text-emotion-classification

.gitignore

@@ -0,0 +1,46 @@
+# Python
+__pycache__/
+*.py[cod]
+*$py.class
+.venv/
+venv/
+ENV/
+.env
+.env.*
+
+# Conda
+.conda/
+
+# Jupyter
+.ipynb_checkpoints/
+
+# OS / IDE
+.DS_Store
+Thumbs.db
+.vscode/
+.idea/
+.cursor/
+
+# Logs
+*.log
+
+# Build / packaging
+build/
+dist/
+*.spec
+
+# Hugging Face / Transformers caches
+.cache/
+
+# Model training artifacts (NOT needed for inference)
+sentiment_roberta/checkpoint-*/
+sentiment_roberta/**/optimizer.pt
+sentiment_roberta/**/scheduler.pt
+sentiment_roberta/**/scaler.pt
+sentiment_roberta/**/rng_state.pth
+sentiment_roberta/**/trainer_state.json
+sentiment_roberta/**/training_args.bin
+sentiment_roberta/training_args.bin
+
+# Optional: keep only inference model files in sentiment_roberta/
+# (Do NOT ignore model.safetensors/config/tokenizer* by default)

LICENSE

@@ -0,0 +1,201 @@
+                                 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

@@ -1,3 +1,59 @@
----
-license: apache-2.0
----
+# text-emotion-classification
+
+A text emotion recognition application that can be quickly deployed and used locally. You can perform interactive inference simply by running `main.py`.
+
+[中文版](./README_zh.md)
+
+## Features
+
+- **Local Inference**: Loads the `sentiment_roberta` model directory within the repository for text emotion classification.
+- **Label Mapping**: Reads `id -> Chinese Emotion Name` mapping from `text-emotion.yaml`.
+- **Interactive CLI**: Enter text in the command line to output the emotion category and confidence level.
+
+## Directory Structure (Key Files)
+
+- `main.py`: Entry script (run directly).
+- `sentiment_roberta/`: Exported Transformers model directory (contains `config.json`, `model.safetensors`, tokenizer, etc.).
+- `text-emotion.yaml`: Label mapping file.
+- `release-note.md`: Release notes (used by GitHub Actions as the release body).
+
+## Environment Requirements
+
+- **Python 3.10** (Recommended, matches the author's environment; 3.9+ is theoretically compatible but not fully verified).
+- **Dependency Management**: Conda environment (recommended) or venv.
+- **PyTorch**:
+  - **CPU Inference**: Install the CPU version of `torch`.
+  - **GPU Inference**: Requires an NVIDIA GPU + corresponding CUDA version (the author's environment uses `torch==2.10.0+cu128` / `torchvision==0.25.0+cu128` built with CUDA 12.8).
+
+The author's conda environment export file is provided: `environment.yml`.
+
+## Installation
+
+### Using Conda Environment File (Recommended)
+
+```bash
+conda env create -f environment.yml
+conda activate text-emotion-classification
+```
+
+## Usage
+
+```bash
+python main.py
+```
+
+Follow the prompts to enter text:
+- **Enter any text**: Outputs emotion prediction and confidence.
+- **Empty input (Enter)**: Exits the program.
+
+## FAQ
+
+- **Cannot find model directory `sentiment_roberta`**
+  - Ensure `sentiment_roberta/` exists in the root directory and contains files like `config.json` and `model.safetensors`.
+- **Inference Device**
+  - The program automatically selects `cuda` if available; otherwise, it defaults to `cpu`.
+
+## License
+
+See [Apache 2.0 License](./LICENSE).
+

