Upload folder using huggingface_hub

.gitattributes

@@ -1,35 +1,3 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
+*.safetensors 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 [yyyy] [name of copyright owner]
+
+   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 +1,146 @@
+---
+license: apache-2.0
+library_name: vllm
+inference: false
+base_model: CohereLabs/North-Mini-Code-1.0-w4a16
+tags:
+- north-mini-code
+- speculative-decoding
+- draft-model
+- dflash
+- code
+---
+
+# North Mini Code 1.0 DFlash
+
+This is a research-preview **auxiliary draft checkpoint** for speculative decoding with `CohereLabs/North-Mini-Code-1.0-w4a16`.
+It is **not** a standalone language model and it cannot generate text without the North verifier/target model.
+It will likely also work with `CohereLabs/North-Mini-Code-1.0-fp8` with slightly lower acceptance rates.
+
+## Training
+
+This DFlash draft model was trained on 10,000 Magicoder prompts with on-policy supervision from North Mini Code.
+
+## Important Notes
+
+- not a base model
+- not a fine-tuning target for standalone inference
+- not a correctness guarantee
+- not byte-parity with target-only greedy decoding
+
+## Architecture
+
+- speculator type: `DFlashDraftModel`
+- draft layers: 5 Qwen3 sliding-window layers
+- hidden size: 2048
+- attention heads: 32
+- key/value heads: 4
+- head dim: 128
+- MLP intermediate size: 768
+- sliding window: 2048
+- draft vocabulary: 32,000
+- target vocabulary: 262,144
+- block size: 8
+- `sample_from_anchor`: `false`
+- auxiliary target hidden-state taps: layers `[2, 24, 46]`
+- tensors: 62
+- serialized tensor elements: 733,274,624
+- BF16 parameters: 732,980,480
+- selected weight hash: `0ac5964c48003f2eab08c4691357dedc11227d88302ea7c76fc47aaddab6d5b9`
+
+Largest tensors include the target embedding matrix, `lm_head.weight`, and the draft `fc.weight` projection.
+The tensor inventory is recorded in `tensor_info.json`.
+
+## Training data and supervision
+
+- prompt dataset: `ise-uiuc/Magicoder-Evol-Instruct-110K`
+- license: Apache-2.0
+- training rows: 10,000
+- selected rows: 0-499, 600-5099, and 6100-11099
+- locked holdout: rows 500-599, never trained
+- supervision: on-policy responses and target hidden states generated once from `CohereLabs/North-Mini-Code-1.0-w4a16`
+- response cap: 2,048 tokens
+- target layers used for supervision: `[2, 24, 46]`
+- later acceptance-mined continuation data: not included in this release checkpoint
+
+Training metadata is recorded in `training_metadata.json`.
+
+## Matched GB10 benchmarks
+
+These numbers come from the same matched serving contract on a GB10 (DGX Spark) machine running Marlin (which is suboptimal but predictable).
+Compare the rows **within the same host and contract only**.
+These absolute token/s values are not representative of maximum performance, simply a demonstration that the draft model works. :)
+
+| Contract | Target-only | DFlash K3 | DFlash / target | DSpark K4 | DSpark / target |
+| --- | ---: | ---: | ---: | ---: | ---: |
+| C1 | 39.9129 tok/s | 75.5106 tok/s | 1.8919x | 79.7341 tok/s | 1.9977x |
+| C2 | 78.9486 tok/s | 121.5232 tok/s | 1.5393x | 127.6174 tok/s | 1.6165x |
+
+| Model | C1 EAL | C1 draft acceptance | C2 EAL | C2 draft acceptance |
+| --- | ---: | ---: | ---: | ---: |
+| DFlash K3 | 2.2947 | 43.16% | 2.2856 | 42.85% |
+| DSpark K4 | 2.4800 | 37.00% | 2.4779 | 36.95% |
+
+Expected acceptance length (EAL) is the mean emitted tokens per speculative verification step, including the target bonus token.
