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

LICENSE

@@ -0,0 +1,51 @@
+Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+
+OpenMDW License Agreement, version 1.1 (OpenMDW-1.1)
+
+By exercising rights granted to you under this agreement, you accept and agree
+to its terms.
+
+As used in this agreement, "Model Materials" means the materials provided to
+you under this agreement, consisting of: (1) one or more machine learning
+models (including architecture and parameters); and (2) all related artifacts
+(including associated data, documentation and software) that are provided to
+you hereunder.
+
+Subject to your compliance with this agreement, permission is hereby granted,
+free of charge, to deal in the Model Materials without restriction, including
+under all copyright, patent, database, and trade secret rights included or
+embodied therein.
+
+If you distribute any portion of the Model Materials, you shall retain in your
+distribution (1) a copy of this agreement, and (2) all copyright notices and
+other notices of origin included in the Model Materials that are applicable to
+your distribution.
+
+If you file, maintain, or voluntarily participate in a lawsuit against any
+person or entity asserting that the Model Materials directly or indirectly
+infringe any patent or copyright, then all rights and grants made to you
+hereunder are terminated, unless that lawsuit was in response to a
+corresponding lawsuit first brought against you.
+
+This agreement does not impose any restrictions or obligations with respect to
+any use, modification, or sharing of any outputs generated by using the Model
+Materials.
+
+THE MODEL MATERIALS ARE PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
+OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE, TITLE, NONINFRINGEMENT, ACCURACY, OR THE
+ABSENCE OF LATENT OR OTHER DEFECTS OR ERRORS, WHETHER OR NOT DISCOVERABLE, ALL
+TO THE GREATEST EXTENT PERMISSIBLE UNDER APPLICABLE LAW.
+
+YOU ARE SOLELY RESPONSIBLE FOR (1) CLEARING RIGHTS OF OTHER PERSONS THAT MAY
+APPLY TO THE MODEL MATERIALS OR ANY USE THEREOF, INCLUDING WITHOUT LIMITATION
+ANY PERSON'S COPYRIGHTS OR OTHER RIGHTS INCLUDED OR EMBODIED IN THE MODEL
+MATERIALS; (2) OBTAINING ANY NECESSARY CONSENTS, PERMISSIONS OR OTHER RIGHTS
+REQUIRED FOR ANY USE OF THE MODEL MATERIALS; OR (3) PERFORMING ANY DUE
+DILIGENCE OR UNDERTAKING ANY OTHER INVESTIGATIONS INTO THE MODEL MATERIALS OR
+ANYTHING INCORPORATED OR EMBODIED THEREIN.
+
+IN NO EVENT SHALL THE PROVIDERS OF THE MODEL MATERIALS BE LIABLE FOR ANY CLAIM,
+DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE MODEL MATERIALS, THE
+USE THEREOF OR OTHER DEALINGS THEREIN.

README.md

@@ -0,0 +1,57 @@
+---
+library_name: mlx
+license: other
+license_name: openmdw-1.1
+license_link: https://openmdw.ai/license/1-1/
+base_model: nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16
+pipeline_tag: text-generation
+language:
+- en
+- es
+- fr
+- de
+- it
+- ja
+tags:
+- mlx
+- nvidia
+- nemotron-3.5
+- quantized
+---
+
+# NVIDIA Nemotron 3.5 Lightning 30B-A3B — MLX 4-bit
+
+This is an MLX conversion of [nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16](https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16), quantized with 4-bit affine weights and a group size of 64 using `mlx-lm 0.31.3` and `mlx 0.32.0`.
+
+The conversion was load-tested and generation-tested with MLX on Apple silicon. See the base model card for architecture, intended use, limitations, sampling guidance, and safety information.
+
+## Usage
+
+```bash
+pip install -U mlx-lm
+mlx_lm.generate \
+  --model Vontra/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-MLX-4bit \
+  --prompt "Hello"
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load(
+    "Vontra/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-MLX-4bit"
+)
+response = generate(model, tokenizer, prompt="Hello", max_tokens=256)
+print(response)
+```
+
+## Quantization
+
+- Format: MLX safetensors
+- Mode: affine
+- Bits: 4
+- Group size: 64
+- Reported average: 4.503 bits per weight
+
+## License
+
+The model is distributed under the [OpenMDW License Agreement, version 1.1](https://openmdw.ai/license/1-1/). A copy is included in this repository.

chat_template.jinja

@@ -0,0 +1,190 @@
+{% macro render_extra_keys(json_dict, handled_keys) %}
+    {%- if json_dict is mapping %}
+        {%- for json_key in json_dict if json_key not in handled_keys %}
+            {%- if json_dict[json_key] is mapping or (json_dict[json_key] is sequence and json_dict[json_key] is not string) %}
+                {{- '\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | tojson | safe) ~ '</' ~ json_key ~ '>' }}
+            {%- else %}
+                {{-'\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | string) ~ '</' ~ json_key ~ '>' }}
+            {%- endif %}
+        {%- endfor %}
+    {%- endif %}
+{% endmacro %}
+{%- set enable_thinking = enable_thinking if enable_thinking is defined else True %}
+{%- set truncate_history_thinking = truncate_history_thinking if truncate_history_thinking is defined else True %}
+{%- set ns = namespace(last_user_idx = -1) %}
+{%- set loop_messages = messages %}
+{%- for m in loop_messages %}
+  {%- if m["role"] == "user" %}
+    {%- set ns.last_user_idx = loop.index0 %}
+  {%- endif %}
+{%- endfor %}
+{%- if messages[0]["role"] == "system" %}
+    {%- set system_message = messages[0]["content"] %}
+    {%- set loop_messages = messages[1:] %}
+{%- else %}
+    {%- set system_message = "" %}
+    {%- set loop_messages = messages %}
+{%- endif %}
+{%- if not tools is defined %}
+    {%- set tools = [] %}
+{%- endif %}
+{%- set ns = namespace(last_user_idx = -1) %}
+{%- for m in loop_messages %}
+  {%- if m["role"] == "user" %}
+    {%- set ns.last_user_idx = loop.index0 %}
+  {%- endif %}
+{%- endfor %}
+{%- if system_message is defined %}
+    {{- "<|im_start|>system\n" + system_message }}
+{%- else %}
+    {%- if tools is iterable and tools | length > 0 %}
+        {{- "<|im_start|>system\n" }}
+    {%- endif %}
+{%- endif %}
+{%- if tools is iterable and tools | length > 0 %}
+    {%- if system_message is defined and system_message | length > 0 %}
+        {{- "\n\n" }}
+    {%- endif %}
+    {{- "# Tools\n\nYou have access to the following functions:\n\n" }}
+    {{- "<tools>" }}
+    {%- for tool in tools %}
+        {%- if tool.function is defined %}
+            {%- set tool = tool.function %}
+        {%- endif %}
+        {{- "\n<function>\n<name>" ~ tool.name ~ "</name>" }}
+        {%- if tool.description is defined %}
+            {{- '\n<description>' ~ (tool.description | trim) ~ '</description>' }}
+        {%- endif %}
+        {{- '\n<parameters>' }}
+        {%- if tool.parameters is defined and tool.parameters is mapping and tool.parameters.properties is defined and tool.parameters.properties is mapping %}
+            {%- for param_name, param_fields in tool.parameters.properties|items %}
+                {{- '\n<parameter>' }}
+                {{- '\n<name>' ~ param_name ~ '</name>' }}
+                {%- if param_fields.type is defined %}
+                    {{- '\n<type>' ~ (param_fields.type | string) ~ '</type>' }}
+                {%- endif %}
+                {%- if param_fields.description is defined %}
+                    {{- '\n<description>' ~ (param_fields.description | trim) ~ '</description>' }}
+                {%- endif %}
+                {%- if param_fields.enum is defined %}
+                    {{- '\n<enum>' ~ (param_fields.enum | tojson | safe) ~ '</enum>' }}
+                {%- endif %}
+                {%- set handled_keys = ['name', 'type', 'description', 'enum'] %}
+                {{- render_extra_keys(param_fields, handled_keys) }}
+                {{- '\n</parameter>' }}
+            {%- endfor %}
+        {%- endif %}
+        {% set handled_keys = ['type', 'properties', 'required'] %}
+        {{- render_extra_keys(tool.parameters, handled_keys) }}
+        {%- if tool.parameters is defined and tool.parameters.required is defined %}
+            {{- '\n<required>' ~ (tool.parameters.required | tojson | safe) ~ '</required>' }}
+        {%- endif %}
+        {{- '\n</parameters>' }}
+        {%- set handled_keys = ['type', 'name', 'description', 'parameters'] %}
+        {{- render_extra_keys(tool, handled_keys) }}
+        {{- '\n</function>' }}
+    {%- endfor %}
+    {{- "\n</tools>" }}
+    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
+{%- endif %}
+{%- if system_message is defined %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if tools is iterable and tools | length > 0 %}
+        {{- '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in loop_messages %}
+    {%- if message.role == "assistant" %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is string and message.reasoning_content | trim | length > 0 %}
+            {%- set content = "<think>\n" ~ message.reasoning_content ~ "</think>" ~ (message.content | default('', true)) %}
+        {%- else %}
+            {%- set content = message.content | default('', true) %}
+            {%- if content is string -%}
+                {%- if '<think>' not in content and '</think>' not in content -%}
+                    {%- set content = "<think></think>" ~ content -%}
+                {%- endif -%}
+            {%- else -%}
+                {%- set content = content -%}
+            {%- endif -%}
+        {%- endif %}
+        {%- if message.tool_calls is defined and message.tool_calls is iterable and message.tool_calls | length > 0 %}
+            {{- '<|im_start|>assistant\n' }}
+                {%- set include_content = not (truncate_history_thinking and loop.index0 < ns.last_user_idx) %}
+                {%- if content is string and content | trim | length > 0 %}
+                    {%- if include_content %}
+                        {{- (content | trim) ~ '\n' -}}
+                    {%- else %}
+                        {%- set c = (content | string) %}
+                        {%- if '</think>' in c %}
+                            {%- set c = c.split('</think>')[-1] %}
+                        {%- elif '<think>' in c %}
+                            {%- set c = c.split('<think>')[0] %}
+                        {%- endif %}
+                        {%- set c = "<think></think>" ~ c %}
+                        {%- if c | length > 0 %}
+                            {{- c ~ '\n' -}}
+                        {%- endif %}
+                    {%- endif %}
+                {%- else %}
+                    {{- "<think></think>" -}}
+                {%- endif %}
+                {%- for tool_call in message.tool_calls %}
+                    {%- if tool_call.function is defined %}
+                        {%- set tool_call = tool_call.function %}
+                    {%- endif %}
+                    {{- '<tool_call>\n<function=' ~ tool_call.name ~ '>\n' -}}
+                        {%- if tool_call.arguments is defined %}
+                            {%- for args_name, args_value in tool_call.arguments|items %}
+                                {{- '<parameter=' ~ args_name ~ '>\n' -}}
+                                    {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
+                                {{- args_value ~ '\n</parameter>\n' -}}
+                            {%- endfor %}
+                        {%- endif %}
+                    {{- '</function>\n</tool_call>\n' -}}
+                {%- endfor %}
+                {{- '<|im_end|>\n' }}
+        {%- else %}
+            {%- if not (truncate_history_thinking and loop.index0 < ns.last_user_idx) %}
+                {{- '<|im_start|>assistant\n' ~ (content | default('', true) | string | trim) ~ '<|im_end|>\n' }}
+            {%- else %}
+                {%- set c = (content | default('', true) | string) %}
+                {%- if '<think>' in c and '</think>' in c %}
+                    {%- set c = "<think></think>" ~ c.split('</think>')[-1] %}
+                {%- endif %}
+                {%- set c = c | trim %}
+                {%- if c | length > 0 %}
+                    {{- '<|im_start|>assistant\n' ~ c ~ '<|im_end|>\n' }}
+                {%- else %}
+                    {{- '<|im_start|>assistant\n<|im_end|>\n' }}
+                {%- endif %}
+            {%- endif %}
+        {%- endif %}
+    {%- elif message.role == "user" or message.role == "system" %}
+        {{- '<|im_start|>' + message.role + '\n' }}
+        {%- set content = message.content | string %}
+        {{- content }}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.previtem and loop.previtem.role != "tool" %}
+            {{- '<|im_start|>user\n' }}
+        {%- endif %}
+        {{- '<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>\n' }}
+        {%- if not loop.last and loop.nextitem.role != "tool" %}
+            {{- '<|im_end|>\n' }}
+        {%- elif loop.last %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- else %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {%- if enable_thinking %}
+        {{- '<|im_start|>assistant\n<think>\n' }}
+    {%- else %}
+        {{- '<|im_start|>assistant\n<think></think>' }}
+    {%- endif %}
+{%- endif %}

