Add files using upload-large-folder tool

.gitattributes

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

README.md

@@ -0,0 +1,61 @@
+---
+license: apache-2.0
+base_model: swiss-ai/Apertus-8B-Instruct-2509
+pipeline_tag: text-generation
+library_name: mlx
+tags:
+- multilingual
+- compliant
+- swiss-ai
+- apertus
+- mlx
+extra_gated_prompt: "### Apertus LLM Acceptable Use Policy  \n(1.0 | September 1,\
+  \ 2025)\n\"Agreement\" The Swiss National AI Institute (SNAI) is a partnership between\
+  \ the two Swiss Federal Institutes of Technology, ETH Zurich and EPFL. \n\nBy using\
+  \ the Apertus LLM you agree to indemnify, defend, and hold harmless ETH Zurich and\
+  \ EPFL against any third-party claims arising from your use of Apertus LLM. \n\n\
+  The training data and the Apertus LLM may contain or generate information that directly\
+  \ or indirectly refers to an identifiable individual (Personal Data). You process\
+  \ Personal Data as independent controller in accordance with applicable data protection\
+  \ law. SNAI will regularly provide a file with hash values for download which you\
+  \ can apply as an output filter to your use of our Apertus LLM. The file reflects\
+  \ data protection deletion requests which have been addressed to SNAI as the developer\
+  \ of the Apertus LLM. It allows you to remove Personal Data contained in the model\
+  \ output. We strongly advise downloading and applying this output filter from SNAI\
+  \ every six months following the release of the model.  "
+extra_gated_fields:
+  Your Name: text
+  Country: country
+  Affiliation: text
+  geo: ip_location
+  By clicking Submit below I accept the terms of use: checkbox
+extra_gated_button_content: Submit
+---
+
+# mlx-community/Apertus-8B-Instruct-2509-8bit
+
+This model [mlx-community/Apertus-8B-Instruct-2509-8bit](https://huggingface.co/mlx-community/Apertus-8B-Instruct-2509-8bit) was
+converted to MLX format from [swiss-ai/Apertus-8B-Instruct-2509](https://huggingface.co/swiss-ai/Apertus-8B-Instruct-2509)
+using mlx-lm version **0.27.0**.
+
+## Use with mlx
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("mlx-community/Apertus-8B-Instruct-2509-8bit")
+
+prompt = "hello"
+
+if tokenizer.chat_template is not None:
+    messages = [{"role": "user", "content": prompt}]
+    prompt = tokenizer.apply_chat_template(
+        messages, add_generation_prompt=True
+    )
+
+response = generate(model, tokenizer, prompt=prompt, verbose=True)
+```

chat_template.jinja

@@ -0,0 +1,327 @@
+{%- 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 %}
+        {{- "// " + 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 ns = namespace(in_assistant=false, in_tool=false, in_inner=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, a helpful assistant created by the SwissAI initiative.\nKnowledge cutoff: 2024-04\nCurrent date: ' + strftime_now('%Y-%m-%d') + 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 -%}
+            {{ ']' }}
+            {%- 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 }}
+                    {%- 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 -%}
+                    {{ ']' }}
+                    {%- 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 -%}
+                            {{ ']' }}
+                            {%- 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 -%}
+                            {{ ']' }}
+                            {%- 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 -%}
+                            {{- '{"' + tool_call.name + '": ' + tool_call.arguments + '}' }}
+                            {%- if not loop.last -%}
+                                {{- ", " }}
+                            {%- endif -%}
+                        {%- endfor -%}
+                        {{ ']' + end_tool_calls_token }}
+                    {%- 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 -%}
+                        {{ '[' }}
+                        {%- for tool_output in block.outputs -%}
+                            {{- tool_output.output }}
+                            {%- if not loop.last -%}
+                                {{- ", " }}
+                            {%- endif -%}
+                        {%- endfor -%}
+                        {{- ']' }}
+                    {%- elif block.type == 'response' -%}
+                        {%- if ns.in_tool -%}
+                            {{ ']' }}
+                            {%- 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 == 'function' -%}
+                    {%- set function = tool_call.function -%}
+                    {{- '{"' + function.name + '": ' + function.arguments + '}' }}
+                    {%- if not loop.last -%}
+                        {{- ", " }}
+                    {%- endif -%}
+                {%- else -%}
+                    {{- raise_exception("Invalid tool call type: " + tool_call.type) -}}
+                {%- endif -%}
+            {%- endfor -%}
+            {{ ']' + end_tool_calls_token }}
+        {%- endif -%}
+    {%- elif message.role == 'tool' -%}
+        {%- if not ns.in_assistant -%}
+            {{- raise_exception("Tool message outside of assistant") -}}
+        {%- endif -%}
+        {%- if not ns.in_tool -%}
+            {{ '[' }}
+            {%- set ns.in_tool = true -%}
+        {%- else -%}
+            {{ ", "}}
+        {%- endif -%}
+        {{ message.content }}
+    {%- else -%}
+        {{- raise_exception("Invalid message role") -}}
+    {%- endif -%}
+{%- endfor -%}
+{%- if ns.in_tool -%}
+    {{ ']' }}
+{%- endif -%}
+{%- if add_generation_prompt -%}
+    {{ assistant_token }}
+{%- endif -%}