+
+## Additional result: NVIDIA RTX 3090
+
+DFlash was also tested on an NVIDIA RTX 3090 under the same family of matched conditions.
+That result is specific to DFlash; do not infer DSpark RTX 3090 portability from it.
+
+- target-only: 110.2714 tok/s
+- DFlash K3: 153.7188 tok/s
+- official Eagle K3: 77.9583 tok/s
+
+Also being realistic, you wouldn't try to serve this on a single 3090 anyway the model weights leave no room for context.
+
+## Default proposal depth
+
+Default proposal depth is **K3**.
+That is the selected deployment setting in `config.json` and the configuration used for the release evidence.
+More speculative tokens hit diminishing returns past position 3 for this DFlash drafter. You're likely to see the best speed here.
+
+## Runtime boundary
+
+This checkpoint is served as the **top-level model** because `config.json` already embeds the verifier reference.
+Use it only with the companion North runtime, published at https://github.com/sdougbrown/north-mini-code-draft-runtime; this card does not describe a separate target-model `--speculative_config` deployment. The companion is a thin overlay on official vLLM 0.27.1 carrying PRs #49819 and #50937 (Cohere2MoE auxiliary hidden states, and an expert-bias loading fix), published as `ghcr.io/sdougbrown/north-mini-code-runtime:v0.27.1-49819-50937`.
+
+```bash
+export DRAFT_MODEL="${DRAFT_MODEL:?set this to the downloaded DFlash directory or Hub model ID}"
+export VLLM_USE_V2_MODEL_RUNNER=1
+vllm serve "${DRAFT_MODEL}" \
+  --tensor-parallel-size 1 \
+  --max-model-len 320000 \
+  --tool-call-parser cohere_command4 \
+  --reasoning-parser cohere_command4 \
+  --enable-auto-tool-choice
+```
+
+## Limitations
+
+- 32K draft vocabulary, not the 262,144-token target vocabulary
+- target-dependent: cannot run standalone
+- quantized greedy outputs are not guaranteed to match target-only greedy byte-for-byte
+- throughput and acceptance do not establish correctness or response quality
+- absolute throughput is host-specific
+
+## References
+
+- North base model: https://huggingface.co/CohereLabs/North-Mini-Code-1.0-w4a16
+- Magicoder dataset: https://huggingface.co/datasets/ise-uiuc/Magicoder-Evol-Instruct-110K
+- Companion North runtime: https://github.com/sdougbrown/north-mini-code-draft-runtime
+- Companion image: `ghcr.io/sdougbrown/north-mini-code-runtime:v0.27.1-49819-50937`
+- Official Eagle card: https://huggingface.co/CohereLabs/North-Mini-Code-1.0-eagle
+- Speculators: pinned commit `f7ec34182826bc89934ce710283421778022b74d`, version `0.6.0`
+
+## Files in this repo
+
+- `README.md`
+- `config.json`
+- `config.py`
+- `model.safetensors`
+- `tensor_info.json`
+- `training_metadata.json`
+- `SHA256SUMS`
+- `LICENSE`
+- `.gitattributes`

SHA256SUMS

@@ -0,0 +1,8 @@
+078e723fbb0c75ae4271d24636729e6cea73c59781b0ca8a041a7303f2451513  config.json
+4fcc12b665f4cb711021b9ec8a490f30bc05201366dda8af90c4ff2dd0c31572  config.py
+f5759376846057560e61ec2111f74f4f4d5904820c100541b935c244ea0c1396  .gitattributes
+cfc7749b96f63bd31c3c42b5c471bf756814053e847c10f3eb003417bc523d30  LICENSE
+0ac5964c48003f2eab08c4691357dedc11227d88302ea7c76fc47aaddab6d5b9  model.safetensors
+e90afc38ed2fe3b8966eab4cd201bc2e41de120fbdb8b735dd45808e360ab969  README.md
+307d55e820b8d1b61a031ec8c9d31b42c7612a53f1b9898cc290c72d91ab6366  tensor_info.json
+38be2119ec57a3871b1c706645a9deafa1be4b354157e71c6f4df2832ed71488  training_metadata.json

config.json

@@ -0,0 +1,77 @@
+{
+  "architectures": [
+    "DFlashDraftModel"
+  ],
+  "auto_map": {
+    "": "config.DFlashSpeculatorConfig"
+  },
+  "aux_hidden_state_layer_ids": [
+    2,
+    24,
+    46
+  ],
+  "block_size": 8,
+  "draft_vocab_size": 32000,
+  "dtype": "bfloat16",
+  "mask_token_id": 1,
+  "sample_from_anchor": false,
+  "sliding_window_non_causal": false,
+  "speculators_config": {
+    "algorithm": "dflash",
+    "default_proposal_method": "greedy",
+    "proposal_methods": [
+      {
+        "accept_tolerance": 0.0,
+        "proposal_type": "greedy",
+        "speculative_tokens": 3,
+        "verifier_accept_k": 1
