Instructions to use AutomatosX/AX-Nemotron-3.5-Lightning-30B-A3B-MLX-AXQ-MXFP4-MTP with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AutomatosX/AX-Nemotron-3.5-Lightning-30B-A3B-MLX-AXQ-MXFP4-MTP with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("AutomatosX/AX-Nemotron-3.5-Lightning-30B-A3B-MLX-AXQ-MXFP4-MTP")

prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True
)

text = generate(model, tokenizer, prompt=prompt, verbose=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use AutomatosX/AX-Nemotron-3.5-Lightning-30B-A3B-MLX-AXQ-MXFP4-MTP with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "AutomatosX/AX-Nemotron-3.5-Lightning-30B-A3B-MLX-AXQ-MXFP4-MTP"

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "AutomatosX/AX-Nemotron-3.5-Lightning-30B-A3B-MLX-AXQ-MXFP4-MTP"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use AutomatosX/AX-Nemotron-3.5-Lightning-30B-A3B-MLX-AXQ-MXFP4-MTP with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "AutomatosX/AX-Nemotron-3.5-Lightning-30B-A3B-MLX-AXQ-MXFP4-MTP"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "AutomatosX/AX-Nemotron-3.5-Lightning-30B-A3B-MLX-AXQ-MXFP4-MTP"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "AutomatosX/AX-Nemotron-3.5-Lightning-30B-A3B-MLX-AXQ-MXFP4-MTP",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use AutomatosX/AX-Nemotron-3.5-Lightning-30B-A3B-MLX-AXQ-MXFP4-MTP with Hermes Agent:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "AutomatosX/AX-Nemotron-3.5-Lightning-30B-A3B-MLX-AXQ-MXFP4-MTP"

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default AutomatosX/AX-Nemotron-3.5-Lightning-30B-A3B-MLX-AXQ-MXFP4-MTP

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use AutomatosX/AX-Nemotron-3.5-Lightning-30B-A3B-MLX-AXQ-MXFP4-MTP with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "AutomatosX/AX-Nemotron-3.5-Lightning-30B-A3B-MLX-AXQ-MXFP4-MTP"

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "AutomatosX/AX-Nemotron-3.5-Lightning-30B-A3B-MLX-AXQ-MXFP4-MTP" \
  --custom-provider-id mlx-lm \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

AutomatosX commited on 6 days ago

Commit

5ab1716

verified ·

1 Parent(s): b144016

Publish AX-Nemotron-3.5-Lightning-30B-A3B-MLX-AXQ-MXFP4-MTP development checkpoint

Browse files

Files changed (25) hide show

.gitattributes +1 -0
LICENSE +51 -0
README.md +43 -0
SHA256SUMS.txt +23 -0
ax_expert_stream.json +945 -0
ax_nemotron_mtp_manifest.json +18 -0
axquant_manifest.json +233 -0
axquant_mtp_sidecar_manifest.json +31 -0
axquant_nemotron_release.json +11 -0
axquant_plan.json +0 -0
axquant_quantizer_execution.json +0 -0
axquant_runtime.json +60 -0
axquant_source_binding.json +72 -0
chat_template.jinja +190 -0
config.json +1764 -0
generation_config.json +13 -0
model-00001-of-00004.safetensors +3 -0
model-00002-of-00004.safetensors +3 -0
model-00003-of-00004.safetensors +3 -0
model-00004-of-00004.safetensors +3 -0
model.safetensors.index.json +573 -0
mtp.safetensors +3 -0
special_tokens_map.json +30 -0
tokenizer.json +3 -0
tokenizer_config.json +18 -0

.gitattributes CHANGED Viewed

@@ -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

 *.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 ADDED Viewed

	@@ -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 ADDED Viewed

	@@ -0,0 +1,43 @@

+---
+library_name: mlx
+base_model: nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16
+license: other
+license_name: openmdw-1.1
+license_link: https://openmdw.ai/license/1-1/
+pipeline_tag: text-generation
+tags:
+- axquant
+- mlx
+- mxfp
+- mtp
+---
+# AX-Nemotron-3.5-Lightning-30B-A3B-MLX-AXQ-MXFP4-MTP
+This repository contains an AXQuant development conversion of the pinned NVIDIA BF16 source. The main checkpoint uses standard MLX-LM config, tokenizer, index, and safetensors files. MXFP quantization is applied to eligible backbone weights; protected tensors keep their declared precision.
+## Source and format
+- Source: [nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16](https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16)
+- Immutable source revision: `a9904d24bcc1d289a1950fa9d2b978c47cf903b9`
+- AXQuant physical format: `MXFP4`
+- AXQuant plan and file hashes are included in this repository.
+- This is a development artifact; no quality certificate is claimed.
+## MTP payload
+The source integrates Nemotron-H MTP tensors into its original checkpoint shards. AXQuant preserves those tensor payloads byte-for-byte in `mtp.safetensors` and records the source and payload digests in `ax_nemotron_mtp_manifest.json`. Runtime compatibility is unverified. This package does not claim MTP execution support in MLX-LM, AX Engine, MTPLX, or oMLX; each runtime owns that support.
+## Load the standard MLX backbone
+```python
+from mlx_lm import load, generate
+model, tokenizer = load("AutomatosX/AX-Nemotron-3.5-Lightning-30B-A3B-MLX-AXQ-MXFP4-MTP")
+print(generate(model, tokenizer, prompt="Hello", max_tokens=32))
+```
+The example loads the text backbone. It does not load or activate the separate MTP payload. Super needs substantial memory; actual use depends on format, context, and runtime.
+## License and notices
+The source uses OpenMDW License 1.1; its license and notices are included.

SHA256SUMS.txt ADDED Viewed

	@@ -0,0 +1,23 @@

+d7c8a9e5d1896d0a9588319cc7b1433e64645ad6d9e55632c30b78d8c038c23b  LICENSE
+ad266cf4c73292dcc407e39ffe1dc5cd61f1c6657d54b14eda2837ce99f52af0  README.md
+5b4862085ddde5aeb5f265208f90b619e18ffee6b660a2cf14801deb585db6fb  ax_expert_stream.json
+9338ce8221bd67be7172acf465172fdf0fd023722bd0034e579e9e97dd359af5  ax_nemotron_mtp_manifest.json
+84a4060ece33dd6677e600ce32e942908c8ff98f1063303a433f8aa99e21a06d  axquant_manifest.json
+70868bd7b9910518b65bb4de2cd9d2119cb54db0d3b4db4c44a21b1b8233bf08  axquant_mtp_sidecar_manifest.json
+4dc952d9ebdc20c6c305cc21a3b59b0a22a3681235d984c5dfd3f2a7535aad7a  axquant_nemotron_release.json
+c2e42c84a337de4b5a1912d7f38f6f7a48655318a4a5b65520a825a7329f99f7  axquant_plan.json
+ebe3b092d78768fbbd4747c6c68690469c9b3ba74aa8861434704fcdf98713c8  axquant_quantizer_execution.json
+d4241b54dce14c034a940b929768f3836b1af8b64c74a5ae05f8eb87cc22a4ab  axquant_runtime.json
+33c63f90e12b93ee1ad1993fd00b1cb75423eea0eb0306787b50c6509fb5915d  axquant_source_binding.json
+58933db77d3099b4f78c55a38347a72e1ea05b97d6bd8f38775303dc0194e0a9  chat_template.jinja
+6a6d3246c4db834f09eae87deff809e157ca26617a23bded100de42a0ff5a1fa  config.json
+0ed94823ae737b507aef6af01e837041b7aa2fb0306793a310cd201d89a31ff4  generation_config.json
+a8b6891cdb0d7a97316fe841c48fc0b926588a555ecd5b08ed471e7468d58f51  model-00001-of-00004.safetensors
+033922fe5c61923583d6cd8e72028b5d5fb1c5b0e788556356492581c7b7d70f  model-00002-of-00004.safetensors
+35999dfcfdc58c5084e50df422b1b5ad6fb5a2f80c643f159c61fd4cd5ab75d8  model-00003-of-00004.safetensors
+3c28f34687c69b0011ac52de0c557540d967d8df37442ebddc69dc71027c5c03  model-00004-of-00004.safetensors
+3e068938b04a3279ca3e6e1197882741cd5f67d5f7bce238a099f9cbb4da429e  model.safetensors.index.json
+40dd606b285acd5045bd4246a916463eeb1d5f4cc7a4ebe051555985ec436e72  mtp.safetensors
+e9435fefd6d838fd9fcbbc44b97a8e3ff322be7f6dfb7e4fd2468586574bb52b  special_tokens_map.json
+623c34567aebb18582765289fbe23d901c62704d6518d71866e0e58db892b5b7  tokenizer.json
+ec380f0a6c0c2e294eb2435f5ec521fb2121cfc970e6ebf023d06829714a4eaa  tokenizer_config.json