config.json

@@ -0,0 +1,134 @@
+{
+    "architectures": [
+        "NemotronHForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 1,
+    "chunk_size": 128,
+    "conv_kernel": 4,
+    "dtype": "bfloat16",
+    "eos_token_id": [
+        2,
+        11
+    ],
+    "expand": 2,
+    "head_dim": 128,
+    "hidden_dropout": 0.0,
+    "hidden_size": 2688,
+    "initializer_range": 0.02,
+    "intermediate_size": 1856,
+    "layer_norm_epsilon": 1e-05,
+    "layers_block_type": [
+        "mamba",
+        "moe",
+        "mamba",
+        "moe",
+        "mamba",
+        "attention",
+        "moe",
+        "mamba",
+        "moe",
+        "mamba",
+        "moe",
+        "mamba",
+        "attention",
+        "moe",
+        "mamba",
+        "moe",
+        "mamba",
+        "moe",
+        "mamba",
+        "attention",
+        "moe",
+        "mamba",
+        "moe",
+        "mamba",
+        "moe",
+        "mamba",
+        "attention",
+        "moe",
+        "mamba",
+        "moe",
+        "mamba",
+        "moe",
+        "mamba",
+        "attention",
+        "moe",
+        "mamba",
+        "moe",
+        "mamba",
+        "moe",
+        "mamba",
+        "moe",
+        "mamba",
+        "attention",
+        "moe",
+        "mamba",
+        "moe",
+        "mamba",
+        "moe",
+        "mamba",
+        "moe",
+        "mamba",
+        "moe"
+    ],
+    "mamba_head_dim": 64,
+    "mamba_hidden_act": "silu",
+    "mamba_num_heads": 64,
+    "mamba_proj_bias": false,
+    "mamba_ssm_cache_dtype": "float32",
+    "max_position_embeddings": 262144,
+    "mlp_bias": false,
+    "mlp_hidden_act": "relu2",
+    "model_type": "nemotron_h",
+    "moe_intermediate_size": 1856,
+    "moe_latent_size": null,
+    "moe_shared_expert_intermediate_size": 3712,
+    "moe_shared_expert_overlap": true,
+    "mtp_layers_block_type": [
+        "attention",
+        "moe"
+    ],
+    "n_group": 1,
+    "n_groups": 8,
+    "n_routed_experts": 128,
+    "n_shared_experts": 1,
+    "norm_eps": 1e-05,
+    "norm_topk_prob": true,
+    "num_attention_heads": 32,
+    "num_experts_per_tok": 6,
+    "num_hidden_layers": 52,
+    "num_key_value_heads": 2,
+    "num_logits_to_keep": 1,
+    "num_nextn_predict_layers": 1,
+    "pad_token_id": 0,
+    "partial_rotary_factor": 1.0,
+    "quantization": {
+        "group_size": 64,
+        "bits": 4,
+        "mode": "affine"
+    },
+    "quantization_config": {
+        "group_size": 64,
+        "bits": 4,
+        "mode": "affine"
+    },
+    "rescale_prenorm_residual": true,
+    "residual_in_fp32": false,
+    "rope_theta": 10000,
+    "routed_scaling_factor": 2.5,
+    "sliding_window": null,
+    "ssm_state_size": 128,
+    "tie_word_embeddings": false,
+    "time_step_floor": 0.0001,
+    "time_step_max": 0.1,
+    "time_step_min": 0.001,
+    "topk_group": 1,
+    "transformers_version": "4.57.6",
+    "use_bias": false,
+    "use_cache": true,
+    "use_conv_bias": true,
+    "use_mamba_kernels": true,
+    "vocab_size": 131072
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": [
+    2,
+    11
+  ],
+  "pad_token_id": 0,
+  "top_p": 0.95,
+  "transformers_version": "4.57.6",
+  "temperature": 1.0
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7cc60a26a46712e471d74c64dc4460558b15194a879a99426c5647ef1d588ca6
+size 5118631458

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed6020dad4cdeac47bb24d31ce8d212a607476358845b8620f1767b2fae30b3a
+size 5291568451

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcc12aa6d00fa75447fc01ba7efe288e5bae025ae44aaad0afde265ac3abb7f1
+size 5291568415

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fcd77b940874080dce8c63843c93957d96565284b7810063e592b6febd63089
+size 2073657055

