ruhui 0.1.0__tar.gz

ruhui-0.1.0/LICENSE

@@ -0,0 +1,176 @@
+                                 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

ruhui-0.1.0/NOTICE

@@ -0,0 +1,12 @@
+Ruhui
+Copyright 2026 AnyForge
+
+This product is a fork of Laya (https://github.com/NandhaKishorM/laya),
+copyright the respective contributors, licensed under the Apache License 2.0.
+
+Modifications include, but are not limited to:
+- A multilingual (mmBERT-base) backbone fine-tuned for Chinese/English decision tasks.
+- Package and model renamed to "ruhui".
+- Single-checkpoint routing.
+
+See LICENSE for the full license text.

ruhui-0.1.0/PKG-INFO

@@ -0,0 +1,175 @@
+Metadata-Version: 2.4
+Name: ruhui
+Version: 0.1.0
+Summary: Ruhui: 非自回归 System 1 决策引擎（中文/多语言），带校准概率。命名取自房谋杜断的杜如晦。
+Author: AnyForge
+License: Apache-2.0
+Project-URL: Homepage, https://github.com/anyforge/ruhui
+Keywords: decision-model,rlcd,calibration,system-one,routing,guardrails,moderation,triage,chinese
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+License-File: NOTICE
+Requires-Dist: torch>=2.0.0
+Requires-Dist: transformers>=4.48.0
+Requires-Dist: safetensors>=0.4.0
+Requires-Dist: huggingface_hub>=0.20.0
+Requires-Dist: numpy>=1.20.0
+Dynamic: license-file
+
+# Ruhui · 如晦
+
+**A non-autoregressive System 1 decision engine for Chinese & multilingual text, with calibrated probabilities.**
+
+**非自回归 System 1 决策引擎（中文/多语言），带校准概率。**
+
+Named after Du Ruhui (杜如晦, courtesy name Keming 克明) of the "Fang Mou Du Duan" (房谋杜断) pair — Fang Xuanling was the strategist, Du Ruhui the decisive judge. *Ruhui* inherits the "decisive" half: a fast System 1 decision maker that generates no text, has nothing to parse, and therefore cannot hallucinate.
+
+命名取自「房谋杜断」的杜如晦（字克明），「晦」音近「hui」。房玄龄善谋、杜如晦善断——Ruhui 取「断」之意：System 1 快速决策，不生成文本、无可解析输出、因此无幻觉。
+
+Architecture forked from [Laya](https://github.com/NandhaKishorM/laya) (Apache 2.0), with two key changes:
+架构参照 [Laya](https://github.com/NandhaKishorM/laya)（Apache 2.0），在此基础上：
+
+- **Chinese/multilingual backbone**: `mmBERT-base` (100+ languages) instead of English-only ModernBERT.
+  **中文/多语言底座**：`mmBERT-base`（100+ 语言），而非英语-only 的 ModernBERT。
+- **Bilingual soft-label fine-tuning**: 30+ domain datasets (intent / sentiment / safety / agent decision / tool-calling / …).
+  **中英双语软标签微调**：覆盖 30+ 领域数据集（意图/情感/安全/智能体决策/工具调用等）。
+
+---
+
+## Architecture · 架构
+
+```
+bidirectional encoder (mmBERT-base)
+  → type injection (choice / score / noul)
+  → 2-layer decision head
+  → parallel scoring at [MASK] slots
+  → softmax distribution (calibrated probabilities via strictly-proper-scoring-rule RLCD)
+```
+
+Three decision primitives · 三种决策原语：
+
+| Primitive · 原语 | Output · 输出 |
+|---|---|
+| **choice** | top label + full probability distribution + confidence |
+| **score** | expected level on an ordinal rubric |