config.json

@@ -0,0 +1,38 @@
+{
+    "architectures": [
+        "ApertusForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 1,
+    "dtype": "bfloat16",
+    "eos_token_id": 68,
+    "hidden_act": "xielu",
+    "hidden_dropout": 0.0,
+    "hidden_size": 4096,
+    "initializer_range": 0.02,
+    "intermediate_size": 21504,
+    "max_position_embeddings": 65536,
+    "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,
+    "rms_norm_eps": 1e-05,
+    "rope_scaling": {
+        "factor": 8.0,
+        "high_freq_factor": 4.0,
+        "low_freq_factor": 1.0,
+        "original_max_position_embeddings": 8192,
+        "rope_type": "llama3",
+        "type": "llama3"
+    },
+    "rope_theta": 12000000,
+    "tie_word_embeddings": false,
+    "transformers_version": "4.56.0.dev0",
+    "use_cache": false,
+    "vocab_size": 131072
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": [2, 68, 72],
+  "transformers_version": "4.54.0.dev0"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36fcf8ce7cfbfcfca9273035d9040edffee7f9e1622d29eece61c9fe0ad8ac51
+size 5259824750

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bc8ac5913fe0e9b04eed8ece00be709c688d742671a18fd521572bcc9a4df2e
+size 5234713015

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a796d03b186166f652d38533819cd14518ac6cc45120a811786ffe998ede8d4c
+size 4538447086

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fe8663058b35beed5c4408547e2929861d40586e2029c3a6a43aaa75fb5fd48
+size 1073741951