README_zh.md

@@ -0,0 +1,57 @@
+# text-emotion-classification
+
+一个可本地快捷部署使用的文本情绪识别模型应用。项目直接运行 `main.py` 即可进行交互式推理。
+
+## 功能
+
+- **本地推理**：加载仓库内的 `sentiment_roberta` 模型目录进行文本情绪分类。
+- **标签映射**：从 `text-emotion.yaml` 读取 `id -> 情绪中文名` 映射。
+- **交互式 CLI**：命令行输入文本，输出情绪类别与置信度。
+
+## 目录结构（关键文件）
+
+- `main.py`：入口脚本（直接运行即可）
+- `sentiment_roberta/`：已导出的 Transformers 模型目录（包含 `config.json`、`model.safetensors`、tokenizer 等）
+- `text-emotion.yaml`：标签映射文件
+- `release-note.md`：Release 说明（由 GitHub Action 用作 release body）
+
+## 运行环境配置要求
+
+- Python 3.10（推荐，与作者环境一致；3.9+ 理论可用但未完整验证）
+- 依赖管理方式：Conda 环境（推荐）或 venv
+- PyTorch：
+  - CPU 推理：安装 CPU 版 `torch`
+  - GPU 推理：需要 NVIDIA GPU + 对应版本 CUDA（本仓库作者环境为 `torch==2.10.0+cu128` / `torchvision==0.25.0+cu128`，即 CUDA 12.8 构建）
+
+本仓库提供了作者的 conda 环境导出文件：`environment.yml`。
+
+## 安装
+
+### 使用 conda 环境文件（推荐，复现作者环境）
+
+```bash
+conda env create -f environment.yml
+conda activate text-emotion-classification
+```
+
+## 运行
+
+```bash
+python main.py
+```
+
+运行后按提示输入文本：
+
+- 输入任意文本并回车：输出情绪预测与置信度
+- 直接回车：退出
+
+## 常见问题
+
+- **找不到模型目录 `sentiment_roberta`**
+  - 请确认仓库根目录下存在 `sentiment_roberta/`，且其中包含 `config.json`、`model.safetensors` 等文件。
+- **模型推理设备**
+  - 程序会自动选择 `cuda`（如可用）否则使用 `cpu`。
+
+## License
+
+见 [Apache 2.0 License](./LICENSE)。