ax_expert_stream.json ADDED Viewed

	@@ -0,0 +1,945 @@

+{
+  "estimated_full_resident_bytes": 20186121088,
+  "estimated_max_layer_expert_bytes": 678494208,
+  "estimated_resident_bytes": 4580754304,
+  "experts_per_tok": 6,
+  "generated_by": "axquant",
+  "mode": "layer-stack",
+  "num_experts": 128,
+  "required": false,
+  "resident_roles": [
+    "embedding",
+    "attention",
+    "router",
+    "shared_expert",
+    "norm",
+    "lm_head",
+    "mtp"
+  ],
+  "schema_version": "axquant.expert-stream.v1",
+  "streamed_roles": [
+    "expert"
+  ],
+  "tensors": [
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00001-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 1,
+      "name": "backbone.layers.1.mixer.switch_mlp.fc2.scales",
+      "num_experts": 128,
+      "proj": "down"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00001-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 1,
+      "name": "backbone.layers.1.mixer.switch_mlp.fc2.weight",
+      "num_experts": 128,
+      "proj": "down"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00001-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 1,
+      "name": "backbone.layers.1.mixer.switch_mlp.fc1.scales",
+      "num_experts": 128,
+      "proj": "gate_up"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00001-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 1,
+      "name": "backbone.layers.1.mixer.switch_mlp.fc1.weight",
+      "num_experts": 128,
+      "proj": "gate_up"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00001-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 3,
+      "name": "backbone.layers.3.mixer.switch_mlp.fc2.scales",
+      "num_experts": 128,
+      "proj": "down"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00001-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 3,
+      "name": "backbone.layers.3.mixer.switch_mlp.fc2.weight",
+      "num_experts": 128,
+      "proj": "down"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00001-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 3,
+      "name": "backbone.layers.3.mixer.switch_mlp.fc1.scales",
+      "num_experts": 128,
+      "proj": "gate_up"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00001-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 3,
+      "name": "backbone.layers.3.mixer.switch_mlp.fc1.weight",
+      "num_experts": 128,
+      "proj": "gate_up"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00001-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 6,
+      "name": "backbone.layers.6.mixer.switch_mlp.fc2.scales",
+      "num_experts": 128,
+      "proj": "down"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00001-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 6,
+      "name": "backbone.layers.6.mixer.switch_mlp.fc2.weight",
+      "num_experts": 128,
+      "proj": "down"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00001-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 6,
+      "name": "backbone.layers.6.mixer.switch_mlp.fc1.scales",
+      "num_experts": 128,
+      "proj": "gate_up"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00001-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 6,
+      "name": "backbone.layers.6.mixer.switch_mlp.fc1.weight",
+      "num_experts": 128,
+      "proj": "gate_up"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00001-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 8,
+      "name": "backbone.layers.8.mixer.switch_mlp.fc2.scales",
+      "num_experts": 128,
+      "proj": "down"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00001-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 8,
+      "name": "backbone.layers.8.mixer.switch_mlp.fc2.weight",
+      "num_experts": 128,
+      "proj": "down"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00001-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 8,
+      "name": "backbone.layers.8.mixer.switch_mlp.fc1.scales",
+      "num_experts": 128,
+      "proj": "gate_up"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00001-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 8,
+      "name": "backbone.layers.8.mixer.switch_mlp.fc1.weight",
+      "num_experts": 128,
+      "proj": "gate_up"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00001-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 10,
+      "name": "backbone.layers.10.mixer.switch_mlp.fc2.scales",
+      "num_experts": 128,
+      "proj": "down"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00001-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 10,
+      "name": "backbone.layers.10.mixer.switch_mlp.fc2.weight",
+      "num_experts": 128,
+      "proj": "down"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00001-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 10,
+      "name": "backbone.layers.10.mixer.switch_mlp.fc1.scales",
+      "num_experts": 128,
+      "proj": "gate_up"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00001-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 10,
+      "name": "backbone.layers.10.mixer.switch_mlp.fc1.weight",
+      "num_experts": 128,
+      "proj": "gate_up"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00001-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 13,
+      "name": "backbone.layers.13.mixer.switch_mlp.fc2.scales",
+      "num_experts": 128,
+      "proj": "down"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00001-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 13,
+      "name": "backbone.layers.13.mixer.switch_mlp.fc2.weight",
+      "num_experts": 128,
+      "proj": "down"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00001-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 13,
+      "name": "backbone.layers.13.mixer.switch_mlp.fc1.scales",
+      "num_experts": 128,
+      "proj": "gate_up"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00001-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 13,
+      "name": "backbone.layers.13.mixer.switch_mlp.fc1.weight",
+      "num_experts": 128,
+      "proj": "gate_up"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00002-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 15,
+      "name": "backbone.layers.15.mixer.switch_mlp.fc2.scales",
+      "num_experts": 128,
+      "proj": "down"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00001-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 15,
+      "name": "backbone.layers.15.mixer.switch_mlp.fc2.weight",
+      "num_experts": 128,
+      "proj": "down"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00001-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 15,
+      "name": "backbone.layers.15.mixer.switch_mlp.fc1.scales",
+      "num_experts": 128,
+      "proj": "gate_up"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00001-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 15,
+      "name": "backbone.layers.15.mixer.switch_mlp.fc1.weight",
+      "num_experts": 128,
+      "proj": "gate_up"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00002-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 17,
+      "name": "backbone.layers.17.mixer.switch_mlp.fc2.scales",
+      "num_experts": 128,
+      "proj": "down"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00002-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 17,
+      "name": "backbone.layers.17.mixer.switch_mlp.fc2.weight",
+      "num_experts": 128,
+      "proj": "down"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00002-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 17,
+      "name": "backbone.layers.17.mixer.switch_mlp.fc1.scales",
+      "num_experts": 128,
+      "proj": "gate_up"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00002-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 17,
+      "name": "backbone.layers.17.mixer.switch_mlp.fc1.weight",
+      "num_experts": 128,
+      "proj": "gate_up"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00002-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 20,
+      "name": "backbone.layers.20.mixer.switch_mlp.fc2.scales",
+      "num_experts": 128,
+      "proj": "down"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00002-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 20,
+      "name": "backbone.layers.20.mixer.switch_mlp.fc2.weight",
+      "num_experts": 128,
+      "proj": "down"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00002-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 20,
+      "name": "backbone.layers.20.mixer.switch_mlp.fc1.scales",
+      "num_experts": 128,
+      "proj": "gate_up"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00002-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 20,
+      "name": "backbone.layers.20.mixer.switch_mlp.fc1.weight",
+      "num_experts": 128,
+      "proj": "gate_up"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00002-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 22,
+      "name": "backbone.layers.22.mixer.switch_mlp.fc2.scales",
+      "num_experts": 128,
+      "proj": "down"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00002-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 22,
+      "name": "backbone.layers.22.mixer.switch_mlp.fc2.weight",
+      "num_experts": 128,
+      "proj": "down"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00002-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 22,
+      "name": "backbone.layers.22.mixer.switch_mlp.fc1.scales",
+      "num_experts": 128,
+      "proj": "gate_up"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00002-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 22,
+      "name": "backbone.layers.22.mixer.switch_mlp.fc1.weight",
+      "num_experts": 128,
+      "proj": "gate_up"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00002-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 24,
+      "name": "backbone.layers.24.mixer.switch_mlp.fc2.scales",
+      "num_experts": 128,
+      "proj": "down"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00002-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 24,
+      "name": "backbone.layers.24.mixer.switch_mlp.fc2.weight",
+      "num_experts": 128,
+      "proj": "down"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00002-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 24,
+      "name": "backbone.layers.24.mixer.switch_mlp.fc1.scales",
+      "num_experts": 128,
+      "proj": "gate_up"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00002-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 24,
+      "name": "backbone.layers.24.mixer.switch_mlp.fc1.weight",
+      "num_experts": 128,
+      "proj": "gate_up"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00002-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 27,
+      "name": "backbone.layers.27.mixer.switch_mlp.fc2.scales",
+      "num_experts": 128,
