initial commit

.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.md

@@ -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 Poolside
+
+   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 +1,123 @@
+---
+library_name: vllm
+inference: false
+extra_gated_description: >-
+  To learn more about how we process your personal data, please read our <a
+  href="https://poolside.ai/legal/privacy">Privacy Policy</a>.
+tags:
+- laguna-m.1
+- vllm
+- sglang
+- bf16
+- moe
+license: apache-2.0
+pipeline_tag: text-generation
+---
+
+<p align="center">
+  <img alt="poolside-banner" src="https://poolside.ai/assets/laguna/laguna-m1-banner.svg" width="800px">
+</p>
+
+<p align="center">
+  <a href="https://poolside.ai/blog/laguna-a-deeper-dive"><strong>Release blog post</strong></a> ·
+  <a href="https://poolside.ai/assets/laguna/laguna-m1-xs2-technical-report.pdf"><strong>Technical report</strong></a>
+</p>
+
+<br>
+
+# Laguna M.1-base
+
+Laguna M.1-base is the **pre-trained base checkpoint** for [Laguna M.1](https://huggingface.co/poolside/Laguna-M.1), a 225B total parameter Mixture-of-Experts model with 23B activated parameters per token. This is the base model **prior to post-training and reinforcement learning** — it is a text-completion model with no instruction-following, reasoning, or tool-calling behavior. For agentic coding and chat use, use the post-trained [Laguna M.1](https://huggingface.co/poolside/Laguna-M.1).
+
+> [!NOTE]
+> For details on how we trained Laguna, check out our [release blog post](https://poolside.ai/blog/laguna-a-deeper-dive) and [technical report](https://poolside.ai/assets/laguna/laguna-m1-xs2-technical-report.pdf).
+
+## Highlights
+
+* **Large sparse MoE**: Laguna M.1 is a 70-layer MoE transformer with 225B total parameters and 23B activated parameters per token
+* **High-capacity expert routing**: After 3 dense SwiGLU layers, Laguna M.1 uses 67 sparse MoE layers with 256 experts, top-k=16 routing and auxiliary-loss-free load balancing
+* **Global attention architecture**: Laguna M.1 uses global attention across all layers with 64 Q-heads, 8 KV-heads and softplus attention output gating
+* **Pre-instruct base checkpoint**: Trained with pre-training only; intended as a starting point for further training rather than direct chat/agentic use
+* **Apache 2.0 license**: Use and modify freely for commercial and non-commercial purposes
+
+---
+
+## Model overview
+
+- Stage: pre-training only (no post-training or reinforcement learning)
+- Number of parameters: 225B total with 23B activated per token
+- Optimizer: Muon
+- Layers: 70 layers with global attention
+- Experts: 256 experts with 1 shared expert; top-k=16 routing
+- Dense layers: first 3 layers are dense SwiGLU; remaining 67 layers are sparse MoE
+- Attention: 64 Q-heads, 8 KV-heads, head dimension 128, with softplus attention output gating
+- Positional encoding: RoPE with YaRN
+- Modality: text-to-text (completion)
+- Context window: 262,144 tokens
+
+## Usage
+
+Laguna M.1-base is a text-completion model. It has no chat template, reasoning, or tool-calling support — serve it without the reasoning/tool-call parsers and prompt it with raw text.
+
+### vLLM
+
+Laguna support is available in [vLLM](https://github.com/vllm-project/vllm) (v0.21.0 and later, [vllm-project/vllm#41129](https://github.com/vllm-project/vllm/pull/41129)).
+
+```shell
+pip install 'vllm>=0.21.0'
+
+vllm serve \
+    --model poolside/Laguna-M.1-base \
+    --served-model-name laguna-base
+```
+
+Query the completions endpoint from any OpenAI-compatible client:
+
+```python
+from openai import OpenAI
+
+client = OpenAI(base_url="http://localhost:8000/v1", api_key="EMPTY")
+
+completion = client.completions.create(
+    model="laguna-base",
+    prompt="def fibonacci(n):\n",
+    max_tokens=128,
+    temperature=0.7,
+)
+print(completion.choices[0].text)
+```
+
+### SGLang
+
+Laguna M.1-base is supported in SGLang via [sgl-project/sglang#28400](https://github.com/sgl-project/sglang/pull/28400). As a completion model, serve it without the reasoning/tool-call parsers. A full serving recipe will be added here.
+
+### Transformers
+
+Laguna is supported in Transformers `v5.7.0` and later ([huggingface/transformers#45673](https://github.com/huggingface/transformers/pull/45673)).
+
+> [!NOTE]
+> Laguna M.1-base is a 225B-parameter model; loading the BF16 checkpoint in Transformers requires substantial multi-GPU memory (`device_map="auto"` shards across available devices). For single-node serving, vLLM is recommended.
+
+```python
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_id = "poolside/Laguna-M.1-base"
+
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(model_id, dtype=torch.bfloat16, device_map="auto")
+
+inputs = tokenizer("def fibonacci(n):\n", return_tensors="pt").to(model.device)
+outputs = model.generate(**inputs, max_new_tokens=128, do_sample=True, temperature=0.7)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+```
+
+## License
+
+This model is licensed under the [Apache 2.0 License](https://huggingface.co/poolside/Laguna-M.1-base/blob/main/LICENSE.md).
+
+## Intended and Responsible Use 
+
+Laguna M.1 is designed for software engineering and agentic coding use cases, and you are responsible for confirming that it is appropriate for your intended application. Laguna M.1 is subject to the [Apache 2.0 License](https://huggingface.co/poolside/Laguna-M.1/blob/main/LICENSE.md), and should be used consistently with Poolside's [Acceptable Use Policy](https://poolside.ai/legal/acceptable-use-policy). We advise against circumventing Laguna M.1 safety guardrails without implementing substantially equivalent mitigations appropriate for your use case.
+
+Please report security vulnerabilities or safety concerns to [security@poolside.ai](mailto:security@poolside.ai).

