Feature Extraction
Transformers
Safetensors
sentence-transformers
Chinese
English
mteb
custom_code
Eval Results (legacy)
Instructions to use openbmb/MiniCPM-Embedding with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use openbmb/MiniCPM-Embedding with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="openbmb/MiniCPM-Embedding", trust_remote_code=True)# Load model directly from transformers import MiniCPM model = MiniCPM.from_pretrained("openbmb/MiniCPM-Embedding", trust_remote_code=True, dtype="auto") - sentence-transformers
How to use openbmb/MiniCPM-Embedding with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("openbmb/MiniCPM-Embedding", trust_remote_code=True) sentences = [ "The weather is lovely today.", "It's so sunny outside!", "He drove to the stadium." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3] - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -267,7 +267,7 @@ library_name: transformers
|
|
| 267 |
---
|
| 268 |
## MiniCPM-Embedding
|
| 269 |
|
| 270 |
-
**MiniCPM-Embedding** 是面壁智能与清华大学自然语言处理实验室(THUNLP)共同开发的中英双语言文本嵌入模型,有如下特点:
|
| 271 |
- 出色的中文、英文检索能力。
|
| 272 |
- 出色的中英跨语言检索能力。
|
| 273 |
|
|
@@ -279,7 +279,7 @@ MiniCPM-Embedding 基于 [MiniCPM-2B-sft-bf16](https://huggingface.co/openbmb/Mi
|
|
| 279 |
- 重排模型:[MiniCPM-Reranker](https://huggingface.co/openbmb/MiniCPM-Reranker)
|
| 280 |
- 面向 RAG 场景的 LoRA 插件:[MiniCPM3-RAG-LoRA](https://huggingface.co/openbmb/MiniCPM3-RAG-LoRA)
|
| 281 |
|
| 282 |
-
**MiniCPM-Embedding** is a bilingual & cross-lingual text embedding model developed by ModelBest Inc.
|
| 283 |
|
| 284 |
- Exceptional Chinese and English retrieval capabilities.
|
| 285 |
- Outstanding cross-lingual retrieval capabilities between Chinese and English.
|
|
|
|
| 267 |
---
|
| 268 |
## MiniCPM-Embedding
|
| 269 |
|
| 270 |
+
**MiniCPM-Embedding** 是面壁智能与清华大学自然语言处理实验室(THUNLP)、东北大学信息检索小组(NEUIR)共同开发的中英双语言文本嵌入模型,有如下特点:
|
| 271 |
- 出色的中文、英文检索能力。
|
| 272 |
- 出色的中英跨语言检索能力。
|
| 273 |
|
|
|
|
| 279 |
- 重排模型:[MiniCPM-Reranker](https://huggingface.co/openbmb/MiniCPM-Reranker)
|
| 280 |
- 面向 RAG 场景的 LoRA 插件:[MiniCPM3-RAG-LoRA](https://huggingface.co/openbmb/MiniCPM3-RAG-LoRA)
|
| 281 |
|
| 282 |
+
**MiniCPM-Embedding** is a bilingual & cross-lingual text embedding model developed by ModelBest Inc. , THUNLP and NEUIR , featuring:
|
| 283 |
|
| 284 |
- Exceptional Chinese and English retrieval capabilities.
|
| 285 |
- Outstanding cross-lingual retrieval capabilities between Chinese and English.
|