modeling stuff

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

LICENSE

@@ -0,0 +1,202 @@
+
+                                 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 +1,182 @@
+---
+license: apache-2.0
+pipeline_tag: text-generation
+library_name: transformers
+tags:
+- vllm
+---
+
+<p align="center">
+  <img alt="gpt-oss-20b" src="https://raw.githubusercontent.com/openai/gpt-oss/main/docs/gpt-oss-20b.svg">
+</p>
+
+<p align="center">
+  <a href="https://gpt-oss.com"><strong>Try gpt-oss</strong></a> ·
+  <a href="https://cookbook.openai.com/topic/gpt-oss"><strong>Guides</strong></a> ·
+  <a href="https://arxiv.org/abs/2508.10925"><strong>Model card</strong></a> ·
+  <a href="https://openai.com/index/introducing-gpt-oss/"><strong>OpenAI blog</strong></a>
+</p>
+
+<br>
+
+Welcome to the gpt-oss series, [OpenAI’s open-weight models](https://openai.com/open-models) designed for powerful reasoning, agentic tasks, and versatile developer use cases.
+
+We’re releasing two flavors of these open models:
+- `gpt-oss-120b` — for production, general purpose, high reasoning use cases that fit into a single 80GB GPU (like NVIDIA H100 or AMD MI300X) (117B parameters with 5.1B active parameters)
+- `gpt-oss-20b` — for lower latency, and local or specialized use cases (21B parameters with 3.6B active parameters)
+
+Both models were trained on our [harmony response format](https://github.com/openai/harmony) and should only be used with the harmony format as it will not work correctly otherwise.
+
+
+> [!NOTE]
+> This model card is dedicated to the smaller `gpt-oss-20b` model. Check out [`gpt-oss-120b`](https://huggingface.co/openai/gpt-oss-120b) for the larger model.
+
+# Highlights
+
+* **Permissive Apache 2.0 license:** Build freely without copyleft restrictions or patent risk—ideal for experimentation, customization, and commercial deployment.  
+* **Configurable reasoning effort:** Easily adjust the reasoning effort (low, medium, high) based on your specific use case and latency needs.  
+* **Full chain-of-thought:** Gain complete access to the model’s reasoning process, facilitating easier debugging and increased trust in outputs. It’s not intended to be shown to end users.  
+* **Fine-tunable:** Fully customize models to your specific use case through parameter fine-tuning.
+* **Agentic capabilities:** Use the models’ native capabilities for function calling, [web browsing](https://github.com/openai/gpt-oss/tree/main?tab=readme-ov-file#browser), [Python code execution](https://github.com/openai/gpt-oss/tree/main?tab=readme-ov-file#python), and Structured Outputs.
+* **MXFP4 quantization:** The models were post-trained with MXFP4 quantization of the MoE weights, making `gpt-oss-120b` run on a single 80GB GPU (like NVIDIA H100 or AMD MI300X) and the `gpt-oss-20b` model run within 16GB of memory. All evals were performed with the same MXFP4 quantization.
+
+---
+
+# Inference examples
+
+## Transformers
+
+You can use `gpt-oss-120b` and `gpt-oss-20b` with Transformers. If you use the Transformers chat template, it will automatically apply the [harmony response format](https://github.com/openai/harmony). If you use `model.generate` directly, you need to apply the harmony format manually using the chat template or use our [openai-harmony](https://github.com/openai/harmony) package.
+
+To get started, install the necessary dependencies to setup your environment:
+
+```
+pip install -U transformers kernels torch 
+```
+
+Once, setup you can proceed to run the model by running the snippet below:
+
+```py
+from transformers import pipeline
+import torch
+
+model_id = "openai/gpt-oss-20b"
+
+pipe = pipeline(
+    "text-generation",
+    model=model_id,
+    torch_dtype="auto",
+    device_map="auto",
+)
+
+messages = [
+    {"role": "user", "content": "Explain quantum mechanics clearly and concisely."},
+]
+
+outputs = pipe(
+    messages,
+    max_new_tokens=256,
+)
+print(outputs[0]["generated_text"][-1])
+```
+
+Alternatively, you can run the model via [`Transformers Serve`](https://huggingface.co/docs/transformers/main/serving) to spin up a OpenAI-compatible webserver:
+
+```
+transformers serve
+transformers chat localhost:8000 --model-name-or-path openai/gpt-oss-20b
+```
+
+[Learn more about how to use gpt-oss with Transformers.](https://cookbook.openai.com/articles/gpt-oss/run-transformers)
+
+## vLLM
+
+vLLM recommends using [uv](https://docs.astral.sh/uv/) for Python dependency management. You can use vLLM to spin up an OpenAI-compatible webserver. The following command will automatically download the model and start the server.
+
+```bash
+uv pip install --pre vllm==0.10.1+gptoss \
+    --extra-index-url https://wheels.vllm.ai/gpt-oss/ \
+    --extra-index-url https://download.pytorch.org/whl/nightly/cu128 \
+    --index-strategy unsafe-best-match
+
+vllm serve openai/gpt-oss-20b
+```
+
+[Learn more about how to use gpt-oss with vLLM.](https://cookbook.openai.com/articles/gpt-oss/run-vllm)
+
+## PyTorch / Triton
+
+To learn about how to use this model with PyTorch and Triton, check out our [reference implementations in the gpt-oss repository](https://github.com/openai/gpt-oss?tab=readme-ov-file#reference-pytorch-implementation).
+
+## Ollama
+
+If you are trying to run gpt-oss on consumer hardware, you can use Ollama by running the following commands after [installing Ollama](https://ollama.com/download).
+
+```bash
+# gpt-oss-20b
+ollama pull gpt-oss:20b
+ollama run gpt-oss:20b
+```
+
+[Learn more about how to use gpt-oss with Ollama.](https://cookbook.openai.com/articles/gpt-oss/run-locally-ollama)
+
+#### LM Studio
+
+If you are using [LM Studio](https://lmstudio.ai/) you can use the following commands to download.
+
+```bash
+# gpt-oss-20b
+lms get openai/gpt-oss-20b
+```
+
+Check out our [awesome list](https://github.com/openai/gpt-oss/blob/main/awesome-gpt-oss.md) for a broader collection of gpt-oss resources and inference partners.
+
+---
+
+# Download the model
+
+You can download the model weights from the [Hugging Face Hub](https://huggingface.co/collections/openai/gpt-oss-68911959590a1634ba11c7a4) directly from Hugging Face CLI:
+
+```shell
+# gpt-oss-20b
+huggingface-cli download openai/gpt-oss-20b --include "original/*" --local-dir gpt-oss-20b/
+pip install gpt-oss
+python -m gpt_oss.chat model/
+```
+
+# Reasoning levels
+
+You can adjust the reasoning level that suits your task across three levels:
+
+* **Low:** Fast responses for general dialogue.  
+* **Medium:** Balanced speed and detail.  
+* **High:** Deep and detailed analysis.
+
+The reasoning level can be set in the system prompts, e.g., "Reasoning: high".
+
+# Tool use
+
+The gpt-oss models are excellent for:
+* Web browsing (using built-in browsing tools)
+* Function calling with defined schemas
+* Agentic operations like browser tasks
+
+# Fine-tuning
+
+Both gpt-oss models can be fine-tuned for a variety of specialized use cases.
+
+This smaller model `gpt-oss-20b` can be fine-tuned on consumer hardware, whereas the larger [`gpt-oss-120b`](https://huggingface.co/openai/gpt-oss-120b) can be fine-tuned on a single H100 node.
+
+# Citation
+
+```bibtex
+@misc{openai2025gptoss120bgptoss20bmodel,
+      title={gpt-oss-120b & gpt-oss-20b Model Card}, 
+      author={OpenAI},
+      year={2025},
+      eprint={2508.10925},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL},
+      url={https://arxiv.org/abs/2508.10925}, 
+}
+```

USAGE_POLICY

@@ -0,0 +1 @@
+We aim for our tools to be used safely, responsibly, and democratically, while maximizing your control over how you use them. By using OpenAI gpt-oss-20b, you agree to comply with all applicable law.