+| **noul** | calibrated P(true) |
+
+---
+
+## Installation · 安装
+
+```bash
+pip install ruhui
+```
+
+Python 3.10+. Dependencies: `torch`, `transformers`, `safetensors`, `huggingface_hub`, `numpy`.
+依赖：`torch`、`transformers`、`safetensors`、`huggingface_hub`、`numpy`。
+
+---
+
+## Quick Start · 快速开始
+
+```python
+import ruhui
+
+# Load the fine-tuned ruhui checkpoint (from the hub, or a local directory)
+# 加载微调后的 ruhui checkpoint（从仓库拉取，或本地目录路径）
+agent = ruhui.load("anyforge/ruhui")
+
+# The Router also accepts a local path (skips hub download):
+# Router 同样支持本地路径（不走仓库下载）：
+router = ruhui.Router(model_path="./pretrained/ruhui")
+result = router.predict(state, questions)
+
+# Answer multiple structured questions in a single forward pass
+# 一次前向传播回答多个结构化问题
+result = agent.predict(
+    {"message": "我被重复扣款了，请退款"},
+    {
+        "intent": {
+            "type": "choice",
+            "instructions": "客户想做什么？",
+            "criteria": {"refund": "退款", "technical": "技术问题", "billing": "账单咨询"},
+        },
+        "churn_risk": {
+            "type": "noul",
+            "instructions": "客户是否威胁要离开？",
+        },
+    },
+)
+print(result["answers"])
+```
+
+---
+
+## Fine-Tuning · 微调
+
+Fine-tune ruhui on your own domain data (RLCD + soft distillation + temperature calibration).
+在自己的领域数据上微调（RLCD + 软蒸馏 + 温度校准）。
+
+1. **Prepare soft-label data** · 准备软标签数据
+   `datas/soft_*.jsonl`, each line: `text` + `qtype` + `soft_label.probabilities`.
+   每行含 `text` + `qtype` + `soft_label.probabilities`。
+
+2. **Build training items** · 转训练 items：
+   ```bash
+   python3 scripts/prepare_train_data.py \
+     --model_dir <base_model_dir> \
+     --soft_dir <soft_label_dir> \
+     --out <train_items.pt>
+   ```
+
+3. **Train** · 训练：
+   ```bash
+   python3 scripts/train.py \
+     --model_dir <base_model_dir> \
+     --train_items <train_items.pt> \
+     --output_dir <output_dir> \
+     --epochs 4
+   ```
+
+4. **Inference** · 推理：
+   ```bash
+   python3 scripts/predict.py --model_dir <output_dir> --text "..." \
+     --question-type noul --instruction "..."
+   ```
+
+---
+
+## Repository Layout · 目录结构
+
+```
+ruhui/
+  ruhui/            # package · 包（agent / router / common / presets / …）
+  scripts/          # fine-tuning + inference scripts · 微调 + 推理脚本
+    prepare_train_data.py
+    train.py
+    predict.py
+  tests/
+  pyproject.toml
+```
+
+---
+
+## Model Repositories · 模型仓库
+
+- Hugging Face: `anyforge/ruhui`
+- ModelScope: `anyforge/ruhui`
+
+> Single checkpoint: fine-tuned from `mmBERT-base`, bilingual (Chinese/English). Load it directly with `ruhui.load("anyforge/ruhui")`.
+> 单一 checkpoint：基于 `mmBERT-base` 微调，中英双语。直接 `ruhui.load("anyforge/ruhui")` 加载。
+
+## License
+
+Apache 2.0 (inherited from Laya). Developed by AnyForge.
+Apache 2.0（参照 Laya）。Developed by AnyForge。