model.safetensors.index.json

@@ -0,0 +1,459 @@
+{
+    "metadata": {
+        "total_size": 16106676480,
+        "total_parameters": 8053338240
+    },
+    "weight_map": {
+        "lm_head.weight": "model-00004-of-00004.safetensors",
+        "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+        "model.layers.0.attention_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.0.feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.0.mlp.act_fn.alpha_n": "model-00001-of-00004.safetensors",
+        "model.layers.0.mlp.act_fn.alpha_p": "model-00001-of-00004.safetensors",
+        "model.layers.0.mlp.act_fn.beta": "model-00001-of-00004.safetensors",
+        "model.layers.0.mlp.act_fn.eps": "model-00001-of-00004.safetensors",
+        "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.1.attention_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.1.feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.1.mlp.act_fn.alpha_n": "model-00001-of-00004.safetensors",
+        "model.layers.1.mlp.act_fn.alpha_p": "model-00001-of-00004.safetensors",
+        "model.layers.1.mlp.act_fn.beta": "model-00001-of-00004.safetensors",
+        "model.layers.1.mlp.act_fn.eps": "model-00001-of-00004.safetensors",
+        "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.10.attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.10.feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.10.mlp.act_fn.alpha_n": "model-00002-of-00004.safetensors",
+        "model.layers.10.mlp.act_fn.alpha_p": "model-00002-of-00004.safetensors",
+        "model.layers.10.mlp.act_fn.beta": "model-00002-of-00004.safetensors",
+        "model.layers.10.mlp.act_fn.eps": "model-00002-of-00004.safetensors",
+        "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.10.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.10.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.11.attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.11.feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.11.mlp.act_fn.alpha_n": "model-00002-of-00004.safetensors",
+        "model.layers.11.mlp.act_fn.alpha_p": "model-00002-of-00004.safetensors",
+        "model.layers.11.mlp.act_fn.beta": "model-00002-of-00004.safetensors",
+        "model.layers.11.mlp.act_fn.eps": "model-00002-of-00004.safetensors",
+        "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.12.attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.12.feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.12.mlp.act_fn.alpha_n": "model-00002-of-00004.safetensors",
+        "model.layers.12.mlp.act_fn.alpha_p": "model-00002-of-00004.safetensors",
+        "model.layers.12.mlp.act_fn.beta": "model-00002-of-00004.safetensors",
+        "model.layers.12.mlp.act_fn.eps": "model-00002-of-00004.safetensors",
+        "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.12.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.12.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.13.attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.13.feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.13.mlp.act_fn.alpha_n": "model-00002-of-00004.safetensors",
+        "model.layers.13.mlp.act_fn.alpha_p": "model-00002-of-00004.safetensors",
+        "model.layers.13.mlp.act_fn.beta": "model-00002-of-00004.safetensors",
+        "model.layers.13.mlp.act_fn.eps": "model-00002-of-00004.safetensors",
+        "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.13.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.13.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.14.attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.14.feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.14.mlp.act_fn.alpha_n": "model-00002-of-00004.safetensors",
+        "model.layers.14.mlp.act_fn.alpha_p": "model-00002-of-00004.safetensors",
+        "model.layers.14.mlp.act_fn.beta": "model-00002-of-00004.safetensors",
+        "model.layers.14.mlp.act_fn.eps": "model-00002-of-00004.safetensors",
+        "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.14.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.14.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.15.attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.15.feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.15.mlp.act_fn.alpha_n": "model-00002-of-00004.safetensors",
+        "model.layers.15.mlp.act_fn.alpha_p": "model-00002-of-00004.safetensors",
+        "model.layers.15.mlp.act_fn.beta": "model-00002-of-00004.safetensors",
+        "model.layers.15.mlp.act_fn.eps": "model-00002-of-00004.safetensors",
+        "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.15.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.16.attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.16.feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.16.mlp.act_fn.alpha_n": "model-00002-of-00004.safetensors",
+        "model.layers.16.mlp.act_fn.alpha_p": "model-00002-of-00004.safetensors",
+        "model.layers.16.mlp.act_fn.beta": "model-00002-of-00004.safetensors",
+        "model.layers.16.mlp.act_fn.eps": "model-00002-of-00004.safetensors",
+        "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.16.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.16.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.17.attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.17.feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.17.mlp.act_fn.alpha_n": "model-00002-of-00004.safetensors",
+        "model.layers.17.mlp.act_fn.alpha_p": "model-00002-of-00004.safetensors",
+        "model.layers.17.mlp.act_fn.beta": "model-00002-of-00004.safetensors",
+        "model.layers.17.mlp.act_fn.eps": "model-00002-of-00004.safetensors",
+        "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.17.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.17.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.18.attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.18.feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.18.mlp.act_fn.alpha_n": "model-00002-of-00004.safetensors",
