Instructions to use iampanda/zpoint_large_embedding_zh with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use iampanda/zpoint_large_embedding_zh with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("iampanda/zpoint_large_embedding_zh") 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
|
@@ -1074,7 +1074,7 @@ library_name: sentence-transformers
|
|
| 1074 |
- For classification/clustering tasks, we sampled 5 hard negative samples from other classes/cluster for each sample.
|
| 1075 |
- For classification/clustering tasks, we also used the category names of each class and cluster as positive and negative samples.
|
| 1076 |
|
| 1077 |
-
2) **Data synthesis by LLM (
|
| 1078 |
- For retrieval tasks, we used LLM to rewrite each query, generating five different rewritten results.
|
| 1079 |
- For retrieval tasks, we also generated five new queries for some documents by LLM.
|
| 1080 |
- For non-retrieval tasks, we used LLM to rewrite the queries, generating five rewritten results for each query.
|
|
|
|
| 1074 |
- For classification/clustering tasks, we sampled 5 hard negative samples from other classes/cluster for each sample.
|
| 1075 |
- For classification/clustering tasks, we also used the category names of each class and cluster as positive and negative samples.
|
| 1076 |
|
| 1077 |
+
2) **Data synthesis by LLM (ZPoint-72B)**
|
| 1078 |
- For retrieval tasks, we used LLM to rewrite each query, generating five different rewritten results.
|
| 1079 |
- For retrieval tasks, we also generated five new queries for some documents by LLM.
|
| 1080 |
- For non-retrieval tasks, we used LLM to rewrite the queries, generating five rewritten results for each query.
|