model.safetensors.index.json

@@ -0,0 +1,737 @@
+{
+    "metadata": {
+        "total_size": 17775339392,
+        "total_parameters": 31577935872
+    },
+    "weight_map": {
+        "backbone.embeddings.biases": "model-00001-of-00004.safetensors",
+        "backbone.embeddings.scales": "model-00001-of-00004.safetensors",
+        "backbone.embeddings.weight": "model-00001-of-00004.safetensors",
+        "backbone.layers.0.mixer.A_log": "model-00001-of-00004.safetensors",
+        "backbone.layers.0.mixer.D": "model-00001-of-00004.safetensors",
+        "backbone.layers.0.mixer.conv1d.bias": "model-00001-of-00004.safetensors",
+        "backbone.layers.0.mixer.conv1d.weight": "model-00001-of-00004.safetensors",
+        "backbone.layers.0.mixer.dt_bias": "model-00001-of-00004.safetensors",
+        "backbone.layers.0.mixer.in_proj.biases": "model-00001-of-00004.safetensors",
+        "backbone.layers.0.mixer.in_proj.scales": "model-00001-of-00004.safetensors",
+        "backbone.layers.0.mixer.in_proj.weight": "model-00001-of-00004.safetensors",
+        "backbone.layers.0.mixer.norm.weight": "model-00001-of-00004.safetensors",
+        "backbone.layers.0.mixer.out_proj.biases": "model-00001-of-00004.safetensors",
+        "backbone.layers.0.mixer.out_proj.scales": "model-00001-of-00004.safetensors",
+        "backbone.layers.0.mixer.out_proj.weight": "model-00001-of-00004.safetensors",
+        "backbone.layers.0.norm.weight": "model-00001-of-00004.safetensors",
+        "backbone.layers.1.mixer.gate.e_score_correction_bias": "model-00001-of-00004.safetensors",
+        "backbone.layers.1.mixer.gate.weight": "model-00001-of-00004.safetensors",
+        "backbone.layers.1.mixer.shared_experts.down_proj.biases": "model-00001-of-00004.safetensors",
+        "backbone.layers.1.mixer.shared_experts.down_proj.scales": "model-00001-of-00004.safetensors",
+        "backbone.layers.1.mixer.shared_experts.down_proj.weight": "model-00001-of-00004.safetensors",
+        "backbone.layers.1.mixer.shared_experts.up_proj.biases": "model-00001-of-00004.safetensors",
+        "backbone.layers.1.mixer.shared_experts.up_proj.scales": "model-00001-of-00004.safetensors",
+        "backbone.layers.1.mixer.shared_experts.up_proj.weight": "model-00001-of-00004.safetensors",
+        "backbone.layers.1.mixer.switch_mlp.fc1.biases": "model-00001-of-00004.safetensors",
+        "backbone.layers.1.mixer.switch_mlp.fc1.scales": "model-00001-of-00004.safetensors",
+        "backbone.layers.1.mixer.switch_mlp.fc1.weight": "model-00001-of-00004.safetensors",
+        "backbone.layers.1.mixer.switch_mlp.fc2.biases": "model-00001-of-00004.safetensors",
+        "backbone.layers.1.mixer.switch_mlp.fc2.scales": "model-00001-of-00004.safetensors",
+        "backbone.layers.1.mixer.switch_mlp.fc2.weight": "model-00001-of-00004.safetensors",
+        "backbone.layers.1.norm.weight": "model-00001-of-00004.safetensors",
+        "backbone.layers.10.mixer.gate.e_score_correction_bias": "model-00001-of-00004.safetensors",
+        "backbone.layers.10.mixer.gate.weight": "model-00001-of-00004.safetensors",
+        "backbone.layers.10.mixer.shared_experts.down_proj.biases": "model-00001-of-00004.safetensors",
+        "backbone.layers.10.mixer.shared_experts.down_proj.scales": "model-00001-of-00004.safetensors",
+        "backbone.layers.10.mixer.shared_experts.down_proj.weight": "model-00001-of-00004.safetensors",
+        "backbone.layers.10.mixer.shared_experts.up_proj.biases": "model-00001-of-00004.safetensors",
+        "backbone.layers.10.mixer.shared_experts.up_proj.scales": "model-00001-of-00004.safetensors",
+        "backbone.layers.10.mixer.shared_experts.up_proj.weight": "model-00001-of-00004.safetensors",
+        "backbone.layers.10.mixer.switch_mlp.fc1.biases": "model-00001-of-00004.safetensors",
+        "backbone.layers.10.mixer.switch_mlp.fc1.scales": "model-00001-of-00004.safetensors",
+        "backbone.layers.10.mixer.switch_mlp.fc1.weight": "model-00001-of-00004.safetensors",
+        "backbone.layers.10.mixer.switch_mlp.fc2.biases": "model-00001-of-00004.safetensors",
+        "backbone.layers.10.mixer.switch_mlp.fc2.scales": "model-00001-of-00004.safetensors",
+        "backbone.layers.10.mixer.switch_mlp.fc2.weight": "model-00001-of-00004.safetensors",
+        "backbone.layers.10.norm.weight": "model-00001-of-00004.safetensors",
+        "backbone.layers.11.mixer.A_log": "model-00001-of-00004.safetensors",
+        "backbone.layers.11.mixer.D": "model-00001-of-00004.safetensors",
+        "backbone.layers.11.mixer.conv1d.bias": "model-00001-of-00004.safetensors",
+        "backbone.layers.11.mixer.conv1d.weight": "model-00001-of-00004.safetensors",
+        "backbone.layers.11.mixer.dt_bias": "model-00001-of-00004.safetensors",
+        "backbone.layers.11.mixer.in_proj.biases": "model-00001-of-00004.safetensors",
+        "backbone.layers.11.mixer.in_proj.scales": "model-00001-of-00004.safetensors",
+        "backbone.layers.11.mixer.in_proj.weight": "model-00001-of-00004.safetensors",
+        "backbone.layers.11.mixer.norm.weight": "model-00001-of-00004.safetensors",
+        "backbone.layers.11.mixer.out_proj.biases": "model-00001-of-00004.safetensors",
+        "backbone.layers.11.mixer.out_proj.scales": "model-00001-of-00004.safetensors",
+        "backbone.layers.11.mixer.out_proj.weight": "model-00001-of-00004.safetensors",
+        "backbone.layers.11.norm.weight": "model-00001-of-00004.safetensors",
+        "backbone.layers.12.mixer.k_proj.biases": "model-00001-of-00004.safetensors",
+        "backbone.layers.12.mixer.k_proj.scales": "model-00001-of-00004.safetensors",
+        "backbone.layers.12.mixer.k_proj.weight": "model-00001-of-00004.safetensors",
+        "backbone.layers.12.mixer.o_proj.biases": "model-00001-of-00004.safetensors",
+        "backbone.layers.12.mixer.o_proj.scales": "model-00001-of-00004.safetensors",
+        "backbone.layers.12.mixer.o_proj.weight": "model-00001-of-00004.safetensors",
+        "backbone.layers.12.mixer.q_proj.biases": "model-00001-of-00004.safetensors",
+        "backbone.layers.12.mixer.q_proj.scales": "model-00001-of-00004.safetensors",
+        "backbone.layers.12.mixer.q_proj.weight": "model-00001-of-00004.safetensors",
+        "backbone.layers.12.mixer.v_proj.biases": "model-00001-of-00004.safetensors",
+        "backbone.layers.12.mixer.v_proj.scales": "model-00001-of-00004.safetensors",
+        "backbone.layers.12.mixer.v_proj.weight": "model-00001-of-00004.safetensors",
+        "backbone.layers.12.norm.weight": "model-00001-of-00004.safetensors",
+        "backbone.layers.13.mixer.gate.e_score_correction_bias": "model-00001-of-00004.safetensors",
+        "backbone.layers.13.mixer.gate.weight": "model-00001-of-00004.safetensors",
+        "backbone.layers.13.mixer.shared_experts.down_proj.biases": "model-00001-of-00004.safetensors",
+        "backbone.layers.13.mixer.shared_experts.down_proj.scales": "model-00001-of-00004.safetensors",
+        "backbone.layers.13.mixer.shared_experts.down_proj.weight": "model-00001-of-00004.safetensors",
+        "backbone.layers.13.mixer.shared_experts.up_proj.biases": "model-00001-of-00004.safetensors",
+        "backbone.layers.13.mixer.shared_experts.up_proj.scales": "model-00001-of-00004.safetensors",
+        "backbone.layers.13.mixer.shared_experts.up_proj.weight": "model-00001-of-00004.safetensors",
+        "backbone.layers.13.mixer.switch_mlp.fc1.biases": "model-00001-of-00004.safetensors",
+        "backbone.layers.13.mixer.switch_mlp.fc1.scales": "model-00001-of-00004.safetensors",
+        "backbone.layers.13.mixer.switch_mlp.fc1.weight": "model-00001-of-00004.safetensors",
+        "backbone.layers.13.mixer.switch_mlp.fc2.biases": "model-00001-of-00004.safetensors",
+        "backbone.layers.13.mixer.switch_mlp.fc2.scales": "model-00001-of-00004.safetensors",
+        "backbone.layers.13.mixer.switch_mlp.fc2.weight": "model-00001-of-00004.safetensors",
+        "backbone.layers.13.norm.weight": "model-00001-of-00004.safetensors",
+        "backbone.layers.14.mixer.A_log": "model-00001-of-00004.safetensors",
+        "backbone.layers.14.mixer.D": "model-00001-of-00004.safetensors",
+        "backbone.layers.14.mixer.conv1d.bias": "model-00001-of-00004.safetensors",
+        "backbone.layers.14.mixer.conv1d.weight": "model-00001-of-00004.safetensors",
+        "backbone.layers.14.mixer.dt_bias": "model-00001-of-00004.safetensors",
+        "backbone.layers.14.mixer.in_proj.biases": "model-00001-of-00004.safetensors",
+        "backbone.layers.14.mixer.in_proj.scales": "model-00001-of-00004.safetensors",
+        "backbone.layers.14.mixer.in_proj.weight": "model-00001-of-00004.safetensors",
+        "backbone.layers.14.mixer.norm.weight": "model-00001-of-00004.safetensors",
+        "backbone.layers.14.mixer.out_proj.biases": "model-00001-of-00004.safetensors",
+        "backbone.layers.14.mixer.out_proj.scales": "model-00001-of-00004.safetensors",
+        "backbone.layers.14.mixer.out_proj.weight": "model-00001-of-00004.safetensors",
+        "backbone.layers.14.norm.weight": "model-00001-of-00004.safetensors",
+        "backbone.layers.15.mixer.gate.e_score_correction_bias": "model-00002-of-00004.safetensors",
+        "backbone.layers.15.mixer.gate.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.15.mixer.shared_experts.down_proj.biases": "model-00002-of-00004.safetensors",
+        "backbone.layers.15.mixer.shared_experts.down_proj.scales": "model-00002-of-00004.safetensors",
+        "backbone.layers.15.mixer.shared_experts.down_proj.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.15.mixer.shared_experts.up_proj.biases": "model-00002-of-00004.safetensors",
+        "backbone.layers.15.mixer.shared_experts.up_proj.scales": "model-00002-of-00004.safetensors",
+        "backbone.layers.15.mixer.shared_experts.up_proj.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.15.mixer.switch_mlp.fc1.biases": "model-00001-of-00004.safetensors",
+        "backbone.layers.15.mixer.switch_mlp.fc1.scales": "model-00001-of-00004.safetensors",
+        "backbone.layers.15.mixer.switch_mlp.fc1.weight": "model-00001-of-00004.safetensors",
+        "backbone.layers.15.mixer.switch_mlp.fc2.biases": "model-00002-of-00004.safetensors",
+        "backbone.layers.15.mixer.switch_mlp.fc2.scales": "model-00002-of-00004.safetensors",
+        "backbone.layers.15.mixer.switch_mlp.fc2.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.15.norm.weight": "model-00001-of-00004.safetensors",
+        "backbone.layers.16.mixer.A_log": "model-00002-of-00004.safetensors",