+      }
+    ],
+    "verifier": {
+      "architectures": [
+        "Cohere2MoeForCausalLM"
+      ],
+      "name_or_path": "CohereLabs/North-Mini-Code-1.0-w4a16"
+    }
+  },
+  "speculators_model_type": "dflash",
+  "speculators_version": "0.6.0",
+  "target_hidden_size": null,
+  "tie_word_embeddings": false,
+  "transformer_layer_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": null,
+    "eos_token_id": null,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 2048,
+    "initializer_range": 0.02,
+    "intermediate_size": 768,
+    "layer_types": [
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention"
+    ],
+    "max_position_embeddings": 500000,
+    "max_window_layers": 28,
+    "model_type": "qwen3",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 5,
+    "num_key_value_heads": 4,
+    "pad_token_id": null,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "rope_theta": 50000,
+      "rope_type": "default"
+    },
+    "sliding_window": 2048,
+    "tie_word_embeddings": false,
+    "use_cache": true,
+    "use_sliding_window": true,
+    "vocab_size": 262144
+  },
+  "transformers_version": "5.13.1"
+}

config.py

@@ -0,0 +1,105 @@
+from typing import Any, Literal
+
+from pydantic import Field, field_serializer, field_validator
+from transformers import AutoConfig, PretrainedConfig
+from transformers.models.qwen3.modeling_qwen3 import (
+    Qwen3Config,
+)
+
+from speculators import SpeculatorModelConfig
+
+__all__ = [
+    "DFlashSpeculatorConfig",
+]
+
+
+@SpeculatorModelConfig.register("dflash")
+class DFlashSpeculatorConfig(SpeculatorModelConfig):
+    """
+    Configuration for DFlash speculator with vocabulary mapping.
+
+    DFlash features vocabulary mapping between the 32K draft vocabulary and
+    the 262,144-token target vocabulary, enabling reduced-vocabulary speculation.
+
+    :param transformer_layer_config: Configuration for the transformer decoder layer
+    :param draft_vocab_size: Size of draft model vocabulary for speculation
+    """
+
+    speculators_model_type: Literal["dflash"] = "dflash"
+    architectures: list[str] = Field(
+        default_factory=lambda: ["DFlashSpeculator"],
+        description="Model architectures that can load these weights",
+    )
+
+    transformer_layer_config: PretrainedConfig = Field(
+        default_factory=Qwen3Config,
+        description="Configuration for the transformer decoder layer",
+    )
+
+    draft_vocab_size: int = Field(
+        default=32000,
+        description="Size of draft model vocabulary for speculation",
+    )
+
+    block_size: int = Field(
+        default=8,
+        description=(
+            "Default size of the draft block predicted with a forward pass of the model"
+        ),
+    )
+
+    target_hidden_size: int | None = Field(
+        default=None,
+        description="Hidden size of the target model (if different from draft model)",
+    )
+
+    aux_hidden_state_layer_ids: list[int] | None = Field(
+        default=None,
+        description="Layer IDs of the DFlash auxiliary hidden state layers",
+    )
+
+    mask_token_id: int | None = Field(
+        default=None,
+        description="Token ID used for masking",
+    )
+
+    sliding_window_non_causal: bool = Field(
+        default=False,
+        description="Use non-causal (bidirectional) masking within draft blocks for "
+        "sliding window attention layers. Full attention layers are always "
+        "bidirectional.",
+    )
+
+    sample_from_anchor: bool = Field(
+        default=False,
+        description=(
+            "Whether to sample from the anchor position. "
+            "False: anchor is the bonus token, only mask tokens predict "
+            "(block_size-1 speculative tokens). "
+            "True: sample from anchor and all mask positions "
+            "(block_size speculative tokens). "
+        ),
+    )
+
+    @field_serializer("transformer_layer_config")
+    def serialize_transformer_config(self, value: PretrainedConfig) -> dict:
+        """Serialize transformer config to dict."""