chat_template.jinja

@@ -0,0 +1,331 @@
+{#-
+  In addition to the normal inputs of `messages` and `tools`, this template also accepts the
+  following kwargs:
+  - "builtin_tools": A list, can contain "browser" and/or "python".
+  - "model_identity": A string that optionally describes the model identity.
+  - "reasoning_effort": A string that describes the reasoning effort, defaults to "medium".
+ #}
+
+{#- Tool Definition Rendering ============================================== #}
+{%- macro render_typescript_type(param_spec, required_params, is_nullable=false) -%}
+    {%- if param_spec.type == "array" -%}
+        {%- if param_spec['items'] -%}
+            {%- if param_spec['items']['type'] == "string" -%}
+                {{- "string[]" }}
+            {%- elif param_spec['items']['type'] == "number" -%}
+                {{- "number[]" }}
+            {%- elif param_spec['items']['type'] == "integer" -%}
+                {{- "number[]" }}
+            {%- elif param_spec['items']['type'] == "boolean" -%}
+                {{- "boolean[]" }}
+            {%- else -%}
+                {%- set inner_type = render_typescript_type(param_spec['items'], required_params) -%}
+                {%- if inner_type == "object | object" or inner_type|length > 50 -%}
+                    {{- "any[]" }}
+                {%- else -%}
+                    {{- inner_type + "[]" }}
+                {%- endif -%}
+            {%- endif -%}
+            {%- if param_spec.nullable -%}
+                {{- " | null" }}
+            {%- endif -%}
+        {%- else -%}
+            {{- "any[]" }}
+            {%- if param_spec.nullable -%}
+                {{- " | null" }}
+            {%- endif -%}
+        {%- endif -%}
+    {%- elif param_spec.type is defined and param_spec.type is iterable and param_spec.type is not string and param_spec.type is not mapping and param_spec.type[0] is defined -%}
+        {#- Handle array of types like ["object", "object"] from Union[dict, list] #}
+        {%- if param_spec.type | length > 1 -%}
+            {{- param_spec.type | join(" | ") }}
+        {%- else -%}
+            {{- param_spec.type[0] }}
+        {%- endif -%}
+    {%- elif param_spec.oneOf -%}
+        {#- Handle oneOf schemas - check for complex unions and fallback to any #}
+        {%- set has_object_variants = false -%}
+        {%- for variant in param_spec.oneOf -%}
+            {%- if variant.type == "object" -%}
+                {%- set has_object_variants = true -%}
+            {%- endif -%}
+        {%- endfor -%}
+        {%- if has_object_variants and param_spec.oneOf|length > 1 -%}
+            {{- "any" }}
+        {%- else -%}
+            {%- for variant in param_spec.oneOf -%}
+                {{- render_typescript_type(variant, required_params) -}}
+                {%- if variant.description %}
+                    {{- "// " + variant.description }}
+                {%- endif -%}
+                {%- if variant.default is defined %}
+                    {{ "// default: " + variant.default|tojson }}
+                {%- endif -%}
+                {%- if not loop.last %}
+                    {{- " | " }}
+                {% endif -%}
+            {%- endfor -%}
+        {%- endif -%}
+    {%- elif param_spec.type == "string" -%}
+        {%- if param_spec.enum -%}
+            {{- '"' + param_spec.enum|join('" | "') + '"' -}}
+        {%- else -%}
+            {{- "string" }}
+            {%- if param_spec.nullable %}
+                {{- " | null" }}
+            {%- endif -%}
+        {%- endif -%}
+    {%- elif param_spec.type == "number" -%}
+        {{- "number" }}
+    {%- elif param_spec.type == "integer" -%}
+        {{- "number" }}
+    {%- elif param_spec.type == "boolean" -%}
+        {{- "boolean" }}
+
+    {%- elif param_spec.type == "object" -%}
+        {%- if param_spec.properties -%}
+            {{- "{\n" }}
+            {%- for prop_name, prop_spec in param_spec.properties.items() -%}
+                {{- prop_name -}}
+                {%- if prop_name not in (param_spec.required or []) -%}
+                    {{- "?" }}
+                {%- endif -%}
+                {{- ": " }}
+                {{ render_typescript_type(prop_spec, param_spec.required or []) }}
+                {%- if not loop.last -%}
+                    {{-", " }}
+                {%- endif -%}
+            {%- endfor -%}
+            {{- "}" }}
+        {%- else -%}
+            {{- "object" }}
+        {%- endif -%}
+    {%- else -%}
+        {{- "any" }}
+    {%- endif -%}
+{%- endmacro -%}
+
+{%- macro render_tool_namespace(namespace_name, tools) -%}
+    {{- "## " + namespace_name + "\n\n" }}
+    {{- "namespace " + namespace_name + " {\n\n" }}
+    {%- for tool in tools %}
+        {%- set tool = tool.function %}
+        {{- "// " + tool.description + "\n" }}
+        {{- "type "+ tool.name + " = " }}
+        {%- if tool.parameters and tool.parameters.properties %}
+            {{- "(_: {\n" }}
+            {%- for param_name, param_spec in tool.parameters.properties.items() %}
+                {%- if param_spec.description %}
+                    {{- "// " + param_spec.description + "\n" }}
+                {%- endif %}
+                {{- param_name }}
+                {%- if param_name not in (tool.parameters.required or []) -%}
+                    {{- "?" }}
+                {%- endif -%}
+                {{- ": " }}
+                {{- render_typescript_type(param_spec, tool.parameters.required or []) }}
+                {%- if param_spec.default is defined -%}
+                    {%- if param_spec.enum %}
+                        {{- ", // default: " + param_spec.default }}
+                    {%- elif param_spec.oneOf %}
+                        {{- "// default: " + param_spec.default }}
+                    {%- else %}
+                        {{- ", // default: " + param_spec.default|tojson }}
+                    {%- endif -%}
+                {%- endif -%}
+                {%- if not loop.last %}
+                    {{- ",\n" }}
+                {%- else %}
+                    {{- ",\n" }}
+                {%- endif -%}
+            {%- endfor %}
+            {{- "}) => any;\n\n" }}
+        {%- else -%}
+            {{- "() => any;\n\n" }}
+        {%- endif -%}
+    {%- endfor %}
+    {{- "} // namespace " + namespace_name }}
+{%- endmacro -%}
+
+{%- macro render_builtin_tools(browser_tool, python_tool) -%}
+    {%- if browser_tool %}
+        {{- "## browser\n\n" }}
+        {{- "// Tool for browsing.\n" }}
+        {{- "// The `cursor` appears in brackets before each browsing display: `[{cursor}]`.\n" }}
+        {{- "// Cite information from the tool using the following format:\n" }}
+        {{- "// `【{cursor}†L{line_start}(-L{line_end})?】`, for example: `【6†L9-L11】` or `【8†L3】`.\n" }}
+        {{- "// Do not quote more than 10 words directly from the tool output.\n" }}
+        {{- "// sources=web (default: web)\n" }}
+        {{- "namespace browser {\n\n" }}
+        {{- "// Searches for information related to `query` and displays `topn` results.\n" }}
+        {{- "type search = (_: {\n" }}
+        {{- "query: string,\n" }}
+        {{- "topn?: number, // default: 10\n" }}
+        {{- "source?: string,\n" }}
+        {{- "}) => any;\n\n" }}
+        {{- "// Opens the link `id` from the page indicated by `cursor` starting at line number `loc`, showing `num_lines` lines.\n" }}
+        {{- "// Valid link ids are displayed with the formatting: `【{id}†.*】`.\n" }}
+        {{- "// If `cursor` is not provided, the most recent page is implied.\n" }}
+        {{- "// If `id` is a string, it is treated as a fully qualified URL associated with `source`.\n" }}
+        {{- "// If `loc` is not provided, the viewport will be positioned at the beginning of the document or centered on the most relevant passage, if available.\n" }}
+        {{- "// Use this function without `id` to scroll to a new location of an opened page.\n" }}
+        {{- "type open = (_: {\n" }}
+        {{- "id?: number | string, // default: -1\n" }}
+        {{- "cursor?: number, // default: -1\n" }}
+        {{- "loc?: number, // default: -1\n" }}
+        {{- "num_lines?: number, // default: -1\n" }}
+        {{- "view_source?: boolean, // default: false\n" }}
+        {{- "source?: string,\n" }}
+        {{- "}) => any;\n\n" }}
+        {{- "// Finds exact matches of `pattern` in the current page, or the page given by `cursor`.\n" }}
+        {{- "type find = (_: {\n" }}
+        {{- "pattern: string,\n" }}
+        {{- "cursor?: number, // default: -1\n" }}
+        {{- "}) => any;\n\n" }}
+        {{- "} // namespace browser\n\n" }}
+    {%- endif -%}
+
+    {%- if python_tool %}
+        {{- "## python\n\n" }}
+        {{- "Use this tool to execute Python code in your chain of thought. The code will not be shown to the user. This tool should be used for internal reasoning, but not for code that is intended to be visible to the user (e.g. when creating plots, tables, or files).\n\n" }}
+        {{- "When you send a message containing Python code to python, it will be executed in a stateful Jupyter notebook environment. python will respond with the output of the execution or time out after 120.0 seconds. The drive at '/mnt/data' can be used to save and persist user files. Internet access for this session is UNKNOWN. Depends on the cluster.\n\n" }}
+    {%- endif -%}
+{%- endmacro -%}
+
+{#- System Message Construction ============================================ #}
+{%- macro build_system_message() -%}
+    {%- if model_identity is not defined %}
+        {%- set model_identity = "You are ChatGPT, a large language model trained by OpenAI." %}
+    {%- endif %}
+    {{- model_identity + "\n" }}
+    {{- "Knowledge cutoff: 2024-06\n" }}
+    {{- "Current date: " + strftime_now("%Y-%m-%d") + "\n\n" }}
+    {%- if reasoning_effort is not defined %}
+        {%- set reasoning_effort = "medium" %}
+    {%- endif %}
+    {{- "Reasoning: " + reasoning_effort + "\n\n" }}
+    {%- if builtin_tools %}
+        {{- "# Tools\n\n" }}
+        {%- set available_builtin_tools = namespace(browser=false, python=false) %}
+        {%- for tool in builtin_tools %}
+            {%- if tool == "browser" %}
+                {%- set available_builtin_tools.browser = true %}
+            {%- elif tool == "python" %}
+                {%- set available_builtin_tools.python = true %}
+            {%- endif %}
+        {%- endfor %}
+        {{- render_builtin_tools(available_builtin_tools.browser, available_builtin_tools.python) }}
+    {%- endif -%}
+    {{- "# Valid channels: analysis, commentary, final. Channel must be included for every message." }}
+    {%- if tools -%}
+        {{- "\nCalls to these tools must go to the commentary channel: 'functions'." }}
+    {%- endif -%}
+{%- endmacro -%}
+
+{#- Main Template Logic ================================================= #}
+{#- Set defaults #}
+
+{#- Render system message #}
+{{- "<|start|>system<|message|>" }}
+{{- build_system_message() }}
+{{- "<|end|>" }}
+
+{#- Extract developer message #}
+{%- if messages[0].role == "developer" or messages[0].role == "system" %}
+    {%- set developer_message = messages[0].content %}
+    {%- set loop_messages = messages[1:] %}
+{%- else %}
+    {%- set developer_message = "" %}
+    {%- set loop_messages = messages %}
+{%- endif %}
+
+{#- Render developer message #}
+{%- if developer_message or tools %}
+    {{- "<|start|>developer<|message|>" }}
+    {%- if developer_message %}
+        {{- "# Instructions\n\n" }}
+        {{- developer_message }}
+        {{- "\n\n" }}
+    {%- endif %}
+    {%- if tools -%}
+        {{- "# Tools\n\n" }}
+        {{- render_tool_namespace("functions", tools) }}
+    {%- endif -%}
+    {{- "<|end|>" }}
+{%- endif %}
+
+{#- Render messages #}
+{%- set last_tool_call = namespace(name=none) %}
+{%- for message in loop_messages -%}
+    {#- At this point only assistant/user/tool messages should remain #}
+    {%- if message.role == 'assistant' -%}
+        {#- Checks to ensure the messages are being passed in the format we expect #}
+        {%- if "content" in message %}
+            {%- if "<|channel|>analysis<|message|>" in message.content or "<|channel|>final<|message|>" in message.content %}
+                {{- raise_exception("You have passed a message containing <|channel|> tags in the content field. Instead of doing this, you should pass analysis messages (the string between '<|message|>' and '<|end|>') in the 'thinking' field, and final messages (the string between '<|message|>' and '<|end|>') in the 'content' field.") }}
+            {%- endif %}
+        {%- endif %}
+        {%- if "thinking" in message %}
+            {%- if "<|channel|>analysis<|message|>" in message.thinking or "<|channel|>final<|message|>" in message.thinking %}
+                {{- raise_exception("You have passed a message containing <|channel|> tags in the thinking field. Instead of doing this, you should pass analysis messages (the string between '<|message|>' and '<|end|>') in the 'thinking' field, and final messages (the string between '<|message|>' and '<|end|>') in the 'content' field.") }}
+            {%- endif %}
+        {%- endif %}
+        {%- if "tool_calls" in message %}
+            {#- We need very careful handling here - we want to drop the tool call analysis message if the model #}
+            {#- has output a later <|final|> message, but otherwise we want to retain it. This is the only case #}
+            {#- when we render CoT/analysis messages in inference. #}
+            {%- set future_final_message = namespace(found=false) %}
+            {%- for future_message in loop_messages[loop.index:] %}
+                {%- if future_message.role == 'assistant' and "tool_calls" not in future_message %}
+                    {%- set future_final_message.found = true %}
+                {%- endif %}
+            {%- endfor %}
+            {#- We assume max 1 tool call per message, and so we infer the tool call name #}
+            {#- in "tool" messages from the most recent assistant tool call name #}
+            {%- set tool_call = message.tool_calls[0] %}
+            {%- if tool_call.function %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {%- if message.content and message.thinking %}
+                {{- raise_exception("Cannot pass both content and thinking in an assistant message with tool calls! Put the analysis message in one or the other, but not both.") }}
+            {%- elif message.content and not future_final_message.found %}
+                {{- "<|start|>assistant<|channel|>analysis<|message|>" + message.content + "<|end|>" }}
+            {%- elif message.thinking and not future_final_message.found %}
+                {{- "<|start|>assistant<|channel|>analysis<|message|>" + message.thinking + "<|end|>" }}
+            {%- endif %}
+            {{- "<|start|>assistant to=" }}
+            {{- "functions." + tool_call.name + "<|channel|>commentary " }}
+            {{- (tool_call.content_type if tool_call.content_type is defined else "json") + "<|message|>" }}
+            {{- tool_call.arguments|tojson }}
+            {{- "<|call|>" }}
+            {%- set last_tool_call.name = tool_call.name %}
+        {%- elif loop.last and not add_generation_prompt %}
+            {#- Only render the CoT if the final turn is an assistant turn and add_generation_prompt is false #}
+            {#- This is a situation that should only occur in training, never in inference. #}
+            {%- if "thinking" in message %}
+                {{- "<|start|>assistant<|channel|>analysis<|message|>" + message.thinking + "<|end|>" }}
+            {%- endif %}
+            {#- <|return|> indicates the end of generation, but <|end|> does not #}
+            {#- <|return|> should never be an input to the model, but we include it as the final token #}
+            {#- when training, so the model learns to emit it. #}
+            {{- "<|start|>assistant<|channel|>final<|message|>" + message.content + "<|return|>" }}
+        {%- else %}
+            {#- CoT is dropped during all previous turns, so we never render it for inference #}
+            {{- "<|start|>assistant<|channel|>final<|message|>" + message.content + "<|end|>" }}
+            {%- set last_tool_call.name = none %}
+        {%- endif %}
+    {%- elif message.role == 'tool' -%}
+        {%- if last_tool_call.name is none %}
+            {{- raise_exception("Message has tool role, but there was no previous assistant message with a tool call!") }}
+        {%- endif %}
+        {{- "<|start|>functions." + last_tool_call.name }}
+        {{- " to=assistant<|channel|>commentary<|message|>" + message.content|tojson + "<|end|>" }}
+    {%- elif message.role == 'user' -%}
+        {{- "<|start|>user<|message|>" + message.content + "<|end|>" }}
+    {%- endif -%}
+{%- endfor -%}
+
+{#- Generation prompt #}
+{%- if add_generation_prompt -%}
+<|start|>assistant
+{%- endif -%}

