openai-mirror/gpt-oss-safeguard-20b
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: openai-mirror/gpt-oss-safeguard-20b
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-10-08 04:23:13 +08:00
commit 58b34837ef
16 changed files with 1005 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

52
.gitattributes vendored Normal file
View File

@@ -0,0 +1,52 @@
*.7z filter=lfs diff=lfs merge=lfs -text
*.arrow filter=lfs diff=lfs merge=lfs -text
*.bin filter=lfs diff=lfs merge=lfs -text
*.bin.* filter=lfs diff=lfs merge=lfs -text
*.bz2 filter=lfs diff=lfs merge=lfs -text
*.ftz filter=lfs diff=lfs merge=lfs -text
*.gz filter=lfs diff=lfs merge=lfs -text
*.h5 filter=lfs diff=lfs merge=lfs -text
*.joblib filter=lfs diff=lfs merge=lfs -text
*.lfs.* filter=lfs diff=lfs merge=lfs -text
*.model filter=lfs diff=lfs merge=lfs -text
*.msgpack filter=lfs diff=lfs merge=lfs -text
*.onnx filter=lfs diff=lfs merge=lfs -text
*.ot filter=lfs diff=lfs merge=lfs -text
*.parquet filter=lfs diff=lfs merge=lfs -text
*.pb filter=lfs diff=lfs merge=lfs -text
*.pt filter=lfs diff=lfs merge=lfs -text
*.pth filter=lfs diff=lfs merge=lfs -text
*.rar filter=lfs diff=lfs merge=lfs -text
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
*.tar.* filter=lfs diff=lfs merge=lfs -text
*.tflite filter=lfs diff=lfs merge=lfs -text
*.tgz filter=lfs diff=lfs merge=lfs -text
*.xz filter=lfs diff=lfs merge=lfs -text
*.zip filter=lfs diff=lfs merge=lfs -text
*.zstandard filter=lfs diff=lfs merge=lfs -text
*.tfevents* filter=lfs diff=lfs merge=lfs -text
*.db* filter=lfs diff=lfs merge=lfs -text
*.ark* filter=lfs diff=lfs merge=lfs -text
**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
*.ckpt filter=lfs diff=lfs merge=lfs -text
*.gguf* filter=lfs diff=lfs merge=lfs -text
*.ggml filter=lfs diff=lfs merge=lfs -text
*.llamafile* filter=lfs diff=lfs merge=lfs -text
*.pt2 filter=lfs diff=lfs merge=lfs -text
*.mlmodel filter=lfs diff=lfs merge=lfs -text
*.npy filter=lfs diff=lfs merge=lfs -text
*.npz filter=lfs diff=lfs merge=lfs -text
*.pickle filter=lfs diff=lfs merge=lfs -text
*.pkl filter=lfs diff=lfs merge=lfs -text
*.tar filter=lfs diff=lfs merge=lfs -text
*.wasm filter=lfs diff=lfs merge=lfs -text
*.zst filter=lfs diff=lfs merge=lfs -text
*tfevents* filter=lfs diff=lfs merge=lfs -text
model-00002-of-00002.safetensors filter=lfs diff=lfs merge=lfs -text
tokenizer.json filter=lfs diff=lfs merge=lfs -text
model-00000-of-00002.safetensors filter=lfs diff=lfs merge=lfs -text
model-00001-of-00002.safetensors filter=lfs diff=lfs merge=lfs -text

202
LICENSE Normal file
View File

@@ -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.

