Upload model

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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

LICENSE

@@ -0,0 +1,202 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright 2026 Alibaba Cloud
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

README.md

@@ -0,0 +1,34 @@
+---
+license: apache-2.0
+library_name: mlx
+pipeline_tag: text-generation
+base_model:
+  - incoai/Qwen3.6-35B-A3B-Splash
+tags:
+  - mlx
+  - dflash2
+  - speculative-decoding
+  - qwen3.6
+  - 4-bit
+---
+
+# Qwen3.6-35B-A3B-DFlash2-4bit
+
+The DFlash 2 draft model for Qwen3.6-35B-A3B, as a standard safetensors checkpoint with MLX affine
+4-bit weights (group size 64).
+
+## Source and changes
+
+- Source: the `draft/` files of [`incoai/Qwen3.6-35B-A3B-Splash`](https://huggingface.co/incoai/Qwen3.6-35B-A3B-Splash),
+  revision `0f4714b2db37b5f3c42a10de07281e74f88e4adc` (Apache-2.0). That package names its draft source as
+  `incoai/Qwen3.6-35B-A3B-DFlash2`, revision `8e713508f0bb02f03b5cb5cabbc8d9604f924be2`.
+- The draft model was made by Inco AI. This repository is not published or endorsed by Inco AI.
+- Changes: the Splash runtime storage (tiled q4 integers with bf16 scales and biases) was converted to row-major
+  MLX affine storage in one `model.safetensors`, and a `config.json` was written. The integers, scales and biases
+  are moved bit for bit; no tensor was requantized (208 tensors). The original unquantized weights are not
+  recovered. Mask token id and RoPE parameters come from the target's configuration.
+  `source.json` lists the SHA-256 of every source file.
+
+## License
+
+Apache-2.0, as the source package. See `LICENSE`.

config.json

@@ -0,0 +1,54 @@
+{
+  "architectures": [
+    "DFlash2DraftModel"
+  ],
+  "model_type": "qwen3",
+  "dtype": "bfloat16",
+  "hidden_size": 2048,
+  "intermediate_size": 6144,
+  "num_hidden_layers": 6,
+  "vocab_size": 248320,
+  "num_attention_heads": 32,
+  "num_key_value_heads": 8,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "attention_bias": false,
+  "tie_word_embeddings": false,
+  "rms_norm_eps": 1e-06,
+  "max_position_embeddings": 262144,
+  "rope_parameters": {
+    "rope_type": "default",
+    "rope_theta": 10000000.0
+  },
+  "block_size": 8,
+  "is_causal": false,
+  "quantization": {
+    "mode": "affine",
+    "bits": 4,
+    "group_size": 64
+  },
+  "quantization_config": {
+    "mode": "affine",
+    "bits": 4,
+    "group_size": 64
+  },
+  "dflash_config": {
+    "mask_token_id": 248077,
+    "target_layer_ids": [
+      1,
+      6,
+      11,
+      16,
+      22,
+      27,
+      32,
+      37
+    ],
+    "conv_kernel_size": 2,
+    "conv_group_size": 16,
+    "selector_rank": 256,
+    "selector_top_k": 16,
+    "use_swa": true,
+    "swa_window_size": 2048
+  }
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e316cb7c76dd53f86e992482351e3310c55c11fa8baa331c0709bba7530826d5
+size 478987120