environment.yml

@@ -0,0 +1,185 @@
+name: text-emotion-classification
+channels:
+  - conda-forge
+  - defaults
+dependencies:
+  - asttokens=3.0.1
+  - blas=1.0
+  - boto3=1.42.34
+  - botocore=1.42.34
+  - bottleneck=1.4.2
+  - brotlicffi=1.2.0.0
+  - bzip2=1.0.8
+  - ca-certificates=2026.1.4
+  - cairo=1.18.4
+  - certifi=2026.01.04
+  - cffi=2.0.0
+  - charset-normalizer=3.4.4
+  - colorama=0.4.6
+  - comm=0.2.3
+  - contourpy=1.3.1
+  - cycler=0.12.1
+  - debugpy=1.8.20
+  - decorator=5.2.1
+  - exceptiongroup=1.3.1
+  - executing=2.2.1
+  - expat=2.7.4
+  - fontconfig=2.15.0
+  - fonttools=4.61.0
+  - freetype=2.14.1
+  - graphite2=1.3.14
+  - harfbuzz=12.3.0
+  - icc_rt=2022.1.0
+  - icu=73.1
+  - idna=3.11
+  - intel-openmp=2025.0.0
+  - ipykernel=7.2.0
+  - ipython=8.37.0
+  - jedi=0.19.2
+  - jmespath=1.1.0
+  - joblib=1.5.3
+  - jpeg=9f
+  - jupyter_client=8.8.0
+  - jupyter_core=5.9.1
+  - kiwisolver=1.4.9
+  - krb5=1.21.3
+  - lcms2=2.16
+  - lerc=3.0
+  - libdeflate=1.17
+  - libexpat=2.7.4
+  - libffi=3.4.4
+  - libglib=2.86.3
+  - libhwloc=2.12.1
+  - libiconv=1.16
+  - libkrb5=1.22.1
+  - libpng=1.6.54
+  - libpq=17.6
+  - libsodium=1.0.20
+  - libtiff=4.5.1
+  - libwebp-base=1.6.0
+  - libxml2=2.13.9
+  - libzlib=1.3.1
+  - lz4-c=1.9.4
+  - matplotlib=3.10.8
+  - matplotlib-base=3.10.8
+  - matplotlib-inline=0.2.1
+  - mkl=2025.0.0
+  - mkl-service=2.5.2
+  - mkl_fft=2.1.1
+  - mkl_random=1.3.0
+  - mysql-common=9.3.0
+  - mysql-libs=9.3.0
+  - nest-asyncio=1.6.0
+  - numexpr=2.14.1
+  - numpy-base=2.2.5
+  - openjpeg=2.5.2
+  - openssl=3.6.1
+  - packaging=25.0
+  - pandas=2.3.3
+  - parso=0.8.6
+  - pcre2=10.46
+  - pickleshare=0.7.5
+  - pip=26.0.1
+  - pixman=0.46.4
+  - platformdirs=4.5.1
+  - prompt-toolkit=3.0.52
+  - psutil=7.2.2
+  - pure_eval=0.2.3
+  - pycparser=2.23
+  - pygments=2.19.2
+  - pyparsing=3.2.5
+  - pyqt=6.9.1
+  - pyqt6-sip=13.10.2
+  - pysocks=1.7.1
+  - python=3.10.19
+  - python-dateutil=2.9.0post0
+  - python-tzdata=2025.3
+  - python_abi=3.10
+  - pytz=2025.2
+  - pywin32=311
+  - pyzmq=27.1.0
+  - qtbase=6.9.2
+  - qtdeclarative=6.9.2
+  - qtsvg=6.9.2
+  - qttools=6.9.2
+  - qtwebchannel=6.9.2
+  - qtwebsockets=6.9.2
+  - regex=2025.11.3
+  - requests=2.32.5
+  - s3transfer=0.16.0
+  - sacremoses=0.1.1
+  - scikit-learn=1.7.1
+  - scipy=1.15.3
+  - setuptools=80.10.2
+  - sip=6.12.0
+  - six=1.17.0
+  - sqlite=3.51.1
+  - stack_data=0.6.3
+  - tbb=2022.3.0
+  - tbb-devel=2022.3.0
+  - threadpoolctl=3.5.0
+  - tk=8.6.15
+  - tomli=2.4.0
+  - tornado=6.5.4
+  - tqdm=4.67.3
+  - traitlets=5.14.3
+  - typing_extensions=4.15.0
+  - tzdata=2025c
+  - ucrt=10.0.22621.0
+  - urllib3=2.6.3
+  - vc=14.3
+  - vc14_runtime=14.44.35208
+  - vs2015_runtime=14.44.35208
+  - wcwidth=0.6.0
+  - wheel=0.46.3
+  - win_inet_pton=1.1.0
+  - xz=5.6.4
+  - zeromq=4.3.5
+  - zlib=1.3.1
+  - zstd=1.5.7
+  - pip:
+      - accelerate==1.12.0
+      - aiohappyeyeballs==2.6.1
+      - aiohttp==3.13.3
+      - aiosignal==1.4.0
+      - annotated-doc==0.0.4
+      - anyio==4.12.1
+      - async-timeout==5.0.1
+      - attrs==25.4.0
+      - click==8.3.1
+      - datasets==4.5.0
+      - dill==0.4.0
+      - filelock==3.20.0
+      - frozenlist==1.8.0
+      - fsspec==2025.10.0
+      - h11==0.16.0
+      - hf-xet==1.2.0
+      - httpcore==1.0.9
+      - httpx==0.28.1
+      - huggingface-hub==1.4.1
+      - jinja2==3.1.6
+      - markdown-it-py==4.0.0
+      - markupsafe==2.1.5
+      - mdurl==0.1.2
+      - mpmath==1.3.0
+      - multidict==6.7.1
+      - multiprocess==0.70.18
+      - networkx==3.4.2
+      - numpy==2.2.6
+      - pillow==12.0.0
+      - propcache==0.4.1
+      - pyarrow==23.0.0
+      - pyyaml==6.0.3
+      - rich==14.3.2
+      - safetensors==0.7.0
+      - shellingham==1.5.4
+      - sympy==1.14.0
+      - tokenizers==0.22.2
+      - torch==2.10.0+cu128
+      - torchvision==0.25.0+cu128
+      - transformers==5.1.0
+      - typer==0.23.1
+      - typer-slim==0.23.1
+      - xxhash==3.6.0
+      - yarl==1.22.0
+