53
README.md Normal file
View File

@@ -0,0 +1,53 @@
---
license: apache-2.0
pipeline_tag: text-generation
library_name: transformers
tags:
- vllm
base_model:
- openai/gpt-oss-20b
base_model_relation: finetune
---
<p align="center">
<img alt="gpt-oss-safeguard-20b" src="https://raw.githubusercontent.com/openai/gpt-oss-safeguard/refs/heads/main/docs/gpt-oss-safeguard-20b.png">
</p>
<p align="center">
<a href="https://huggingface.co/spaces/openai/gpt-oss-safeguard-20b"><strong>Try gpt-oss-safeguard</strong></a> ·
<a href="https://cookbook.openai.com/articles/gpt-oss-safeguard-guide"><strong>Guide</strong></a> ·
<a href="https://arxiv.org/abs/2508.10925"><strong>Model card</strong></a> ·
<a href="https://openai.com/index/introducing-gpt-oss-safeguard/"><strong>OpenAI blog</strong></a>
</p>
<br>
`gpt-oss-safeguard-120b` and `gpt-oss-safeguard-20b` are safety reasoning models built-upon gpt-oss. With these models, you can classify text content based on safety policies that you provide and perform a suite of foundational safety tasks. These models are intended for safety use cases. For other applications, we recommend using [gpt-oss models](https://huggingface.co/collections/openai/gpt-oss).
This model `gpt-oss-safeguard-20b` (21B parameters with 3.6B active parameters) fits into GPUs with 16GB of VRAM. Check out [`gpt-oss-safeguard-120b`](https://huggingface.co/openai/gpt-oss-safeguard-120b) (117B parameters with 5.1B active parameters) for the larger model.
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.
## Highlights
* **Trained to reason about safety** : Trained and tuned for safety reasoning to accommodate use cases like LLM input-output filtering, online content labeling and offline labeling for Trust and Safety use cases.
* **Bring your own policy:** Interprets your written policy, so it generalizes across products and use cases with minimal engineering.
* **Reasoned decisions, not just scores:** Gain complete access to the model’s reasoning process, facilitating easier debugging and increased trust in policy decisions. Keep in mind Raw CoT is meant for developers and safety practitioners. It’s not intended for exposure to general users or use cases outside of safety contexts.
* **Configurable reasoning effort:** Easily adjust the reasoning effort (low, medium, high) based on your specific use case and latency needs.
* **Permissive Apache 2.0 license:** Build freely without copyleft restrictions or patent risk—ideal for experimentation, customization, and commercial deployment.
## Inference examples
You can use gpt-oss-safeguard-120b and gpt-oss-safeguard-20b similar to gpt-oss-120b and gpt-oss-20b as described in our [respective cookbooks](https://cookbook.openai.com/topic/gpt-oss). We’ve also provided a detailed [prompting guide](https://cookbook.openai.com/articles/gpt-oss-safeguard-guide) that provides guidelines for how to craft your policy and use it with the models.
## Download the model
To download the model weights from [Hugging Face hub](https://huggingface.co/collections/openai/gpt-oss-safeguard) using [similar instructions](https://huggingface.co/openai/gpt-oss-120b#download-the-model) to gpt-oss-120b.
## Join the ROOST Model Community
gpt-oss-safeguard is a model partner of the [Robust Open Online Safety Tools (ROOST)](http://roost.tools/) Model Community. The ROOST Model Community (RMC) is a group of safety practitioners exploring open source AI models to protect online spaces. As an RMC model partner, OpenAI is committed to incorporating user feedback and jointly iterating on future releases in pursuit of open safety. Visit the [RMC GitHub repo](https://github.com/roostorg/open-models) to learn more about this partnership and how to get involved.
## Resources
* [Try gpt-oss-safeguard](https://huggingface.co/spaces/openai/gpt-oss-safeguard-20b)
* [OpenAI blog](https://openai.com/index/introducing-gpt-oss-safeguard/)

1
USAGE_POLICY Normal file
View File

@@ -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-safeguard-120b and gpt-oss-safeguard-20b, you agree to comply with all applicable law.