+        return value.to_diff_dict()
+
+    @field_validator("transformer_layer_config", mode="before")
+    @classmethod
+    def validate_transformer_config(cls, value: Any) -> PretrainedConfig:
+        """Validate and convert transformer config."""
+        if isinstance(value, dict):
+            config_class: type[PretrainedConfig] = Qwen3Config
+            if "model_type" in value:
+                config_class = AutoConfig.for_model(
+                    model_type=value["model_type"]
+                ).__class__
+            return config_class(**value)
+        return value
+
+    @property
+    def target_vocab_size(self) -> int:
+        """Get target vocabulary size from transformer config."""
+        return self.transformer_layer_config.vocab_size

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ac5964c48003f2eab08c4691357dedc11227d88302ea7c76fc47aaddab6d5b9
+size 1466485696

tensor_info.json

@@ -0,0 +1,741 @@
+{
+  "algorithm": "dflash",
+  "base_model": "CohereLabs/North-Mini-Code-1.0-w4a16",
+  "checkpoint_epoch": 4,
+  "default_speculative_tokens": 3,
+  "largest_tensors": [
+    {
+      "dtype": "BF16",
+      "name": "embed_tokens.weight",
+      "parameters": 536870912,
+      "shape": [
+        262144,
+        2048
+      ]
+    },
+    {
+      "dtype": "BF16",
+      "name": "lm_head.weight",
+      "parameters": 65536000,
+      "shape": [
+        32000,
+        2048
+      ]
+    },
+    {
+      "dtype": "BF16",
+      "name": "fc.weight",
+      "parameters": 12582912,
+      "shape": [
+        2048,
+        6144
+      ]
+    },
+    {
+      "dtype": "BF16",
+      "name": "layers.0.self_attn.o_proj.weight",
+      "parameters": 8388608,
+      "shape": [
+        2048,
+        4096
+      ]
+    },
+    {
+      "dtype": "BF16",
+      "name": "layers.0.self_attn.q_proj.weight",
+      "parameters": 8388608,
+      "shape": [
+        4096,
+        2048
+      ]
+    },
+    {
+      "dtype": "BF16",
+      "name": "layers.1.self_attn.o_proj.weight",
+      "parameters": 8388608,
+      "shape": [
+        2048,
+        4096
+      ]
+    },
+    {
+      "dtype": "BF16",
+      "name": "layers.1.self_attn.q_proj.weight",
+      "parameters": 8388608,
+      "shape": [
+        4096,
+        2048
+      ]
+    },
+    {
+      "dtype": "BF16",
+      "name": "layers.2.self_attn.o_proj.weight",
+      "parameters": 8388608,
+      "shape": [
+        2048,
+        4096
+      ]
+    },
+    {
+      "dtype": "BF16",
+      "name": "layers.2.self_attn.q_proj.weight",
+      "parameters": 8388608,
+      "shape": [
+        4096,
+        2048
+      ]
+    },
+    {
+      "dtype": "BF16",
+      "name": "layers.3.self_attn.o_proj.weight",
+      "parameters": 8388608,
+      "shape": [
+        2048,
+        4096
+      ]
+    },
+    {
+      "dtype": "BF16",
+      "name": "layers.3.self_attn.q_proj.weight",
+      "parameters": 8388608,
+      "shape": [
+        4096,
+        2048
+      ]
+    },
+    {
+      "dtype": "BF16",
+      "name": "layers.4.self_attn.o_proj.weight",
+      "parameters": 8388608,
+      "shape": [
+        2048,
+        4096
+      ]
+    },
+    {
+      "dtype": "BF16",
+      "name": "layers.4.self_attn.q_proj.weight",