config.json

@@ -0,0 +1,131 @@
+{
+  "architectures": [
+    "LagunaForCausalLM"
+  ],
+  "auto_map": {
+    "AutoConfig": "configuration_laguna.LagunaConfig",
+    "AutoModelForCausalLM": "modeling_laguna.LagunaForCausalLM"
+  },
+  "model_type": "laguna",
+  "vocab_size": 100352,
+  "hidden_size": 4096,
+  "intermediate_size": 16384,
+  "num_hidden_layers": 70,
+  "num_attention_heads": 64,
+  "num_key_value_heads": 8,
+  "head_dim": 128,
+  "max_position_embeddings": 262144,
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "rms_norm_eps": 1e-06,
+  "num_experts": 256,
+  "num_experts_per_tok": 16,
+  "moe_intermediate_size": 1024,
+  "shared_expert_intermediate_size": 1024,
+  "norm_topk_prob": true,
+  "router_aux_loss_coef": 0.00025,
+  "decoder_sparse_step": 1,
+  "mlp_only_layers": [
+    0,
+    1,
+    2
+  ],
+  "bos_token_id": 2,
+  "eos_token_id": [
+    2,
+    24
+  ],
+  "pad_token_id": 9,
+  "tie_word_embeddings": false,
+  "use_cache": true,
+  "torch_dtype": "bfloat16",
+  "gating": "per-element",
+  "sliding_window": 0,
+  "rope_parameters": {
+    "full_attention": {
+      "rope_theta": 500000.0,
+      "rope_type": "yarn",
+      "factor": 64.0,
+      "original_max_position_embeddings": 4096,
+      "beta_slow": 1.0,
+      "beta_fast": 64.0,
+      "attention_factor": 1.0,
+      "partial_rotary_factor": 1.0
+    }
+  },
+  "moe_apply_router_weight_on_input": false,
+  "partial_rotary_factor": 1.0,
+  "mlp_layer_types": [
+    "dense",
+    "dense",
+    "dense",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse"
+  ],
+  "moe_routed_scaling_factor": 1.0
+}