model.safetensors.index.json

@@ -0,0 +1,215 @@
+{
+  "metadata": {
+    "total_size": 478964736
+  },
+  "weight_map": {
+    "layers.0.input_layernorm.weight": "model.safetensors",
+    "layers.0.attention_conv.base_kernel": "model.safetensors",
+    "layers.0.attention_conv.kernel_projection.weight": "model.safetensors",
+    "layers.0.attention_conv.kernel_projection.scales": "model.safetensors",
+    "layers.0.attention_conv.kernel_projection.biases": "model.safetensors",
+    "layers.0.self_attn.q_proj.weight": "model.safetensors",
+    "layers.0.self_attn.q_proj.scales": "model.safetensors",
+    "layers.0.self_attn.q_proj.biases": "model.safetensors",
+    "layers.0.self_attn.k_proj.weight": "model.safetensors",
+    "layers.0.self_attn.k_proj.scales": "model.safetensors",
+    "layers.0.self_attn.k_proj.biases": "model.safetensors",
+    "layers.0.self_attn.v_proj.weight": "model.safetensors",
+    "layers.0.self_attn.v_proj.scales": "model.safetensors",
+    "layers.0.self_attn.v_proj.biases": "model.safetensors",
+    "layers.0.self_attn.q_norm.weight": "model.safetensors",
+    "layers.0.self_attn.k_norm.weight": "model.safetensors",
+    "layers.0.self_attn.o_proj.weight": "model.safetensors",
+    "layers.0.self_attn.o_proj.scales": "model.safetensors",
+    "layers.0.self_attn.o_proj.biases": "model.safetensors",
+    "layers.0.post_attention_layernorm.weight": "model.safetensors",
+    "layers.0.mlp_conv.base_kernel": "model.safetensors",
+    "layers.0.mlp_conv.kernel_projection.weight": "model.safetensors",
+    "layers.0.mlp_conv.kernel_projection.scales": "model.safetensors",
+    "layers.0.mlp_conv.kernel_projection.biases": "model.safetensors",
+    "layers.0.mlp.gate_proj.weight": "model.safetensors",
+    "layers.0.mlp.gate_proj.scales": "model.safetensors",
+    "layers.0.mlp.gate_proj.biases": "model.safetensors",
+    "layers.0.mlp.up_proj.weight": "model.safetensors",
+    "layers.0.mlp.up_proj.scales": "model.safetensors",
+    "layers.0.mlp.up_proj.biases": "model.safetensors",
+    "layers.0.mlp.down_proj.weight": "model.safetensors",
+    "layers.0.mlp.down_proj.scales": "model.safetensors",
+    "layers.0.mlp.down_proj.biases": "model.safetensors",
+    "layers.1.input_layernorm.weight": "model.safetensors",
+    "layers.1.attention_conv.base_kernel": "model.safetensors",
+    "layers.1.attention_conv.kernel_projection.weight": "model.safetensors",
+    "layers.1.attention_conv.kernel_projection.scales": "model.safetensors",
+    "layers.1.attention_conv.kernel_projection.biases": "model.safetensors",
+    "layers.1.self_attn.q_proj.weight": "model.safetensors",
+    "layers.1.self_attn.q_proj.scales": "model.safetensors",
+    "layers.1.self_attn.q_proj.biases": "model.safetensors",
+    "layers.1.self_attn.k_proj.weight": "model.safetensors",
+    "layers.1.self_attn.k_proj.scales": "model.safetensors",
+    "layers.1.self_attn.k_proj.biases": "model.safetensors",
+    "layers.1.self_attn.v_proj.weight": "model.safetensors",
+    "layers.1.self_attn.v_proj.scales": "model.safetensors",
+    "layers.1.self_attn.v_proj.biases": "model.safetensors",
+    "layers.1.self_attn.q_norm.weight": "model.safetensors",
+    "layers.1.self_attn.k_norm.weight": "model.safetensors",
+    "layers.1.self_attn.o_proj.weight": "model.safetensors",
+    "layers.1.self_attn.o_proj.scales": "model.safetensors",
+    "layers.1.self_attn.o_proj.biases": "model.safetensors",
+    "layers.1.post_attention_layernorm.weight": "model.safetensors",
+    "layers.1.mlp_conv.base_kernel": "model.safetensors",
+    "layers.1.mlp_conv.kernel_projection.weight": "model.safetensors",
+    "layers.1.mlp_conv.kernel_projection.scales": "model.safetensors",
+    "layers.1.mlp_conv.kernel_projection.biases": "model.safetensors",
+    "layers.1.mlp.gate_proj.weight": "model.safetensors",
+    "layers.1.mlp.gate_proj.scales": "model.safetensors",
+    "layers.1.mlp.gate_proj.biases": "model.safetensors",
+    "layers.1.mlp.up_proj.weight": "model.safetensors",
+    "layers.1.mlp.up_proj.scales": "model.safetensors",
+    "layers.1.mlp.up_proj.biases": "model.safetensors",
+    "layers.1.mlp.down_proj.weight": "model.safetensors",
+    "layers.1.mlp.down_proj.scales": "model.safetensors",
+    "layers.1.mlp.down_proj.biases": "model.safetensors",
+    "layers.2.input_layernorm.weight": "model.safetensors",
+    "layers.2.attention_conv.base_kernel": "model.safetensors",
