_fn.eps": "model-00002-of-00002.safetensors",
+        "model.layers.29.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.29.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.29.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.29.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.29.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.29.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.29.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.29.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.29.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.29.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.29.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.29.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.3.attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.mlp.act_fn.alpha_n": "model-00001-of-00002.safetensors",
+        "model.layers.3.mlp.act_fn.alpha_p": "model-00001-of-00002.safetensors",
+        "model.layers.3.mlp.act_fn.beta": "model-00001-of-00002.safetensors",
+        "model.layers.3.mlp.act_fn.eps": "model-00001-of-00002.safetensors",
+        "model.layers.3.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.3.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.3.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.30.attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.30.feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.30.mlp.act_fn.alpha_n": "model-00002-of-00002.safetensors",
+        "model.layers.30.mlp.act_fn.alpha_p": "model-00002-of-00002.safetensors",
+        "model.layers.30.mlp.act_fn.beta": "model-00002-of-00002.safetensors",
+        "model.layers.30.mlp.act_fn.eps": "model-00002-of-00002.safetensors",
+        "model.layers.30.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.30.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.30.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.30.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.30.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.30.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.30.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.30.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.30.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.30.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.30.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.30.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.31.attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.31.feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.31.mlp.act_fn.alpha_n": "model-00002-of-00002.safetensors",
+        "model.layers.31.mlp.act_fn.alpha_p": "model-00002-of-00002.safetensors",
+        "model.layers.31.mlp.act_fn.beta": "model-00002-of-00002.safetensors",
+        "model.layers.31.mlp.act_fn.eps": "model-00002-of-00002.safetensors",
+        "model.layers.31.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.31.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.31.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.31.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.31.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.31.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.31.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.31.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.31.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.31.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.31.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
+        "model.layers.31.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.4.attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.mlp.act_fn.alpha_n": "model-00001-of-00002.safetensors",
+        "model.layers.4.mlp.act_fn.alpha_p": "model-00001-of-00002.safetensors",
+        "model.layers.4.mlp.act_fn.beta": "model-00001-of-00002.safetensors",
+        "model.layers.4.mlp.act_fn.eps": "model-00001-of-00002.safetensors",
+        "model.layers.4.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.4.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.4.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.mlp.act_fn.alpha_n": "model-00001-of-00002.safetensors",
+        "model.layers.5.mlp.act_fn.alpha_p": "model-00001-of-00002.safetensors",
+        "model.layers.5.mlp.act_fn.beta": "model-00001-of-00002.safetensors",
+        "model.layers.5.mlp.act_fn.eps": "model-00001-of-00002.safetensors",
+        "model.layers.5.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.5.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.5.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.mlp.act_fn.alpha_n": "model-00001-of-00002.safetensors",
+        "model.layers.6.mlp.act_fn.alpha_p": "model-00001-of-00002.safetensors",
+        "model.layers.6.mlp.act_fn.beta": "model-00001-of-00002.safetensors",
+        "model.layers.6.mlp.act_fn.eps": "model-00001-of-00002.safetensors",
+        "model.layers.6.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.6.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.6.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.mlp.act_fn.alpha_n": "model-00001-of-00002.safetensors",
+        "model.layers.7.mlp.act_fn.alpha_p": "model-00001-of-00002.safetensors",
+        "model.layers.7.mlp.act_fn.beta": "model-00001-of-00002.safetensors",
+        "model.layers.7.mlp.act_fn.eps": "model-00001-of-00002.safetensors",
+        "model.layers.7.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.7.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.7.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.mlp.act_fn.alpha_n": "model-00001-of-00002.safetensors",
+        "model.layers.8.mlp.act_fn.alpha_p": "model-00001-of-00002.safetensors",
+        "model.layers.8.mlp.act_fn.beta": "model-00001-of-00002.safetensors",
+        "model.layers.8.mlp.act_fn.eps": "model-00001-of-00002.safetensors",
+        "model.layers.8.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.8.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.8.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.mlp.act_fn.alpha_n": "model-00001-of-00002.safetensors",
+        "model.layers.9.mlp.act_fn.alpha_p": "model-00001-of-00002.safetensors",
+        "model.layers.9.mlp.act_fn.beta": "model-00001-of-00002.safetensors",
+        "model.layers.9.mlp.act_fn.eps": "model-00001-of-00002.safetensors",
+        "model.layers.9.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.9.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.9.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.norm.weight": "model-00002-of-00002.safetensors"
+    }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f2f6198ea5789e5a90ec7c5ec5cf0d5242cf5b8de007105537c91d777581582
+size 44028400

tokenizer_config.json

@@ -0,0 +1,89 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_count": 135368,
+  "audio_begin_token": [
+    131080
+  ],
+  "audio_end_token": [
+    131081
+  ],
+  "audio_token": "<|audio|>",
+  "audio_tokenizer": {
+    "codebook_size": 4096,
+    "type": "wavtokenizer"
+  },
+  "backend": "tokenizers",
+  "base_vocab_size": 131072,
+  "boa_token": "<|audio_start|>",
+  "boi_token": "<|img_start|>",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eoa_token": "<|audio_end|>",
+  "eoi_token": "<|img_end|>",
+  "eol_token": "<|img_end_of_row|>",
+  "eos_token": "</s>",
+  "image_token": "<|image|>",
+  "image_wrapper_token": "<|img_token_start|>",
+  "is_local": true,
+  "local_files_only": true,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 1000000000000000019884624838656,
+  "model_specific_special_tokens": {
+    "audio_token": "<|audio|>",
+    "boa_token": "<|audio_start|>",
+    "boi_token": "<|img_start|>",
+    "eoa_token": "<|audio_end|>",
+    "eoi_token": "<|img_end|>",
+    "eol_token": "<|img_end_of_row|>",
+    "image_token": "<|image|>",
+    "image_wrapper_token": "<|img_token_start|>"
+  },
+  "omnimodal_config": {
+    "modalities": [
+      {
+        "end_token": 131074,
+        "name": "vision",
+        "offset": 131272,
+        "start_token": 131073,
+        "vocab_size": 131072
+      },
+      {
+        "end_token": 131081,
+        "name": "audio",
+        "offset": 262344,
+        "start_token": 131080,
+        "vocab_size": 4096
+      }
+    ],
+    "omni_special_token_offset": 131072
+  },
+  "pad_token": "<pad>",
+  "padding_side": "left",
+  "processor_class": "Apertus1p5Processor",
+  "sft_assistant_begin_sequence": [
+    67
+  ],
+  "sft_eot_token": [
+    68
+  ],
+  "sft_user_begin_sequence": [
+    65
+  ],
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<unk>",
+  "vision_begin_token": [
+    131073
+  ],
+  "vision_end_token": [
+    131074
+  ],
+  "vision_tokenizer": {
+    "codebook_size": 131072,
+    "path": "/capstor/store/cscs/swissai/infra01/MLLM/tokenizer/Emu3.5-VisionTokenizer",
+    "type": "Emu3.5"
+  },
+  "vocab_size": 131072
+}