406
chat_template.jinja Normal file
View File

@@ -0,0 +1,406 @@
{#-
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 -%}
{{- "{
" }}
{%- 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 + "
" }}
{{- "namespace " + namespace_name + " {
" }}
{%- for tool in tools %}
{%- set tool = tool.function %}
{{- "// " + tool.description + "
" }}
{{- "type "+ tool.name + " = " }}
{%- if tool.parameters and tool.parameters.properties %}
{{- "(_: {
" }}
{%- for param_name, param_spec in tool.parameters.properties.items() %}
{%- if param_spec.description %}
{{- "// " + param_spec.description + "
" }}
{%- 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 %}
{{- ",
" }}
{%- else %}
{{- ",
" }}
{%- endif -%}
{%- endfor %}
{{- "}) => any;
" }}
{%- else -%}
{{- "() => any;
" }}
{%- endif -%}
{%- endfor %}
{{- "} // namespace " + namespace_name }}
{%- endmacro -%}
{%- macro render_builtin_tools(browser_tool, python_tool) -%}
{%- if browser_tool %}
{{- "## browser
" }}
{{- "// Tool for browsing.
" }}
{{- "// The `cursor` appears in brackets before each browsing display: `[{cursor}]`.
" }}
{{- "// Cite information from the tool using the following format:
" }}
{{- "// `【{cursor}†L{line_start}(-L{line_end})?】`, for example: `【6†L9-L11】` or `【8†L3】`.
" }}
{{- "// Do not quote more than 10 words directly from the tool output.
" }}
{{- "// sources=web (default: web)
" }}
{{- "namespace browser {
" }}
{{- "// Searches for information related to `query` and displays `topn` results.
" }}
{{- "type search = (_: {
" }}
{{- "query: string,
" }}
{{- "topn?: number, // default: 10
" }}
{{- "source?: string,
" }}
{{- "}) => any;
" }}
{{- "// Opens the link `id` from the page indicated by `cursor` starting at line number `loc`, showing `num_lines` lines.
" }}
{{- "// Valid link ids are displayed with the formatting: `【{id}†.*】`.
" }}
{{- "// If `cursor` is not provided, the most recent page is implied.
" }}
{{- "// If `id` is a string, it is treated as a fully qualified URL associated with `source`.
" }}
{{- "// 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.
" }}
{{- "// Use this function without `id` to scroll to a new location of an opened page.
" }}
{{- "type open = (_: {
" }}
{{- "id?: number | string, // default: -1
" }}
{{- "cursor?: number, // default: -1
" }}
{{- "loc?: number, // default: -1
" }}
{{- "num_lines?: number, // default: -1
" }}
{{- "view_source?: boolean, // default: false
" }}
{{- "source?: string,
" }}
{{- "}) => any;
" }}
{{- "// Finds exact matches of `pattern` in the current page, or the page given by `cursor`.
" }}
{{- "type find = (_: {
" }}
{{- "pattern: string,
" }}
{{- "cursor?: number, // default: -1
" }}
{{- "}) => any;
" }}
{{- "} // namespace browser
" }}
{%- endif -%}
{%- if python_tool %}
{{- "## python
" }}
{{- "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).
" }}
{{- "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.
" }}
{%- 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 + "
" }}
{{- "Knowledge cutoff: 2024-06
" }}
{{- "Current date: " + strftime_now("%Y-%m-%d") + "
" }}
{%- if reasoning_effort is not defined %}
{%- set reasoning_effort = "medium" %}
{%- endif %}
{{- "Reasoning: " + reasoning_effort + "
" }}
{%- if builtin_tools %}
{{- "# Tools
" }}
{%- 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 -%}
{{- "
Calls 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
" }}
{{- developer_message }}
{%- endif %}
{%- if tools -%}
{{- "
" }}
{{- "# Tools
" }}
{{- 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 -%}

3
chat_template.json Normal file
View File

File diff suppressed because one or more lines are too long

76
config.json Normal file
View File

@@ -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": "4.57.0.dev0",
"use_cache": true,
"vocab_size": 201088
}

1
configuration.json Normal file
View File

@@ -0,0 +1 @@
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}

10
generation_config.json Normal file
View File

@@ -0,0 +1,10 @@
{
"bos_token_id": 199998,
"do_sample": true,
"eos_token_id": [
200002,
199999
],
"pad_token_id": 199999,
"transformers_version": "4.57.0.dev0"
}

3
model-00000-of-00002.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ef82af3aff019605840ebd545957b8493a65a179a8c11339e50753d311195d12
size 4792272488

3
model-00001-of-00002.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:19684279c3bf220c0bf6e63a86ee22a2724debb6972c7ad59b0d8aa42dff642d
size 4798702184

3
model-00002-of-00002.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e18569972d3995dd7327e4423a6a3de5b1356223d4f710808bfcbac09f2b4d5d
size 4170342232

1
model.safetensors.index.json Normal file
View File

File diff suppressed because one or more lines are too long

5
special_tokens_map.json Normal file
View File

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

3
tokenizer.json Normal file
View File

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

183
tokenizer_config.json Normal file
View File

@@ -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"
}