+        "backbone.layers.16.mixer.D": "model-00002-of-00004.safetensors",
+        "backbone.layers.16.mixer.conv1d.bias": "model-00002-of-00004.safetensors",
+        "backbone.layers.16.mixer.conv1d.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.16.mixer.dt_bias": "model-00002-of-00004.safetensors",
+        "backbone.layers.16.mixer.in_proj.biases": "model-00002-of-00004.safetensors",
+        "backbone.layers.16.mixer.in_proj.scales": "model-00002-of-00004.safetensors",
+        "backbone.layers.16.mixer.in_proj.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.16.mixer.norm.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.16.mixer.out_proj.biases": "model-00002-of-00004.safetensors",
+        "backbone.layers.16.mixer.out_proj.scales": "model-00002-of-00004.safetensors",
+        "backbone.layers.16.mixer.out_proj.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.16.norm.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.17.mixer.gate.e_score_correction_bias": "model-00002-of-00004.safetensors",
+        "backbone.layers.17.mixer.gate.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.17.mixer.shared_experts.down_proj.biases": "model-00002-of-00004.safetensors",
+        "backbone.layers.17.mixer.shared_experts.down_proj.scales": "model-00002-of-00004.safetensors",
+        "backbone.layers.17.mixer.shared_experts.down_proj.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.17.mixer.shared_experts.up_proj.biases": "model-00002-of-00004.safetensors",
+        "backbone.layers.17.mixer.shared_experts.up_proj.scales": "model-00002-of-00004.safetensors",
+        "backbone.layers.17.mixer.shared_experts.up_proj.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.17.mixer.switch_mlp.fc1.biases": "model-00002-of-00004.safetensors",
+        "backbone.layers.17.mixer.switch_mlp.fc1.scales": "model-00002-of-00004.safetensors",
+        "backbone.layers.17.mixer.switch_mlp.fc1.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.17.mixer.switch_mlp.fc2.biases": "model-00002-of-00004.safetensors",
+        "backbone.layers.17.mixer.switch_mlp.fc2.scales": "model-00002-of-00004.safetensors",
+        "backbone.layers.17.mixer.switch_mlp.fc2.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.17.norm.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.18.mixer.A_log": "model-00002-of-00004.safetensors",
+        "backbone.layers.18.mixer.D": "model-00002-of-00004.safetensors",
+        "backbone.layers.18.mixer.conv1d.bias": "model-00002-of-00004.safetensors",
+        "backbone.layers.18.mixer.conv1d.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.18.mixer.dt_bias": "model-00002-of-00004.safetensors",
+        "backbone.layers.18.mixer.in_proj.biases": "model-00002-of-00004.safetensors",
+        "backbone.layers.18.mixer.in_proj.scales": "model-00002-of-00004.safetensors",
+        "backbone.layers.18.mixer.in_proj.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.18.mixer.norm.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.18.mixer.out_proj.biases": "model-00002-of-00004.safetensors",
+        "backbone.layers.18.mixer.out_proj.scales": "model-00002-of-00004.safetensors",
+        "backbone.layers.18.mixer.out_proj.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.18.norm.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.19.mixer.k_proj.biases": "model-00002-of-00004.safetensors",
+        "backbone.layers.19.mixer.k_proj.scales": "model-00002-of-00004.safetensors",
+        "backbone.layers.19.mixer.k_proj.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.19.mixer.o_proj.biases": "model-00002-of-00004.safetensors",
+        "backbone.layers.19.mixer.o_proj.scales": "model-00002-of-00004.safetensors",
+        "backbone.layers.19.mixer.o_proj.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.19.mixer.q_proj.biases": "model-00002-of-00004.safetensors",
+        "backbone.layers.19.mixer.q_proj.scales": "model-00002-of-00004.safetensors",
+        "backbone.layers.19.mixer.q_proj.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.19.mixer.v_proj.biases": "model-00002-of-00004.safetensors",
+        "backbone.layers.19.mixer.v_proj.scales": "model-00002-of-00004.safetensors",
+        "backbone.layers.19.mixer.v_proj.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.19.norm.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.2.mixer.A_log": "model-00001-of-00004.safetensors",
+        "backbone.layers.2.mixer.D": "model-00001-of-00004.safetensors",
+        "backbone.layers.2.mixer.conv1d.bias": "model-00001-of-00004.safetensors",
+        "backbone.layers.2.mixer.conv1d.weight": "model-00001-of-00004.safetensors",
+        "backbone.layers.2.mixer.dt_bias": "model-00001-of-00004.safetensors",
+        "backbone.layers.2.mixer.in_proj.biases": "model-00001-of-00004.safetensors",
+        "backbone.layers.2.mixer.in_proj.scales": "model-00001-of-00004.safetensors",
+        "backbone.layers.2.mixer.in_proj.weight": "model-00001-of-00004.safetensors",
+        "backbone.layers.2.mixer.norm.weight": "model-00001-of-00004.safetensors",
+        "backbone.layers.2.mixer.out_proj.biases": "model-00001-of-00004.safetensors",
+        "backbone.layers.2.mixer.out_proj.scales": "model-00001-of-00004.safetensors",
+        "backbone.layers.2.mixer.out_proj.weight": "model-00001-of-00004.safetensors",
+        "backbone.layers.2.norm.weight": "model-00001-of-00004.safetensors",
+        "backbone.layers.20.mixer.gate.e_score_correction_bias": "model-00002-of-00004.safetensors",
+        "backbone.layers.20.mixer.gate.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.20.mixer.shared_experts.down_proj.biases": "model-00002-of-00004.safetensors",
+        "backbone.layers.20.mixer.shared_experts.down_proj.scales": "model-00002-of-00004.safetensors",
+        "backbone.layers.20.mixer.shared_experts.down_proj.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.20.mixer.shared_experts.up_proj.biases": "model-00002-of-00004.safetensors",
+        "backbone.layers.20.mixer.shared_experts.up_proj.scales": "model-00002-of-00004.safetensors",
+        "backbone.layers.20.mixer.shared_experts.up_proj.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.20.mixer.switch_mlp.fc1.biases": "model-00002-of-00004.safetensors",
+        "backbone.layers.20.mixer.switch_mlp.fc1.scales": "model-00002-of-00004.safetensors",
+        "backbone.layers.20.mixer.switch_mlp.fc1.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.20.mixer.switch_mlp.fc2.biases": "model-00002-of-00004.safetensors",
+        "backbone.layers.20.mixer.switch_mlp.fc2.scales": "model-00002-of-00004.safetensors",
+        "backbone.layers.20.mixer.switch_mlp.fc2.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.20.norm.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.21.mixer.A_log": "model-00002-of-00004.safetensors",
+        "backbone.layers.21.mixer.D": "model-00002-of-00004.safetensors",
+        "backbone.layers.21.mixer.conv1d.bias": "model-00002-of-00004.safetensors",
+        "backbone.layers.21.mixer.conv1d.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.21.mixer.dt_bias": "model-00002-of-00004.safetensors",
+        "backbone.layers.21.mixer.in_proj.biases": "model-00002-of-00004.safetensors",
+        "backbone.layers.21.mixer.in_proj.scales": "model-00002-of-00004.safetensors",
+        "backbone.layers.21.mixer.in_proj.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.21.mixer.norm.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.21.mixer.out_proj.biases": "model-00002-of-00004.safetensors",
+        "backbone.layers.21.mixer.out_proj.scales": "model-00002-of-00004.safetensors",
+        "backbone.layers.21.mixer.out_proj.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.21.norm.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.22.mixer.gate.e_score_correction_bias": "model-00002-of-00004.safetensors",
+        "backbone.layers.22.mixer.gate.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.22.mixer.shared_experts.down_proj.biases": "model-00002-of-00004.safetensors",
+        "backbone.layers.22.mixer.shared_experts.down_proj.scales": "model-00002-of-00004.safetensors",
+        "backbone.layers.22.mixer.shared_experts.down_proj.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.22.mixer.shared_experts.up_proj.biases": "model-00002-of-00004.safetensors",
+        "backbone.layers.22.mixer.shared_experts.up_proj.scales": "model-00002-of-00004.safetensors",
+        "backbone.layers.22.mixer.shared_experts.up_proj.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.22.mixer.switch_mlp.fc1.biases": "model-00002-of-00004.safetensors",
+        "backbone.layers.22.mixer.switch_mlp.fc1.scales": "model-00002-of-00004.safetensors",
+        "backbone.layers.22.mixer.switch_mlp.fc1.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.22.mixer.switch_mlp.fc2.biases": "model-00002-of-00004.safetensors",
+        "backbone.layers.22.mixer.switch_mlp.fc2.scales": "model-00002-of-00004.safetensors",
+        "backbone.layers.22.mixer.switch_mlp.fc2.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.22.norm.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.23.mixer.A_log": "model-00002-of-00004.safetensors",
+        "backbone.layers.23.mixer.D": "model-00002-of-00004.safetensors",
+        "backbone.layers.23.mixer.conv1d.bias": "model-00002-of-00004.safetensors",
+        "backbone.layers.23.mixer.conv1d.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.23.mixer.dt_bias": "model-00002-of-00004.safetensors",
+        "backbone.layers.23.mixer.in_proj.biases": "model-00002-of-00004.safetensors",
+        "backbone.layers.23.mixer.in_proj.scales": "model-00002-of-00004.safetensors",
+        "backbone.layers.23.mixer.in_proj.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.23.mixer.norm.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.23.mixer.out_proj.biases": "model-00002-of-00004.safetensors",
+        "backbone.layers.23.mixer.out_proj.scales": "model-00002-of-00004.safetensors",
+        "backbone.layers.23.mixer.out_proj.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.23.norm.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.24.mixer.gate.e_score_correction_bias": "model-00002-of-00004.safetensors",
+        "backbone.layers.24.mixer.gate.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.24.mixer.shared_experts.down_proj.biases": "model-00002-of-00004.safetensors",
+        "backbone.layers.24.mixer.shared_experts.down_proj.scales": "model-00002-of-00004.safetensors",