+    "layers.2.attention_conv.kernel_projection.weight": "model.safetensors",
+    "layers.2.attention_conv.kernel_projection.scales": "model.safetensors",
+    "layers.2.attention_conv.kernel_projection.biases": "model.safetensors",
+    "layers.2.self_attn.q_proj.weight": "model.safetensors",
+    "layers.2.self_attn.q_proj.scales": "model.safetensors",
+    "layers.2.self_attn.q_proj.biases": "model.safetensors",
+    "layers.2.self_attn.k_proj.weight": "model.safetensors",
+    "layers.2.self_attn.k_proj.scales": "model.safetensors",
+    "layers.2.self_attn.k_proj.biases": "model.safetensors",
+    "layers.2.self_attn.v_proj.weight": "model.safetensors",
+    "layers.2.self_attn.v_proj.scales": "model.safetensors",
+    "layers.2.self_attn.v_proj.biases": "model.safetensors",
+    "layers.2.self_attn.q_norm.weight": "model.safetensors",
+    "layers.2.self_attn.k_norm.weight": "model.safetensors",
+    "layers.2.self_attn.o_proj.weight": "model.safetensors",
+    "layers.2.self_attn.o_proj.scales": "model.safetensors",
+    "layers.2.self_attn.o_proj.biases": "model.safetensors",
+    "layers.2.post_attention_layernorm.weight": "model.safetensors",
+    "layers.2.mlp_conv.base_kernel": "model.safetensors",
+    "layers.2.mlp_conv.kernel_projection.weight": "model.safetensors",
+    "layers.2.mlp_conv.kernel_projection.scales": "model.safetensors",
+    "layers.2.mlp_conv.kernel_projection.biases": "model.safetensors",
+    "layers.2.mlp.gate_proj.weight": "model.safetensors",
+    "layers.2.mlp.gate_proj.scales": "model.safetensors",
+    "layers.2.mlp.gate_proj.biases": "model.safetensors",
+    "layers.2.mlp.up_proj.weight": "model.safetensors",
+    "layers.2.mlp.up_proj.scales": "model.safetensors",
+    "layers.2.mlp.up_proj.biases": "model.safetensors",
+    "layers.2.mlp.down_proj.weight": "model.safetensors",
+    "layers.2.mlp.down_proj.scales": "model.safetensors",
+    "layers.2.mlp.down_proj.biases": "model.safetensors",
+    "layers.3.input_layernorm.weight": "model.safetensors",
+    "layers.3.attention_conv.base_kernel": "model.safetensors",
+    "layers.3.attention_conv.kernel_projection.weight": "model.safetensors",
+    "layers.3.attention_conv.kernel_projection.scales": "model.safetensors",
+    "layers.3.attention_conv.kernel_projection.biases": "model.safetensors",
+    "layers.3.self_attn.q_proj.weight": "model.safetensors",
+    "layers.3.self_attn.q_proj.scales": "model.safetensors",
+    "layers.3.self_attn.q_proj.biases": "model.safetensors",
+    "layers.3.self_attn.k_proj.weight": "model.safetensors",
+    "layers.3.self_attn.k_proj.scales": "model.safetensors",
+    "layers.3.self_attn.k_proj.biases": "model.safetensors",
+    "layers.3.self_attn.v_proj.weight": "model.safetensors",
+    "layers.3.self_attn.v_proj.scales": "model.safetensors",
+    "layers.3.self_attn.v_proj.biases": "model.safetensors",
+    "layers.3.self_attn.q_norm.weight": "model.safetensors",
+    "layers.3.self_attn.k_norm.weight": "model.safetensors",
+    "layers.3.self_attn.o_proj.weight": "model.safetensors",
+    "layers.3.self_attn.o_proj.scales": "model.safetensors",
+    "layers.3.self_attn.o_proj.biases": "model.safetensors",
+    "layers.3.post_attention_layernorm.weight": "model.safetensors",
+    "layers.3.mlp_conv.base_kernel": "model.safetensors",
+    "layers.3.mlp_conv.kernel_projection.weight": "model.safetensors",
+    "layers.3.mlp_conv.kernel_projection.scales": "model.safetensors",
+    "layers.3.mlp_conv.kernel_projection.biases": "model.safetensors",
+    "layers.3.mlp.gate_proj.weight": "model.safetensors",
+    "layers.3.mlp.gate_proj.scales": "model.safetensors",
+    "layers.3.mlp.gate_proj.biases": "model.safetensors",
+    "layers.3.mlp.up_proj.weight": "model.safetensors",
+    "layers.3.mlp.up_proj.scales": "model.safetensors",
+    "layers.3.mlp.up_proj.biases": "model.safetensors",
+    "layers.3.mlp.down_proj.weight": "model.safetensors",
+    "layers.3.mlp.down_proj.scales": "model.safetensors",
+    "layers.3.mlp.down_proj.biases": "model.safetensors",
+    "layers.4.input_layernorm.weight": "model.safetensors",
+    "layers.4.attention_conv.base_kernel": "model.safetensors",
+    "layers.4.attention_conv.kernel_projection.weight": "model.safetensors",
+    "layers.4.attention_conv.kernel_projection.scales": "model.safetensors",
+    "layers.4.attention_conv.kernel_projection.biases": "model.safetensors",