config.json

@@ -0,0 +1,76 @@
+{
+  "architectures": [
+    "GptOssForCausalLM"
+  ],
+  "attention_bias": true,
+  "attention_dropout": 0.0,
+  "eos_token_id": 200002,
+  "experts_per_token": 4,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2880,
+  "initial_context_length": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 2880,
+  "layer_types": [
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 131072,
+  "model_type": "gpt_oss",
+  "num_attention_heads": 64,
+  "num_experts_per_tok": 4,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 8,
+  "num_local_experts": 32,
+  "output_router_logits": false,
+  "pad_token_id": 199999,
+  "quantization_config": {
+    "modules_to_not_convert": [
+      "model.layers.*.self_attn",
+      "model.layers.*.mlp.router",
+      "model.embed_tokens",
+      "lm_head"
+    ],
+    "quant_method": "mxfp4"
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "beta_fast": 32.0,
+    "beta_slow": 1.0,
+    "factor": 32.0,
+    "original_max_position_embeddings": 4096,
+    "rope_type": "yarn",
+    "truncate": false
+  },
+  "rope_theta": 150000,
+  "router_aux_loss_coef": 0.9,
+  "sliding_window": 128,
+  "swiglu_limit": 7.0,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.55.0.dev0",
+  "use_cache": true,
+  "vocab_size": 201088
+}

configuration_gpt_oss.py

@@ -0,0 +1,127 @@
+# coding=utf-8
+# Copyright 2025 The HuggingFace 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.
+"""openai model configuration"""
+
+from transformers.configuration_utils import PretrainedConfig, layer_type_validation
+from transformers.modeling_rope_utils import rope_config_validation
+
+
+class GptOssConfig(PretrainedConfig):
+    r"""
+    This will yield a configuration to that of the BERT
+    [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased) architecture.
+
+    """
+
+    model_type = "gpt_oss"
+    base_model_pp_plan = {
+        "embed_tokens": (["input_ids"], ["inputs_embeds"]),
+        "layers": (["hidden_states", "attention_mask"], ["hidden_states"]),
+        "norm": (["hidden_states"], ["hidden_states"]),
+    }
+    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.o_proj": "rowwise",
+        "layers.*.self_attn.sinks": "local_rowwise",
+        "layers.*.mlp.experts": "gather",
+        "layers.*.mlp.router": "ep_router",
+        "layers.*.mlp.experts.gate_up_proj": "grouped_gemm",
+        "layers.*.mlp.experts.gate_up_proj_bias": "grouped_gemm",
+        "layers.*.mlp.experts.down_proj": "grouped_gemm",
+        "layers.*.mlp.experts.down_proj_bias": "grouped_gemm",
+    }
+
+    def __init__(
+        self,
+        num_hidden_layers: int = 36,
+        num_local_experts: int = 128,
+        vocab_size: int = 201088,
+        hidden_size: int = 2880,
+        intermediate_size: int = 2880,
+        head_dim: int = 64,
+        num_attention_heads: int = 64,
+        num_key_value_heads: int = 8,
+        sliding_window: int = 128,
+        rope_theta: float = 150000.0,
+        tie_word_embeddings=False,
+        hidden_act: str = "silu",
+        initializer_range: float = 0.02,
+        max_position_embeddings=131072,
+        rms_norm_eps: float = 1e-5,
+        rope_scaling={
+            "rope_type": "yarn",
+            "factor": 32.0,
+            "beta_fast": 32.0,
+            "beta_slow": 1.0,
+            "truncate": False,
+            "original_max_position_embeddings": 4096,
+        },
+        attention_dropout: float = 0.0,
+        num_experts_per_tok=4,
+        router_aux_loss_coef: float = 0.9,
+        output_router_logits=False,
+        use_cache=True,
+        layer_types=None,
+        **kwargs,
+    ):
+        self.vocab_size = vocab_size
+        self.hidden_size = hidden_size
+        self.intermediate_size = intermediate_size
+        self.num_hidden_layers = num_hidden_layers
+        self.num_attention_heads = num_attention_heads
+        self.num_local_experts = num_local_experts
+        self.sliding_window = sliding_window
+        self.num_experts_per_tok = num_experts_per_tok
+        # for backward compatibility
+        if num_key_value_heads is None:
+            num_key_value_heads = num_attention_heads
+
+        self.num_key_value_heads = num_key_value_heads
+        self.hidden_act = hidden_act
+        self.initializer_range = initializer_range
+        self.rms_norm_eps = rms_norm_eps
+        self.rope_theta = rope_theta
+        self.rope_scaling = rope_scaling
+        self.attention_dropout = attention_dropout
+        self.head_dim = head_dim if head_dim is not None else self.hidden_size // self.num_attention_heads
+        self.layer_types = layer_types
+        if self.layer_types is None:
+            self.layer_types = [
+                "sliding_attention" if bool((i + 1) % 2) else "full_attention" for i in range(self.num_hidden_layers)
+            ]
+        layer_type_validation(self.layer_types)
+
+        self.attention_bias = True
+        self.max_position_embeddings = max_position_embeddings
+        self.router_aux_loss_coef = router_aux_loss_coef
+        self.output_router_logits = output_router_logits
+        self.use_cache = use_cache
+
+        # Validate the correctness of rotary position embeddings parameters
+        # BC: if there is a 'type' field, copy it it to 'rope_type'.
+        if self.rope_scaling is not None and "type" in self.rope_scaling:
+            self.rope_scaling["rope_type"] = self.rope_scaling["type"]
+        rope_config_validation(self)
+
+        super().__init__(
+            tie_word_embeddings=tie_word_embeddings,
+            **kwargs,
+        )
+
+
+__all__ = ["GptOssConfig"]
+

generation_config.json

@@ -0,0 +1,11 @@
+{
+  "bos_token_id": 199998,
+  "do_sample": true,
+  "eos_token_id": [
+    200002,
+    199999,
+    200012
+  ],
+  "pad_token_id": 199999,
+  "transformers_version": "4.55.0.dev0"
+}