ruhui-0.1.0/README.md

@@ -0,0 +1,147 @@
+# Ruhui · 如晦
+
+**A non-autoregressive System 1 decision engine for Chinese & multilingual text, with calibrated probabilities.**
+
+**非自回归 System 1 决策引擎（中文/多语言），带校准概率。**
+
+Named after Du Ruhui (杜如晦, courtesy name Keming 克明) of the "Fang Mou Du Duan" (房谋杜断) pair — Fang Xuanling was the strategist, Du Ruhui the decisive judge. *Ruhui* inherits the "decisive" half: a fast System 1 decision maker that generates no text, has nothing to parse, and therefore cannot hallucinate.
+
+命名取自「房谋杜断」的杜如晦（字克明），「晦」音近「hui」。房玄龄善谋、杜如晦善断——Ruhui 取「断」之意：System 1 快速决策，不生成文本、无可解析输出、因此无幻觉。
+
+Architecture forked from [Laya](https://github.com/NandhaKishorM/laya) (Apache 2.0), with two key changes:
+架构参照 [Laya](https://github.com/NandhaKishorM/laya)（Apache 2.0），在此基础上：
+
+- **Chinese/multilingual backbone**: `mmBERT-base` (100+ languages) instead of English-only ModernBERT.
+  **中文/多语言底座**：`mmBERT-base`（100+ 语言），而非英语-only 的 ModernBERT。
+- **Bilingual soft-label fine-tuning**: 30+ domain datasets (intent / sentiment / safety / agent decision / tool-calling / …).
+  **中英双语软标签微调**：覆盖 30+ 领域数据集（意图/情感/安全/智能体决策/工具调用等）。
+
+---
+
+## Architecture · 架构
+
+```
+bidirectional encoder (mmBERT-base)
+  → type injection (choice / score / noul)
+  → 2-layer decision head
+  → parallel scoring at [MASK] slots
+  → softmax distribution (calibrated probabilities via strictly-proper-scoring-rule RLCD)
+```
+
+Three decision primitives · 三种决策原语：
+
+| Primitive · 原语 | Output · 输出 |
+|---|---|
+| **choice** | top label + full probability distribution + confidence |
+| **score** | expected level on an ordinal rubric |
+| **noul** | calibrated P(true) |
+
+---
+
+## Installation · 安装
+
+```bash
+pip install ruhui
+```
+
+Python 3.10+. Dependencies: `torch`, `transformers`, `safetensors`, `huggingface_hub`, `numpy`.
+依赖：`torch`、`transformers`、`safetensors`、`huggingface_hub`、`numpy`。
+
+---
+
+## Quick Start · 快速开始
+
+```python
+import ruhui
+
+# Load the fine-tuned ruhui checkpoint (from the hub, or a local directory)
+# 加载微调后的 ruhui checkpoint（从仓库拉取，或本地目录路径）
+agent = ruhui.load("anyforge/ruhui")
+
+# The Router also accepts a local path (skips hub download):
+# Router 同样支持本地路径（不走仓库下载）：
+router = ruhui.Router(model_path="./pretrained/ruhui")
+result = router.predict(state, questions)
+
+# Answer multiple structured questions in a single forward pass
+# 一次前向传播回答多个结构化问题
+result = agent.predict(
+    {"message": "我被重复扣款了，请退款"},
+    {
+        "intent": {
+            "type": "choice",
+            "instructions": "客户想做什么？",
+            "criteria": {"refund": "退款", "technical": "技术问题", "billing": "账单咨询"},
+        },
+        "churn_risk": {
+            "type": "noul",
+            "instructions": "客户是否威胁要离开？",
+        },
+    },
+)
+print(result["answers"])
+```
+
+---
+
+## Fine-Tuning · 微调
+
+Fine-tune ruhui on your own domain data (RLCD + soft distillation + temperature calibration).
+在自己的领域数据上微调（RLCD + 软蒸馏 + 温度校准）。
+
+1. **Prepare soft-label data** · 准备软标签数据
+   `datas/soft_*.jsonl`, each line: `text` + `qtype` + `soft_label.probabilities`.
+   每行含 `text` + `qtype` + `soft_label.probabilities`。
+
+2. **Build training items** · 转训练 items：
+   ```bash
+   python3 scripts/prepare_train_data.py \
+     --model_dir <base_model_dir> \
+     --soft_dir <soft_label_dir> \
+     --out <train_items.pt>
+   ```
+
+3. **Train** · 训练：
+   ```bash
+   python3 scripts/train.py \
+     --model_dir <base_model_dir> \
+     --train_items <train_items.pt> \
+     --output_dir <output_dir> \
+     --epochs 4
+   ```
+
+4. **Inference** · 推理：
+   ```bash
+   python3 scripts/predict.py --model_dir <output_dir> --text "..." \
+     --question-type noul --instruction "..."
+   ```
+
+---
+
+## Repository Layout · 目录结构
+
+```
+ruhui/
+  ruhui/            # package · 包（agent / router / common / presets / …）
+  scripts/          # fine-tuning + inference scripts · 微调 + 推理脚本
+    prepare_train_data.py
+    train.py
+    predict.py
+  tests/
+  pyproject.toml
+```
+
+---
+
+## Model Repositories · 模型仓库
+
+- Hugging Face: `anyforge/ruhui`
+- ModelScope: `anyforge/ruhui`
+
+> Single checkpoint: fine-tuned from `mmBERT-base`, bilingual (Chinese/English). Load it directly with `ruhui.load("anyforge/ruhui")`.
+> 单一 checkpoint：基于 `mmBERT-base` 微调，中英双语。直接 `ruhui.load("anyforge/ruhui")` 加载。
+
+## License
+
+Apache 2.0 (inherited from Laya). Developed by AnyForge.
+Apache 2.0（参照 Laya）。Developed by AnyForge。