+      "parameters": 8388608,
+      "shape": [
+        4096,
+        2048
+      ]
+    },
+    {
+      "dtype": "BF16",
+      "name": "layers.0.mlp.down_proj.weight",
+      "parameters": 1572864,
+      "shape": [
+        2048,
+        768
+      ]
+    },
+    {
+      "dtype": "BF16",
+      "name": "layers.0.mlp.gate_proj.weight",
+      "parameters": 1572864,
+      "shape": [
+        768,
+        2048
+      ]
+    },
+    {
+      "dtype": "BF16",
+      "name": "layers.0.mlp.up_proj.weight",
+      "parameters": 1572864,
+      "shape": [
+        768,
+        2048
+      ]
+    },
+    {
+      "dtype": "BF16",
+      "name": "layers.1.mlp.down_proj.weight",
+      "parameters": 1572864,
+      "shape": [
+        2048,
+        768
+      ]
+    },
+    {
+      "dtype": "BF16",
+      "name": "layers.1.mlp.gate_proj.weight",
+      "parameters": 1572864,
+      "shape": [
+        768,
+        2048
+      ]
+    },
+    {
+      "dtype": "BF16",
+      "name": "layers.1.mlp.up_proj.weight",
+      "parameters": 1572864,
+      "shape": [
+        768,
+        2048
+      ]
+    },
+    {
+      "dtype": "BF16",
+      "name": "layers.2.mlp.down_proj.weight",
+      "parameters": 1572864,
+      "shape": [
+        2048,
+        768
+      ]
+    }
+  ],
+  "model_family": "North Mini Code speculative draft",
+  "model_file": {
+    "name": "model.safetensors",
+    "safetensors_metadata": {
+      "format": "pt"
+    },
+    "sha256": "0ac5964c48003f2eab08c4691357dedc11227d88302ea7c76fc47aaddab6d5b9",
+    "size_bytes": 1466485696
+  },
+  "parameter_count": 733274624,
+  "parameters_by_dtype": {
+    "BF16": 732980480,
+    "BOOL": 262144,
+    "I64": 32000
+  },
+  "schema_version": 1,
+  "tensor_count": 62,
+  "tensors": [
+    {
+      "dtype": "I64",
+      "name": "d2t",
+      "parameters": 32000,
+      "shape": [
+        32000
+      ]
+    },
+    {
+      "dtype": "BF16",
+      "name": "embed_tokens.weight",
+      "parameters": 536870912,
+      "shape": [
+        262144,
+        2048
+      ]
+    },
+    {
+      "dtype": "BF16",
+      "name": "fc.weight",
+      "parameters": 12582912,
+      "shape": [
+        2048,
+        6144
+      ]
+    },
+    {
+      "dtype": "BF16",
+      "name": "hidden_norm.weight",
+      "parameters": 2048,
+      "shape": [
+        2048
+      ]
+    },
+    {
+      "dtype": "BF16",
+      "name": "layers.0.input_layernorm.weight",
+      "parameters": 2048,
+      "shape": [
+        2048
+      ]
+    },
+    {
+      "dtype": "BF16",
+      "name": "layers.0.mlp.down_proj.weight",
+      "parameters": 1572864,
+      "shape": [
+        2048,
+        768
+      ]
+    },
+    {
+      "dtype": "BF16",
+      "name": "layers.0.mlp.gate_proj.weight",
+      "parameters": 1572864,
+      "shape": [
+        768,
+        2048
+      ]
+    },
+    {
+      "dtype": "BF16",
+      "name": "layers.0.mlp.up_proj.weight",
+      "parameters": 1572864,
+      "shape": [
+        768,
+        2048
+      ]
+    },
+    {
+      "dtype": "BF16",
+      "name": "layers.0.post_attention_layernorm.weight",
+      "parameters": 2048,
+      "shape": [
+        2048
+      ]
+    },
+    {
+      "dtype": "BF16",