+      "proj": "down"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00002-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 27,
+      "name": "backbone.layers.27.mixer.switch_mlp.fc2.weight",
+      "num_experts": 128,
+      "proj": "down"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00002-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 27,
+      "name": "backbone.layers.27.mixer.switch_mlp.fc1.scales",
+      "num_experts": 128,
+      "proj": "gate_up"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00002-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 27,
+      "name": "backbone.layers.27.mixer.switch_mlp.fc1.weight",
+      "num_experts": 128,
+      "proj": "gate_up"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00002-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 29,
+      "name": "backbone.layers.29.mixer.switch_mlp.fc2.scales",
+      "num_experts": 128,
+      "proj": "down"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00002-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 29,
+      "name": "backbone.layers.29.mixer.switch_mlp.fc2.weight",
+      "num_experts": 128,
+      "proj": "down"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00002-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 29,
+      "name": "backbone.layers.29.mixer.switch_mlp.fc1.scales",
+      "num_experts": 128,
+      "proj": "gate_up"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00002-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 29,
+      "name": "backbone.layers.29.mixer.switch_mlp.fc1.weight",
+      "num_experts": 128,
+      "proj": "gate_up"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00002-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 31,
+      "name": "backbone.layers.31.mixer.switch_mlp.fc2.scales",
+      "num_experts": 128,
+      "proj": "down"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00002-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 31,
+      "name": "backbone.layers.31.mixer.switch_mlp.fc2.weight",
+      "num_experts": 128,
+      "proj": "down"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00002-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 31,
+      "name": "backbone.layers.31.mixer.switch_mlp.fc1.scales",
+      "num_experts": 128,
+      "proj": "gate_up"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00002-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 31,
+      "name": "backbone.layers.31.mixer.switch_mlp.fc1.weight",
+      "num_experts": 128,
+      "proj": "gate_up"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00003-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 34,
+      "name": "backbone.layers.34.mixer.switch_mlp.fc2.scales",
+      "num_experts": 128,
+      "proj": "down"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00003-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 34,
+      "name": "backbone.layers.34.mixer.switch_mlp.fc2.weight",
+      "num_experts": 128,
+      "proj": "down"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00003-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 34,
+      "name": "backbone.layers.34.mixer.switch_mlp.fc1.scales",
+      "num_experts": 128,
+      "proj": "gate_up"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00003-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 34,
+      "name": "backbone.layers.34.mixer.switch_mlp.fc1.weight",
+      "num_experts": 128,
+      "proj": "gate_up"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00003-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 36,
+      "name": "backbone.layers.36.mixer.switch_mlp.fc2.scales",
+      "num_experts": 128,
+      "proj": "down"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00003-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 36,
+      "name": "backbone.layers.36.mixer.switch_mlp.fc2.weight",
+      "num_experts": 128,
+      "proj": "down"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00003-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 36,
+      "name": "backbone.layers.36.mixer.switch_mlp.fc1.scales",
+      "num_experts": 128,
+      "proj": "gate_up"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00003-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 36,
+      "name": "backbone.layers.36.mixer.switch_mlp.fc1.weight",
+      "num_experts": 128,
+      "proj": "gate_up"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00003-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 38,
+      "name": "backbone.layers.38.mixer.switch_mlp.fc2.scales",
+      "num_experts": 128,
+      "proj": "down"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00003-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 38,
+      "name": "backbone.layers.38.mixer.switch_mlp.fc2.weight",
+      "num_experts": 128,
+      "proj": "down"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00003-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 38,
+      "name": "backbone.layers.38.mixer.switch_mlp.fc1.scales",
+      "num_experts": 128,
+      "proj": "gate_up"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00003-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 38,
+      "name": "backbone.layers.38.mixer.switch_mlp.fc1.weight",
+      "num_experts": 128,
+      "proj": "gate_up"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00003-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 40,
+      "name": "backbone.layers.40.mixer.switch_mlp.fc2.scales",
+      "num_experts": 128,
+      "proj": "down"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00003-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 40,
+      "name": "backbone.layers.40.mixer.switch_mlp.fc2.weight",
+      "num_experts": 128,
+      "proj": "down"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00003-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 40,
+      "name": "backbone.layers.40.mixer.switch_mlp.fc1.scales",
+      "num_experts": 128,
+      "proj": "gate_up"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00003-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 40,
+      "name": "backbone.layers.40.mixer.switch_mlp.fc1.weight",
+      "num_experts": 128,
+      "proj": "gate_up"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00003-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 43,
+      "name": "backbone.layers.43.mixer.switch_mlp.fc2.scales",
+      "num_experts": 128,
+      "proj": "down"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00003-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 43,
+      "name": "backbone.layers.43.mixer.switch_mlp.fc2.weight",
+      "num_experts": 128,
+      "proj": "down"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00003-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 43,
+      "name": "backbone.layers.43.mixer.switch_mlp.fc1.scales",
+      "num_experts": 128,
+      "proj": "gate_up"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00003-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 43,
+      "name": "backbone.layers.43.mixer.switch_mlp.fc1.weight",
+      "num_experts": 128,
+      "proj": "gate_up"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00003-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 45,
+      "name": "backbone.layers.45.mixer.switch_mlp.fc2.scales",
+      "num_experts": 128,
+      "proj": "down"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00003-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 45,
+      "name": "backbone.layers.45.mixer.switch_mlp.fc2.weight",
+      "num_experts": 128,
+      "proj": "down"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00003-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 45,
+      "name": "backbone.layers.45.mixer.switch_mlp.fc1.scales",
+      "num_experts": 128,
+      "proj": "gate_up"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00003-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 45,
+      "name": "backbone.layers.45.mixer.switch_mlp.fc1.weight",
+      "num_experts": 128,
+      "proj": "gate_up"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00003-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 47,
+      "name": "backbone.layers.47.mixer.switch_mlp.fc2.scales",
+      "num_experts": 128,
+      "proj": "down"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00003-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 47,
+      "name": "backbone.layers.47.mixer.switch_mlp.fc2.weight",
+      "num_experts": 128,
+      "proj": "down"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00003-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 47,
+      "name": "backbone.layers.47.mixer.switch_mlp.fc1.scales",
+      "num_experts": 128,
+      "proj": "gate_up"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00003-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 47,
+      "name": "backbone.layers.47.mixer.switch_mlp.fc1.weight",
+      "num_experts": 128,
+      "proj": "gate_up"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00004-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 49,
+      "name": "backbone.layers.49.mixer.switch_mlp.fc2.scales",
+      "num_experts": 128,
+      "proj": "down"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00004-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 49,
+      "name": "backbone.layers.49.mixer.switch_mlp.fc2.weight",
+      "num_experts": 128,
+      "proj": "down"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00003-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 49,
+      "name": "backbone.layers.49.mixer.switch_mlp.fc1.scales",
+      "num_experts": 128,
+      "proj": "gate_up"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00003-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 49,
+      "name": "backbone.layers.49.mixer.switch_mlp.fc1.weight",
+      "num_experts": 128,
+      "proj": "gate_up"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00004-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 51,
+      "name": "backbone.layers.51.mixer.switch_mlp.fc2.scales",
+      "num_experts": 128,
+      "proj": "down"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00004-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 51,
+      "name": "backbone.layers.51.mixer.switch_mlp.fc2.weight",
+      "num_experts": 128,
+      "proj": "down"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00004-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 51,
+      "name": "backbone.layers.51.mixer.switch_mlp.fc1.scales",
+      "num_experts": 128,
+      "proj": "gate_up"
+    },
+    {
+      "bits": 4,
+      "expert_axis": 0,
+      "file": "model-00004-of-00004.safetensors",
+      "group_size": 32,
+      "layer": 51,
+      "name": "backbone.layers.51.mixer.switch_mlp.fc1.weight",
+      "num_experts": 128,
+      "proj": "gate_up"
+    }
+  ]
+}