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"total_size": 13761264768}, "weight_map": {"model.layers.0.input_layernorm.weight": "model-00000-of-00002.safetensors", "model.layers.0.self_attn.o_proj.bias": "model-00000-of-00002.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00000-of-00002.safetensors", "model.layers.0.self_attn.q_proj.bias": "model-00000-of-00002.safetensors", "model.layers.0.self_attn.k_proj.bias": "model-00000-of-00002.safetensors", "model.layers.0.self_attn.v_proj.bias": "model-00000-of-00002.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00000-of-00002.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00000-of-00002.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00000-of-00002.safetensors", "model.layers.0.self_attn.sinks": "model-00000-of-00002.safetensors", "model.layers.0.mlp.router.bias": "model-00000-of-00002.safetensors", "model.layers.0.mlp.router.weight": "model-00000-of-00002.safetensors", "model.layers.0.mlp.experts.gate_up_proj_bias": "model-00000-of-00002.safetensors", "model.layers.0.mlp.experts.gate_up_proj_blocks": "model-00000-of-00002.safetensors", "model.layers.0.mlp.experts.gate_up_proj_scales": "model-00000-of-00002.safetensors", "model.layers.0.mlp.experts.down_proj_bias": "model-00000-of-00002.safetensors", "model.layers.0.mlp.experts.down_proj_blocks": "model-00000-of-00002.safetensors", "model.layers.0.mlp.experts.down_proj_scales": "model-00000-of-00002.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00000-of-00002.safetensors", "model.layers.1.input_layernorm.weight": "model-00000-of-00002.safetensors", "model.layers.1.self_attn.o_proj.bias": "model-00000-of-00002.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00000-of-00002.safetensors", "model.layers.1.self_attn.q_proj.bias": "model-00000-of-00002.safetensors", "model.layers.1.self_attn.k_proj.bias": "model-00000-of-00002.safetensors", "model.layers.1.self_attn.v_proj.bias": "model-00000-of-00002.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00000-of-00002.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00000-of-00002.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00000-of-00002.safetensors", "model.layers.1.self_attn.sinks": "model-00000-of-00002.safetensors", "model.layers.1.mlp.router.bias": "model-00000-of-00002.safetensors", "model.layers.1.mlp.router.weight": "model-00000-of-00002.safetensors", "model.layers.1.mlp.experts.gate_up_proj_bias": "model-00000-of-00002.safetensors", "model.layers.1.mlp.experts.gate_up_proj_blocks": "model-00000-of-00002.safetensors", "model.layers.1.mlp.experts.gate_up_proj_scales": "model-00000-of-00002.safetensors", "model.layers.1.mlp.experts.down_proj_bias": "model-00000-of-00002.safetensors", "model.layers.1.mlp.experts.down_proj_blocks": "model-00000-of-00002.safetensors", "model.layers.1.mlp.experts.down_proj_scales": "model-00000-of-00002.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00000-of-00002.safetensors", "model.layers.10.input_layernorm.weight": "model-00000-of-00002.safetensors", "model.layers.10.self_attn.o_proj.bias": "model-00000-of-00002.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00000-of-00002.safetensors", "model.layers.10.self_attn.q_proj.bias": "model-00000-of-00002.safetensors", "model.layers.10.self_attn.k_proj.bias": "model-00000-of-00002.safetensors", "model.layers.10.self_attn.v_proj.bias": "model-00000-of-00002.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00000-of-00002.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00000-of-00002.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00000-of-00002.safetensors", "model.layers.10.self_attn.sinks": "model-00000-of-00002.safetensors", "model.layers.10.mlp.router.bias": "model-00000-of-00002.safetensors", "model.layers.10.mlp.router.weight": "model-00000-of-00002.safetensors", "model.layers.10.mlp.experts.gate_up_proj_bias": "model-00000-of-00002.safetensors", "model.layers.10.mlp.experts.gate_up_proj_blocks": "model-00000-of-00002.safetensors", "model.layers.10.mlp.experts.gate_up_proj_scales": "model-00000-of-00002.safetensors", "model.layers.10.mlp.experts.down_proj_bias": "model-00000-of-00002.safetensors", "model.layers.10.mlp.experts.down_proj_blocks": "model-00000-of-00002.safetensors", "model.layers.10.mlp.experts.down_proj_scales": "model-00000-of-00002.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00000-of-00002.safetensors", "model.layers.11.input_layernorm.weight": "model-00000-of-00002.safetensors", "model.layers.11.self_attn.o_proj.bias": "model-00000-of-00002.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00000-of-00002.safetensors", "model.layers.11.self_attn.q_proj.bias": "model-00000-of-00002.safetensors", "model.layers.11.self_attn.k_proj.bias": "model-00000-of-00002.safetensors", "model.layers.11.self_attn.v_proj.bias": "model-00000-of-00002.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00000-of-00002.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00000-of-00002.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00000-of-00002.safetensors", "model.layers.11.self_attn.sinks": "model-00000-of-00002.safetensors", "model.layers.11.mlp.router.bias": "model-00000-of-00002.safetensors", "model.layers.11.mlp.router.weight": "model-00000-of-00002.safetensors", "model.layers.11.mlp.experts.gate_up_proj_bias": "model-00000-of-00002.safetensors", "model.layers.11.mlp.experts.gate_up_proj_blocks": "model-00000-of-00002.safetensors", "model.layers.11.mlp.experts.gate_up_proj_scales": "model-00000-of-00002.safetensors", "model.layers.11.mlp.experts.down_proj_bias": "model-00000-of-00002.safetensors", "model.layers.11.mlp.experts.down_proj_blocks": "model-00000-of-00002.safetensors", "model.layers.11.mlp.experts.down_proj_scales": "model-00000-of-00002.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00000-of-00002.safetensors", "model.layers.12.input_layernorm.weight": "model-00000-of-00002.safetensors", "model.layers.12.self_attn.o_proj.bias": "model-00000-of-00002.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00000-of-00002.safetensors", "model.layers.12.self_attn.q_proj.bias": "model-00000-of-00002.safetensors", "model.layers.12.self_attn.k_proj.bias": "model-00000-of-00002.safetensors", "model.layers.12.self_attn.v_proj.bias": "model-00000-of-00002.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00000-of-00002.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00000-of-00002.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00000-of-00002.safetensors", "model.layers.12.self_attn.sinks": "model-00000-of-00002.safetensors", "model.layers.12.mlp.router.bias": "model-00000-of-00002.safetensors", "model.layers.12.mlp.router.weight": "model-00000-of-00002.safetensors", "model.layers.12.mlp.experts.gate_up_proj_bias": "model-00000-of-00002.safetensors", "model.layers.12.mlp.experts.gate_up_proj_blocks": "model-00000-of-00002.safetensors", "model.layers.12.mlp.experts.gate_up_proj_scales": "model-00000-of-00002.safetensors", "model.layers.12.mlp.experts.down_proj_bias": "model-00000-of-00002.safetensors", "model.layers.12.mlp.experts.down_proj_blocks": "model-00000-of-00002.safetensors", "model.layers.12.mlp.experts.down_proj_scales": "model-00000-of-00002.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00000-of-00002.safetensors", "model.layers.13.input_layernorm.weight": "model-00000-of-00002.safetensors", "model.layers.13.self_attn.o_proj.bias": "model-00000-of-00002.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00000-of-00002.safetensors", "model.layers.13.self_attn.q_proj.bias": "model-00000-of-00002.safetensors", "model.layers.13.self_attn.k_proj.bias": "model-00000-of-00002.safetensors", "model.layers.13.self_attn.v_proj.bias": "model-00000-of-00002.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00000-of-00002.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00000-of-00002.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00000-of-00002.safetensors", "model.layers.13.self_attn.sinks": "model-00000-of-00002.safetensors", "model.layers.13.mlp.router.bias": "model-00000-of-00002.safetensors", "model.layers.13.mlp.router.weight": "model-00000-of-00002.safetensors", "model.layers.13.mlp.experts.gate_up_proj_bias": "model-00000-of-00002.safetensors", "model.layers.13.mlp.experts.gate_up_proj_blocks": "model-00000-of-00002.safetensors", "model.layers.13.mlp.experts.gate_up_proj_scales": "model-00000-of-00002.safetensors", "model.layers.13.mlp.experts.down_proj_bias": "model-00000-of-00002.safetensors", "model.layers.13.mlp.experts.down_proj_blocks": "model-00000-of-00002.safetensors", "model.layers.13.mlp.experts.down_proj_scales": "model-00000-of-00002.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00000-of-00002.safetensors", "model.layers.14.input_layernorm.weight": "model-00000-of-00002.safetensors", "model.layers.14.self_attn.o_proj.bias": "model-00000-of-00002.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00000-of-00002.safetensors", "model.layers.14.self_attn.q_proj.bias": "model-00000-of-00002.safetensors", "model.layers.14.self_attn.k_proj.bias": "model-00000-of-00002.safetensors", "model.layers.14.self_attn.v_proj.bias": "model-00000-of-00002.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00000-of-00002.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00000-of-00002.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00000-of-00002.safetensors", "model.layers.14.self_attn.sinks": "model-00000-of-00002.safetensors", "model.layers.14.mlp.router.bias": "model-00000-of-00002.safetensors", "model.layers.14.mlp.router.weight": "model-00000-of-00002.safetensors", "model.layers.14.mlp.experts.gate_up_proj_bias": "model-00000-of-00002.safetensors", "model.layers.14.mlp.experts.gate_up_proj_blocks": "model-00000-of-00002.safetensors", "model.layers.14.mlp.experts.gate_up_proj_scales": "model-00000-of-00002.safetensors", "model.layers.14.mlp.experts.down_proj_bias": "model-00000-of-00002.safetensors", "model.layers.14.mlp.experts.down_proj_blocks": "model-00000-of-00002.safetensors", "model.layers.14.mlp.experts.down_proj_scales": "model-00000-of-00002.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00000-of-00002.safetensors", "model.layers.15.input_layernorm.weight": "model-00000-of-00002.safetensors", "model.layers.15.self_attn.o_proj.bias": "model-00000-of-00002.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00000-of-00002.safetensors", "model.layers.15.self_attn.q_proj.bias": "model-00000-of-00002.safetensors", "model.layers.15.self_attn.k_proj.bias": "model-00000-of-00002.safetensors", "model.layers.15.self_attn.v_proj.bias": "model-00000-of-00002.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00000-of-00002.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00000-of-00002.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00000-of-00002.safetensors", "model.layers.15.self_attn.sinks": "model-00000-of-00002.safetensors", "model.layers.15.mlp.router.bias": "model-00000-of-00002.safetensors", "model.layers.15.mlp.router.weight": "model-00000-of-00002.safetensors", "model.layers.15.mlp.experts.gate_up_proj_bias": "model-00000-of-00002.safetensors", "model.layers.15.mlp.experts.gate_up_proj_blocks": "model-00000-of-00002.safetensors", "model.layers.15.mlp.experts.gate_up_proj_scales": "model-00000-of-00002.safetensors", "model.layers.15.mlp.experts.down_proj_bias": "model-00000-of-00002.safetensors", "model.layers.15.mlp.experts.down_proj_blocks": "model-00000-of-00002.safetensors", "model.layers.15.mlp.experts.down_proj_scales": "model-00000-of-00002.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00000-of-00002.safetensors", "model.layers.16.input_layernorm.weight": "model-00000-of-00002.safetensors", "model.layers.16.self_attn.o_proj.bias": "model-00000-of-00002.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00000-of-00002.safetensors", "model.layers.16.self_attn.q_proj.bias": "model-00000-of-00002.safetensors", "model.layers.16.self_attn.k_proj.bias": "model-00000-of-00002.safetensors", "model.layers.16.self_attn.v_proj.bias": "model-00000-of-00002.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00000-of-00002.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00000-of-00002.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00000-of-00002.safetensors", "model.layers.16.self_attn.sinks": "model-00000-of-00002.safetensors", "model.layers.16.mlp.router.bias": "model-00000-of-00002.safetensors", "model.layers.16.mlp.router.weight": "model-00000-of-00002.safetensors", "model.layers.16.mlp.experts.gate_up_proj_bias": "model-00000-of-00002.safetensors", "model.layers.16.mlp.experts.gate_up_proj_blocks": "model-00000-of-00002.safetensors", "model.layers.16.mlp.experts.gate_up_proj_scales": "model-00000-of-00002.safetensors", "model.layers.16.mlp.experts.down_proj_bias": "model-00000-of-00002.safetensors", "model.layers.16.mlp.experts.down_proj_blocks": "model-00000-of-00002.safetensors", "model.layers.16.mlp.experts.down_proj_scales": "model-00000-of-00002.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00000-of-00002.safetensors", "model.layers.17.input_layernorm.weight": "model-00000-of-00002.safetensors", "model.layers.17.self_attn.o_proj.bias": "model-00000-of-00002.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00000-of-00002.safetensors", "model.layers.17.self_attn.q_proj.bias": "model-00000-of-00002.safetensors", "model.layers.17.self_attn.k_proj.bias": "model-00000-of-00002.safetensors", "model.layers.17.self_attn.v_proj.bias": "model-00000-of-00002.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00000-of-00002.