+        "model.layers.18.mlp.act_fn.alpha_p": "model-00002-of-00004.safetensors",
+        "model.layers.18.mlp.act_fn.beta": "model-00002-of-00004.safetensors",
+        "model.layers.18.mlp.act_fn.eps": "model-00002-of-00004.safetensors",
+        "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.18.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.18.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.19.attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.19.feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.19.mlp.act_fn.alpha_n": "model-00002-of-00004.safetensors",
+        "model.layers.19.mlp.act_fn.alpha_p": "model-00002-of-00004.safetensors",
+        "model.layers.19.mlp.act_fn.beta": "model-00002-of-00004.safetensors",
+        "model.layers.19.mlp.act_fn.eps": "model-00002-of-00004.safetensors",
+        "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.2.attention_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.2.feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.2.mlp.act_fn.alpha_n": "model-00001-of-00004.safetensors",
+        "model.layers.2.mlp.act_fn.alpha_p": "model-00001-of-00004.safetensors",
+        "model.layers.2.mlp.act_fn.beta": "model-00001-of-00004.safetensors",
+        "model.layers.2.mlp.act_fn.eps": "model-00001-of-00004.safetensors",
+        "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.20.attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.20.feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.20.mlp.act_fn.alpha_n": "model-00002-of-00004.safetensors",
+        "model.layers.20.mlp.act_fn.alpha_p": "model-00002-of-00004.safetensors",
+        "model.layers.20.mlp.act_fn.beta": "model-00002-of-00004.safetensors",
+        "model.layers.20.mlp.act_fn.eps": "model-00002-of-00004.safetensors",
+        "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.20.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.20.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.21.attention_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.21.feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.21.mlp.act_fn.alpha_n": "model-00003-of-00004.safetensors",
+        "model.layers.21.mlp.act_fn.alpha_p": "model-00003-of-00004.safetensors",
+        "model.layers.21.mlp.act_fn.beta": "model-00003-of-00004.safetensors",
+        "model.layers.21.mlp.act_fn.eps": "model-00003-of-00004.safetensors",
+        "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.22.attention_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.22.feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.22.mlp.act_fn.alpha_n": "model-00003-of-00004.safetensors",
+        "model.layers.22.mlp.act_fn.alpha_p": "model-00003-of-00004.safetensors",
+        "model.layers.22.mlp.act_fn.beta": "model-00003-of-00004.safetensors",
+        "model.layers.22.mlp.act_fn.eps": "model-00003-of-00004.safetensors",
+        "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.22.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.22.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.23.attention_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.23.feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.23.mlp.act_fn.alpha_n": "model-00003-of-00004.safetensors",
+        "model.layers.23.mlp.act_fn.alpha_p": "model-00003-of-00004.safetensors",
+        "model.layers.23.mlp.act_fn.beta": "model-00003-of-00004.safetensors",
+        "model.layers.23.mlp.act_fn.eps": "model-00003-of-00004.safetensors",
+        "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.24.attention_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.24.feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.24.mlp.act_fn.alpha_n": "model-00003-of-00004.safetensors",
+        "model.layers.24.mlp.act_fn.alpha_p": "model-00003-of-00004.safetensors",
+        "model.layers.24.mlp.act_fn.beta": "model-00003-of-00004.safetensors",
+        "model.layers.24.mlp.act_fn.eps": "model-00003-of-00004.safetensors",
+        "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.24.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.24.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.25.attention_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.25.feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.25.mlp.act_fn.alpha_n": "model-00003-of-00004.safetensors",
+        "model.layers.25.mlp.act_fn.alpha_p": "model-00003-of-00004.safetensors",
+        "model.layers.25.mlp.act_fn.beta": "model-00003-of-00004.safetensors",
+        "model.layers.25.mlp.act_fn.eps": "model-00003-of-00004.safetensors",
+        "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.25.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.25.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.26.attention_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.26.feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.26.mlp.act_fn.alpha_n": "model-00003-of-00004.safetensors",
+        "model.layers.26.mlp.act_fn.alpha_p": "model-00003-of-00004.safetensors",
+        "model.layers.26.mlp.act_fn.beta": "model-00003-of-00004.safetensors",
+        "model.layers.26.mlp.act_fn.eps": "model-00003-of-00004.safetensors",
+        "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.26.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.26.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.27.attention_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.27.feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.27.mlp.act_fn.alpha_n": "model-00003-of-00004.safetensors",
+        "model.layers.27.mlp.act_fn.alpha_p": "model-00003-of-00004.safetensors",
+        "model.layers.27.mlp.act_fn.beta": "model-00003-of-00004.safetensors",
+        "model.layers.27.mlp.act_fn.eps": "model-00003-of-00004.safetensors",