ax_nemotron_mtp_manifest.json ADDED Viewed

	@@ -0,0 +1,18 @@

+{
+  "arch_id": "nemotron_h_mtp_v1",
+  "created_at": "2026-10-04T05:39:07.316211Z",
+  "development_only": true,
+  "mtp_tensor_count": 270,
+  "mtp_tensor_names_sha256": "8183b42de4bb62dfd622dc778f788a5069cf76ca700bc119e69dccb89738da1a",
+  "payload_sha256": "40dd606b285acd5045bd4246a916463eeb1d5f4cc7a4ebe051555985ec436e72",
+  "payload_status": "byte-preserved-from-integrated-source",
+  "runtime_compatibility": "unverified",
+  "schema_version": "axquant.nemotron-mtp.v1",
+  "source_model": {
+    "architecture": "NemotronHForCausalLM",
+    "format": "mlx",
+    "local_path": null,
+    "model_id": "nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16",
+    "revision": "a9904d24bcc1d289a1950fa9d2b978c47cf903b9"
+  }
+}

axquant_manifest.json ADDED Viewed

	@@ -0,0 +1,233 @@

+{
+  "axquant_version": "1.9.0",
+  "calibration": null,
+  "created_at": "2026-10-04T05:39:17.114201Z",
+  "effective_bpw": 5.609812258365519,
+  "files": [
+    {
+      "path": "README.md",
+      "sha256": "748c964f9b7e5f2c3770ce013bbc0153be7c54311d9692c343b6188eefe77ac6",
+      "size_bytes": 81
+    },
+    {
+      "path": "ax_expert_stream.json",
+      "sha256": "5b4862085ddde5aeb5f265208f90b619e18ffee6b660a2cf14801deb585db6fb",
+      "size_bytes": 24345
+    },
+    {
+      "path": "ax_nemotron_mtp_manifest.json",
+      "sha256": "9338ce8221bd67be7172acf465172fdf0fd023722bd0034e579e9e97dd359af5",
+      "size_bytes": 715
+    },
+    {
+      "path": "axquant_mtp_sidecar_manifest.json",
+      "sha256": "70868bd7b9910518b65bb4de2cd9d2119cb54db0d3b4db4c44a21b1b8233bf08",
+      "size_bytes": 916
+    },
+    {
+      "path": "axquant_plan.json",
+      "sha256": "c2e42c84a337de4b5a1912d7f38f6f7a48655318a4a5b65520a825a7329f99f7",
+      "size_bytes": 5767126
+    },
+    {
+      "path": "axquant_quantizer_execution.json",
+      "sha256": "ebe3b092d78768fbbd4747c6c68690469c9b3ba74aa8861434704fcdf98713c8",
+      "size_bytes": 1542593
+    },
+    {
+      "path": "axquant_runtime.json",
+      "sha256": "d4241b54dce14c034a940b929768f3836b1af8b64c74a5ae05f8eb87cc22a4ab",
+      "size_bytes": 1768
+    },
+    {
+      "path": "axquant_source_binding.json",
+      "sha256": "33c63f90e12b93ee1ad1993fd00b1cb75423eea0eb0306787b50c6509fb5915d",
+      "size_bytes": 1939
+    },
+    {
+      "path": "chat_template.jinja",
+      "sha256": "58933db77d3099b4f78c55a38347a72e1ea05b97d6bd8f38775303dc0194e0a9",
+      "size_bytes": 9867
+    },
+    {
+      "path": "config.json",
+      "sha256": "6a6d3246c4db834f09eae87deff809e157ca26617a23bded100de42a0ff5a1fa",
+      "size_bytes": 49950
+    },
+    {
+      "path": "generation_config.json",
+      "sha256": "0ed94823ae737b507aef6af01e837041b7aa2fb0306793a310cd201d89a31ff4",
+      "size_bytes": 210
+    },
+    {
+      "path": "model-00001-of-00004.safetensors",
+      "sha256": "a8b6891cdb0d7a97316fe841c48fc0b926588a555ecd5b08ed471e7468d58f51",
+      "size_bytes": 5363002645
+    },
+    {
+      "path": "model-00002-of-00004.safetensors",
+      "sha256": "033922fe5c61923583d6cd8e72028b5d5fb1c5b0e788556356492581c7b7d70f",
+      "size_bytes": 5062215102
+    },
+    {
+      "path": "model-00003-of-00004.safetensors",
+      "sha256": "35999dfcfdc58c5084e50df422b1b5ad6fb5a2f80c643f159c61fd4cd5ab75d8",
+      "size_bytes": 5324699122
+    },
+    {
+      "path": "model-00004-of-00004.safetensors",
+      "sha256": "3c28f34687c69b0011ac52de0c557540d967d8df37442ebddc69dc71027c5c03",
+      "size_bytes": 1765617718
+    },
+    {
+      "path": "model.safetensors.index.json",
+      "sha256": "3e068938b04a3279ca3e6e1197882741cd5f67d5f7bce238a099f9cbb4da429e",
+      "size_bytes": 50165
+    },
+    {
+      "path": "mtp.safetensors",
+      "sha256": "40dd606b285acd5045bd4246a916463eeb1d5f4cc7a4ebe051555985ec436e72",
+      "size_bytes": 2670685376
+    },
+    {
+      "path": "special_tokens_map.json",
+      "sha256": "e9435fefd6d838fd9fcbbc44b97a8e3ff322be7f6dfb7e4fd2468586574bb52b",
+      "size_bytes": 563
+    },
+    {
+      "path": "tokenizer.json",
+      "sha256": "623c34567aebb18582765289fbe23d901c62704d6518d71866e0e58db892b5b7",
+      "size_bytes": 17077484
+    },
+    {
+      "path": "tokenizer_config.json",
+      "sha256": "ec380f0a6c0c2e294eb2435f5ec521fb2121cfc970e6ebf023d06829714a4eaa",
+      "size_bytes": 430
+    }
+  ],
+  "format": "mlx",
+  "logical_parameters": 32913266240,
+  "main_logical_parameters": 31577940288,
+  "main_weight_file_size_bytes": 17515534587,
+  "measured_main_bpw": 4.437410274958589,
+  "measured_total_bpw": 4.906524880467166,
+  "mtp_acceptance_retention": null,
+  "mtp_distribution": {
+    "bf16": {
+      "fraction": 1.0,
+      "parameters": 1335325952
+    }
+  },
+  "mtp_measured_speedup": null,
+  "mtp_policy": {
+    "candidate_bits": [
+      8,
+      16
+    ],
+    "min_bits": 16,
+    "mode": "protected",
+    "optimize_for_acceptance": false,
+    "preserve_external_sidecar": true,
+    "protect_norms": true,
+    "protect_output_head": true
+  },
+  "mtp_present": true,
+  "mtp_weight_file_size_bytes": 2670685376,
+  "plan_sha256": "7b14fa640d0bf1ff5d291e2fae3c4721a56cc4e1b2282d13282da328b5f413ab",
+  "profile": "general",
+  "protected_weight_file_size_bytes": 0,
+  "quantizer": "axquant",
+  "runtime": {
+    "ax_engine": {
+      "decode_kernel": null,
+      "fused_mtp": null,
+      "kernel_evidence": "unmeasured",
+      "model_manifest": "model-manifest.json",
+      "preferred_group_size": 32
+    },
+    "compatible_runtimes": [
+      {
+        "compatibility_level": "B",
+        "manifest": "config.json",
+        "mtp_support": "runtime-dependent",
+        "name": "mlx-lm",
+        "notes": [
+          "Standard backbone inference is the compatibility target.",
+          "AXQuant MTP metadata may be ignored by MLX-LM."
+        ],
+        "standard_inference": true,
+        "standard_mlx_weights": true,
+        "support_level": "standard-inference"
+      }
+    ],
+    "created_at": "2026-10-04T05:39:07.516717Z",
+    "kv_cache": null,
+    "memory_policy": {
+      "expert_stream": "optional",
+      "expert_stream_manifest": "ax_expert_stream.json",
+      "kv_cache_precision": "runtime-default",
+      "mtp_buffers": "preallocate-when-enabled",
+      "prefix_cache": "runtime-managed",
+      "unified_memory_safety_margin": "benchmark-required"
+    },
+    "mtp": {
+      "acceptance_retention": null,
+      "detected": true,
+      "draft_tokens": null,
+      "enabled_by_default": false,
+      "head_precision": null,
+      "measured_speedup": null,
+      "optimized": false,
+      "recommended_temperature_max": null,
+      "sidecar_file": "mtp.safetensors",
+      "verification_mode": "runtime-default"
+    },
+    "optimization_scope": "text-path",
+    "primary_runtime": {
+      "compatibility_level": "A",
+      "manifest": "model-manifest.json",
+      "mtp_support": "native",
+      "name": "ax-engine",
+      "notes": [
+        "Runtime claims require a passing AX Engine doctor and benchmark report."
+      ],
+      "standard_inference": true,
+      "standard_mlx_weights": true,
+      "support_level": "optimized"
+    },
+    "schema_version": "axquant.runtime.v1"
+  },
+  "schema_version": "axquant.artifact.v2",
+  "software_versions": {
+    "ax_engine": "7.5.7",
+    "axquant": "1.9.0",
+    "mlx": "0.32.1",
+    "mlx_lm": "0.31.3",
+    "pydantic": "2.13.4",
+    "python": "3.12.13",
+    "safetensors": "0.8.0"
+  },
+  "source_model": {
+    "architecture": "NemotronHForCausalLM",
+    "format": "mlx",
+    "local_path": null,
+    "model_id": "nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16",
+    "revision": "a9904d24bcc1d289a1950fa9d2b978c47cf903b9"
+  },
+  "target_class": "6bit",
+  "weight_distribution": {
+    "4bit": {
+      "fraction": 0.9377505388538431,
+      "parameters": 30864433152
+    },
+    "8bit": {
+      "fraction": 0.010704544891743932,
+      "parameters": 352321536
+    },
+    "bf16": {
+      "fraction": 0.05154491625441304,
+      "parameters": 1696511552
+    }
+  },
+  "weight_file_size_bytes": 20186219963
+}

axquant_mtp_sidecar_manifest.json ADDED Viewed

	@@ -0,0 +1,31 @@

+{
+  "created_at": "2026-10-04T05:39:06.057376Z",
+  "dtypes": [
+    "BF16",
+    "F32"
+  ],
+  "output": {
+    "path": "mtp.safetensors",
+    "sha256": "40dd606b285acd5045bd4246a916463eeb1d5f4cc7a4ebe051555985ec436e72",
+    "size_bytes": 2670685376
+  },
+  "parameters": 1335325952,
+  "role": "mtp",
+  "schema_version": "axquant.protected-tensor-sidecar.v1",
+  "source_files": [
+    {
+      "path": "model-00014-of-00014.safetensors",
+      "sha256": "64577b275ca4e7e5266eae0903674f7f46ec2a8cbf4f4f1a3207f80d503cd1d0",
+      "size_bytes": 2670685240
+    }
+  ],
+  "source_model": {
+    "architecture": "NemotronHForCausalLM",
+    "format": "mlx",
+    "local_path": null,
+    "model_id": "nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16",
+    "revision": "a9904d24bcc1d289a1950fa9d2b978c47cf903b9"
+  },
+  "tensor_count": 270,
+  "tensor_names_sha256": "8183b42de4bb62dfd622dc778f788a5069cf76ca700bc119e69dccb89738da1a"
+}

axquant_nemotron_release.json ADDED Viewed

	@@ -0,0 +1,11 @@

+{
+  "development_only": true,
+  "file_count": 24,
+  "format": "mxfp4",
+  "mtp_sha256": "40dd606b285acd5045bd4246a916463eeb1d5f4cc7a4ebe051555985ec436e72",
+  "mtp_tensor_count": 270,
+  "pack": "lightning-mxfp4",
+  "repo": "AutomatosX/AX-Nemotron-3.5-Lightning-30B-A3B-MLX-AXQ-MXFP4-MTP",
+  "source_model": "nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16",
+  "source_revision": "a9904d24bcc1d289a1950fa9d2b978c47cf903b9"
+}