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00000-of-00002.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00000-of-00002.safetensors", "model.layers.17.self_attn.sinks": "model-00000-of-00002.safetensors", "model.layers.17.mlp.router.bias": "model-00000-of-00002.safetensors", "model.layers.17.mlp.router.weight": "model-00000-of-00002.safetensors", "model.layers.17.mlp.experts.gate_up_proj_bias": "model-00000-of-00002.safetensors", "model.layers.17.mlp.experts.gate_up_proj_blocks": "model-00000-of-00002.safetensors", "model.layers.17.mlp.experts.gate_up_proj_scales": "model-00000-of-00002.safetensors", "model.layers.17.mlp.experts.down_proj_bias": "model-00000-of-00002.safetensors", "model.layers.17.mlp.experts.down_proj_blocks": "model-00000-of-00002.safetensors", "model.layers.17.mlp.experts.down_proj_scales": "model-00000-of-00002.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00000-of-00002.safetensors", "model.layers.18.input_layernorm.weight": "model-00000-of-00002.safetensors", "model.layers.18.self_attn.o_proj.bias": "model-00000-of-00002.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00000-of-00002.safetensors", "model.layers.18.self_attn.q_proj.bias": "model-00000-of-00002.safetensors", "model.layers.18.self_attn.k_proj.bias": "model-00000-of-00002.safetensors", "model.layers.18.self_attn.v_proj.bias": "model-00000-of-00002.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.18.self_attn.sinks": "model-00001-of-00002.safetensors", "model.layers.18.mlp.router.bias": "model-00001-of-00002.safetensors", "model.layers.18.mlp.router.weight": "model-00001-of-00002.safetensors", "model.layers.18.mlp.experts.gate_up_proj_bias": "model-00001-of-00002.safetensors", "model.layers.18.mlp.experts.gate_up_proj_blocks": "model-00001-of-00002.safetensors", "model.layers.18.mlp.experts.gate_up_proj_scales": "model-00001-of-00002.safetensors", "model.layers.18.mlp.experts.down_proj_bias": "model-00001-of-00002.safetensors", "model.layers.18.mlp.experts.down_proj_blocks": "model-00001-of-00002.safetensors", "model.layers.18.mlp.experts.down_proj_scales": "model-00001-of-00002.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.19.self_attn.o_proj.bias": "model-00001-of-00002.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.19.self_attn.sinks": "model-00001-of-00002.safetensors", "model.layers.19.mlp.router.bias": "model-00001-of-00002.safetensors", "model.layers.19.mlp.router.weight": "model-00001-of-00002.safetensors", "model.layers.19.mlp.experts.gate_up_proj_bias": "model-00001-of-00002.safetensors", "model.layers.19.mlp.experts.gate_up_proj_blocks": "model-00001-of-00002.safetensors", "model.layers.19.mlp.experts.gate_up_proj_scales": "model-00001-of-00002.safetensors", "model.layers.19.mlp.experts.down_proj_bias": "model-00001-of-00002.safetensors", "model.layers.19.mlp.experts.down_proj_blocks": "model-00001-of-00002.safetensors", "model.layers.19.mlp.experts.down_proj_scales": "model-00001-of-00002.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.2.self_attn.o_proj.bias": "model-00001-of-00002.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.self_attn.sinks": "model-00001-of-00002.safetensors", "model.layers.2.mlp.router.bias": "model-00001-of-00002.safetensors", "model.layers.2.mlp.router.weight": "model-00001-of-00002.safetensors", "model.layers.2.mlp.experts.gate_up_proj_bias": "model-00001-of-00002.safetensors", "model.layers.2.mlp.experts.gate_up_proj_blocks": "model-00001-of-00002.safetensors", "model.layers.2.mlp.experts.gate_up_proj_scales": "model-00001-of-00002.safetensors", "model.layers.2.mlp.experts.down_proj_bias": "model-00001-of-00002.safetensors", "model.layers.2.mlp.experts.down_proj_blocks": "model-00001-of-00002.safetensors", "model.layers.2.mlp.experts.down_proj_scales": "model-00001-of-00002.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.20.self_attn.o_proj.bias": "model-00001-of-00002.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.20.self_attn.sinks": "model-00001-of-00002.safetensors", "model.layers.20.mlp.router.bias": "model-00001-of-00002.safetensors", "model.layers.20.mlp.router.weight": "model-00001-of-00002.safetensors", "model.layers.20.mlp.experts.gate_up_proj_bias": "model-00001-of-00002.safetensors", "model.layers.20.mlp.experts.gate_up_proj_blocks": "model-00001-of-00002.safetensors", "model.layers.20.mlp.experts.gate_up_proj_scales": "model-00001-of-00002.safetensors", "model.layers.20.mlp.experts.down_proj_bias": "model-00001-of-00002.safetensors", "model.layers.20.mlp.experts.down_proj_blocks": "model-00001-of-00002.safetensors", "model.layers.20.mlp.experts.down_proj_scales": "model-00001-of-00002.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.21.self_attn.o_proj.bias": "model-00001-of-00002.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.21.self_attn.sinks": "model-00001-of-00002.safetensors", "model.layers.21.mlp.router.bias": "model-00001-of-00002.safetensors", "model.layers.21.mlp.router.weight": "model-00001-of-00002.safetensors", "model.layers.21.mlp.experts.gate_up_proj_bias": "model-00001-of-00002.safetensors", "model.layers.21.mlp.experts.gate_up_proj_blocks": "model-00001-of-00002.safetensors", "model.layers.21.mlp.experts.gate_up_proj_scales": "model-00001-of-00002.safetensors", "model.layers.21.mlp.experts.down_proj_bias": "model-00001-of-00002.safetensors", "model.layers.21.mlp.experts.down_proj_blocks": "model-00001-of-00002.safetensors", "model.layers.21.mlp.experts.down_proj_scales": "model-00001-of-00002.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.22.self_attn.o_proj.bias": "model-00001-of-00002.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", "model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.22.self_attn.sinks": "model-00001-of-00002.safetensors", "model.layers.22.mlp.router.bias": "model-00001-of-00002.safetensors", "model.layers.22.mlp.router.weight": "model-00001-of-00002.safetensors", "model.layers.22.mlp.experts.gate_up_proj_bias": "model-00001-of-00002.safetensors", "model.layers.22.mlp.experts.gate_up_proj_blocks": "model-00001-of-00002.safetensors", "model.layers.22.mlp.experts.gate_up_proj_scales": "model-00001-of-00002.safetensors", "model.layers.22.mlp.experts.down_proj_bias": "model-00001-of-00002.safetensors", "model.layers.22.mlp.experts.down_proj_blocks": "model-00001-of-00002.safetensors", "model.layers.22.mlp.experts.down_proj_scales": "model-00001-of-00002.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.23.self_attn.o_proj.bias": "model-00001-of-00002.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", "model.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.23.self_attn.sinks": "model-00001-of-00002.safetensors", "model.layers.23.mlp.router.bias": "model-00001-of-00002.safetensors", "model.layers.23.mlp.router.weight": "model-00001-of-00002.safetensors", "model.layers.23.mlp.experts.gate_up_proj_bias": "model-00001-of-00002.safetensors", "model.layers.23.mlp.experts.gate_up_proj_blocks": "model-00001-of-00002.safetensors", "model.layers.23.mlp.experts.gate_up_proj_scales": "model-00001-of-00002.safetensors", "model.layers.23.mlp.experts.down_proj_bias": "model-00001-of-00002.safetensors", "model.layers.23.mlp.experts.down_proj_blocks": "model-00001-of-00002.safetensors", "model.layers.23.mlp.experts.down_proj_scales": "model-00001-of-00002.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.3.self_attn.o_proj.bias": "model-00001-of-00002.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.3.self_attn.sinks": "model-00001-of-00002.safetensors", "model.layers.3.mlp.router.bias": "model-00001-of-00002.safetensors", "model.layers.3.mlp.router.weight": "model-00001-of-00002.safetensors", "model.layers.3.mlp.experts.gate_up_proj_bias": "model-00001-of-00002.safetensors", "model.layers.3.mlp.experts.gate_up_proj_blocks": "model-00001-of-00002.safetensors", "model.layers.3.mlp.experts.gate_up_proj_scales": "model-00001-of-00002.safetensors", "model.layers.3.mlp.experts.down_proj_bias": "model-00001-of-00002.safetensors", "model.layers.3.mlp.experts.down_proj_blocks": "model-00001-of-00002.safetensors", "model.layers.3.mlp.experts.down_proj_scales": "model-00001-of-00002.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.4.self_attn.o_proj.bias": "model-00001-of-00002.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.4.self_attn.sinks": "model-00001-of-00002.safetensors", "model.layers.4.mlp.router.bias": "model-00001-of-00002.safetensors", "model.layers.4.mlp.router.weight": "model-00001-of-00002.safetensors", "model.layers.4.mlp.experts.gate_up_proj_bias": "model-00001-of-00002.safetensors", "model.layers.4.mlp.experts.gate_up_proj_blocks": "model-00001-of-00002.safetensors", "model.layers.4.mlp.experts.gate_up_proj_scales": "model-00001-of-00002.safetensors", "model.layers.4.mlp.experts.down_proj_bias": "model-00001-of-00002.safetensors", "model.layers.4.mlp.experts.down_proj_blocks": "model-00001-of-00002.safetensors", "model.layers.4.mlp.experts.down_proj_scales": "model-00001-of-00002.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.5.self_attn.o_proj.bias": "model-00001-of-00002.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.5.self_attn.sinks": "model-00001-of-00002.safetensors", "model.layers.5.mlp.router.bias": "model-00001-of-00002.safetensors", "model.layers.5.mlp.router.weight": "model-00001-of-00002.safetensors", "model.layers.5.mlp.experts.gate_up_proj_bias": "model-00001-of-00002.safetensors", "model.layers.5.mlp.experts.gate_up_proj_blocks": "model-00001-of-00002.safetensors", "model.layers.5.mlp.experts.gate_up_proj_scales": "model-00001-of-00002.safetensors", "model.layers.5.mlp.experts.down_proj_bias": "model-00001-of-00002.safetensors", "model.layers.5.mlp.experts.down_proj_blocks": "model-00001-of-00002.safetensors", "model.layers.5.mlp.experts.down_proj_scales": "model-00001-of-00002.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.6.self_attn.o_proj.bias": "model-00001-of-00002.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.6.self_attn.sinks": "model-00001-of-00002.safetensors", "model.layers.6.mlp.router.bias": "model-00001-of-00002.safetensors", "model.layers.6.mlp.router.weight": "model-00001-of-00002.safetensors", "model.layers.6.mlp.experts.gate_up_proj_bias": "model-00001-of-00002.safetensors", "model.layers.6.mlp.experts.gate_up_proj_blocks": "model-00002-of-00002.safetensors", "model.layers.6.mlp.experts.gate_up_proj_scales": "model-00002-of-00002.safetensors", "model.layers.6.mlp.experts.down_proj_bias": "model-00002-of-00002.safetensors", "model.layers.6.mlp.experts.down_proj_blocks": "model-00002-of-00002.safetensors", "model.layers.6.mlp.experts.down_proj_scales": "model-00002-of-00002.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.7.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.7.self_attn.o_proj.bias": "model-00002-of-00002.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.7.self_attn.sinks": "model-00002-of-00002.safetensors", "model.layers.7.mlp.router.bias": "model-00002-of-00002.safetensors", "model.layers.7.mlp.router.weight": "model-00002-of-00002.safetensors", "model.layers.7.mlp.experts.gate_up_proj_bias": "model-00002-of-00002.safetensors", "model.layers.7.mlp.experts.gate_up_proj_blocks": "model-00002-of-00002.safetensors", "model.layers.7.mlp.experts.gate_up_proj_scales": "model-00002-of-00002.safetensors", "model.layers.7.mlp.experts.down_proj_bias": "model-00002-of-00002.safetensors", "model.layers.7.mlp.experts.down_proj_blocks": "model-00002-of-00002.safetensors", "model.layers.7.mlp.experts.down_proj_scales": "model-00002-of-00002.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.8.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.8.self_attn.o_proj.bias": "model-00002-of-00002.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.8.self_attn.sinks": "model-00002-of-00002.safetensors", "model.layers.8.mlp.router.bias": "model-00002-of-00002.safetensors", "model.layers.8.mlp.router.weight": "model-00002-of-00002.safetensors", "model.layers.8.mlp.experts.gate_up_proj_bias": "model-00002-of-00002.safetensors", "model.layers.8.mlp.experts.gate_up_proj_blocks": "model-00002-of-00002.safetensors", "model.layers.8.mlp.experts.gate_up_proj_scales": "model-00002-of-00002.safetensors", "model.layers.8.mlp.experts.down_proj_bias": "model-00002-of-00002.safetensors", "model.layers.8.mlp.experts.down_proj_blocks": "model-00002-of-00002.safetensors", "model.layers.8.mlp.experts.down_proj_scales": "model-00002-of-00002.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.9.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.9.self_attn.o_proj.bias": "model-00002-of-00002.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.9.self_attn.sinks": "model-00002-of-00002.safetensors", "model.layers.9.mlp.router.bias": "model-00002-of-00002.safetensors", "model.layers.9.mlp.router.weight": "model-00002-of-00002.safetensors", "model.layers.9.mlp.experts.gate_up_proj_bias": "model-00002-of-00002.safetensors", "model.layers.9.mlp.experts.gate_up_proj_blocks": "model-00002-of-00002.safetensors", "model.layers.9.mlp.experts.gate_up_proj_scales": "model-00002-of-00002.safetensors", "model.layers.9.mlp.experts.down_proj_bias": "model-00002-of-00002.safetensors", "model.layers.9.mlp.experts.down_proj_blocks": "model-00002-of-00002.safetensors", "model.layers.9.mlp.experts.down_proj_scales": "model-00002-of-00002.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.embed_tokens.weight": "model-00002-of-00002.safetensors", "model.norm.weight": "model-00002-of-00002.safetensors", "lm_head.weight": "model-00002-of-00002.safetensors"}}