+        "backbone.layers.24.mixer.shared_experts.down_proj.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.24.mixer.shared_experts.up_proj.biases": "model-00002-of-00004.safetensors",
+        "backbone.layers.24.mixer.shared_experts.up_proj.scales": "model-00002-of-00004.safetensors",
+        "backbone.layers.24.mixer.shared_experts.up_proj.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.24.mixer.switch_mlp.fc1.biases": "model-00002-of-00004.safetensors",
+        "backbone.layers.24.mixer.switch_mlp.fc1.scales": "model-00002-of-00004.safetensors",
+        "backbone.layers.24.mixer.switch_mlp.fc1.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.24.mixer.switch_mlp.fc2.biases": "model-00002-of-00004.safetensors",
+        "backbone.layers.24.mixer.switch_mlp.fc2.scales": "model-00002-of-00004.safetensors",
+        "backbone.layers.24.mixer.switch_mlp.fc2.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.24.norm.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.25.mixer.A_log": "model-00002-of-00004.safetensors",
+        "backbone.layers.25.mixer.D": "model-00002-of-00004.safetensors",
+        "backbone.layers.25.mixer.conv1d.bias": "model-00002-of-00004.safetensors",
+        "backbone.layers.25.mixer.conv1d.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.25.mixer.dt_bias": "model-00002-of-00004.safetensors",
+        "backbone.layers.25.mixer.in_proj.biases": "model-00002-of-00004.safetensors",
+        "backbone.layers.25.mixer.in_proj.scales": "model-00002-of-00004.safetensors",
+        "backbone.layers.25.mixer.in_proj.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.25.mixer.norm.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.25.mixer.out_proj.biases": "model-00002-of-00004.safetensors",
+        "backbone.layers.25.mixer.out_proj.scales": "model-00002-of-00004.safetensors",
+        "backbone.layers.25.mixer.out_proj.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.25.norm.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.26.mixer.k_proj.biases": "model-00002-of-00004.safetensors",
+        "backbone.layers.26.mixer.k_proj.scales": "model-00002-of-00004.safetensors",
+        "backbone.layers.26.mixer.k_proj.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.26.mixer.o_proj.biases": "model-00002-of-00004.safetensors",
+        "backbone.layers.26.mixer.o_proj.scales": "model-00002-of-00004.safetensors",
+        "backbone.layers.26.mixer.o_proj.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.26.mixer.q_proj.biases": "model-00002-of-00004.safetensors",
+        "backbone.layers.26.mixer.q_proj.scales": "model-00002-of-00004.safetensors",
+        "backbone.layers.26.mixer.q_proj.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.26.mixer.v_proj.biases": "model-00002-of-00004.safetensors",
+        "backbone.layers.26.mixer.v_proj.scales": "model-00002-of-00004.safetensors",
+        "backbone.layers.26.mixer.v_proj.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.26.norm.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.27.mixer.gate.e_score_correction_bias": "model-00002-of-00004.safetensors",
+        "backbone.layers.27.mixer.gate.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.27.mixer.shared_experts.down_proj.biases": "model-00002-of-00004.safetensors",
+        "backbone.layers.27.mixer.shared_experts.down_proj.scales": "model-00002-of-00004.safetensors",
+        "backbone.layers.27.mixer.shared_experts.down_proj.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.27.mixer.shared_experts.up_proj.biases": "model-00002-of-00004.safetensors",
+        "backbone.layers.27.mixer.shared_experts.up_proj.scales": "model-00002-of-00004.safetensors",
+        "backbone.layers.27.mixer.shared_experts.up_proj.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.27.mixer.switch_mlp.fc1.biases": "model-00002-of-00004.safetensors",
+        "backbone.layers.27.mixer.switch_mlp.fc1.scales": "model-00002-of-00004.safetensors",
+        "backbone.layers.27.mixer.switch_mlp.fc1.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.27.mixer.switch_mlp.fc2.biases": "model-00002-of-00004.safetensors",
+        "backbone.layers.27.mixer.switch_mlp.fc2.scales": "model-00002-of-00004.safetensors",
+        "backbone.layers.27.mixer.switch_mlp.fc2.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.27.norm.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.28.mixer.A_log": "model-00002-of-00004.safetensors",
+        "backbone.layers.28.mixer.D": "model-00002-of-00004.safetensors",
+        "backbone.layers.28.mixer.conv1d.bias": "model-00002-of-00004.safetensors",
+        "backbone.layers.28.mixer.conv1d.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.28.mixer.dt_bias": "model-00002-of-00004.safetensors",
+        "backbone.layers.28.mixer.in_proj.biases": "model-00002-of-00004.safetensors",
+        "backbone.layers.28.mixer.in_proj.scales": "model-00002-of-00004.safetensors",
+        "backbone.layers.28.mixer.in_proj.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.28.mixer.norm.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.28.mixer.out_proj.biases": "model-00002-of-00004.safetensors",
+        "backbone.layers.28.mixer.out_proj.scales": "model-00002-of-00004.safetensors",
+        "backbone.layers.28.mixer.out_proj.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.28.norm.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.29.mixer.gate.e_score_correction_bias": "model-00002-of-00004.safetensors",
+        "backbone.layers.29.mixer.gate.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.29.mixer.shared_experts.down_proj.biases": "model-00002-of-00004.safetensors",
+        "backbone.layers.29.mixer.shared_experts.down_proj.scales": "model-00002-of-00004.safetensors",
+        "backbone.layers.29.mixer.shared_experts.down_proj.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.29.mixer.shared_experts.up_proj.biases": "model-00002-of-00004.safetensors",
+        "backbone.layers.29.mixer.shared_experts.up_proj.scales": "model-00002-of-00004.safetensors",
+        "backbone.layers.29.mixer.shared_experts.up_proj.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.29.mixer.switch_mlp.fc1.biases": "model-00002-of-00004.safetensors",
+        "backbone.layers.29.mixer.switch_mlp.fc1.scales": "model-00002-of-00004.safetensors",
+        "backbone.layers.29.mixer.switch_mlp.fc1.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.29.mixer.switch_mlp.fc2.biases": "model-00002-of-00004.safetensors",
+        "backbone.layers.29.mixer.switch_mlp.fc2.scales": "model-00002-of-00004.safetensors",
+        "backbone.layers.29.mixer.switch_mlp.fc2.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.29.norm.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.3.mixer.gate.e_score_correction_bias": "model-00001-of-00004.safetensors",
+        "backbone.layers.3.mixer.gate.weight": "model-00001-of-00004.safetensors",
+        "backbone.layers.3.mixer.shared_experts.down_proj.biases": "model-00001-of-00004.safetensors",
+        "backbone.layers.3.mixer.shared_experts.down_proj.scales": "model-00001-of-00004.safetensors",
+        "backbone.layers.3.mixer.shared_experts.down_proj.weight": "model-00001-of-00004.safetensors",
+        "backbone.layers.3.mixer.shared_experts.up_proj.biases": "model-00001-of-00004.safetensors",
+        "backbone.layers.3.mixer.shared_experts.up_proj.scales": "model-00001-of-00004.safetensors",
+        "backbone.layers.3.mixer.shared_experts.up_proj.weight": "model-00001-of-00004.safetensors",
+        "backbone.layers.3.mixer.switch_mlp.fc1.biases": "model-00001-of-00004.safetensors",
+        "backbone.layers.3.mixer.switch_mlp.fc1.scales": "model-00001-of-00004.safetensors",
+        "backbone.layers.3.mixer.switch_mlp.fc1.weight": "model-00001-of-00004.safetensors",
+        "backbone.layers.3.mixer.switch_mlp.fc2.biases": "model-00001-of-00004.safetensors",
+        "backbone.layers.3.mixer.switch_mlp.fc2.scales": "model-00001-of-00004.safetensors",
+        "backbone.layers.3.mixer.switch_mlp.fc2.weight": "model-00001-of-00004.safetensors",
+        "backbone.layers.3.norm.weight": "model-00001-of-00004.safetensors",
+        "backbone.layers.30.mixer.A_log": "model-00002-of-00004.safetensors",
+        "backbone.layers.30.mixer.D": "model-00002-of-00004.safetensors",
+        "backbone.layers.30.mixer.conv1d.bias": "model-00002-of-00004.safetensors",
+        "backbone.layers.30.mixer.conv1d.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.30.mixer.dt_bias": "model-00002-of-00004.safetensors",
+        "backbone.layers.30.mixer.in_proj.biases": "model-00002-of-00004.safetensors",
+        "backbone.layers.30.mixer.in_proj.scales": "model-00002-of-00004.safetensors",
+        "backbone.layers.30.mixer.in_proj.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.30.mixer.norm.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.30.mixer.out_proj.biases": "model-00002-of-00004.safetensors",
+        "backbone.layers.30.mixer.out_proj.scales": "model-00002-of-00004.safetensors",
+        "backbone.layers.30.mixer.out_proj.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.30.norm.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.31.mixer.gate.e_score_correction_bias": "model-00003-of-00004.safetensors",
+        "backbone.layers.31.mixer.gate.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.31.mixer.shared_experts.down_proj.biases": "model-00003-of-00004.safetensors",
+        "backbone.layers.31.mixer.shared_experts.down_proj.scales": "model-00003-of-00004.safetensors",
+        "backbone.layers.31.mixer.shared_experts.down_proj.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.31.mixer.shared_experts.up_proj.biases": "model-00003-of-00004.safetensors",
+        "backbone.layers.31.mixer.shared_experts.up_proj.scales": "model-00003-of-00004.safetensors",
+        "backbone.layers.31.mixer.shared_experts.up_proj.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.31.mixer.switch_mlp.fc1.biases": "model-00002-of-00004.safetensors",
+        "backbone.layers.31.mixer.switch_mlp.fc1.scales": "model-00002-of-00004.safetensors",
+        "backbone.layers.31.mixer.switch_mlp.fc1.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.31.mixer.switch_mlp.fc2.biases": "model-00003-of-00004.safetensors",
+        "backbone.layers.31.mixer.switch_mlp.fc2.scales": "model-00003-of-00004.safetensors",
+        "backbone.layers.31.mixer.switch_mlp.fc2.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.31.norm.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.32.mixer.A_log": "model-00003-of-00004.safetensors",