+      "name": "layers.0.self_attn.k_norm.weight",
+      "parameters": 128,
+      "shape": [
+        128
+      ]
+    },
+    {
+      "dtype": "BF16",
+      "name": "layers.0.self_attn.k_proj.weight",
+      "parameters": 1048576,
+      "shape": [
+        512,
+        2048
+      ]
+    },
+    {
+      "dtype": "BF16",
+      "name": "layers.0.self_attn.o_proj.weight",
+      "parameters": 8388608,
+      "shape": [
+        2048,
+        4096
+      ]
+    },
+    {
+      "dtype": "BF16",
+      "name": "layers.0.self_attn.q_norm.weight",
+      "parameters": 128,
+      "shape": [
+        128
+      ]
+    },
+    {
+      "dtype": "BF16",
+      "name": "layers.0.self_attn.q_proj.weight",
+      "parameters": 8388608,
+      "shape": [
+        4096,
+        2048
+      ]
+    },
+    {
+      "dtype": "BF16",
+      "name": "layers.0.self_attn.v_proj.weight",
+      "parameters": 1048576,
+      "shape": [
+        512,
+        2048
+      ]
+    },
+    {
+      "dtype": "BF16",
+      "name": "layers.1.input_layernorm.weight",
+      "parameters": 2048,
+      "shape": [
+        2048
+      ]
+    },
+    {
+      "dtype": "BF16",
+      "name": "layers.1.mlp.down_proj.weight",
+      "parameters": 1572864,
+      "shape": [
+        2048,
+        768
+      ]
+    },
+    {
+      "dtype": "BF16",
+      "name": "layers.1.mlp.gate_proj.weight",
+      "parameters": 1572864,
+      "shape": [
+        768,
+        2048
+      ]
+    },
+    {
+      "dtype": "BF16",
+      "name": "layers.1.mlp.up_proj.weight",
+      "parameters": 1572864,
+      "shape": [
+        768,
+        2048
+      ]
+    },
+    {
+      "dtype": "BF16",
+      "name": "layers.1.post_attention_layernorm.weight",
+      "parameters": 2048,
+      "shape": [
+        2048
+      ]
+    },
+    {
+      "dtype": "BF16",
+      "name": "layers.1.self_attn.k_norm.weight",
+      "parameters": 128,
+      "shape": [
+        128
+      ]
+    },
+    {
+      "dtype": "BF16",
+      "name": "layers.1.self_attn.k_proj.weight",
+      "parameters": 1048576,
+      "shape": [
+        512,
+        2048
+      ]
+    },
+    {
+      "dtype": "BF16",
+      "name": "layers.1.self_attn.o_proj.weight",
+      "parameters": 8388608,
+      "shape": [
+        2048,
+        4096
+      ]
+    },
+    {
+      "dtype": "BF16",
+      "name": "layers.1.self_attn.q_norm.weight",
+      "parameters": 128,
+      "shape": [
+        128
+      ]
+    },
+    {
+      "dtype": "BF16",
+      "name": "layers.1.self_attn.q_proj.weight",
+      "parameters": 8388608,
+      "shape": [
+        4096,
+        2048
+      ]
+    },
+    {
+      "dtype": "BF16",
+      "name": "layers.1.self_attn.v_proj.weight",
+      "parameters": 1048576,
+      "shape": [
+        512,
+        2048
+      ]
+    },
+    {
+      "dtype": "BF16",
+      "name": "layers.2.input_layernorm.weight",
+      "parameters": 2048,
+      "shape": [
+        2048
+      ]
+    },
+    {
+      "dtype": "BF16",
+      "name": "layers.2.mlp.down_proj.weight",
+      "parameters": 1572864,
+      "shape": [
+        2048,
+        768
+      ]
+    },
+    {
+      "dtype": "BF16",
+      "name": "layers.2.mlp.gate_proj.weight",