modeling_gpt_oss.py

@@ -0,0 +1,721 @@
+#                🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨��🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨��🚨🚨🚨🚨🚨🚨🚨🚨🚨
+#           This file was automatically generated from src/transformers/models/gpt_oss/modular_gpt_oss.py.
+#               Do NOT edit this file manually as any edits will be overwritten by the generation of
+#             the file from the modular. If any change should be done, please apply the change to the
+#                          modular_gpt_oss.py file directly. One of our CI enforces this.
+#                🚨🚨🚨🚨🚨🚨��🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨��🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
+# coding=utf-8
+# Copyright 2025 The HuggingFace 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 Callable, Optional, Union
+
+import torch
+from torch import nn
+from torch.nn import functional as F
+
+from transformers.cache_utils import Cache, DynamicCache
+from transformers.generation import GenerationMixin
+from transformers.integrations.hub_kernels import use_kernel_forward_from_hub
+from transformers.masking_utils import create_causal_mask, create_sliding_window_causal_mask
+from transformers.modeling_layers import (
+    GenericForSequenceClassification,
+    GenericForTokenClassification,
+    GradientCheckpointingLayer,
+)
+from transformers.modeling_outputs import MoeCausalLMOutputWithPast, MoeModelOutputWithPast
+from transformers.modeling_rope_utils import ROPE_INIT_FUNCTIONS, dynamic_rope_update
+from transformers.modeling_utils import ALL_ATTENTION_FUNCTIONS, PreTrainedModel
+from transformers.processing_utils import Unpack
+from transformers.utils import TransformersKwargs, auto_docstring, can_return_tuple
+from transformers.utils.deprecation import deprecate_kwarg
+from transformers.utils.generic import OutputRecorder, check_model_inputs
+from .configuration_gpt_oss import GptOssConfig
+
+
+@use_kernel_forward_from_hub("RMSNorm")
+class GptOssRMSNorm(nn.Module):
+    def __init__(self, hidden_size, eps=1e-6):
+        """
+        GptOssRMSNorm is equivalent to T5LayerNorm
+        """
+        super().__init__()
+        self.weight = nn.Parameter(torch.ones(hidden_size))
+        self.variance_epsilon = eps
+
+    def forward(self, hidden_states):
+        input_dtype = hidden_states.dtype
+        hidden_states = hidden_states.to(torch.float32)
+        variance = hidden_states.pow(2).mean(-1, keepdim=True)
+        hidden_states = hidden_states * torch.rsqrt(variance + self.variance_epsilon)
+        return (self.weight * hidden_states).to(input_dtype)  # main diff with Llama
+
+    def extra_repr(self):
+        return f"{tuple(self.weight.shape)}, eps={self.variance_epsilon}"
+
+
+class GptOssExperts(nn.Module):
+    def __init__(self, config):
+        super().__init__()
+        self.intermediate_size = config.intermediate_size
+        self.num_experts = config.num_local_experts
+        self.hidden_size = config.hidden_size
+        self.expert_dim = self.intermediate_size
+        self.gate_up_proj = nn.Parameter(torch.empty(self.num_experts, self.hidden_size, 2 * self.expert_dim))
+        self.gate_up_proj_bias = nn.Parameter(torch.empty(self.num_experts, 2 * self.expert_dim))
+        self.down_proj = nn.Parameter(torch.empty((self.num_experts, self.expert_dim, self.hidden_size)))
+        self.down_proj_bias = nn.Parameter(torch.empty(self.num_experts, self.hidden_size))
+        self.alpha = 1.702
+        self.limit = 7.0
+
+    def forward(self, hidden_states: torch.Tensor, router_indices=None, routing_weights=None) -> torch.Tensor:
+        """
+        When training it is more efficient to just loop over the experts and compute the output for each expert
+        as otherwise the memory would explode.
+
+        For inference we can sacrifice some memory and compute the output for all experts at once. By repeating the inputs.
+
+        Args:
+            hidden_states (torch.Tensor): (batch_size, seq_len, hidden_size)
+            selected_experts (torch.Tensor): (batch_size * token_num, top_k)
+            routing_weights (torch.Tensor): (batch_size * token_num, num_experts)
+        Returns:
+            torch.Tensor
+        """
+        batch_size = hidden_states.shape[0]
+        hidden_states = hidden_states.reshape(-1, self.hidden_size)  # (num_tokens, hidden_size)
+        num_experts = routing_weights.shape[1]
+        if hidden_states.device.type == "cpu" or self.training:
+            next_states = torch.zeros_like(hidden_states, dtype=hidden_states.dtype, device=hidden_states.device)
+            with torch.no_grad():
+                expert_mask = torch.nn.functional.one_hot(router_indices, num_classes=num_experts)
+                expert_mask = expert_mask.permute(2, 1, 0)
+                # we sum on the top_k and on the sequence length to get which experts
+                # are hit this time around
+                expert_hit = torch.greater(expert_mask.sum(dim=(-1, -2)), 0).nonzero()
+            for expert_idx in expert_hit[:]:
+                # expert_idx only have 1 element, so we can use scale for fast indexing
+                expert_idx = expert_idx[0]
+                with torch.no_grad():
+                    _, token_idx = torch.where(expert_mask[expert_idx])
+                current_state = hidden_states[token_idx]
+                gate_up = current_state @ self.gate_up_proj[expert_idx] + self.gate_up_proj_bias[expert_idx]
+                gate, up = gate_up[..., ::2], gate_up[..., 1::2]
+                gate = gate.clamp(min=None, max=self.limit)
+                up = up.clamp(min=-self.limit, max=self.limit)
+                glu = gate * torch.sigmoid(gate * self.alpha)
+                gated_output = (up + 1) * glu
+                out = gated_output @ self.down_proj[expert_idx] + self.down_proj_bias[expert_idx]
+                weighted_output = out * routing_weights[token_idx, expert_idx, None]
+                next_states.index_add_(0, token_idx, weighted_output.to(hidden_states.dtype))
+            next_states = next_states.view(batch_size, -1, self.hidden_size)
+        else:
+            hidden_states = hidden_states.repeat(num_experts, 1)
+            hidden_states = hidden_states.view(num_experts, -1, self.hidden_size)
+            gate_up = torch.bmm(hidden_states, self.gate_up_proj) + self.gate_up_proj_bias[..., None, :]
+            gate, up = gate_up[..., ::2], gate_up[..., 1::2]
+            gate = gate.clamp(min=None, max=self.limit)
+            up = up.clamp(min=-self.limit, max=self.limit)
+            glu = gate * torch.sigmoid(gate * self.alpha)
+            next_states = torch.bmm(((up + 1) * glu), self.down_proj)
+            next_states = next_states + self.down_proj_bias[..., None, :]
+            next_states = next_states.view(num_experts, batch_size, -1, self.hidden_size)
+            next_states = next_states * routing_weights.transpose(0, 1).view(num_experts, batch_size, -1)[..., None]
+            next_states = next_states.sum(dim=0)
+        return next_states
+
+
+class GptOssTopKRouter(nn.Module):
+    def __init__(self, config):
+        super().__init__()
+        self.top_k = config.num_experts_per_tok
+        self.num_experts = config.num_local_experts
+        self.hidden_dim = config.hidden_size
+        self.weight = nn.Parameter(torch.empty(self.num_experts, self.hidden_dim))
+        self.bias = nn.Parameter(torch.empty(self.num_experts))
+
+    def forward(self, hidden_states):
+        hidden_states = hidden_states.reshape(-1, self.hidden_dim)
+        router_logits = F.linear(hidden_states, self.weight, self.bias)  # (seq_len, num_experts)
+        router_top_value, router_indices = torch.topk(router_logits, self.top_k, dim=-1)  # (seq_len, top_k)
+        router_top_value = torch.nn.functional.softmax(router_top_value, dim=1, dtype=router_top_value.dtype)
+        router_scores = torch.zeros_like(router_logits).scatter_(1, router_indices, router_top_value)
+        return router_scores, router_indices
+
+
+@use_kernel_forward_from_hub("MegaBlocksMoeMLP")
+class GptOssMLP(nn.Module):
+    def __init__(self, config):
+        super().__init__()
+        self.router = GptOssTopKRouter(config)
+        self.experts = GptOssExperts(config)
+
+    def forward(self, hidden_states):
+        router_scores, router_indices = self.router(hidden_states)  # (num_experts, seq_len)
+        routed_out = self.experts(hidden_states, router_indices=router_indices, routing_weights=router_scores)
+        return routed_out, router_scores
+
+
+class GptOssRotaryEmbedding(nn.Module):
+    inv_freq: torch.Tensor  # fix linting for `register_buffer`
+
+    def __init__(self, config: GptOssConfig, device=None):
+        super().__init__()
+        # BC: "rope_type" was originally "type"
+        if hasattr(config, "rope_scaling") and isinstance(config.rope_scaling, dict):
+            self.rope_type = config.rope_scaling.get("rope_type", config.rope_scaling.get("type"))
+        else:
+            self.rope_type = "default"
+        self.max_seq_len_cached = config.max_position_embeddings
+        self.original_max_seq_len = config.max_position_embeddings
+
+        self.config = config
+        self.rope_init_fn = ROPE_INIT_FUNCTIONS[self.rope_type]
+
+        inv_freq, self.attention_scaling = self.rope_init_fn(self.config, device)
+        self.register_buffer("inv_freq", inv_freq, persistent=False)
+        self.original_inv_freq = self.inv_freq
+
+    @torch.no_grad()
+    @dynamic_rope_update  # power user: used with advanced RoPE types (e.g. dynamic rope)
+    def forward(self, x, position_ids):
+        inv_freq_expanded = self.inv_freq[None, :, None].float().expand(position_ids.shape[0], -1, 1).to(x.device)
+        position_ids_expanded = position_ids[:, None, :].float()
+
+        device_type = x.device.type if isinstance(x.device.type, str) and x.device.type != "mps" else "cpu"
+        with torch.autocast(device_type=device_type, enabled=False):  # Force float32
+            freqs = (inv_freq_expanded.float() @ position_ids_expanded.float()).transpose(1, 2)
+            emb = freqs
+            cos = emb.cos() * self.attention_scaling
+            sin = emb.sin() * self.attention_scaling
+
+        return cos.to(x.dtype), sin.to(x.dtype)
+
+
+def repeat_kv(hidden_states: torch.Tensor, n_rep: int) -> torch.Tensor:
+    """
+    This is the equivalent of torch.repeat_interleave(x, dim=1, repeats=n_rep). The hidden states go from (batch,
+    num_key_value_heads, seqlen, head_dim) to (batch, num_attention_heads, seqlen, head_dim)
+    """
+    batch, num_key_value_heads, slen, head_dim = hidden_states.shape
+    if n_rep == 1:
+        return hidden_states
+    hidden_states = hidden_states[:, :, None, :, :].expand(batch, num_key_value_heads, n_rep, slen, head_dim)
+    return hidden_states.reshape(batch, num_key_value_heads * n_rep, slen, head_dim)
+
+
+def _apply_rotary_emb(
+    x: torch.Tensor,
+    cos: torch.Tensor,
+    sin: torch.Tensor,
+) -> torch.Tensor:
+    first_half, second_half = torch.chunk(x, 2, dim=-1)
+    first_ = first_half * cos - second_half * sin
+    second_ = second_half * cos + first_half * sin
+    return torch.cat((first_, second_), dim=-1)
+
+
+def apply_rotary_pos_emb(q, k, cos, sin, position_ids=None, unsqueeze_dim=1):
+    cos = cos.unsqueeze(unsqueeze_dim)
+    sin = sin.unsqueeze(unsqueeze_dim)
+    q_embed = _apply_rotary_emb(q, cos, sin)
+    k_embed = _apply_rotary_emb(k, cos, sin)
+    return q_embed, k_embed
+
+
+def eager_attention_forward(
+    module: nn.Module,
+    query: torch.Tensor,
+    key: torch.Tensor,
+    value: torch.Tensor,
+    attention_mask: Optional[torch.Tensor],
+    scaling: float,
+    dropout: float = 0.0,
+    **kwargs,
+):
+    key_states = repeat_kv(key, module.num_key_value_groups)
+    value_states = repeat_kv(value, module.num_key_value_groups)
+    attn_weights = torch.matmul(query, key_states.transpose(2, 3)) * scaling
+    if attention_mask is not None:
+        causal_mask = attention_mask[:, :, :, : key_states.shape[-2]]
+        attn_weights = attn_weights + causal_mask
+
+    sinks = module.sinks.reshape(1, -1, 1, 1).expand(query.shape[0], -1, query.shape[-2], -1)
+    combined_logits = torch.cat([attn_weights, sinks], dim=-1)
+
+    # This was not in the original implementation and slightly affect results; it prevents overflow in BF16/FP16
+    # when training with bsz>1 we clamp max values.
+
+    combined_logits = combined_logits - combined_logits.max(dim=-1, keepdim=True).values
+    probs = F.softmax(combined_logits, dim=-1, dtype=combined_logits.dtype)
+    scores = probs[..., :-1]  # we drop the sink here
+    attn_weights = nn.functional.dropout(scores, p=dropout, training=module.training)
+    attn_output = torch.matmul(attn_weights, value_states)
+    attn_output = attn_output.transpose(1, 2).contiguous()
+    return attn_output, attn_weights
+
+
+class GptOssAttention(nn.Module):
+    """Multi-headed attention from 'Attention Is All You Need' paper"""
+
+    def __init__(self, config: GptOssConfig, layer_idx: int):
+        super().__init__()
+        self.config = config
+        self.layer_idx = layer_idx
+        self.head_dim = getattr(config, "head_dim", config.hidden_size // config.num_attention_heads)
+        self.num_key_value_groups = config.num_attention_heads // config.num_key_value_heads
+        self.scaling = self.head_dim**-0.5
+        self.attention_dropout = config.attention_dropout
+        self.is_causal = True
+        self.q_proj = nn.Linear(
+            config.hidden_size, config.num_attention_heads * self.head_dim, bias=config.attention_bias
+        )
+        self.k_proj = nn.Linear(
+            config.hidden_size, config.num_key_value_heads * self.head_dim, bias=config.attention_bias
+        )
+        self.v_proj = nn.Linear(
+            config.hidden_size, config.num_key_value_heads * self.head_dim, bias=config.attention_bias
+        )
+        self.o_proj = nn.Linear(
+            config.num_attention_heads * self.head_dim, config.hidden_size, bias=config.attention_bias
+        )
+        self.sliding_window = config.sliding_window if config.layer_types[layer_idx] == "sliding_attention" else None
+        self.sinks = nn.Parameter(torch.empty(config.num_attention_heads))
+
+    @deprecate_kwarg("past_key_value", new_name="past_key_values", version="4.58")
+    def forward(
+        self,
+        hidden_states: torch.Tensor,
+        position_embeddings: tuple[torch.Tensor, torch.Tensor],
+        attention_mask: Optional[torch.Tensor],
+        past_key_values: Optional[Cache] = None,
+        cache_position: Optional[torch.LongTensor] = None,
+        **kwargs: Unpack[TransformersKwargs],
+    ) -> tuple[torch.Tensor, torch.Tensor]:
+        input_shape = hidden_states.shape[:-1]
+        hidden_shape = (*input_shape, -1, self.head_dim)
+
+        query_states = self.q_proj(hidden_states).view(hidden_shape).transpose(1, 2)
+        key_states = self.k_proj(hidden_states).view(hidden_shape).transpose(1, 2)
+        value_states = self.v_proj(hidden_states).view(hidden_shape).transpose(1, 2)
+
+        cos, sin = position_embeddings
+        query_states, key_states = apply_rotary_pos_emb(query_states, key_states, cos, sin)
+
+        if past_key_values is not None:
+            cache_kwargs = {"cache_position": cache_position}
+            key_states, value_states = past_key_values.update(key_states, value_states, self.layer_idx, cache_kwargs)
+
+        attention_interface: Callable = eager_attention_forward
+        if self.config._attn_implementation != "eager":
+            attention_interface = ALL_ATTENTION_FUNCTIONS[self.config._attn_implementation]
+
+        attn_output, attn_weights = attention_interface(
+            self,
+            query_states,
+            key_states,
+            value_states,
+            attention_mask,
+            dropout=0.0 if not self.training else self.attention_dropout,
+            scaling=self.scaling,
+            sliding_window=self.sliding_window,
+            s_aux=self.sinks,  # diff with Llama
+            **kwargs,
+        )
+
