Sentence Similarity
sentence-transformers
Safetensors
Chinese
English
text-embeddings-inference
feature-extraction
semantic-search
retrieval
traditional-chinese
lora
Instructions to use BluePlanetAI/BPVELA-E560M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use BluePlanetAI/BPVELA-E560M with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("BluePlanetAI/BPVELA-E560M") sentences = [ "那是 個快樂的人", "那是 條快樂的狗", "那是 個非常幸福的人", "今天是晴天" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Notebooks
- Google Colab
- Kaggle
Upload BPVELA-E560M-v1.0.0
Browse files
README.md
CHANGED
|
@@ -20,6 +20,40 @@ base_model:
|
|
| 20 |
|
| 21 |
`BPVELA-E560M` is the accuracy-first BPVELA release line for Traditional Chinese retrieval and embedding use cases.
|
| 22 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 23 |
## Summary
|
| 24 |
|
| 25 |
- Series version: `v1.0.0`
|
|
|
|
| 20 |
|
| 21 |
`BPVELA-E560M` is the accuracy-first BPVELA release line for Traditional Chinese retrieval and embedding use cases.
|
| 22 |
|
| 23 |
+
## 繁體中文說明
|
| 24 |
+
|
| 25 |
+
`BPVELA-E560M` 是 BPVELA 目前的 accuracy-first 系列,針對繁體中文語意檢索、相似度比對與 retrieval-first RAG 場景做優化。
|
| 26 |
+
|
| 27 |
+
### 模型摘要
|
| 28 |
+
|
| 29 |
+
- 系列版本:`v1.0.0`
|
| 30 |
+
- 基底模型:`intfloat/multilingual-e5-large`
|
| 31 |
+
- 釋出形式:LoRA adapter 加上 SentenceTransformer 組件
|
| 32 |
+
- 建議用途:semantic retrieval、retrieval-first RAG、similarity search
|
| 33 |
+
- 主要語言:Traditional Chinese / 繁體中文
|
| 34 |
+
|
| 35 |
+
### 重要說明
|
| 36 |
+
|
| 37 |
+
這個 repository 釋出的是 LoRA adapter,不是 merged full checkpoint。使用時需要以 base model 為底,再載入這個 adapter。
|
| 38 |
+
|
| 39 |
+
### 驗證摘要
|
| 40 |
+
|
| 41 |
+
- Taiwan-md pair benchmark:Spearman `0.8400`、Pearson `0.9224`
|
| 42 |
+
- Wrapped retrieval smoke:pass rate `1.0000`、retrieval hit rate `1.0000`、top-1 rate `0.9667`
|
| 43 |
+
|
| 44 |
+
### Query / Passage 格式
|
| 45 |
+
|
| 46 |
+
這條模型線基於 E5,做檢索時建議保留標準前綴。
|
| 47 |
+
|
| 48 |
+
- Query:`query: 你的問題`
|
| 49 |
+
- Passage:`passage: 文件內容`
|
| 50 |
+
|
| 51 |
+
### 備註
|
| 52 |
+
|
| 53 |
+
- `bpvela_model_config.yaml` 保留了專案內部使用的載入設定。
|
| 54 |
+
- 這個公開模型 repo 不需要包含 Taiwan-md corpus 或 FAISS index。
|
| 55 |
+
- 公開前請再確認最終 license。
|
| 56 |
+
|
| 57 |
## Summary
|
| 58 |
|
| 59 |
- Series version: `v1.0.0`
|