+        "backbone.layers.32.mixer.D": "model-00003-of-00004.safetensors",
+        "backbone.layers.32.mixer.conv1d.bias": "model-00003-of-00004.safetensors",
+        "backbone.layers.32.mixer.conv1d.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.32.mixer.dt_bias": "model-00003-of-00004.safetensors",
+        "backbone.layers.32.mixer.in_proj.biases": "model-00003-of-00004.safetensors",
+        "backbone.layers.32.mixer.in_proj.scales": "model-00003-of-00004.safetensors",
+        "backbone.layers.32.mixer.in_proj.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.32.mixer.norm.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.32.mixer.out_proj.biases": "model-00003-of-00004.safetensors",
+        "backbone.layers.32.mixer.out_proj.scales": "model-00003-of-00004.safetensors",
+        "backbone.layers.32.mixer.out_proj.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.32.norm.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.33.mixer.k_proj.biases": "model-00003-of-00004.safetensors",
+        "backbone.layers.33.mixer.k_proj.scales": "model-00003-of-00004.safetensors",
+        "backbone.layers.33.mixer.k_proj.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.33.mixer.o_proj.biases": "model-00003-of-00004.safetensors",
+        "backbone.layers.33.mixer.o_proj.scales": "model-00003-of-00004.safetensors",
+        "backbone.layers.33.mixer.o_proj.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.33.mixer.q_proj.biases": "model-00003-of-00004.safetensors",
+        "backbone.layers.33.mixer.q_proj.scales": "model-00003-of-00004.safetensors",
+        "backbone.layers.33.mixer.q_proj.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.33.mixer.v_proj.biases": "model-00003-of-00004.safetensors",
+        "backbone.layers.33.mixer.v_proj.scales": "model-00003-of-00004.safetensors",
+        "backbone.layers.33.mixer.v_proj.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.33.norm.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.34.mixer.gate.e_score_correction_bias": "model-00003-of-00004.safetensors",
+        "backbone.layers.34.mixer.gate.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.34.mixer.shared_experts.down_proj.biases": "model-00003-of-00004.safetensors",
+        "backbone.layers.34.mixer.shared_experts.down_proj.scales": "model-00003-of-00004.safetensors",
+        "backbone.layers.34.mixer.shared_experts.down_proj.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.34.mixer.shared_experts.up_proj.biases": "model-00003-of-00004.safetensors",
+        "backbone.layers.34.mixer.shared_experts.up_proj.scales": "model-00003-of-00004.safetensors",
+        "backbone.layers.34.mixer.shared_experts.up_proj.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.34.mixer.switch_mlp.fc1.biases": "model-00003-of-00004.safetensors",
+        "backbone.layers.34.mixer.switch_mlp.fc1.scales": "model-00003-of-00004.safetensors",
+        "backbone.layers.34.mixer.switch_mlp.fc1.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.34.mixer.switch_mlp.fc2.biases": "model-00003-of-00004.safetensors",
+        "backbone.layers.34.mixer.switch_mlp.fc2.scales": "model-00003-of-00004.safetensors",
+        "backbone.layers.34.mixer.switch_mlp.fc2.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.34.norm.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.35.mixer.A_log": "model-00003-of-00004.safetensors",
+        "backbone.layers.35.mixer.D": "model-00003-of-00004.safetensors",
+        "backbone.layers.35.mixer.conv1d.bias": "model-00003-of-00004.safetensors",
+        "backbone.layers.35.mixer.conv1d.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.35.mixer.dt_bias": "model-00003-of-00004.safetensors",
+        "backbone.layers.35.mixer.in_proj.biases": "model-00003-of-00004.safetensors",
+        "backbone.layers.35.mixer.in_proj.scales": "model-00003-of-00004.safetensors",
+        "backbone.layers.35.mixer.in_proj.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.35.mixer.norm.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.35.mixer.out_proj.biases": "model-00003-of-00004.safetensors",
+        "backbone.layers.35.mixer.out_proj.scales": "model-00003-of-00004.safetensors",
+        "backbone.layers.35.mixer.out_proj.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.35.norm.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.36.mixer.gate.e_score_correction_bias": "model-00003-of-00004.safetensors",
+        "backbone.layers.36.mixer.gate.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.36.mixer.shared_experts.down_proj.biases": "model-00003-of-00004.safetensors",
+        "backbone.layers.36.mixer.shared_experts.down_proj.scales": "model-00003-of-00004.safetensors",
+        "backbone.layers.36.mixer.shared_experts.down_proj.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.36.mixer.shared_experts.up_proj.biases": "model-00003-of-00004.safetensors",
+        "backbone.layers.36.mixer.shared_experts.up_proj.scales": "model-00003-of-00004.safetensors",
+        "backbone.layers.36.mixer.shared_experts.up_proj.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.36.mixer.switch_mlp.fc1.biases": "model-00003-of-00004.safetensors",
+        "backbone.layers.36.mixer.switch_mlp.fc1.scales": "model-00003-of-00004.safetensors",
+        "backbone.layers.36.mixer.switch_mlp.fc1.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.36.mixer.switch_mlp.fc2.biases": "model-00003-of-00004.safetensors",
+        "backbone.layers.36.mixer.switch_mlp.fc2.scales": "model-00003-of-00004.safetensors",
+        "backbone.layers.36.mixer.switch_mlp.fc2.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.36.norm.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.37.mixer.A_log": "model-00003-of-00004.safetensors",
+        "backbone.layers.37.mixer.D": "model-00003-of-00004.safetensors",
+        "backbone.layers.37.mixer.conv1d.bias": "model-00003-of-00004.safetensors",
+        "backbone.layers.37.mixer.conv1d.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.37.mixer.dt_bias": "model-00003-of-00004.safetensors",
+        "backbone.layers.37.mixer.in_proj.biases": "model-00003-of-00004.safetensors",
+        "backbone.layers.37.mixer.in_proj.scales": "model-00003-of-00004.safetensors",
+        "backbone.layers.37.mixer.in_proj.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.37.mixer.norm.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.37.mixer.out_proj.biases": "model-00003-of-00004.safetensors",
+        "backbone.layers.37.mixer.out_proj.scales": "model-00003-of-00004.safetensors",
+        "backbone.layers.37.mixer.out_proj.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.37.norm.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.38.mixer.gate.e_score_correction_bias": "model-00003-of-00004.safetensors",
+        "backbone.layers.38.mixer.gate.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.38.mixer.shared_experts.down_proj.biases": "model-00003-of-00004.safetensors",
+        "backbone.layers.38.mixer.shared_experts.down_proj.scales": "model-00003-of-00004.safetensors",
+        "backbone.layers.38.mixer.shared_experts.down_proj.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.38.mixer.shared_experts.up_proj.biases": "model-00003-of-00004.safetensors",
+        "backbone.layers.38.mixer.shared_experts.up_proj.scales": "model-00003-of-00004.safetensors",
+        "backbone.layers.38.mixer.shared_experts.up_proj.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.38.mixer.switch_mlp.fc1.biases": "model-00003-of-00004.safetensors",
+        "backbone.layers.38.mixer.switch_mlp.fc1.scales": "model-00003-of-00004.safetensors",
+        "backbone.layers.38.mixer.switch_mlp.fc1.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.38.mixer.switch_mlp.fc2.biases": "model-00003-of-00004.safetensors",
+        "backbone.layers.38.mixer.switch_mlp.fc2.scales": "model-00003-of-00004.safetensors",
+        "backbone.layers.38.mixer.switch_mlp.fc2.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.38.norm.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.39.mixer.A_log": "model-00003-of-00004.safetensors",
+        "backbone.layers.39.mixer.D": "model-00003-of-00004.safetensors",
+        "backbone.layers.39.mixer.conv1d.bias": "model-00003-of-00004.safetensors",
+        "backbone.layers.39.mixer.conv1d.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.39.mixer.dt_bias": "model-00003-of-00004.safetensors",
+        "backbone.layers.39.mixer.in_proj.biases": "model-00003-of-00004.safetensors",
+        "backbone.layers.39.mixer.in_proj.scales": "model-00003-of-00004.safetensors",
+        "backbone.layers.39.mixer.in_proj.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.39.mixer.norm.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.39.mixer.out_proj.biases": "model-00003-of-00004.safetensors",
+        "backbone.layers.39.mixer.out_proj.scales": "model-00003-of-00004.safetensors",
+        "backbone.layers.39.mixer.out_proj.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.39.norm.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.4.mixer.A_log": "model-00001-of-00004.safetensors",
+        "backbone.layers.4.mixer.D": "model-00001-of-00004.safetensors",
+        "backbone.layers.4.mixer.conv1d.bias": "model-00001-of-00004.safetensors",
+        "backbone.layers.4.mixer.conv1d.weight": "model-00001-of-00004.safetensors",
+        "backbone.layers.4.mixer.dt_bias": "model-00001-of-00004.safetensors",
+        "backbone.layers.4.mixer.in_proj.biases": "model-00001-of-00004.safetensors",
+        "backbone.layers.4.mixer.in_proj.scales": "model-00001-of-00004.safetensors",
+        "backbone.layers.4.mixer.in_proj.weight": "model-00001-of-00004.safetensors",
+        "backbone.layers.4.mixer.norm.weight": "model-00001-of-00004.safetensors",
+        "backbone.layers.4.mixer.out_proj.biases": "model-00001-of-00004.safetensors",
+        "backbone.layers.4.mixer.out_proj.scales": "model-00001-of-00004.safetensors",
+        "backbone.layers.4.mixer.out_proj.weight": "model-00001-of-00004.safetensors",
+        "backbone.layers.4.norm.weight": "model-00001-of-00004.safetensors",
+        "backbone.layers.40.mixer.gate.e_score_correction_bias": "model-00003-of-00004.safetensors",
+        "backbone.layers.40.mixer.gate.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.40.mixer.shared_experts.down_proj.biases": "model-00003-of-00004.safetensors",
+        "backbone.layers.40.mixer.shared_experts.down_proj.scales": "model-00003-of-00004.safetensors",