configuration_laguna.py

@@ -0,0 +1,213 @@
+# Copyright 2026 Poolside and the HuggingFace Inc. team. All rights reserved.
+#
+# 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.
+from typing import Any, Literal
+
+from huggingface_hub.dataclasses import strict
+
+from transformers.configuration_utils import PreTrainedConfig
+from transformers.modeling_rope_utils import RopeParameters
+from transformers.utils import auto_docstring
+
+
+@auto_docstring(checkpoint="poolside/laguna-XS.2")
+@strict
+class LagunaConfig(PreTrainedConfig):
+    r"""
+    partial_rotary_factor (`float`, *optional*):
+        Fraction of ``head_dim`` to rotate. Folded into each ``rope_parameters[layer_type]``
+        entry by ``__post_init__``.
+    num_attention_heads_per_layer (`list[int]`, *optional*):
+        Per-layer override for ``num_attention_heads``. Length must equal ``num_hidden_layers``.
+    mlp_layer_types (`list[str]`, *optional*):
+        Per-layer MLP type — ``"dense"`` or ``"sparse"``. Length must equal
+        ``num_hidden_layers``. Defaults to first layer dense, rest sparse.
+    moe_routed_scaling_factor (`float`, *optional*, defaults to 1.0):
+        Scalar applied to routed-expert output before combining with the shared-expert output.
+    moe_apply_router_weight_on_input (`bool`, *optional*, defaults to `False`):
+        Whether to apply router weights to the MoE input rather than the output. Not supported
+        in transformers yet; ``True`` will raise a ``NotImplementedError`` for now.
+    moe_router_logit_softcapping (`float`, *optional*, defaults to 0.0):
+        Scaling factor when applying tanh softcapping on the logits of the MoE router logits.
+
+    Example:
+
+    ```python
+    >>> from transformers import LagunaModel, LagunaConfig
+
+    >>> configuration = LagunaConfig()
+    >>> model = LagunaModel(configuration)
+    >>> configuration = model.config
+    ```
+    """
+
+    model_type = "laguna"
+    keys_to_ignore_at_inference = ["past_key_values"]
+    base_model_tp_plan = {
+        "layers.*.self_attn.q_proj": "colwise",
+        "layers.*.self_attn.k_proj": "colwise",
+        "layers.*.self_attn.v_proj": "colwise",
+        "layers.*.self_attn.g_proj": "colwise",
+        "layers.*.self_attn.o_proj": "rowwise",
+        "layers.*.self_attn.q_norm": "replicated_with_grad_allreduce",
+        "layers.*.self_attn.k_norm": "replicated_with_grad_allreduce",
+        "layers.*.mlp.gate_proj": "colwise",
+        "layers.*.mlp.up_proj": "colwise",
+        "layers.*.mlp.down_proj": "rowwise",
+        "layers.*.mlp.experts.gate_up_proj": "packed_colwise",
+        "layers.*.mlp.experts.down_proj": "rowwise",
+        "layers.*.mlp.experts": "moe_tp_experts",
+        "layers.*.mlp.shared_experts.gate_proj": "colwise",
+        "layers.*.mlp.shared_experts.up_proj": "colwise",
+        "layers.*.mlp.shared_experts.down_proj": "rowwise",
+    }
+    base_model_pp_plan = {
+        "embed_tokens": (["input_ids"], ["inputs_embeds"]),
+        "layers": (["hidden_states", "attention_mask"], ["hidden_states"]),
+        "norm": (["hidden_states"], ["hidden_states"]),
+    }
+
+    # Qwen2Moe-inherited defaults we want to override for Laguna's typical shape.
+    vocab_size: int = 100352
+    hidden_size: int = 2048
+    intermediate_size: int = 8192
+    num_hidden_layers: int = 40
+    num_attention_heads: int = 48
+    num_key_value_heads: int = 8
+    hidden_act: str = "silu"
+    max_position_embeddings: int = 131072
+    initializer_range: float = 0.02
+    rms_norm_eps: float = 1e-6
+    use_cache: bool = True
+    tie_word_embeddings: bool = False
+    rope_parameters: RopeParameters | dict | None = None
+    sliding_window: int | None = None
+    attention_dropout: float | int = 0.0
+    moe_intermediate_size: int = 512
+    shared_expert_intermediate_size: int = 512
+    num_experts_per_tok: int = 8
+    num_experts: int = 256
+    output_router_logits: bool = False
+    router_aux_loss_coef: float = 0.001
+    layer_types: list[str] | None = None
+    pad_token_id: int | None = None
+    bos_token_id: int | None = None
+    eos_token_id: int | list[int] | None = None
+
+    # Laguna-specific attention
+    head_dim: int = 128
+    attention_bias: bool = False
+    partial_rotary_factor: float | None = None
+    num_attention_heads_per_layer: list[int] | None = None
+    # Laguna-specific MoE
+    mlp_layer_types: list[str] | None = None
+    moe_routed_scaling_factor: float = 1.0
+    moe_apply_router_weight_on_input: bool = False
+    moe_router_logit_softcapping: float = 0.0
+
+    def __post_init__(self, **kwargs):
+        if self.layer_types is None:
+            self.layer_types = ["full_attention"] * self.num_hidden_layers