main.py

@@ -0,0 +1,96 @@
+import os
+import sys
+import yaml
+import torch
+import numpy as np
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+
+
+def load_label_map(yaml_path: str):
+    with open(yaml_path, "r", encoding="utf-8") as f:
+        data = yaml.safe_load(f)
+
+    label_map = {}
+    if isinstance(data, list):
+        # 支持两种写法：
+        # - 0: 伤心
+        # - {0: 伤心}
+        for item in data:
+            if isinstance(item, dict):
+                for k, v in item.items():
+                    label_map[int(k)] = str(v)
+            elif isinstance(item, str) and ":" in item:
+                k, v = item.split(":", 1)
+                label_map[int(k.strip())] = v.strip()
+    elif isinstance(data, dict):
+        for k, v in data.items():
+            label_map[int(k)] = str(v)
+    else:
+        raise ValueError(f"无法解析标签映射：{yaml_path}")
+
+    if not label_map:
+        raise ValueError(f"标签映射为空：{yaml_path}")
+
+    return label_map
+
+
+def predict(text: str, tokenizer, model, device: torch.device):
+    inputs = tokenizer(text, return_tensors="pt", truncation=True, padding=True, max_length=128)
+    inputs = {k: v.to(device) for k, v in inputs.items()}
+
+    model.eval()
+    with torch.no_grad():
+        outputs = model(**inputs)
+        logits = outputs.logits
+        probs = torch.softmax(logits, dim=-1).detach().cpu().numpy()[0]
+
+    pred_id = int(np.argmax(probs))
+    confidence = float(probs[pred_id])
+    return pred_id, confidence, probs
+
+
+def main():
+    base_dir = os.path.dirname(os.path.abspath(__file__))
+    model_dir = os.path.join(base_dir, "sentiment_roberta")
+    yaml_path = os.path.join(base_dir, "text-emotion.yaml")
+
+    if not os.path.isdir(model_dir):
+        print(f"找不到模型目录：{model_dir}")
+        print("请先训练并确保训练脚本 output_dir=./sentiment_roberta（相对 data_preload 目录）。")
+        sys.exit(1)
+
+    if not os.path.isfile(yaml_path):
+        print(f"找不到标签映射文件：{yaml_path}")
+        sys.exit(1)
+
+    label_map = load_label_map(yaml_path)
+
+    device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+    print(f"推理设备：{device}")
+
+    tokenizer = AutoTokenizer.from_pretrained(model_dir)
+    model = AutoModelForSequenceClassification.from_pretrained(model_dir)
+    model.to(device)
+
+    print("请输入一段文本（直接回车退出）：")
+    while True:
+        try:
+            text = input("> ").strip()
+        except (EOFError, KeyboardInterrupt):
+            print("\n退出")
+            break
+
+        if not text:
+            print("退出")
+            break
+
+        pred_id, conf, _ = predict(text, tokenizer, model, device)
+        emotion_cn = label_map.get(pred_id, f"未知标签({pred_id})")
+
+        print(f"情绪预测：{emotion_cn}")
+        print(f"置信度：{conf:.4f}")
+
+
+if __name__ == "__main__":
+    main()
+

sentiment_roberta/config.json

@@ -0,0 +1,56 @@
+{
+  "add_cross_attention": false,
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "is_decoder": false,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "problem_type": "single_label_classification",
+  "tie_word_embeddings": true,
+  "transformers_version": "5.1.0",
+  "type_vocab_size": 2,
+  "use_cache": false,
+  "vocab_size": 21128
+}

sentiment_roberta/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a64010a9f27db8eab2ef283add822ec36106abc778399f2bd8dfa5c1d2f189e
+size 409118672

sentiment_roberta/tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "backend": "tokenizers",
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "is_local": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

text-emotion-classification.py

@@ -0,0 +1,66 @@
+from transformers import AutoTokenizer, AutoModelForSequenceClassification, TrainingArguments, Trainer
+from datasets import load_dataset
+import numpy as np
+
+# 1️⃣ 载入中文 RoBERTa 分词器和模型
+model_name = "hfl/chinese-roberta-wwm-ext"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+
+# 指定标签数量，比如 8 类情绪
+model = AutoModelForSequenceClassification.from_pretrained(model_name, num_labels=8)
+
+# 2️⃣ 加载自己情绪数据集
+# 需要 CSV 至少包含两列：text（文本）、label（整数标签）
+dataset = load_dataset(
+    "csv",
+    data_files={
+        "train": "emotion-classification-train.csv",
+        "test": "emotion-classification-train.csv",
+    },
+)
+
+def preprocess(examples):
+    return tokenizer(examples["text"], truncation=True, padding="max_length", max_length=128)
+
+dataset = dataset.map(preprocess, batched=True)
+
+# Transformers Trainer 期望标签列名为 label
+if "labels" in dataset["train"].column_names and "label" not in dataset["train"].column_names:
+    dataset = dataset.rename_column("labels", "label")
+
+def compute_metrics(eval_pred):
+    logits, labels = eval_pred
+    preds = np.argmax(logits, axis=-1)
+    acc = (preds == labels).mean().item() if hasattr((preds == labels).mean(), "item") else float((preds == labels).mean())
+    return {"accuracy": acc}
+
+# 3️⃣ 配置训练参数（保存最优模型）
+training_args = TrainingArguments(
+    output_dir="./sentiment_roberta",
+    eval_strategy="epoch",
+    save_strategy="epoch",
+    learning_rate=2e-5,
+    per_device_train_batch_size=8,
+    per_device_eval_batch_size=8,
+    num_train_epochs=3,
+    load_best_model_at_end=True,
+    metric_for_best_model="accuracy",
+    greater_is_better=True,
+    save_total_limit=2,
+    fp16=True,
+)
+
+trainer = Trainer(
+    model=model,
+    args=training_args,
+    train_dataset=dataset["train"],
+    eval_dataset=dataset["test"],
+    compute_metrics=compute_metrics,
+)
+
+# 4️⃣ 开始训练
+trainer.train()
+
+# 5️⃣ 显式保存最优模型与分词器到 output_dir
+trainer.save_model(training_args.output_dir)
+tokenizer.save_pretrained(training_args.output_dir)