axquant_plan.json ADDED Viewed

The diff for this file is too large to render. See raw diff

axquant_quantizer_execution.json ADDED Viewed

The diff for this file is too large to render. See raw diff

axquant_runtime.json ADDED Viewed

	@@ -0,0 +1,60 @@

+{
+  "ax_engine": {
+    "decode_kernel": null,
+    "fused_mtp": null,
+    "kernel_evidence": "unmeasured",
+    "model_manifest": "model-manifest.json",
+    "preferred_group_size": 32
+  },
+  "compatible_runtimes": [
+    {
+      "compatibility_level": "B",
+      "manifest": "config.json",
+      "mtp_support": "runtime-dependent",
+      "name": "mlx-lm",
+      "notes": [
+        "Standard backbone inference is the compatibility target.",
+        "AXQuant MTP metadata may be ignored by MLX-LM."
+      ],
+      "standard_inference": true,
+      "standard_mlx_weights": true,
+      "support_level": "standard-inference"
+    }
+  ],
+  "created_at": "2026-10-04T05:39:07.516717Z",
+  "kv_cache": null,
+  "memory_policy": {
+    "expert_stream": "optional",
+    "expert_stream_manifest": "ax_expert_stream.json",
+    "kv_cache_precision": "runtime-default",
+    "mtp_buffers": "preallocate-when-enabled",
+    "prefix_cache": "runtime-managed",
+    "unified_memory_safety_margin": "benchmark-required"
+  },
+  "mtp": {
+    "acceptance_retention": null,
+    "detected": true,
+    "draft_tokens": null,
+    "enabled_by_default": false,
+    "head_precision": null,
+    "measured_speedup": null,
+    "optimized": false,
+    "recommended_temperature_max": null,
+    "sidecar_file": "mtp.safetensors",
+    "verification_mode": "runtime-default"
+  },
+  "optimization_scope": "text-path",
+  "primary_runtime": {
+    "compatibility_level": "A",
+    "manifest": "model-manifest.json",
+    "mtp_support": "native",
+    "name": "ax-engine",
+    "notes": [
+      "Runtime claims require a passing AX Engine doctor and benchmark report."
+    ],
+    "standard_inference": true,
+    "standard_mlx_weights": true,
+    "support_level": "optimized"
+  },
+  "schema_version": "axquant.runtime.v1"
+}

axquant_source_binding.json ADDED Viewed

	@@ -0,0 +1,72 @@

+{
+  "config_sha256": "a3827a0f5e311547b40943dc081e3ff2f8a277466e8c1a3df2291e8db8a7617c",
+  "created_at": "2026-10-04T05:19:11.955640Z",
+  "index_sha256": "67f21da80ce245a3e24967f54eef3fa10e67a63eba16ef19a2d0569f06103f50",
+  "members": [
+    {
+      "path": "model-00001-of-00014.safetensors",
+      "size_bytes": 4991210024
+    },
+    {
+      "path": "model-00002-of-00014.safetensors",
+      "size_bytes": 4992601016
+    },
+    {
+      "path": "model-00003-of-00014.safetensors",
+      "size_bytes": 4992601368
+    },
+    {
+      "path": "model-00004-of-00014.safetensors",
+      "size_bytes": 4995692800
+    },
+    {
+      "path": "model-00005-of-00014.safetensors",
+      "size_bytes": 4980553832
+    },
+    {
+      "path": "model-00006-of-00014.safetensors",
+      "size_bytes": 4989423536
+    },
+    {
+      "path": "model-00007-of-00014.safetensors",
+      "size_bytes": 4992601488
+    },
+    {
+      "path": "model-00008-of-00014.safetensors",
+      "size_bytes": 4992601520
+    },
+    {
+      "path": "model-00009-of-00014.safetensors",
+      "size_bytes": 4995692800
+    },
+    {
+      "path": "model-00010-of-00014.safetensors",
+      "size_bytes": 4992601520
+    },
+    {
+      "path": "model-00011-of-00014.safetensors",
+      "size_bytes": 4995692800
+    },
+    {
+      "path": "model-00012-of-00014.safetensors",
+      "size_bytes": 4995692816
+    },
+    {
+      "path": "model-00013-of-00014.safetensors",
+      "size_bytes": 3249723504
+    },
+    {
+      "path": "model-00014-of-00014.safetensors",
+      "size_bytes": 2670685240
+    }
+  ],
+  "plan_sha256": "7b14fa640d0bf1ff5d291e2fae3c4721a56cc4e1b2282d13282da328b5f413ab",
+  "schema_version": "axquant.source-plan-binding.v1",
+  "source_model": {
+    "architecture": "NemotronHForCausalLM",
+    "format": "mlx",
+    "local_path": null,
+    "model_id": "nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16",
+    "revision": "a9904d24bcc1d289a1950fa9d2b978c47cf903b9"
+  }
+}