+        if self.mlp_layer_types is None:
+            self.mlp_layer_types = ["dense"] + ["sparse"] * (self.num_hidden_layers - 1)
+        if self.num_attention_heads_per_layer is None:
+            self.num_attention_heads_per_layer = [self.num_attention_heads] * self.num_hidden_layers
+
+        default_rope_params: dict[Literal["full_attention", "sliding_attention"], dict[str, Any]] = {
+            "full_attention": {"rope_type": "default", "rope_theta": 500000.0},
+            "sliding_attention": {"rope_type": "default", "rope_theta": 10000.0},
+        }
+        if self.rope_parameters is None:
+            self.rope_parameters = default_rope_params
+
+        self._normalize_rope_parameters()
+        # Skip ``Qwen2MoeConfig.__post_init__`` — it references ``mlp_only_layers`` /
+        # ``use_sliding_window`` / ``max_window_layers`` which Laguna drops above.
+        super().__post_init__(**kwargs)
+
+    def _normalize_rope_parameters(self):
+        """Coerce ``rope_parameters`` to the nested ``{layer_type: {...}}`` shape.
+
+        Accepts an already-nested dict as-is, or a flat dict that gets broadcast to every
+        layer type. A top-level ``partial_rotary_factor`` is folded into each sub-dict as
+        a default.
+        """
+        layer_types = set(self.layer_types)
+        rope_params = self.rope_parameters or {}
+        is_nested = isinstance(rope_params, dict) and any(k in layer_types for k in rope_params)
+        if is_nested:
+            nested = {lt: dict(rope_params.get(lt, {})) for lt in layer_types}
+        else:
+            nested = {lt: dict(rope_params) for lt in layer_types}
+
+        if self.partial_rotary_factor is not None:
+            for params in nested.values():
+                params.setdefault("partial_rotary_factor", self.partial_rotary_factor)
+
+        for params in nested.values():
+            params.setdefault("rope_type", "default")
+
+        self.rope_parameters = nested
+        # Null the top-level field now that its value lives in each sub-dict — otherwise
+        # ``standardize_rope_params`` would overwrite per-type values with the global one.
+        self.partial_rotary_factor = None
+
+    def convert_rope_params_to_dict(self, **kwargs):
+        # No need to handle BC for new models, because they have no old-format `rope_scaling`
+        return kwargs
+
+    def _validate_yarn_rope_parameters(self, rope_parameters: dict, ignore_keys=None):
+        """Override: parent reads ``self.rope_parameters["original_max_position_embeddings"]``
+        for its post-hoc factor sanity-check, which works for flat rope configs but raises
+        ``KeyError`` when ``self.rope_parameters`` is the Laguna/Gemma3-style per-layer-type
+        map (its keys are layer types like ``"full_attention"``). Fix locally by reading
+        from the per-call ``rope_parameters`` dict that ``validate_rope`` already passes in.
+        """
+        # Delegate to parent for the shared checks by temporarily swapping in a flat
+        # ``self.rope_parameters`` that has the key the parent expects. Cheapest way to
+        # share the parent's logic without reimplementing it here.
+        flat = getattr(self, "rope_parameters", None)
+        self.rope_parameters = rope_parameters
+        try:
+            super()._validate_yarn_rope_parameters(rope_parameters, ignore_keys=ignore_keys)
+        finally:
+            self.rope_parameters = flat
+
+    def validate_architecture(self):
+        """Part of ``@strict``-powered validation."""
+        if self.moe_apply_router_weight_on_input:
+            raise NotImplementedError(
+                "moe_apply_router_weight_on_input=True is not yet supported in the "
+                "transformers implementation of Laguna."
+            )
+        if (
+            self.num_attention_heads_per_layer is not None
+            and len(self.num_attention_heads_per_layer) != self.num_hidden_layers
+        ):
+            raise ValueError(
+                f"num_attention_heads_per_layer length ({len(self.num_attention_heads_per_layer)}) "
+                f"must equal num_hidden_layers ({self.num_hidden_layers})."
+            )
+        if len(self.layer_types) != self.num_hidden_layers:
+            raise ValueError(
+                f"layer_types length ({len(self.layer_types)}) "
+                f"must equal num_hidden_layers ({self.num_hidden_layers})."
+            )
+        if len(self.mlp_layer_types) != self.num_hidden_layers:
+            raise ValueError(
+                f"mlp_layer_types length ({len(self.mlp_layer_types)}) "
+                f"must equal num_hidden_layers ({self.num_hidden_layers})."
+            )
+
+
+__all__ = ["LagunaConfig"]