+      "parameters": 1572864,
+      "shape": [
+        768,
+        2048
+      ]
+    },
+    {
+      "dtype": "BF16",
+      "name": "layers.2.mlp.up_proj.weight",
+      "parameters": 1572864,
+      "shape": [
+        768,
+        2048
+      ]
+    },
+    {
+      "dtype": "BF16",
+      "name": "layers.2.post_attention_layernorm.weight",
+      "parameters": 2048,
+      "shape": [
+        2048
+      ]
+    },
+    {
+      "dtype": "BF16",
+      "name": "layers.2.self_attn.k_norm.weight",
+      "parameters": 128,
+      "shape": [
+        128
+      ]
+    },
+    {
+      "dtype": "BF16",
+      "name": "layers.2.self_attn.k_proj.weight",
+      "parameters": 1048576,
+      "shape": [
+        512,
+        2048
+      ]
+    },
+    {
+      "dtype": "BF16",
+      "name": "layers.2.self_attn.o_proj.weight",
+      "parameters": 8388608,
+      "shape": [
+        2048,
+        4096
+      ]
+    },
+    {
+      "dtype": "BF16",
+      "name": "layers.2.self_attn.q_norm.weight",
+      "parameters": 128,
+      "shape": [
+        128
+      ]
+    },
+    {
+      "dtype": "BF16",
+      "name": "layers.2.self_attn.q_proj.weight",
+      "parameters": 8388608,
+      "shape": [
+        4096,
+        2048
+      ]
+    },
+    {
+      "dtype": "BF16",
+      "name": "layers.2.self_attn.v_proj.weight",
+      "parameters": 1048576,
+      "shape": [
+        512,
+        2048
+      ]
+    },
+    {
+      "dtype": "BF16",
+      "name": "layers.3.input_layernorm.weight",
+      "parameters": 2048,
+      "shape": [
+        2048
+      ]
+    },
+    {
+      "dtype": "BF16",
+      "name": "layers.3.mlp.down_proj.weight",
+      "parameters": 1572864,
+      "shape": [
+        2048,
+        768
+      ]
+    },
+    {
+      "dtype": "BF16",
+      "name": "layers.3.mlp.gate_proj.weight",
+      "parameters": 1572864,
+      "shape": [
+        768,
+        2048
+      ]
+    },
+    {
+      "dtype": "BF16",
+      "name": "layers.3.mlp.up_proj.weight",
+      "parameters": 1572864,
+      "shape": [
+        768,
+        2048
+      ]
+    },
+    {
+      "dtype": "BF16",
+      "name": "layers.3.post_attention_layernorm.weight",
+      "parameters": 2048,
+      "shape": [
+        2048
+      ]
+    },
+    {
+      "dtype": "BF16",
+      "name": "layers.3.self_attn.k_norm.weight",
+      "parameters": 128,
+      "shape": [
+        128
+      ]
+    },
+    {
+      "dtype": "BF16",
+      "name": "layers.3.self_attn.k_proj.weight",
+      "parameters": 1048576,
+      "shape": [
+        512,
+        2048
+      ]
+    },
+    {
+      "dtype": "BF16",
+      "name": "layers.3.self_attn.o_proj.weight",
+      "parameters": 8388608,
+      "shape": [
+        2048,
+        4096
+      ]
+    },
+    {
+      "dtype": "BF16",
+      "name": "layers.3.self_attn.q_norm.weight",
+      "parameters": 128,
+      "shape": [
+        128
+      ]
+    },
+    {
+      "dtype": "BF16",
+      "name": "layers.3.self_attn.q_proj.weight",
+      "parameters": 8388608,
+      "shape": [
+        4096,
+        2048
+      ]
+    },
+    {
+      "dtype": "BF16",
+      "name": "layers.3.self_attn.v_proj.weight",
+      "parameters": 1048576,
+      "shape": [
+        512,
