Sentence Similarity
sentence-transformers
ONNX
Safetensors
Chinese
English
modernbert
embeddings
medical
clinical-nlp
healthcare
biomedical
fhir
traditional-chinese
taiwan
rag
text-embeddings-inference
Instructions to use weemed/IlhaEmbed with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use weemed/IlhaEmbed with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("weemed/IlhaEmbed") sentences = [ "帶狀皰疹", "皮蛇", "高血壓用藥", "114年成健" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Notebooks
- Google Colab
- Kaggle
docs: use standard Taiwan engineering term Macro 平均
Browse files
README.md
CHANGED
|
@@ -194,7 +194,7 @@ print(normed.shape) # (2, 384)
|
|
| 194 |
- 採用 Granite ModernBERT Lightweight (97M 參數),輸出 384 維度精簡向量。
|
| 195 |
- 經過 25.5k 繁體中文醫學專用詞表剪枝與標準算子 INT8 動態量化,模型檔案大小僅 **36.78 MB**,嚴格符合社區健康站與手持裝置 **<40 MB** 的邊緣硬體預算門禁。
|
| 196 |
- 在純 CPU 4-thread 推論單筆延遲僅 **~1.06 ms**,RTX 4080 GPU 推論延遲僅 **0.61 ms (1,627.2 QPS)**。
|
| 197 |
-
- 於四大台灣臨床語意測試集(台語醫學、臨床黑話、處方簡稱、中英同位語)全面達到 **94.79% INT8 ONNX
|
| 198 |
- 適合社區健檢站一體機(如 *The Mirror*)、離線醫療閘道器與瀏覽器 WebAssembly (WASM) 端執行。
|
| 199 |
|
| 200 |
---
|
|
@@ -214,9 +214,9 @@ print(normed.shape) # (2, 384)
|
|
| 214 |
| **俚語與行話檢索 (n=62)** | **95.2% (59/62)** | **91.94% (57/62)** [INT8] / **98.39% (61/62)** [FP32] | 0.0% ~ 5.0% | ≥ 85.0% |
|
| 215 |
| **臨床縮寫與處方簡稱 (n=399)** | **98.15% (106/108)** | **93.23% (372/399)** [INT8] / **98.50% (393/399)** [FP32] | 0.0% ~ 14.0% | ≥ 90.0% |
|
| 216 |
| **中英臨床同位語 (n=371)** | **93.8% (348/371)** | **95.42% (354/371)** [INT8] / **97.04% (360/371)** [FP32] | 33.0% ~ 45.0% | ≥ 80.0% |
|
| 217 |
-
| **四大語意集
|
| 218 |
|
| 219 |
-
> **誠實量化折損揭示**:逐通道動態 INT8 量化將模型壓縮至 **36.78 MB**(相較 FP32 減少 75% 體積),同時保留高達 **96.25%** 的全精度檢索效能(
|
| 220 |
|
| 221 |
---
|
| 222 |
|
|
|
|
| 194 |
- 採用 Granite ModernBERT Lightweight (97M 參數),輸出 384 維度精簡向量。
|
| 195 |
- 經過 25.5k 繁體中文醫學專用詞表剪枝與標準算子 INT8 動態量化,模型檔案大小僅 **36.78 MB**,嚴格符合社區健康站與手持裝置 **<40 MB** 的邊緣硬體預算門禁。
|
| 196 |
- 在純 CPU 4-thread 推論單筆延遲僅 **~1.06 ms**,RTX 4080 GPU 推論延遲僅 **0.61 ms (1,627.2 QPS)**。
|
| 197 |
+
- 於四大台灣臨床語意測試集(台語醫學、臨床黑話、處方簡稱、中英同位語)全面達到 **94.79% INT8 ONNX Macro 平均 (Macro-average)** 與 **98.48% FP32 GPU Macro 平均 (Macro-average)**。
|
| 198 |
- 適合社區健檢站一體機(如 *The Mirror*)、離線醫療閘道器與瀏覽器 WebAssembly (WASM) 端執行。
|
| 199 |
|
| 200 |
---
|
|
|
|
| 214 |
| **俚語與行話檢索 (n=62)** | **95.2% (59/62)** | **91.94% (57/62)** [INT8] / **98.39% (61/62)** [FP32] | 0.0% ~ 5.0% | ≥ 85.0% |
|
| 215 |
| **臨床縮寫與處方簡稱 (n=399)** | **98.15% (106/108)** | **93.23% (372/399)** [INT8] / **98.50% (393/399)** [FP32] | 0.0% ~ 14.0% | ≥ 90.0% |
|
| 216 |
| **中英臨床同位語 (n=371)** | **93.8% (348/371)** | **95.42% (354/371)** [INT8] / **97.04% (360/371)** [FP32] | 33.0% ~ 45.0% | ≥ 80.0% |
|
| 217 |
+
| **四大語意集 Macro 平均 (Macro-average)** | 95.91% | **94.79%** [INT8 ONNX] / **98.48%** [FP32 GPU] | 42.0% ~ 58.0% | ≥ 88.0% |
|
| 218 |
|
| 219 |
+
> **誠實量化折損揭示**:逐通道動態 INT8 量化將模型壓縮至 **36.78 MB**(相較 FP32 減少 75% 體積),同時保留高達 **96.25%** 的全精度檢索效能(Macro 平均由 98.48% 輕微收斂至 94.79%),全面符合超輕量嵌入設備需求。
|
| 220 |
|
| 221 |
---
|
| 222 |
|