chat_template.jinja ADDED Viewed

	@@ -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 ADDED Viewed

	@@ -0,0 +1,1764 @@

+{
+    "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": 32,
+        "bits": 4,
+        "mode": "affine",
+        "backbone.embeddings": {
+            "group_size": 32,
+            "bits": 8,
+            "mode": "affine"
+        },
+        "backbone.layers.0.mixer.in_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.0.mixer.out_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.1.mixer.switch_mlp.fc1": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.1.mixer.switch_mlp.fc2": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.1.mixer.shared_experts.up_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.1.mixer.shared_experts.down_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.2.mixer.in_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.2.mixer.out_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.3.mixer.switch_mlp.fc1": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.3.mixer.switch_mlp.fc2": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.3.mixer.shared_experts.up_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.3.mixer.shared_experts.down_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.4.mixer.in_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.4.mixer.out_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.5.mixer.q_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.5.mixer.k_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.5.mixer.v_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.5.mixer.o_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.6.mixer.switch_mlp.fc1": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.6.mixer.switch_mlp.fc2": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.6.mixer.shared_experts.up_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.6.mixer.shared_experts.down_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.7.mixer.in_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.7.mixer.out_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.8.mixer.switch_mlp.fc1": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.8.mixer.switch_mlp.fc2": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.8.mixer.shared_experts.up_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.8.mixer.shared_experts.down_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.9.mixer.in_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.9.mixer.out_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.10.mixer.switch_mlp.fc1": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.10.mixer.switch_mlp.fc2": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.10.mixer.shared_experts.up_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.10.mixer.shared_experts.down_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.11.mixer.in_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.11.mixer.out_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.12.mixer.q_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.12.mixer.k_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.12.mixer.v_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.12.mixer.o_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.13.mixer.switch_mlp.fc1": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.13.mixer.switch_mlp.fc2": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.13.mixer.shared_experts.up_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.13.mixer.shared_experts.down_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.14.mixer.in_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.14.mixer.out_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.15.mixer.switch_mlp.fc1": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.15.mixer.switch_mlp.fc2": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.15.mixer.shared_experts.up_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.15.mixer.shared_experts.down_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.16.mixer.in_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.16.mixer.out_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.17.mixer.switch_mlp.fc1": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.17.mixer.switch_mlp.fc2": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.17.mixer.shared_experts.up_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.17.mixer.shared_experts.down_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.18.mixer.in_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.18.mixer.out_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.19.mixer.q_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.19.mixer.k_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.19.mixer.v_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.19.mixer.o_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.20.mixer.switch_mlp.fc1": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.20.mixer.switch_mlp.fc2": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.20.mixer.shared_experts.up_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.20.mixer.shared_experts.down_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.21.mixer.in_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.21.mixer.out_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.22.mixer.switch_mlp.fc1": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.22.mixer.switch_mlp.fc2": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.22.mixer.shared_experts.up_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.22.mixer.shared_experts.down_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.23.mixer.in_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.23.mixer.out_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.24.mixer.switch_mlp.fc1": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.24.mixer.switch_mlp.fc2": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.24.mixer.shared_experts.up_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.24.mixer.shared_experts.down_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.25.mixer.in_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.25.mixer.out_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.26.mixer.q_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.26.mixer.k_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.26.mixer.v_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.26.mixer.o_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.27.mixer.switch_mlp.fc1": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.27.mixer.switch_mlp.fc2": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.27.mixer.shared_experts.up_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.27.mixer.shared_experts.down_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.28.mixer.in_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.28.mixer.out_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.29.mixer.switch_mlp.fc1": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.29.mixer.switch_mlp.fc2": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.29.mixer.shared_experts.up_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.29.mixer.shared_experts.down_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.30.mixer.in_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.30.mixer.out_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.31.mixer.switch_mlp.fc1": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.31.mixer.switch_mlp.fc2": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.31.mixer.shared_experts.up_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.31.mixer.shared_experts.down_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.32.mixer.in_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.32.mixer.out_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.33.mixer.q_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.33.mixer.k_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.33.mixer.v_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.33.mixer.o_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.34.mixer.switch_mlp.fc1": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.34.mixer.switch_mlp.fc2": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.34.mixer.shared_experts.up_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.34.mixer.shared_experts.down_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.35.mixer.in_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.35.mixer.out_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.36.mixer.switch_mlp.fc1": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.36.mixer.switch_mlp.fc2": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.36.mixer.shared_experts.up_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.36.mixer.shared_experts.down_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.37.mixer.in_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.37.mixer.out_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.38.mixer.switch_mlp.fc1": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.38.mixer.switch_mlp.fc2": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.38.mixer.shared_experts.up_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.38.mixer.shared_experts.down_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.39.mixer.in_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.39.mixer.out_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.40.mixer.switch_mlp.fc1": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.40.mixer.switch_mlp.fc2": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.40.mixer.shared_experts.up_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.40.mixer.shared_experts.down_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.41.mixer.in_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.41.mixer.out_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.42.mixer.q_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.42.mixer.k_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.42.mixer.v_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.42.mixer.o_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.43.mixer.switch_mlp.fc1": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.43.mixer.switch_mlp.fc2": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.43.mixer.shared_experts.up_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.43.mixer.shared_experts.down_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.44.mixer.in_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.44.mixer.out_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.45.mixer.switch_mlp.fc1": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.45.mixer.switch_mlp.fc2": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.45.mixer.shared_experts.up_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.45.mixer.shared_experts.down_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.46.mixer.in_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.46.mixer.out_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.47.mixer.switch_mlp.fc1": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.47.mixer.switch_mlp.fc2": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.47.mixer.shared_experts.up_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.47.mixer.shared_experts.down_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.48.mixer.in_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.48.mixer.out_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.49.mixer.switch_mlp.fc1": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.49.mixer.switch_mlp.fc2": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.49.mixer.shared_experts.up_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.49.mixer.shared_experts.down_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.50.mixer.in_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.50.mixer.out_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.51.mixer.switch_mlp.fc1": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.51.mixer.switch_mlp.fc2": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.51.mixer.shared_experts.up_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.51.mixer.shared_experts.down_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        }
+    },