+        2048
+      ]
+    },
+    {
+      "dtype": "BF16",
+      "name": "layers.4.input_layernorm.weight",
+      "parameters": 2048,
+      "shape": [
+        2048
+      ]
+    },
+    {
+      "dtype": "BF16",
+      "name": "layers.4.mlp.down_proj.weight",
+      "parameters": 1572864,
+      "shape": [
+        2048,
+        768
+      ]
+    },
+    {
+      "dtype": "BF16",
+      "name": "layers.4.mlp.gate_proj.weight",
+      "parameters": 1572864,
+      "shape": [
+        768,
+        2048
+      ]
+    },
+    {
+      "dtype": "BF16",
+      "name": "layers.4.mlp.up_proj.weight",
+      "parameters": 1572864,
+      "shape": [
+        768,
+        2048
+      ]
+    },
+    {
+      "dtype": "BF16",
+      "name": "layers.4.post_attention_layernorm.weight",
+      "parameters": 2048,
+      "shape": [
+        2048
+      ]
+    },
+    {
+      "dtype": "BF16",
+      "name": "layers.4.self_attn.k_norm.weight",
+      "parameters": 128,
+      "shape": [
+        128
+      ]
+    },
+    {
+      "dtype": "BF16",
+      "name": "layers.4.self_attn.k_proj.weight",
+      "parameters": 1048576,
+      "shape": [
+        512,
+        2048
+      ]
+    },
+    {
+      "dtype": "BF16",
+      "name": "layers.4.self_attn.o_proj.weight",
+      "parameters": 8388608,
+      "shape": [
+        2048,
+        4096
+      ]
+    },
+    {
+      "dtype": "BF16",
+      "name": "layers.4.self_attn.q_norm.weight",
+      "parameters": 128,
+      "shape": [
+        128
+      ]
+    },
+    {
+      "dtype": "BF16",
+      "name": "layers.4.self_attn.q_proj.weight",
+      "parameters": 8388608,
+      "shape": [
+        4096,
+        2048
+      ]
+    },
+    {
+      "dtype": "BF16",
+      "name": "layers.4.self_attn.v_proj.weight",
+      "parameters": 1048576,
+      "shape": [
+        512,
+        2048
+      ]
+    },
+    {
+      "dtype": "BF16",
+      "name": "lm_head.weight",
+      "parameters": 65536000,
+      "shape": [
+        32000,
+        2048
+      ]
+    },
+    {
+      "dtype": "BF16",
+      "name": "norm.weight",
+      "parameters": 2048,
+      "shape": [
+        2048
+      ]
+    },
+    {
+      "dtype": "BOOL",
+      "name": "t2d",
+      "parameters": 262144,
+      "shape": [
+        262144
+      ]
+    }
+  ]
+}

training_metadata.json

@@ -0,0 +1,23 @@
+{
+  "algorithm": "dflash",
+  "base_model": "CohereLabs/North-Mini-Code-1.0-w4a16",
+  "block_size": 8,
+  "checkpoint_epoch": 4,
+  "default_speculative_tokens": 3,
+  "draft_vocabulary_size": 32000,
+  "model_sha256": "0ac5964c48003f2eab08c4691357dedc11227d88302ea7c76fc47aaddab6d5b9",
+  "schema_version": 1,
+  "seed": 0,
+  "selected_continuations_included": false,
+  "source_checkpoint": "/home/douglasbrown/Serve/hosts/bitey/training/north-dflash/runs/20260807T022043Z-w4a16-native-code10000-longdecode2048/checkpoints/4",
+  "status": "selected_10k_checkpoint",
+  "target_hidden_state_layer_ids": [
+    2,
+    24,
+    46
+  ],
+  "target_supervision": "on-policy generations from CohereLabs/North-Mini-Code-1.0-w4a16",
+  "training_prompt_dataset": "ise-uiuc/Magicoder-Evol-Instruct-110K",
+  "training_prompt_dataset_license": "apache-2.0",
+  "training_rows": 10000
+}