text-emotion.yaml

@@ -0,0 +1,8 @@
+- 0: 伤心
+- 1: 生气
+- 2: 关心
+- 3: 惊讶
+- 4: 开心
+- 5: 平静
+- 6: 厌恶
+- 7: 恐惧

train-data-preload.py

@@ -0,0 +1,66 @@
+import pandas as pd
+
+df1 = pd.read_csv(
+    "hf://datasets/zzhdbw/Simplified_Chinese_Multi-Emotion_Dialogue_Dataset/Simplified_Chinese_Multi-Emotion_Dialogue_Dataset.csv"
+)
+
+df2 = pd.read_csv(
+    "hf://datasets/jakeazcona/short-text-multi-labeled-emotion-classification/FINALDATA.csv"
+)
+
+# df1: 中文情绪 -> 统一标签
+# 伤心：0，生气：1，关心：2，惊讶：3，开心：4，平静：5，厌恶：6
+# （如 df1 还包含其它情绪，将被置为 NA 并在后续丢弃）
+DF1_LABEL_MAP = {
+    "伤心": 0,
+    "生气": 1,
+    "关心": 2,
+    "惊讶": 3,
+    "开心": 4,
+    "平静": 5,
+    "厌恶": 6,
+}
+
+# df2: emotion 数字 -> 统一标签
+# 0：1，1：7，2：2，3：3，4：4，5：5
+DF2_EMOTION_MAP = {
+    0: 1,
+    1: 7,
+    2: 2,
+    3: 3,
+    4: 4,
+    5: 5,
+}
+
+# 统一列名（将 df1 的 text 和 df2 的 sample 统一到新表的 text 字段）
+if "label" not in df1.columns or "text" not in df1.columns:
+    raise KeyError(f"df1 缺少必要列: label 或 text，现有列: {list(df1.columns)}")
+if "emotion" not in df2.columns or "sample" not in df2.columns:
+    raise KeyError(f"df2 缺少必要列: emotion 或 sample，现有列: {list(df2.columns)}")
+
+df1_std = df1.copy()
+df1_std["label"] = df1_std["label"].map(DF1_LABEL_MAP)
+# df1 保持 text 字段名不变
+
+df2_std = df2.copy()
+# 确保 emotion 可被当作 int 映射
+df2_std["emotion"] = pd.to_numeric(df2_std["emotion"], errors="coerce")
+df2_std["label"] = df2_std["emotion"].map(DF2_EMOTION_MAP)
+# 将 df2 的 sample 重命名为 text
+df2_std = df2_std.rename(columns={"sample": "text"})
+
+# 只保留 text 和 label 两列进行合并
+final_cols = ["text", "label"]
+
+merged = pd.concat([
+    df1_std[final_cols],
+    df2_std[final_cols],
+], ignore_index=True)
+
+# 丢弃无法映射的样本
+merged = merged.dropna(subset=["label"]).copy()
+merged["label"] = merged["label"].astype(int)
+
+# 输出
+merged.to_csv("emotion-classification-train.csv", index=False, encoding="utf-8-sig")
+print(f"merged saved: emotion-classification-train.csv, rows={len(merged)}, cols={len(merged.columns)}")