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 2,
+  "do_sample": true,
+  "eos_token_id": [
+    2,
+    24
+  ],
+  "max_new_tokens": 2048,
+  "pad_token_id": 9,
+  "temperature": 0.7,
+  "top_p": 0.9
+}

model-00001-of-00089.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8632741e8c945e64f8481bdca8d61dbbfc0575492c648ca2b65bc7df477a4ea
+size 5119451664

model-00002-of-00089.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27d383368c041bd3e353ea999184486a6ce0fedfe3dc340530eb5fde14df9eba
+size 5085993864

model-00003-of-00089.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80d6a582d23f5fe52e06da316271bd4dc6fa599c6b0190b5d6466e3f6f1b521c
+size 5117432672

model-00004-of-00089.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53af63b5eba2512d2f381f451af52182d8c6d4810b5f1a4a04fb04d468cc9d7b
+size 5119410552

model-00005-of-00089.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d123586a70e89ca15b646ca5a3b89df9a840a7156fd2a5963c3b7e58f15817bb
+size 5117126864

model-00006-of-00089.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13d6513689c47ed54f1926add13a5c18ae320f93020a62272ef62526af586ef5
+size 5117126776

model-00007-of-00089.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c9c1aa557c300cfcd4ec3e33795b45129f23b1eff22b8be8211a4bb81abd150
+size 5117126776

model-00008-of-00089.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1ea2a19570b0e4843fea911864cad4dbe4cb44911473781d4dc13f83afb9626
+size 5117126880

model-00009-of-00089.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:caa88e1bc4f6027f6d25851a68c54baf1d68b506ed4d64c81a306335e2599473
+size 5117126936

model-00010-of-00089.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe1c7577d7701a5b92dc7b769a8424aa023050dd79153e83b3b174642f5d0b0e
+size 5117126840

model-00011-of-00089.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c811ad9526c67011805c106d0ddf2125bc1008be91b2d3c41acedbd1d31e330
+size 5117126776

model-00012-of-00089.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:795b82c7ce70faed4bb2bffa8faae36eda207fb99eb63eda36837aaf097c6ab0
+size 5117126776

model-00013-of-00089.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1d95a0e9a19310787e8fb670a436f7e79ff5611e624c56c482f4dc2e2e4ccd6
+size 5117127072

model-00014-of-00089.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97a5d58a7c1ababab558ca338521a19c308bd77a3b66f67880315925714312cb
+size 5117127560

model-00015-of-00089.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73999bbda5f9f3d015ae92e23bd6e4f934d1f68a43ed5a78ef69657d3c4e6d28
+size 5117127416

model-00016-of-00089.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5764691ac7fed32348b36a5ad51892e7d96b8db23c7ee6427a91038c74d00c7b
+size 5117127384

model-00017-of-00089.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6aaa0ed888b3ca70262bf864a40476a9912900186b2ef394bdcbbefaf3400d1d
+size 5117127384