+    "layers.4.self_attn.q_proj.weight": "model.safetensors",
+    "layers.4.self_attn.q_proj.scales": "model.safetensors",
+    "layers.4.self_attn.q_proj.biases": "model.safetensors",
+    "layers.4.self_attn.k_proj.weight": "model.safetensors",
+    "layers.4.self_attn.k_proj.scales": "model.safetensors",
+    "layers.4.self_attn.k_proj.biases": "model.safetensors",
+    "layers.4.self_attn.v_proj.weight": "model.safetensors",
+    "layers.4.self_attn.v_proj.scales": "model.safetensors",
+    "layers.4.self_attn.v_proj.biases": "model.safetensors",
+    "layers.4.self_attn.q_norm.weight": "model.safetensors",
+    "layers.4.self_attn.k_norm.weight": "model.safetensors",
+    "layers.4.self_attn.o_proj.weight": "model.safetensors",
+    "layers.4.self_attn.o_proj.scales": "model.safetensors",
+    "layers.4.self_attn.o_proj.biases": "model.safetensors",
+    "layers.4.post_attention_layernorm.weight": "model.safetensors",
+    "layers.4.mlp_conv.base_kernel": "model.safetensors",
+    "layers.4.mlp_conv.kernel_projection.weight": "model.safetensors",
+    "layers.4.mlp_conv.kernel_projection.scales": "model.safetensors",
+    "layers.4.mlp_conv.kernel_projection.biases": "model.safetensors",
+    "layers.4.mlp.gate_proj.weight": "model.safetensors",
+    "layers.4.mlp.gate_proj.scales": "model.safetensors",
+    "layers.4.mlp.gate_proj.biases": "model.safetensors",
+    "layers.4.mlp.up_proj.weight": "model.safetensors",
+    "layers.4.mlp.up_proj.scales": "model.safetensors",
+    "layers.4.mlp.up_proj.biases": "model.safetensors",
+    "layers.4.mlp.down_proj.weight": "model.safetensors",
+    "layers.4.mlp.down_proj.scales": "model.safetensors",
+    "layers.4.mlp.down_proj.biases": "model.safetensors",
+    "layers.5.input_layernorm.weight": "model.safetensors",
+    "layers.5.attention_conv.base_kernel": "model.safetensors",
+    "layers.5.attention_conv.kernel_projection.weight": "model.safetensors",
+    "layers.5.attention_conv.kernel_projection.scales": "model.safetensors",
+    "layers.5.attention_conv.kernel_projection.biases": "model.safetensors",
+    "layers.5.self_attn.q_proj.weight": "model.safetensors",
+    "layers.5.self_attn.q_proj.scales": "model.safetensors",
+    "layers.5.self_attn.q_proj.biases": "model.safetensors",
+    "layers.5.self_attn.k_proj.weight": "model.safetensors",
+    "layers.5.self_attn.k_proj.scales": "model.safetensors",
+    "layers.5.self_attn.k_proj.biases": "model.safetensors",
+    "layers.5.self_attn.v_proj.weight": "model.safetensors",
+    "layers.5.self_attn.v_proj.scales": "model.safetensors",
+    "layers.5.self_attn.v_proj.biases": "model.safetensors",
+    "layers.5.self_attn.q_norm.weight": "model.safetensors",
+    "layers.5.self_attn.k_norm.weight": "model.safetensors",
+    "layers.5.self_attn.o_proj.weight": "model.safetensors",
+    "layers.5.self_attn.o_proj.scales": "model.safetensors",
+    "layers.5.self_attn.o_proj.biases": "model.safetensors",
+    "layers.5.post_attention_layernorm.weight": "model.safetensors",
+    "layers.5.mlp_conv.base_kernel": "model.safetensors",
+    "layers.5.mlp_conv.kernel_projection.weight": "model.safetensors",
+    "layers.5.mlp_conv.kernel_projection.scales": "model.safetensors",
+    "layers.5.mlp_conv.kernel_projection.biases": "model.safetensors",
+    "layers.5.mlp.gate_proj.weight": "model.safetensors",
+    "layers.5.mlp.gate_proj.scales": "model.safetensors",
+    "layers.5.mlp.gate_proj.biases": "model.safetensors",
+    "layers.5.mlp.up_proj.weight": "model.safetensors",
+    "layers.5.mlp.up_proj.scales": "model.safetensors",
+    "layers.5.mlp.up_proj.biases": "model.safetensors",
+    "layers.5.mlp.down_proj.weight": "model.safetensors",
+    "layers.5.mlp.down_proj.scales": "model.safetensors",
+    "layers.5.mlp.down_proj.biases": "model.safetensors",
+    "fc.weight": "model.safetensors",
+    "fc.scales": "model.safetensors",
+    "fc.biases": "model.safetensors",
+    "hidden_norm.weight": "model.safetensors",
+    "norm.weight": "model.safetensors",
+    "candidate_selector.hidden_projection.weight": "model.safetensors",
+    "candidate_selector.hidden_projection.scales": "model.safetensors",
+    "candidate_selector.hidden_projection.biases": "model.safetensors",
+    "candidate_selector.predecessor_codebook": "model.safetensors",
+    "candidate_selector.successor_codebook": "model.safetensors"
+  }
+}