+        attn_output = attn_output.reshape(*input_shape, -1).contiguous()
+        attn_output = self.o_proj(attn_output)
+        return attn_output, attn_weights
+
+
+class GptOssDecoderLayer(GradientCheckpointingLayer):
+    def __init__(self, config: GptOssConfig, layer_idx: int):
+        super().__init__()
+        self.hidden_size = config.hidden_size
+        self.self_attn = GptOssAttention(config=config, layer_idx=layer_idx)
+        self.mlp = GptOssMLP(config)
+        self.input_layernorm = GptOssRMSNorm(config.hidden_size, eps=config.rms_norm_eps)
+        self.post_attention_layernorm = GptOssRMSNorm(config.hidden_size, eps=config.rms_norm_eps)
+        self.attention_type = config.layer_types[layer_idx]
+
+    @deprecate_kwarg("past_key_value", new_name="past_key_values", version="4.58")
+    def forward(
+        self,
+        hidden_states: torch.Tensor,
+        attention_mask: Optional[torch.Tensor] = None,
+        position_ids: Optional[torch.LongTensor] = None,
+        past_key_values: Optional[Cache] = None,
+        use_cache: Optional[bool] = False,
+        cache_position: Optional[torch.LongTensor] = None,
+        position_embeddings: Optional[tuple[torch.Tensor, torch.Tensor]] = None,  # necessary, but kept here for BC
+        **kwargs: Unpack[TransformersKwargs],
+    ) -> torch.Tensor:
+        residual = hidden_states
+        hidden_states = self.input_layernorm(hidden_states)
+        # Self Attention
+        hidden_states, _ = self.self_attn(
+            hidden_states=hidden_states,
+            attention_mask=attention_mask,
+            position_ids=position_ids,
+            past_key_values=past_key_values,
+            use_cache=use_cache,
+            cache_position=cache_position,
+            position_embeddings=position_embeddings,
+            **kwargs,
+        )
+        hidden_states = residual + hidden_states
+
+        # Fully Connected
+        residual = hidden_states
+        hidden_states = self.post_attention_layernorm(hidden_states)
+        hidden_states, _ = self.mlp(hidden_states)  # diff with llama: router scores
+        hidden_states = residual + hidden_states
+        return hidden_states
+
+
+@auto_docstring
+class GptOssPreTrainedModel(PreTrainedModel):
+    config: GptOssConfig
+    base_model_prefix = "model"
+    supports_gradient_checkpointing = True
+    _no_split_modules = ["GptOssDecoderLayer"]
+    _skip_keys_device_placement = ["past_key_values"]
+    _supports_flash_attn = True
+    _supports_sdpa = False
+    _supports_flex_attn = True
+
+    _can_compile_fullgraph = True
+    _supports_attention_backend = True
+    _can_record_outputs = {
+        "router_logits": OutputRecorder(GptOssTopKRouter, index=0),
+        "hidden_states": GptOssDecoderLayer,
+        "attentions": GptOssAttention,
+    }
+    _keep_in_fp32_modules = ["post_attention_layernorm", "input_layernorm", "norm"]
+    _supports_flash_attention = False
+    _supports_flex_attention = False
+
+    def _init_weights(self, module):
+        std = self.config.initializer_range
+        if isinstance(module, nn.Linear):
+            module.weight.data.normal_(mean=0.0, std=std)
+            if module.bias is not None:
+                module.bias.data.zero_()
+        elif isinstance(module, nn.Parameter):
+            module.data.normal_(mean=0.0, std=std)
+        elif isinstance(module, nn.Embedding):
+            module.weight.data.normal_(mean=0.0, std=std)
+            if module.padding_idx is not None:
+                module.weight.data[module.padding_idx].zero_()
+        elif isinstance(module, GptOssRMSNorm):
+            module.weight.data.fill_(1.0)
+        elif isinstance(module, GptOssExperts):
+            module.gate_up_proj.data.normal_(mean=0.0, std=std)
+            module.gate_up_proj_bias.data.zero_()
+            module.down_proj.data.normal_(mean=0.0, std=std)
+            module.down_proj_bias.data.zero_()
+        elif isinstance(module, GptOssAttention):
+            module.sinks.data.normal_(mean=0.0, std=std)
+        elif isinstance(module, GptOssTopKRouter):
+            module.weight.data.normal_(mean=0.0, std=std)
+            module.bias.data.normal_(mean=0.0, std=std)
+
+
+@auto_docstring
+class GptOssModel(GptOssPreTrainedModel):
+    _no_split_modules = ["GptOssDecoderLayer"]
+
+    def __init__(self, config: GptOssConfig):
+        super().__init__(config)
+        self.padding_idx = config.pad_token_id
+        self.vocab_size = config.vocab_size
+
+        self.embed_tokens = nn.Embedding(config.vocab_size, config.hidden_size, self.padding_idx)
+        self.layers = nn.ModuleList(
+            [GptOssDecoderLayer(config, layer_idx) for layer_idx in range(config.num_hidden_layers)]
+        )
+        self.norm = GptOssRMSNorm(config.hidden_size, eps=config.rms_norm_eps)
+        self.rotary_emb = GptOssRotaryEmbedding(config=config)
+        self.gradient_checkpointing = False
+
+        # Initialize weights and apply final processing
+        self.post_init()
+
+    @check_model_inputs
+    @auto_docstring
+    def forward(
+        self,
+        input_ids: Optional[torch.LongTensor] = None,
+        attention_mask: Optional[torch.Tensor] = None,
+        position_ids: Optional[torch.LongTensor] = None,
+        past_key_values: Optional[list[torch.FloatTensor]] = None,
+        inputs_embeds: Optional[torch.FloatTensor] = None,
+        use_cache: Optional[bool] = None,
+        cache_position: Optional[torch.LongTensor] = None,
+        **kwargs: Unpack[TransformersKwargs],
+    ) -> MoeModelOutputWithPast:
+        if (input_ids is None) ^ (inputs_embeds is not None):
+            raise ValueError("You must specify exactly one of input_ids or inputs_embeds")
+
+        if use_cache and past_key_values is None:
+            past_key_values = DynamicCache(config=self.config)
+
+        if inputs_embeds is None:
+            inputs_embeds = self.embed_tokens(input_ids)
+
+        if cache_position is None:
+            past_seen_tokens = past_key_values.get_seq_length() if past_key_values is not None else 0
+            cache_position = torch.arange(
+                past_seen_tokens, past_seen_tokens + inputs_embeds.shape[1], device=inputs_embeds.device
+            )
+        if position_ids is None:
+            position_ids = cache_position.unsqueeze(0)
+
+        # It may already have been prepared by e.g. `generate`
+        if not isinstance(causal_mask_mapping := attention_mask, dict):
+            mask_kwargs = {
+                "config": self.config,
+                "input_embeds": inputs_embeds,
+                "attention_mask": attention_mask,
+                "cache_position": cache_position,
+                "past_key_values": past_key_values,
+            }
+            causal_mask_mapping = {
+                "full_attention": create_causal_mask(**mask_kwargs),
+                "sliding_attention": create_sliding_window_causal_mask(**mask_kwargs),
+            }
+
+        hidden_states = inputs_embeds
+        position_embeddings = self.rotary_emb(hidden_states, position_ids)
+
+        for decoder_layer in self.layers:
+            hidden_states = decoder_layer(
+                hidden_states,
+                attention_mask=causal_mask_mapping[decoder_layer.attention_type],
+                position_ids=position_ids,
+                past_key_values=past_key_values,
+                use_cache=use_cache,
+                cache_position=cache_position,
+                position_embeddings=position_embeddings,
+                **kwargs,
+            )
+        hidden_states = self.norm(hidden_states)
+        return MoeModelOutputWithPast(
+            last_hidden_state=hidden_states,
+            past_key_values=past_key_values,
+        )
+
+
+def load_balancing_loss_func(
+    gate_logits: Union[torch.Tensor, tuple[torch.Tensor], None],
+    num_experts: Optional[int] = None,
+    top_k=2,
+    attention_mask: Optional[torch.Tensor] = None,
+) -> Union[torch.Tensor, int]:
+    r"""
+    Computes auxiliary load balancing loss as in Switch Transformer - implemented in Pytorch.
+
+    See Switch Transformer (https://huggingface.co/papers/2101.03961) for more details. This function implements the loss
+    function presented in equations (4) - (6) of the paper. It aims at penalizing cases where the routing between
+    experts is too unbalanced.
+
+    Args:
+        gate_logits:
+            Logits from the `gate`, should be a tuple of model.config.num_hidden_layers tensors of
+            shape [batch_size X sequence_length, num_experts].
+        num_experts:
+            Number of experts
+        top_k:
+            The number of experts to route per-token, can be also interpreted as the `top-k` routing
+            parameter.
+        attention_mask (`torch.Tensor`, *optional*):
+            The attention_mask used in forward function
+            shape [batch_size X sequence_length] if not None.
+
+    Returns:
+        The auxiliary loss.
+    """
+    if gate_logits is None or not isinstance(gate_logits, tuple):
+        return 0
+
+    if isinstance(gate_logits, tuple):
+        compute_device = gate_logits[0].device
+        concatenated_gate_logits = torch.cat([layer_gate.to(compute_device) for layer_gate in gate_logits], dim=0)
+
+    routing_weights = torch.nn.functional.softmax(concatenated_gate_logits, dim=-1)
+
+    _, selected_experts = torch.topk(routing_weights, top_k, dim=-1)
+
+    expert_mask = torch.nn.functional.one_hot(selected_experts, num_experts)
+
+    if attention_mask is None:
+        # Compute the percentage of tokens routed to each experts
+        tokens_per_expert = torch.mean(expert_mask.float(), dim=0)
+
+        # Compute the average probability of routing to these experts
+        router_prob_per_expert = torch.mean(routing_weights, dim=0)
+    else:
+        batch_size, sequence_length = attention_mask.shape
+        num_hidden_layers = concatenated_gate_logits.shape[0] // (batch_size * sequence_length)
+
+        # Compute the mask that masks all padding tokens as 0 with the same shape of expert_mask
+        expert_attention_mask = (
+            attention_mask[None, :, :, None, None]
+            .expand((num_hidden_layers, batch_size, sequence_length, top_k, num_experts))
+            .reshape(-1, top_k, num_experts)
+            .to(compute_device)
+        )
+
+        # Compute the percentage of tokens routed to each experts
+        tokens_per_expert = torch.sum(expert_mask.float() * expert_attention_mask, dim=0) / torch.sum(
+            expert_attention_mask, dim=0
+        )
+
+        # Compute the mask that masks all padding tokens as 0 with the same shape of tokens_per_expert
+        router_per_expert_attention_mask = (
+            attention_mask[None, :, :, None]
+            .expand((num_hidden_layers, batch_size, sequence_length, num_experts))
+            .reshape(-1, num_experts)
+            .to(compute_device)
+        )
+
+        # Compute the average probability of routing to these experts
+        router_prob_per_expert = torch.sum(routing_weights * router_per_expert_attention_mask, dim=0) / torch.sum(
+            router_per_expert_attention_mask, dim=0
+        )
+
+    overall_loss = torch.sum(tokens_per_expert * router_prob_per_expert.unsqueeze(0))
+    return overall_loss * num_experts
+
+
+@auto_docstring
+class GptOssForCausalLM(GptOssPreTrainedModel, GenerationMixin):
+    _tied_weights_keys = ["lm_head.weight"]
+    _tp_plan = {"lm_head": "colwise_rep"}
+    _pp_plan = {"lm_head": (["hidden_states"], ["logits"])}
+
+    def __init__(self, config):
+        super().__init__(config)
+        self.model = GptOssModel(config)
+        self.vocab_size = config.vocab_size
+        self.lm_head = nn.Linear(config.hidden_size, config.vocab_size, bias=False)
+        self.router_aux_loss_coef = config.router_aux_loss_coef
+        self.num_experts = config.num_local_experts
+        self.num_experts_per_tok = config.num_experts_per_tok
+
+        # Initialize weights and apply final processing
+        self.post_init()
+
+    @can_return_tuple
+    @auto_docstring
+    def forward(
+        self,
+        input_ids: Optional[torch.LongTensor] = None,
+        attention_mask: Optional[torch.Tensor] = None,
+        position_ids: Optional[torch.LongTensor] = None,
+        past_key_values: Optional[Cache] = None,
+        inputs_embeds: Optional[torch.FloatTensor] = None,
+        labels: Optional[torch.LongTensor] = None,
+        use_cache: Optional[bool] = None,
+        output_router_logits: Optional[bool] = None,
+        cache_position: Optional[torch.LongTensor] = None,
+        logits_to_keep: Union[int, torch.Tensor] = 0,
+        **kwargs: Unpack[TransformersKwargs],
+    ) -> MoeCausalLMOutputWithPast:
+        r"""
+        labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):
+            Labels for computing the masked language modeling loss. Indices should either be in `[0, ...,
+            config.vocab_size]` or -100 (see `input_ids` docstring). Tokens with indices set to `-100` are ignored
+            (masked), the loss is only computed for the tokens with labels in `[0, ..., config.vocab_size]`.
+
+        Example:
+
+        ```python
+        >>> from transformers import AutoTokenizer, GptOssForCausalLM
+
+        >>> model = GptOssForCausalLM.from_pretrained("mistralai/GptOss-8x7B-v0.1")
+        >>> tokenizer = AutoTokenizer.from_pretrained("mistralai/GptOss-8x7B-v0.1")
+
+        >>> prompt = "Hey, are you conscious? Can you talk to me?"
+        >>> inputs = tokenizer(prompt, return_tensors="pt")
+
+        >>> # Generate
+        >>> generate_ids = model.generate(inputs.input_ids, max_length=30)
+        >>> tokenizer.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
+        "Hey, are you conscious? Can you talk to me?\nI'm not conscious, but I can talk to you."
+        ```"""
+
+        output_router_logits = (
+            output_router_logits if output_router_logits is not None else self.config.output_router_logits
+        )
+
+        # decoder outputs consists of (dec_features, layer_state, dec_hidden, dec_attn)
+        outputs: MoeModelOutputWithPast = self.model(
+            input_ids=input_ids,
+            attention_mask=attention_mask,
+            position_ids=position_ids,
+            past_key_values=past_key_values,
+            inputs_embeds=inputs_embeds,
+            use_cache=use_cache,
+            output_router_logits=output_router_logits,
+            cache_position=cache_position,
+            **kwargs,
+        )
+
+        hidden_states = outputs.last_hidden_state
+        # Only compute necessary logits, and do not upcast them to float if we are not computing the loss
+        slice_indices = slice(-logits_to_keep, None) if isinstance(logits_to_keep, int) else logits_to_keep
+        logits = self.lm_head(hidden_states[:, slice_indices, :])
+
+        loss = None
+        if labels is not None:
+            loss = self.loss_function(logits, labels, self.vocab_size, **kwargs)
+
+        aux_loss = None
+        if output_router_logits:
+            aux_loss = load_balancing_loss_func(
+                outputs.router_logits,
+                self.num_experts,
+                self.num_experts_per_tok,
+                attention_mask,
+            )
+            if labels is not None:
+                loss += self.router_aux_loss_coef * aux_loss.to(loss.device)  # make sure to reside in the same device
+
+        return MoeCausalLMOutputWithPast(
+            loss=loss,
+            aux_loss=aux_loss,
+            logits=logits,
+            past_key_values=outputs.past_key_values,
+            hidden_states=outputs.hidden_states,
+            attentions=outputs.attentions,
+            router_logits=outputs.router_logits,
+        )
+
+
+class GptOssForSequenceClassification(GenericForSequenceClassification, GptOssPreTrainedModel):
+    pass
+
+
+class GptOssForTokenClassification(GenericForTokenClassification, GptOssPreTrainedModel):
+    pass
+
+
+__all__ = [
+    "GptOssForCausalLM",
+    "GptOssForSequenceClassification",
+    "GptOssForTokenClassification",
+    "GptOssModel",
+    "GptOssPreTrainedModel",
+]
+

