Text Classification
Transformers
ONNX
Safetensors
Chinese
English
xlm-roberta
llm-routing
cost-optimization
chinese
text-embeddings-inference
Instructions to use GOSHUNCLE/llm-router-complexity with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use GOSHUNCLE/llm-router-complexity with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="GOSHUNCLE/llm-router-complexity")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("GOSHUNCLE/llm-router-complexity") model = AutoModelForSequenceClassification.from_pretrained("GOSHUNCLE/llm-router-complexity", device_map="auto") - Notebooks
- Google Colab
- Kaggle
|
Download README.md from GOSHUNCLE/llm-router-complexity: direct link, hf CLI and curl.
- Browser
- Download file 4.38 kB
-
https://huggingface.co/GOSHUNCLE/llm-router-complexity/resolve/main/README.md
- Command line
-
hf download hf://GOSHUNCLE/llm-router-complexity/README.md
-
curl -L -o README.md https://huggingface.co/GOSHUNCLE/llm-router-complexity/resolve/main/README.md
4.38 kB
| license: apache-2.0 | |
| language: | |
| - zh | |
| - en | |
| base_model: FacebookAI/xlm-roberta-base | |
| pipeline_tag: text-classification | |
| library_name: transformers | |
| tags: | |
| - llm-routing | |
| - cost-optimization | |
| - text-classification | |
| - chinese | |
| widget: | |
| - text: "評估把回焊爐產能提升 20% 需要的資源與風險" | |
| - text: "把 250 mil 換算成 mm" | |
| - text: "根據這些數據推論產能瓶頸並提出改善策略" | |
| # LLM Router — Stage 2 難度路由 | |
| 判斷一則**與工作相關**的請求是**單純**還是**複雜**,據此決定要送往昂貴的雲端大模型(`complex`) | |
| 還是便宜的地端小模型(`simple`)。 | |
| - **標籤**:`simple` / `complex` | |
| - **基礎模型**:`xlm-roberta-base` | |
| - **語言**:繁體中文為主,中英混合 | |
| ## 用途 | |
| 在企業把請求送進昂貴的雲端大模型**之前**先判斷一次,避免兩種常見浪費: | |
| 用最貴的模型做分類、翻譯、單位換算這種小事;以及拿公司的 LLM 額度做與工作無關的事。 | |
| 整個判斷在本地完成,不需要任何 API 金鑰,請求內容也不會送往第三方。 | |
| ## 怎麼用 | |
| ```python | |
| from transformers import AutoTokenizer, AutoModelForSequenceClassification | |
| import torch | |
| repo = "GOSHUNCLE/llm-router-complexity" | |
| tok = AutoTokenizer.from_pretrained(repo) | |
| mdl = AutoModelForSequenceClassification.from_pretrained(repo).eval() | |
| text = "評估把回焊爐產能提升 20% 需要的資源與風險" | |
| inputs = tok(text, return_tensors="pt", truncation=True, max_length=256) | |
| with torch.no_grad(): | |
| probs = torch.softmax(mdl(**inputs).logits, dim=-1)[0] | |
| idx = int(probs.argmax()) | |
| print(mdl.config.id2label[idx], float(probs[idx])) | |
| ``` | |
| 這個模型預設**只處理已經被第一段判為 `work_related` 的請求**。 | |
| 直接拿無關的句子餵給它,結果沒有意義——請先過 | |
| [相關性守門模型](https://huggingface.co/GOSHUNCLE/llm-router-relevance-gate)。 | |
| ## 這是兩段式系統的一部分 | |
| | 階段 | 模型 | 標籤 | | |
| |---|---|---| | |
| | 第一段 相關性守門 | [GOSHUNCLE/llm-router-relevance-gate](https://huggingface.co/GOSHUNCLE/llm-router-relevance-gate) | `work_related` / `not_work_related` | | |
| | 第二段 難度路由 | [GOSHUNCLE/llm-router-complexity](https://huggingface.co/GOSHUNCLE/llm-router-complexity) | `simple` / `complex` | | |
| 完整的路由邏輯(含關鍵詞規則)、可直接試玩的 Demo、訓練腳本與資料集,都在 | |
| **[GOSHUNCLE/liang-task-router](https://huggingface.co/spaces/GOSHUNCLE/liang-task-router)**。 | |
| ## 訓練資料 | |
| 模板式合成資料,電子製造業情境、中英混合,**不需要任何模型或金鑰即可重現** | |
| (`training/generate_synthetic.py`,固定 seed): | |
| - `stage1.jsonl` — 2,000 筆,`work_related` / `not_work_related` 各半 | |
| - `stage2.jsonl` — 1,000 筆,`simple` / `complex` 各半 | |
| 資料不含任何個人資料、公司名稱或真實使用者語料。 | |
| ## 訓練設定 | |
| 以 `xlm-roberta-base` 微調:4 epochs、learning rate 2e-5、batch size 16、max length 256, | |
| 資料切分 80 / 10 / 10(train / validation / test),依 Macro-F1 選最佳 checkpoint。 | |
| ## 限制與注意事項 | |
| - **領域侷限**:訓練情境集中在電子製造業。其他產業的用語可能判不準。 | |
| - **邊界句子會錯**:「看起來簡單、實際需要推理」的句子最容易出錯。 | |
| 實際遇過的例子是「分析 SMT 異常根因」被判成 `simple`。 | |
| - **合成資料偏樂觀**:模板生成的句子比真實使用者的輸入完整很多。 | |
| - **不要單獨拿來做內容審查或合規判斷**。它的用途是分流成本,不是把關風險。 | |
| ## 授權 | |
| Apache License 2.0。基礎模型 `xlm-roberta-base` 為 MIT 授權。 | |
| --- | |
| ## English | |
| Stage 2 of a two-stage LLM cost router: for work-related requests, decides whether the task is | |
| `simple` (route to a cheap/local model) or `complex` (route to an expensive cloud model). | |
| Fine-tuned from `xlm-roberta-base` on synthetic, template-generated data. | |
| Intended to run only on requests already passed by the Stage 1 relevance gate. | |
| No human-labeled benchmark exists yet, so **no accuracy figures are claimed**. | |
| See the [demo Space](https://huggingface.co/spaces/GOSHUNCLE/liang-task-router) for the full | |
| routing logic (keyword rules + both stages), training scripts and dataset. | |
| Licensed under Apache-2.0; base model `xlm-roberta-base` is MIT. | |