+        "backbone.layers.40.mixer.shared_experts.down_proj.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.40.mixer.shared_experts.up_proj.biases": "model-00003-of-00004.safetensors",
+        "backbone.layers.40.mixer.shared_experts.up_proj.scales": "model-00003-of-00004.safetensors",
+        "backbone.layers.40.mixer.shared_experts.up_proj.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.40.mixer.switch_mlp.fc1.biases": "model-00003-of-00004.safetensors",
+        "backbone.layers.40.mixer.switch_mlp.fc1.scales": "model-00003-of-00004.safetensors",
+        "backbone.layers.40.mixer.switch_mlp.fc1.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.40.mixer.switch_mlp.fc2.biases": "model-00003-of-00004.safetensors",
+        "backbone.layers.40.mixer.switch_mlp.fc2.scales": "model-00003-of-00004.safetensors",
+        "backbone.layers.40.mixer.switch_mlp.fc2.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.40.norm.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.41.mixer.A_log": "model-00003-of-00004.safetensors",
+        "backbone.layers.41.mixer.D": "model-00003-of-00004.safetensors",
+        "backbone.layers.41.mixer.conv1d.bias": "model-00003-of-00004.safetensors",
+        "backbone.layers.41.mixer.conv1d.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.41.mixer.dt_bias": "model-00003-of-00004.safetensors",
+        "backbone.layers.41.mixer.in_proj.biases": "model-00003-of-00004.safetensors",
+        "backbone.layers.41.mixer.in_proj.scales": "model-00003-of-00004.safetensors",
+        "backbone.layers.41.mixer.in_proj.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.41.mixer.norm.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.41.mixer.out_proj.biases": "model-00003-of-00004.safetensors",
+        "backbone.layers.41.mixer.out_proj.scales": "model-00003-of-00004.safetensors",
+        "backbone.layers.41.mixer.out_proj.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.41.norm.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.42.mixer.k_proj.biases": "model-00003-of-00004.safetensors",
+        "backbone.layers.42.mixer.k_proj.scales": "model-00003-of-00004.safetensors",
+        "backbone.layers.42.mixer.k_proj.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.42.mixer.o_proj.biases": "model-00003-of-00004.safetensors",
+        "backbone.layers.42.mixer.o_proj.scales": "model-00003-of-00004.safetensors",
+        "backbone.layers.42.mixer.o_proj.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.42.mixer.q_proj.biases": "model-00003-of-00004.safetensors",
+        "backbone.layers.42.mixer.q_proj.scales": "model-00003-of-00004.safetensors",
+        "backbone.layers.42.mixer.q_proj.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.42.mixer.v_proj.biases": "model-00003-of-00004.safetensors",
+        "backbone.layers.42.mixer.v_proj.scales": "model-00003-of-00004.safetensors",
+        "backbone.layers.42.mixer.v_proj.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.42.norm.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.43.mixer.gate.e_score_correction_bias": "model-00003-of-00004.safetensors",
+        "backbone.layers.43.mixer.gate.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.43.mixer.shared_experts.down_proj.biases": "model-00003-of-00004.safetensors",
+        "backbone.layers.43.mixer.shared_experts.down_proj.scales": "model-00003-of-00004.safetensors",
+        "backbone.layers.43.mixer.shared_experts.down_proj.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.43.mixer.shared_experts.up_proj.biases": "model-00003-of-00004.safetensors",
+        "backbone.layers.43.mixer.shared_experts.up_proj.scales": "model-00003-of-00004.safetensors",
+        "backbone.layers.43.mixer.shared_experts.up_proj.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.43.mixer.switch_mlp.fc1.biases": "model-00003-of-00004.safetensors",
+        "backbone.layers.43.mixer.switch_mlp.fc1.scales": "model-00003-of-00004.safetensors",
+        "backbone.layers.43.mixer.switch_mlp.fc1.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.43.mixer.switch_mlp.fc2.biases": "model-00003-of-00004.safetensors",
+        "backbone.layers.43.mixer.switch_mlp.fc2.scales": "model-00003-of-00004.safetensors",
+        "backbone.layers.43.mixer.switch_mlp.fc2.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.43.norm.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.44.mixer.A_log": "model-00003-of-00004.safetensors",
+        "backbone.layers.44.mixer.D": "model-00003-of-00004.safetensors",
+        "backbone.layers.44.mixer.conv1d.bias": "model-00003-of-00004.safetensors",
+        "backbone.layers.44.mixer.conv1d.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.44.mixer.dt_bias": "model-00003-of-00004.safetensors",
+        "backbone.layers.44.mixer.in_proj.biases": "model-00003-of-00004.safetensors",
+        "backbone.layers.44.mixer.in_proj.scales": "model-00003-of-00004.safetensors",
+        "backbone.layers.44.mixer.in_proj.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.44.mixer.norm.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.44.mixer.out_proj.biases": "model-00003-of-00004.safetensors",
+        "backbone.layers.44.mixer.out_proj.scales": "model-00003-of-00004.safetensors",
+        "backbone.layers.44.mixer.out_proj.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.44.norm.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.45.mixer.gate.e_score_correction_bias": "model-00003-of-00004.safetensors",
+        "backbone.layers.45.mixer.gate.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.45.mixer.shared_experts.down_proj.biases": "model-00003-of-00004.safetensors",
+        "backbone.layers.45.mixer.shared_experts.down_proj.scales": "model-00003-of-00004.safetensors",
+        "backbone.layers.45.mixer.shared_experts.down_proj.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.45.mixer.shared_experts.up_proj.biases": "model-00003-of-00004.safetensors",
+        "backbone.layers.45.mixer.shared_experts.up_proj.scales": "model-00003-of-00004.safetensors",
+        "backbone.layers.45.mixer.shared_experts.up_proj.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.45.mixer.switch_mlp.fc1.biases": "model-00003-of-00004.safetensors",
+        "backbone.layers.45.mixer.switch_mlp.fc1.scales": "model-00003-of-00004.safetensors",
+        "backbone.layers.45.mixer.switch_mlp.fc1.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.45.mixer.switch_mlp.fc2.biases": "model-00003-of-00004.safetensors",
+        "backbone.layers.45.mixer.switch_mlp.fc2.scales": "model-00003-of-00004.safetensors",
+        "backbone.layers.45.mixer.switch_mlp.fc2.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.45.norm.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.46.mixer.A_log": "model-00003-of-00004.safetensors",
+        "backbone.layers.46.mixer.D": "model-00003-of-00004.safetensors",
+        "backbone.layers.46.mixer.conv1d.bias": "model-00003-of-00004.safetensors",
+        "backbone.layers.46.mixer.conv1d.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.46.mixer.dt_bias": "model-00003-of-00004.safetensors",
+        "backbone.layers.46.mixer.in_proj.biases": "model-00003-of-00004.safetensors",
+        "backbone.layers.46.mixer.in_proj.scales": "model-00003-of-00004.safetensors",
+        "backbone.layers.46.mixer.in_proj.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.46.mixer.norm.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.46.mixer.out_proj.biases": "model-00003-of-00004.safetensors",
+        "backbone.layers.46.mixer.out_proj.scales": "model-00003-of-00004.safetensors",
+        "backbone.layers.46.mixer.out_proj.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.46.norm.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.47.mixer.gate.e_score_correction_bias": "model-00004-of-00004.safetensors",
+        "backbone.layers.47.mixer.gate.weight": "model-00004-of-00004.safetensors",
+        "backbone.layers.47.mixer.shared_experts.down_proj.biases": "model-00004-of-00004.safetensors",
+        "backbone.layers.47.mixer.shared_experts.down_proj.scales": "model-00004-of-00004.safetensors",
+        "backbone.layers.47.mixer.shared_experts.down_proj.weight": "model-00004-of-00004.safetensors",
+        "backbone.layers.47.mixer.shared_experts.up_proj.biases": "model-00004-of-00004.safetensors",
+        "backbone.layers.47.mixer.shared_experts.up_proj.scales": "model-00004-of-00004.safetensors",
+        "backbone.layers.47.mixer.shared_experts.up_proj.weight": "model-00004-of-00004.safetensors",
+        "backbone.layers.47.mixer.switch_mlp.fc1.biases": "model-00003-of-00004.safetensors",
+        "backbone.layers.47.mixer.switch_mlp.fc1.scales": "model-00003-of-00004.safetensors",
+        "backbone.layers.47.mixer.switch_mlp.fc1.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.47.mixer.switch_mlp.fc2.biases": "model-00004-of-00004.safetensors",
+        "backbone.layers.47.mixer.switch_mlp.fc2.scales": "model-00004-of-00004.safetensors",
+        "backbone.layers.47.mixer.switch_mlp.fc2.weight": "model-00004-of-00004.safetensors",
+        "backbone.layers.47.norm.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.48.mixer.A_log": "model-00004-of-00004.safetensors",
+        "backbone.layers.48.mixer.D": "model-00004-of-00004.safetensors",
+        "backbone.layers.48.mixer.conv1d.bias": "model-00004-of-00004.safetensors",
+        "backbone.layers.48.mixer.conv1d.weight": "model-00004-of-00004.safetensors",
+        "backbone.layers.48.mixer.dt_bias": "model-00004-of-00004.safetensors",
+        "backbone.layers.48.mixer.in_proj.biases": "model-00004-of-00004.safetensors",
+        "backbone.layers.48.mixer.in_proj.scales": "model-00004-of-00004.safetensors",
+        "backbone.layers.48.mixer.in_proj.weight": "model-00004-of-00004.safetensors",
+        "backbone.layers.48.mixer.norm.weight": "model-00004-of-00004.safetensors",
+        "backbone.layers.48.mixer.out_proj.biases": "model-00004-of-00004.safetensors",
+        "backbone.layers.48.mixer.out_proj.scales": "model-00004-of-00004.safetensors",
+        "backbone.layers.48.mixer.out_proj.weight": "model-00004-of-00004.safetensors",
+        "backbone.layers.48.norm.weight": "model-00004-of-00004.safetensors",
+        "backbone.layers.49.mixer.gate.e_score_correction_bias": "model-00004-of-00004.safetensors",
+        "backbone.layers.49.mixer.gate.weight": "model-00004-of-00004.safetensors",
+        "backbone.layers.49.mixer.shared_experts.down_proj.biases": "model-00004-of-00004.safetensors",
