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
Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -1,12 +1,7 @@
|
|
| 1 |
---
|
| 2 |
license: other
|
| 3 |
-
language:
|
| 4 |
-
-
|
| 5 |
-
- en
|
| 6 |
-
tags:
|
| 7 |
-
- text-classification
|
| 8 |
-
- llm-router
|
| 9 |
-
- cost-optimization
|
| 10 |
---
|
| 11 |
|
| 12 |
# llm-cost-router — Stage 2
|
|
@@ -15,12 +10,12 @@ tags:
|
|
| 15 |
|
| 16 |
## 中文
|
| 17 |
本模型為「AI 路由(LLM Cost-Aware Router)」專案的任務分類模型之一,
|
| 18 |
-
以
|
| 19 |
以節省昂貴模型的呼叫成本。訓練資料為電子製造業情境的合成資料 + 少量人工校正。
|
| 20 |
|
| 21 |
## English
|
| 22 |
One of the classifiers of the *LLM Cost-Aware Router* project, fine-tuned from
|
| 23 |
-
|
| 24 |
Trained on synthetic electronics-manufacturing data with light human correction.
|
| 25 |
|
| 26 |
## 限制 / Limitations
|
|
|
|
| 1 |
---
|
| 2 |
license: other
|
| 3 |
+
language: [zh, en]
|
| 4 |
+
tags: [text-classification, llm-router, cost-optimization]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
---
|
| 6 |
|
| 7 |
# llm-cost-router — Stage 2
|
|
|
|
| 10 |
|
| 11 |
## 中文
|
| 12 |
本模型為「AI 路由(LLM Cost-Aware Router)」專案的任務分類模型之一,
|
| 13 |
+
以 xlm-roberta-base 微調,判斷企業員工送給 LLM 的請求該如何路由,
|
| 14 |
以節省昂貴模型的呼叫成本。訓練資料為電子製造業情境的合成資料 + 少量人工校正。
|
| 15 |
|
| 16 |
## English
|
| 17 |
One of the classifiers of the *LLM Cost-Aware Router* project, fine-tuned from
|
| 18 |
+
xlm-roberta-base to route enterprise LLM requests and cut expensive-model cost.
|
| 19 |
Trained on synthetic electronics-manufacturing data with light human correction.
|
| 20 |
|
| 21 |
## 限制 / Limitations
|