source.json

@@ -0,0 +1,55 @@
+{
+  "bundle_repo": "incoai/Qwen3.6-35B-A3B-Splash",
+  "bundle_revision": "0f4714b2db37b5f3c42a10de07281e74f88e4adc",
+  "target": "Qwen3.6-35B-A3B",
+  "original_draft": {
+    "repo_id": "incoai/Qwen3.6-35B-A3B-DFlash2",
+    "revision": "8e713508f0bb02f03b5cb5cabbc8d9604f924be2"
+  },
+  "tensors": 208,
+  "requantized_tensors": 0,
+  "source_bits": 4,
+  "output_bits": 4,
+  "artifacts": [
+    {
+      "path": "layout.json",
+      "sha256": "2e67217507b9b13c613a4ea6deb2cb5bc937547a520bf79a1a4a900db62860d7",
+      "size": 255855
+    },
+    {
+      "path": "draft/layer-0.bin",
+      "sha256": "6e49b64d9448bf9965826d6c92badcd40c3321a7b86066c25b7c30852cc4c5b9",
+      "size": 34324480
+    },
+    {
+      "path": "draft/layer-1.bin",
+      "sha256": "755ef7fcf8107c3a2cd5bd24e96ad726aa06174f72d628413e32fa7b7d8ffdda",
+      "size": 34324480
+    },
+    {
+      "path": "draft/layer-2.bin",
+      "sha256": "126cedd11a4b13febc299df0101a096dd6f6761e86bc0ac5db1dc6f2f78c31c1",
+      "size": 34324480
+    },
+    {
+      "path": "draft/layer-3.bin",
+      "sha256": "d96490a76307408fc2d2e42d86481f3061b04a2289193d2e8face84531b68f9e",
+      "size": 34324480
+    },
+    {
+      "path": "draft/layer-4.bin",
+      "sha256": "92103acb13eb656fc46220f07bdc4f1da0233fed8b27ab5f2877544f1147bd93",
+      "size": 34324480
+    },
+    {
+      "path": "draft/layer-5.bin",
+      "sha256": "2de274812de6d8cdf8bdfb2b6edd43da1b7b4b82e5ffe7316e36d6d50404600d",
+      "size": 34324480
+    },
+    {
+      "path": "draft/model.bin",
+      "sha256": "532f9ca34fd57b0d042f79232bea70770c28e23d69eeb2293a46e9640959926f",
+      "size": 273498112
+    }
+  ]
+}