+        "backbone.layers.49.mixer.shared_experts.down_proj.scales": "model-00004-of-00004.safetensors",
+        "backbone.layers.49.mixer.shared_experts.down_proj.weight": "model-00004-of-00004.safetensors",
+        "backbone.layers.49.mixer.shared_experts.up_proj.biases": "model-00004-of-00004.safetensors",
+        "backbone.layers.49.mixer.shared_experts.up_proj.scales": "model-00004-of-00004.safetensors",
+        "backbone.layers.49.mixer.shared_experts.up_proj.weight": "model-00004-of-00004.safetensors",
+        "backbone.layers.49.mixer.switch_mlp.fc1.biases": "model-00004-of-00004.safetensors",
+        "backbone.layers.49.mixer.switch_mlp.fc1.scales": "model-00004-of-00004.safetensors",
+        "backbone.layers.49.mixer.switch_mlp.fc1.weight": "model-00004-of-00004.safetensors",
+        "backbone.layers.49.mixer.switch_mlp.fc2.biases": "model-00004-of-00004.safetensors",
+        "backbone.layers.49.mixer.switch_mlp.fc2.scales": "model-00004-of-00004.safetensors",
+        "backbone.layers.49.mixer.switch_mlp.fc2.weight": "model-00004-of-00004.safetensors",
+        "backbone.layers.49.norm.weight": "model-00004-of-00004.safetensors",
+        "backbone.layers.5.mixer.k_proj.biases": "model-00001-of-00004.safetensors",
+        "backbone.layers.5.mixer.k_proj.scales": "model-00001-of-00004.safetensors",
+        "backbone.layers.5.mixer.k_proj.weight": "model-00001-of-00004.safetensors",
+        "backbone.layers.5.mixer.o_proj.biases": "model-00001-of-00004.safetensors",
+        "backbone.layers.5.mixer.o_proj.scales": "model-00001-of-00004.safetensors",
+        "backbone.layers.5.mixer.o_proj.weight": "model-00001-of-00004.safetensors",
+        "backbone.layers.5.mixer.q_proj.biases": "model-00001-of-00004.safetensors",
+        "backbone.layers.5.mixer.q_proj.scales": "model-00001-of-00004.safetensors",
+        "backbone.layers.5.mixer.q_proj.weight": "model-00001-of-00004.safetensors",
+        "backbone.layers.5.mixer.v_proj.biases": "model-00001-of-00004.safetensors",
+        "backbone.layers.5.mixer.v_proj.scales": "model-00001-of-00004.safetensors",
+        "backbone.layers.5.mixer.v_proj.weight": "model-00001-of-00004.safetensors",
+        "backbone.layers.5.norm.weight": "model-00001-of-00004.safetensors",
+        "backbone.layers.50.mixer.A_log": "model-00004-of-00004.safetensors",
+        "backbone.layers.50.mixer.D": "model-00004-of-00004.safetensors",
+        "backbone.layers.50.mixer.conv1d.bias": "model-00004-of-00004.safetensors",
+        "backbone.layers.50.mixer.conv1d.weight": "model-00004-of-00004.safetensors",
+        "backbone.layers.50.mixer.dt_bias": "model-00004-of-00004.safetensors",
+        "backbone.layers.50.mixer.in_proj.biases": "model-00004-of-00004.safetensors",
+        "backbone.layers.50.mixer.in_proj.scales": "model-00004-of-00004.safetensors",
+        "backbone.layers.50.mixer.in_proj.weight": "model-00004-of-00004.safetensors",
+        "backbone.layers.50.mixer.norm.weight": "model-00004-of-00004.safetensors",
+        "backbone.layers.50.mixer.out_proj.biases": "model-00004-of-00004.safetensors",
+        "backbone.layers.50.mixer.out_proj.scales": "model-00004-of-00004.safetensors",
+        "backbone.layers.50.mixer.out_proj.weight": "model-00004-of-00004.safetensors",
+        "backbone.layers.50.norm.weight": "model-00004-of-00004.safetensors",
+        "backbone.layers.51.mixer.gate.e_score_correction_bias": "model-00004-of-00004.safetensors",
+        "backbone.layers.51.mixer.gate.weight": "model-00004-of-00004.safetensors",
+        "backbone.layers.51.mixer.shared_experts.down_proj.biases": "model-00004-of-00004.safetensors",
+        "backbone.layers.51.mixer.shared_experts.down_proj.scales": "model-00004-of-00004.safetensors",
+        "backbone.layers.51.mixer.shared_experts.down_proj.weight": "model-00004-of-00004.safetensors",
+        "backbone.layers.51.mixer.shared_experts.up_proj.biases": "model-00004-of-00004.safetensors",
+        "backbone.layers.51.mixer.shared_experts.up_proj.scales": "model-00004-of-00004.safetensors",
+        "backbone.layers.51.mixer.shared_experts.up_proj.weight": "model-00004-of-00004.safetensors",
+        "backbone.layers.51.mixer.switch_mlp.fc1.biases": "model-00004-of-00004.safetensors",
+        "backbone.layers.51.mixer.switch_mlp.fc1.scales": "model-00004-of-00004.safetensors",
+        "backbone.layers.51.mixer.switch_mlp.fc1.weight": "model-00004-of-00004.safetensors",
+        "backbone.layers.51.mixer.switch_mlp.fc2.biases": "model-00004-of-00004.safetensors",
+        "backbone.layers.51.mixer.switch_mlp.fc2.scales": "model-00004-of-00004.safetensors",
+        "backbone.layers.51.mixer.switch_mlp.fc2.weight": "model-00004-of-00004.safetensors",
+        "backbone.layers.51.norm.weight": "model-00004-of-00004.safetensors",
+        "backbone.layers.6.mixer.gate.e_score_correction_bias": "model-00001-of-00004.safetensors",
+        "backbone.layers.6.mixer.gate.weight": "model-00001-of-00004.safetensors",
+        "backbone.layers.6.mixer.shared_experts.down_proj.biases": "model-00001-of-00004.safetensors",
+        "backbone.layers.6.mixer.shared_experts.down_proj.scales": "model-00001-of-00004.safetensors",
+        "backbone.layers.6.mixer.shared_experts.down_proj.weight": "model-00001-of-00004.safetensors",
+        "backbone.layers.6.mixer.shared_experts.up_proj.biases": "model-00001-of-00004.safetensors",
+        "backbone.layers.6.mixer.shared_experts.up_proj.scales": "model-00001-of-00004.safetensors",
+        "backbone.layers.6.mixer.shared_experts.up_proj.weight": "model-00001-of-00004.safetensors",
+        "backbone.layers.6.mixer.switch_mlp.fc1.biases": "model-00001-of-00004.safetensors",
+        "backbone.layers.6.mixer.switch_mlp.fc1.scales": "model-00001-of-00004.safetensors",
+        "backbone.layers.6.mixer.switch_mlp.fc1.weight": "model-00001-of-00004.safetensors",
+        "backbone.layers.6.mixer.switch_mlp.fc2.biases": "model-00001-of-00004.safetensors",
+        "backbone.layers.6.mixer.switch_mlp.fc2.scales": "model-00001-of-00004.safetensors",
+        "backbone.layers.6.mixer.switch_mlp.fc2.weight": "model-00001-of-00004.safetensors",
+        "backbone.layers.6.norm.weight": "model-00001-of-00004.safetensors",
+        "backbone.layers.7.mixer.A_log": "model-00001-of-00004.safetensors",
+        "backbone.layers.7.mixer.D": "model-00001-of-00004.safetensors",
+        "backbone.layers.7.mixer.conv1d.bias": "model-00001-of-00004.safetensors",
+        "backbone.layers.7.mixer.conv1d.weight": "model-00001-of-00004.safetensors",
+        "backbone.layers.7.mixer.dt_bias": "model-00001-of-00004.safetensors",
+        "backbone.layers.7.mixer.in_proj.biases": "model-00001-of-00004.safetensors",
+        "backbone.layers.7.mixer.in_proj.scales": "model-00001-of-00004.safetensors",
+        "backbone.layers.7.mixer.in_proj.weight": "model-00001-of-00004.safetensors",
+        "backbone.layers.7.mixer.norm.weight": "model-00001-of-00004.safetensors",
+        "backbone.layers.7.mixer.out_proj.biases": "model-00001-of-00004.safetensors",
+        "backbone.layers.7.mixer.out_proj.scales": "model-00001-of-00004.safetensors",
+        "backbone.layers.7.mixer.out_proj.weight": "model-00001-of-00004.safetensors",
+        "backbone.layers.7.norm.weight": "model-00001-of-00004.safetensors",
+        "backbone.layers.8.mixer.gate.e_score_correction_bias": "model-00001-of-00004.safetensors",
+        "backbone.layers.8.mixer.gate.weight": "model-00001-of-00004.safetensors",
+        "backbone.layers.8.mixer.shared_experts.down_proj.biases": "model-00001-of-00004.safetensors",
+        "backbone.layers.8.mixer.shared_experts.down_proj.scales": "model-00001-of-00004.safetensors",
+        "backbone.layers.8.mixer.shared_experts.down_proj.weight": "model-00001-of-00004.safetensors",
+        "backbone.layers.8.mixer.shared_experts.up_proj.biases": "model-00001-of-00004.safetensors",
+        "backbone.layers.8.mixer.shared_experts.up_proj.scales": "model-00001-of-00004.safetensors",
+        "backbone.layers.8.mixer.shared_experts.up_proj.weight": "model-00001-of-00004.safetensors",
+        "backbone.layers.8.mixer.switch_mlp.fc1.biases": "model-00001-of-00004.safetensors",
+        "backbone.layers.8.mixer.switch_mlp.fc1.scales": "model-00001-of-00004.safetensors",
+        "backbone.layers.8.mixer.switch_mlp.fc1.weight": "model-00001-of-00004.safetensors",
+        "backbone.layers.8.mixer.switch_mlp.fc2.biases": "model-00001-of-00004.safetensors",
+        "backbone.layers.8.mixer.switch_mlp.fc2.scales": "model-00001-of-00004.safetensors",
+        "backbone.layers.8.mixer.switch_mlp.fc2.weight": "model-00001-of-00004.safetensors",
+        "backbone.layers.8.norm.weight": "model-00001-of-00004.safetensors",
+        "backbone.layers.9.mixer.A_log": "model-00001-of-00004.safetensors",
+        "backbone.layers.9.mixer.D": "model-00001-of-00004.safetensors",
+        "backbone.layers.9.mixer.conv1d.bias": "model-00001-of-00004.safetensors",
+        "backbone.layers.9.mixer.conv1d.weight": "model-00001-of-00004.safetensors",
+        "backbone.layers.9.mixer.dt_bias": "model-00001-of-00004.safetensors",
+        "backbone.layers.9.mixer.in_proj.biases": "model-00001-of-00004.safetensors",
+        "backbone.layers.9.mixer.in_proj.scales": "model-00001-of-00004.safetensors",
+        "backbone.layers.9.mixer.in_proj.weight": "model-00001-of-00004.safetensors",
+        "backbone.layers.9.mixer.norm.weight": "model-00001-of-00004.safetensors",
+        "backbone.layers.9.mixer.out_proj.biases": "model-00001-of-00004.safetensors",
+        "backbone.layers.9.mixer.out_proj.scales": "model-00001-of-00004.safetensors",
+        "backbone.layers.9.mixer.out_proj.weight": "model-00001-of-00004.safetensors",
+        "backbone.layers.9.norm.weight": "model-00001-of-00004.safetensors",
+        "backbone.norm_f.weight": "model-00004-of-00004.safetensors",
+        "lm_head.biases": "model-00004-of-00004.safetensors",
+        "lm_head.scales": "model-00004-of-00004.safetensors",
+        "lm_head.weight": "model-00004-of-00004.safetensors"
+    }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:623c34567aebb18582765289fbe23d901c62704d6518d71866e0e58db892b5b7
+size 17077484

tokenizer_config.json

@@ -0,0 +1,18 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "is_local": true,
+  "local_files_only": false,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 262144,
+  "pad_token": "<|im_end|>",
+  "tokenizer_class": "TokenizersBackend",
+  "tool_parser_type": "qwen3_coder",
+  "unk_token": "<unk>"
+}