+        "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.27.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.27.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.28.attention_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.28.feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.28.mlp.act_fn.alpha_n": "model-00003-of-00004.safetensors",
+        "model.layers.28.mlp.act_fn.alpha_p": "model-00003-of-00004.safetensors",
+        "model.layers.28.mlp.act_fn.beta": "model-00003-of-00004.safetensors",
+        "model.layers.28.mlp.act_fn.eps": "model-00003-of-00004.safetensors",
+        "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.28.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.28.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.29.attention_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.29.feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.29.mlp.act_fn.alpha_n": "model-00003-of-00004.safetensors",
+        "model.layers.29.mlp.act_fn.alpha_p": "model-00003-of-00004.safetensors",
+        "model.layers.29.mlp.act_fn.beta": "model-00003-of-00004.safetensors",
+        "model.layers.29.mlp.act_fn.eps": "model-00003-of-00004.safetensors",
+        "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.29.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.3.attention_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.3.feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.3.mlp.act_fn.alpha_n": "model-00001-of-00004.safetensors",
+        "model.layers.3.mlp.act_fn.alpha_p": "model-00001-of-00004.safetensors",
+        "model.layers.3.mlp.act_fn.beta": "model-00001-of-00004.safetensors",
+        "model.layers.3.mlp.act_fn.eps": "model-00001-of-00004.safetensors",
+        "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.30.attention_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.30.feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.30.mlp.act_fn.alpha_n": "model-00003-of-00004.safetensors",
+        "model.layers.30.mlp.act_fn.alpha_p": "model-00003-of-00004.safetensors",
+        "model.layers.30.mlp.act_fn.beta": "model-00003-of-00004.safetensors",
+        "model.layers.30.mlp.act_fn.eps": "model-00003-of-00004.safetensors",
+        "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.30.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.31.attention_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.31.feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.31.mlp.act_fn.alpha_n": "model-00003-of-00004.safetensors",
+        "model.layers.31.mlp.act_fn.alpha_p": "model-00003-of-00004.safetensors",
+        "model.layers.31.mlp.act_fn.beta": "model-00003-of-00004.safetensors",
+        "model.layers.31.mlp.act_fn.eps": "model-00003-of-00004.safetensors",
+        "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.4.attention_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.4.feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.4.mlp.act_fn.alpha_n": "model-00001-of-00004.safetensors",
+        "model.layers.4.mlp.act_fn.alpha_p": "model-00001-of-00004.safetensors",
+        "model.layers.4.mlp.act_fn.beta": "model-00001-of-00004.safetensors",
+        "model.layers.4.mlp.act_fn.eps": "model-00001-of-00004.safetensors",
+        "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.5.attention_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.5.feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.5.mlp.act_fn.alpha_n": "model-00001-of-00004.safetensors",
+        "model.layers.5.mlp.act_fn.alpha_p": "model-00001-of-00004.safetensors",
+        "model.layers.5.mlp.act_fn.beta": "model-00001-of-00004.safetensors",
+        "model.layers.5.mlp.act_fn.eps": "model-00001-of-00004.safetensors",
+        "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.6.attention_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.6.feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.6.mlp.act_fn.alpha_n": "model-00001-of-00004.safetensors",
+        "model.layers.6.mlp.act_fn.alpha_p": "model-00001-of-00004.safetensors",
+        "model.layers.6.mlp.act_fn.beta": "model-00001-of-00004.safetensors",
+        "model.layers.6.mlp.act_fn.eps": "model-00001-of-00004.safetensors",
+        "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.7.attention_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.7.feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.7.mlp.act_fn.alpha_n": "model-00001-of-00004.safetensors",
+        "model.layers.7.mlp.act_fn.alpha_p": "model-00001-of-00004.safetensors",
+        "model.layers.7.mlp.act_fn.beta": "model-00001-of-00004.safetensors",
+        "model.layers.7.mlp.act_fn.eps": "model-00001-of-00004.safetensors",
+        "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.8.attention_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.8.feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.8.mlp.act_fn.alpha_n": "model-00001-of-00004.safetensors",
+        "model.layers.8.mlp.act_fn.alpha_p": "model-00001-of-00004.safetensors",
+        "model.layers.8.mlp.act_fn.beta": "model-00001-of-00004.safetensors",
+        "model.layers.8.mlp.act_fn.eps": "model-00001-of-00004.safetensors",
+        "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.9.attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.9.feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.9.mlp.act_fn.alpha_n": "model-00002-of-00004.safetensors",
+        "model.layers.9.mlp.act_fn.alpha_p": "model-00002-of-00004.safetensors",
+        "model.layers.9.mlp.act_fn.beta": "model-00002-of-00004.safetensors",
+        "model.layers.9.mlp.act_fn.eps": "model-00002-of-00004.safetensors",
+        "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.9.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+        "model.norm.weight": "model-00003-of-00004.safetensors"
+    }
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|assistant_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d5f2074cd9c771f2d3f35a75ea4c86886ac629fa40580128a1f66c9acb58cc0
+size 17078483