+    "quantization_config": {
+        "group_size": 32,
+        "bits": 4,
+        "mode": "affine",
+        "backbone.embeddings": {
+            "group_size": 32,
+            "bits": 8,
+            "mode": "affine"
+        },
+        "backbone.layers.0.mixer.in_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.0.mixer.out_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.1.mixer.switch_mlp.fc1": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.1.mixer.switch_mlp.fc2": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.1.mixer.shared_experts.up_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.1.mixer.shared_experts.down_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.2.mixer.in_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.2.mixer.out_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.3.mixer.switch_mlp.fc1": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.3.mixer.switch_mlp.fc2": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.3.mixer.shared_experts.up_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.3.mixer.shared_experts.down_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.4.mixer.in_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.4.mixer.out_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.5.mixer.q_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.5.mixer.k_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.5.mixer.v_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.5.mixer.o_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.6.mixer.switch_mlp.fc1": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.6.mixer.switch_mlp.fc2": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.6.mixer.shared_experts.up_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.6.mixer.shared_experts.down_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.7.mixer.in_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.7.mixer.out_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.8.mixer.switch_mlp.fc1": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.8.mixer.switch_mlp.fc2": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.8.mixer.shared_experts.up_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.8.mixer.shared_experts.down_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.9.mixer.in_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.9.mixer.out_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.10.mixer.switch_mlp.fc1": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.10.mixer.switch_mlp.fc2": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.10.mixer.shared_experts.up_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.10.mixer.shared_experts.down_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.11.mixer.in_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.11.mixer.out_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.12.mixer.q_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.12.mixer.k_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.12.mixer.v_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.12.mixer.o_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.13.mixer.switch_mlp.fc1": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.13.mixer.switch_mlp.fc2": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.13.mixer.shared_experts.up_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.13.mixer.shared_experts.down_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.14.mixer.in_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.14.mixer.out_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.15.mixer.switch_mlp.fc1": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.15.mixer.switch_mlp.fc2": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.15.mixer.shared_experts.up_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.15.mixer.shared_experts.down_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.16.mixer.in_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.16.mixer.out_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.17.mixer.switch_mlp.fc1": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.17.mixer.switch_mlp.fc2": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.17.mixer.shared_experts.up_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.17.mixer.shared_experts.down_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.18.mixer.in_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.18.mixer.out_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.19.mixer.q_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.19.mixer.k_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.19.mixer.v_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.19.mixer.o_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.20.mixer.switch_mlp.fc1": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.20.mixer.switch_mlp.fc2": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.20.mixer.shared_experts.up_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.20.mixer.shared_experts.down_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.21.mixer.in_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.21.mixer.out_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.22.mixer.switch_mlp.fc1": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.22.mixer.switch_mlp.fc2": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.22.mixer.shared_experts.up_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.22.mixer.shared_experts.down_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.23.mixer.in_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.23.mixer.out_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.24.mixer.switch_mlp.fc1": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.24.mixer.switch_mlp.fc2": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.24.mixer.shared_experts.up_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.24.mixer.shared_experts.down_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.25.mixer.in_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.25.mixer.out_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.26.mixer.q_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.26.mixer.k_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.26.mixer.v_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.26.mixer.o_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.27.mixer.switch_mlp.fc1": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.27.mixer.switch_mlp.fc2": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.27.mixer.shared_experts.up_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.27.mixer.shared_experts.down_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.28.mixer.in_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.28.mixer.out_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.29.mixer.switch_mlp.fc1": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.29.mixer.switch_mlp.fc2": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.29.mixer.shared_experts.up_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.29.mixer.shared_experts.down_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.30.mixer.in_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.30.mixer.out_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.31.mixer.switch_mlp.fc1": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.31.mixer.switch_mlp.fc2": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.31.mixer.shared_experts.up_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.31.mixer.shared_experts.down_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.32.mixer.in_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.32.mixer.out_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.33.mixer.q_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.33.mixer.k_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.33.mixer.v_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.33.mixer.o_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.34.mixer.switch_mlp.fc1": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.34.mixer.switch_mlp.fc2": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.34.mixer.shared_experts.up_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.34.mixer.shared_experts.down_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.35.mixer.in_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.35.mixer.out_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.36.mixer.switch_mlp.fc1": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.36.mixer.switch_mlp.fc2": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.36.mixer.shared_experts.up_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.36.mixer.shared_experts.down_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.37.mixer.in_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.37.mixer.out_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.38.mixer.switch_mlp.fc1": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.38.mixer.switch_mlp.fc2": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.38.mixer.shared_experts.up_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.38.mixer.shared_experts.down_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.39.mixer.in_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.39.mixer.out_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.40.mixer.switch_mlp.fc1": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.40.mixer.switch_mlp.fc2": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.40.mixer.shared_experts.up_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.40.mixer.shared_experts.down_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.41.mixer.in_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.41.mixer.out_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.42.mixer.q_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.42.mixer.k_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.42.mixer.v_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.42.mixer.o_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.43.mixer.switch_mlp.fc1": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.43.mixer.switch_mlp.fc2": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.43.mixer.shared_experts.up_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.43.mixer.shared_experts.down_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.44.mixer.in_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.44.mixer.out_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.45.mixer.switch_mlp.fc1": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.45.mixer.switch_mlp.fc2": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.45.mixer.shared_experts.up_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.45.mixer.shared_experts.down_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.46.mixer.in_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.46.mixer.out_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.47.mixer.switch_mlp.fc1": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.47.mixer.switch_mlp.fc2": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.47.mixer.shared_experts.up_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.47.mixer.shared_experts.down_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.48.mixer.in_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.48.mixer.out_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.49.mixer.switch_mlp.fc1": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.49.mixer.switch_mlp.fc2": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.49.mixer.shared_experts.up_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.49.mixer.shared_experts.down_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.50.mixer.in_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.50.mixer.out_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.51.mixer.switch_mlp.fc1": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.51.mixer.switch_mlp.fc2": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.51.mixer.shared_experts.up_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        },
+        "backbone.layers.51.mixer.shared_experts.down_proj": {
+            "group_size": 32,
+            "bits": 4,
+            "mode": "mxfp4"
+        }
+    },
+    "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 ADDED Viewed