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "<|startoftext|>",
+  "eos_token": "<|return|>",
+  "pad_token": "<|endoftext|>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0614fe83cadab421296e664e1f48f4261fa8fef6e03e63bb75c20f38e37d07d3
+size 27868174

tokenizer_config.json

@@ -0,0 +1,183 @@
+{
+  "added_tokens_decoder": {
+    "199998": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "199999": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200000": {
+      "content": "<|reserved_200000|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200001": {
+      "content": "<|reserved_200001|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200002": {
+      "content": "<|return|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200003": {
+      "content": "<|constrain|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200004": {
+      "content": "<|reserved_200004|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200005": {
+      "content": "<|channel|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200006": {
+      "content": "<|start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200007": {
+      "content": "<|end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200008": {
+      "content": "<|message|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200009": {
+      "content": "<|reserved_200009|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200010": {
+      "content": "<|reserved_200010|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200011": {
+      "content": "<|reserved_200011|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200012": {
+      "content": "<|call|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200013": {
+      "content": "<|reserved_200013|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200014": {
+      "content": "<|reserved_200014|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200015": {
+      "content": "<|reserved_200015|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200016": {
+      "content": "<|reserved_200016|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200017": {
+      "content": "<|reserved_200017|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200018": {
+      "content": "<|endofprompt|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|return|>",
+  "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}