ruhui-0.1.0/pyproject.toml

@@ -0,0 +1,39 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "ruhui"
+version = "0.1.0"
+description = "Ruhui: 非自回归 System 1 决策引擎（中文/多语言），带校准概率。命名取自房谋杜断的杜如晦。"
+readme = "README.md"
+requires-python = ">=3.10"
+license = { text = "Apache-2.0" }
+authors = [
+    { name = "AnyForge" }
+]
+keywords = ["decision-model", "rlcd", "calibration", "system-one", "routing", "guardrails", "moderation", "triage", "chinese"]
+classifiers = [
+    "Development Status :: 4 - Beta",
+    "Intended Audience :: Developers",
+    "License :: OSI Approved :: Apache Software License",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Programming Language :: Python :: 3.13",
+    "Topic :: Scientific/Engineering :: Artificial Intelligence",
+]
+dependencies = [
+    "torch>=2.0.0",
+    "transformers>=4.48.0",
+    "safetensors>=0.4.0",
+    "huggingface_hub>=0.20.0",
+    "numpy>=1.20.0",
+]
+
+[tool.setuptools]
+packages = ["ruhui"]
+
+[project.urls]
+Homepage = "https://github.com/anyforge/ruhui"

ruhui-0.1.0/ruhui/__init__.py

@@ -0,0 +1,59 @@
+"""Ruhui: 非自回归 System 1 决策引擎（中文/多语言），带校准概率。
+
+参照 Laya 架构 fork，命名取自房谋杜断的杜如晦（字克明），"晦"音近"hui"，
+寓"谋断"——System 1 快速决策。
+"""
+
+from .agent import Agent, RLAgent, load
+from .common import (
+    QTYPES,
+    QTYPE_NAMES,
+    confidence_from_probs,
+    ece_score,
+    proper_reward,
+    render_options,
+    td_lambda_targets,
+)
+from .email import clean_email_body, email_state
+from .lang import analyse as detect_language
+from .lang import detect_script, is_english
+from .presets import (
+    email_questions,
+    guard_questions,
+    moderation_questions,
+    router_questions,
+    triage_questions,
+)
+from .router import DEFAULT_MODELS, RouteDecision, Router
+from .shortlist import embed_fn_from_agent, predict_shortlist, shortlist_choice
+
+__version__ = "0.1.0"
+__all__ = [
+    "Agent",
+    "RLAgent",
+    "load",
+    "Router",
+    "RouteDecision",
+    "DEFAULT_MODELS",
+    "shortlist_choice",
+    "predict_shortlist",
+    "embed_fn_from_agent",
+    "detect_language",
+    "detect_script",
+    "is_english",
+    "clean_email_body",
+    "email_questions",
+    "email_state",
+    "guard_questions",
+    "moderation_questions",
+    "router_questions",
+    "triage_questions",
+    "proper_reward",
+    "td_lambda_targets",
+    "ece_score",
+    "confidence_from_probs",
+    "render_options",
+    "QTYPES",
+    "QTYPE_NAMES",
+    "__version__",
+]