	@@ -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 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:a8b6891cdb0d7a97316fe841c48fc0b926588a555ecd5b08ed471e7468d58f51
+size 5363002645

model-00002-of-00004.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:033922fe5c61923583d6cd8e72028b5d5fb1c5b0e788556356492581c7b7d70f
+size 5062215102

model-00003-of-00004.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:35999dfcfdc58c5084e50df422b1b5ad6fb5a2f80c643f159c61fd4cd5ab75d8
+size 5324699122

model-00004-of-00004.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:3c28f34687c69b0011ac52de0c557540d967d8df37442ebddc69dc71027c5c03
+size 1765617718

model.safetensors.index.json ADDED Viewed

	@@ -0,0 +1,573 @@

+{
+    "metadata": {
+        "total_size": 17515468928,
+        "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.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.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.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.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.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.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.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.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.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.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.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.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.scales": "model-00001-of-00004.safetensors",
+        "backbone.layers.12.mixer.k_proj.weight": "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.scales": "model-00001-of-00004.safetensors",
+        "backbone.layers.12.mixer.q_proj.weight": "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.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.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.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.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.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.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.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.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.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.scales": "model-00002-of-00004.safetensors",
+        "backbone.layers.15.mixer.switch_mlp.fc2.weight": "model-00001-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.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.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.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.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.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.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.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.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.scales": "model-00002-of-00004.safetensors",
+        "backbone.layers.19.mixer.k_proj.weight": "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.scales": "model-00002-of-00004.safetensors",
+        "backbone.layers.19.mixer.q_proj.weight": "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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.scales": "model-00002-of-00004.safetensors",
+        "backbone.layers.26.mixer.k_proj.weight": "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.scales": "model-00002-of-00004.safetensors",
+        "backbone.layers.26.mixer.q_proj.weight": "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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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-00002-of-00004.safetensors",
+        "backbone.layers.31.mixer.gate.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.31.mixer.shared_experts.down_proj.scales": "model-00002-of-00004.safetensors",
+        "backbone.layers.31.mixer.shared_experts.down_proj.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.31.mixer.shared_experts.up_proj.scales": "model-00002-of-00004.safetensors",
+        "backbone.layers.31.mixer.shared_experts.up_proj.weight": "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.scales": "model-00002-of-00004.safetensors",
+        "backbone.layers.31.mixer.switch_mlp.fc2.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.31.norm.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.32.mixer.A_log": "model-00002-of-00004.safetensors",
+        "backbone.layers.32.mixer.D": "model-00002-of-00004.safetensors",
+        "backbone.layers.32.mixer.conv1d.bias": "model-00002-of-00004.safetensors",
+        "backbone.layers.32.mixer.conv1d.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.32.mixer.dt_bias": "model-00002-of-00004.safetensors",
+        "backbone.layers.32.mixer.in_proj.scales": "model-00002-of-00004.safetensors",
+        "backbone.layers.32.mixer.in_proj.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.32.mixer.norm.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.32.mixer.out_proj.scales": "model-00002-of-00004.safetensors",
+        "backbone.layers.32.mixer.out_proj.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.32.norm.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.33.mixer.k_proj.scales": "model-00002-of-00004.safetensors",
+        "backbone.layers.33.mixer.k_proj.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.33.mixer.o_proj.scales": "model-00002-of-00004.safetensors",
+        "backbone.layers.33.mixer.o_proj.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.33.mixer.q_proj.scales": "model-00002-of-00004.safetensors",
+        "backbone.layers.33.mixer.q_proj.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.33.mixer.v_proj.scales": "model-00002-of-00004.safetensors",
+        "backbone.layers.33.mixer.v_proj.weight": "model-00002-of-00004.safetensors",
+        "backbone.layers.33.norm.weight": "model-00002-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.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.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.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.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-00002-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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.scales": "model-00003-of-00004.safetensors",
+        "backbone.layers.42.mixer.k_proj.weight": "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.scales": "model-00003-of-00004.safetensors",
+        "backbone.layers.42.mixer.q_proj.weight": "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.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.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.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.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.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.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.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.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.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.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.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.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-00003-of-00004.safetensors",
+        "backbone.layers.47.mixer.gate.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.47.mixer.shared_experts.down_proj.scales": "model-00003-of-00004.safetensors",
+        "backbone.layers.47.mixer.shared_experts.down_proj.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.47.mixer.shared_experts.up_proj.scales": "model-00003-of-00004.safetensors",
+        "backbone.layers.47.mixer.shared_experts.up_proj.weight": "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.scales": "model-00003-of-00004.safetensors",
+        "backbone.layers.47.mixer.switch_mlp.fc2.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.47.norm.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.48.mixer.A_log": "model-00003-of-00004.safetensors",
+        "backbone.layers.48.mixer.D": "model-00003-of-00004.safetensors",
+        "backbone.layers.48.mixer.conv1d.bias": "model-00003-of-00004.safetensors",
+        "backbone.layers.48.mixer.conv1d.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.48.mixer.dt_bias": "model-00003-of-00004.safetensors",
+        "backbone.layers.48.mixer.in_proj.scales": "model-00003-of-00004.safetensors",
+        "backbone.layers.48.mixer.in_proj.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.48.mixer.norm.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.48.mixer.out_proj.scales": "model-00003-of-00004.safetensors",
+        "backbone.layers.48.mixer.out_proj.weight": "model-00003-of-00004.safetensors",
+        "backbone.layers.48.norm.weight": "model-00003-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.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.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.scales": "model-00003-of-00004.safetensors",
+        "backbone.layers.49.mixer.switch_mlp.fc1.weight": "model-00003-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-00003-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.scales": "model-00001-of-00004.safetensors",
+        "backbone.layers.5.mixer.o_proj.weight": "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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.weight": "model-00004-of-00004.safetensors"
+    }
+}

mtp.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:40dd606b285acd5045bd4246a916463eeb1d5f4cc7a4ebe051555985ec436e72
+size 2670685376

special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,30 @@

+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:623c34567aebb18582765289fbe23d901c62704d6518d71866e0e58db892b5b7
+size 17077484

tokenizer_config.json ADDED Viewed

	@@ -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>"
+}