model-00018-of-00089.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee62de0fef280679505f761e85c02bf3ad426660109c6caf865875dd7ded1303
+size 5117127536

model-00019-of-00089.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6a1b1d7cdcfdba0e30ecdea6922ee6f86e1ac6221cd31c4b6a51320cd113b23
+size 5117127568

model-00020-of-00089.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7864138dff629d384ddc4f9237c9289dca7af03d0e6ecc7c5613ffc4da21c458
+size 5117127384

model-00021-of-00089.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4092d630cf2c4abed2d930bc3882fa5bb47f77d385a3ed5b4eb37729b208fa1
+size 5117127384

model-00022-of-00089.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd7bac418a3c61e8c1ced1dbf38fd22596102c2f02a9b40c418aecd999bf0693
+size 5117127400

model-00023-of-00089.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8813301fb169bc2107a8d23d97edcd88c090c6a8f56872e3ee319291807b193
+size 5117127544

model-00024-of-00089.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5df83bd8ca11dbc5e93d0f175a7789ad6054a2106bb21a71cea3893c21b86e
+size 5117127544

model-00025-of-00089.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b01fa055f90698193bf5025a1d5e2672ae6ea7232790f94506df160afd2d83bc
+size 5117127384

model-00026-of-00089.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe035f0147283f1e6aedfda0783d246c18bf6de6b621bd410572d4ee406eaaa1
+size 5117127384

model-00027-of-00089.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db3936023f48645a0978a2036a69972e7f0eaadfdcf65afbfba2622acc640e3d
+size 5117127424

model-00028-of-00089.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ba05a9e636123a8e3ad79b17e8e3750c8bc4d8b058579525c5d96acdb5b4154
+size 5117127544

model-00029-of-00089.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98d894c0d55a34b13a7ecf9776515bf234021ef6ac0da5d762624797610a41d8
+size 5117127520

model-00030-of-00089.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:372b9c71dacc34e5743a90a164826763fa48269d4ac5771e23196cbb1917fe9b
+size 5117127384

model-00031-of-00089.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:173cfee7e4717f4e4239eb6f090d310349e33c42bf51f8fc25a55fcc0e22dee1
+size 5117127384

model-00032-of-00089.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e183403bbdc936fad5a4ce9474995e1b201566566781df483c4b275be5521b12
+size 5117127440

model-00033-of-00089.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd68bdbb7d5f29afbd31a0a3db19178a5c5d0910a9a5a3bf86061deaf0708c84
+size 5117127544

model-00034-of-00089.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47bc13e69105e2b1bdce672fd294343062b2a9fe4b212b0e9a54b7e1c19ae1eb
+size 5117127496

model-00035-of-00089.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d441d48e5f4203500620e765f131d4c134deeb809b4c914db02693a456a802d
+size 5117127384

model-00036-of-00089.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:540c6ef065d744f0c122ec5a791bd1af5c3b9967bfd6f8bebcb4bb1a9dc7ce0e
+size 5117127384

model-00037-of-00089.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a2d97b4ec661e6ad3b95798a5c6da3f9c76671a6ed72f331cc4aaa46c334bf5
+size 5117127464

model-00038-of-00089.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c5409109530c97194399c87e18e12e9d0bf5503ad94be64da310914c098d5f8
+size 5117127544

model-00039-of-00089.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf441560879fb2629c17601afab7e44b00c24845f2a8c78f53e3304e4e006dd6
+size 5117127480

model-00040-of-00089.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:628f4a143d0b9d8c8689a570d5a23af4dbdfdb86ea98f5bc11dcb3dda9dca894
+size 5117127384

model-00041-of-00089.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3dedabea4d64a9272896e99af10cc0f572b7a53117082d9c8d2fe740e46aa7ea
+size 5117127384

model-00042-of-00089.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:919f86ec5ac75e928bc670d142fb9c852ef700f0076da0aa89c355e8ef078a9b
+size 5117127488

model-00043-of-00089.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f53d4e29422b0df39116c03c5f6f3385d586d1815c16476221da35541875794e
+size 5117127544

model-00044-of-00089.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4065660d8bbd1a05471e9c4f1470832628067adb4011df7aa48fa350e8bd87f
+size 5117127456