Feature Extraction
sentence-transformers
Safetensors
English
Chinese
qwen2
Retrieval
STS
Classification
Clustering
Reranking
vllm
custom_code
text-embeddings-inference
Instructions to use KaLM-Embedding/KaLM-embedding-multilingual-mini-instruct-v2.5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use KaLM-Embedding/KaLM-embedding-multilingual-mini-instruct-v2.5 with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("KaLM-Embedding/KaLM-embedding-multilingual-mini-instruct-v2.5", 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
|
@@ -41,6 +41,7 @@ tags:
|
|
| 41 |
- Large-scale weakly supervised pretraining
|
| 42 |
- High-quality supervised finetuning
|
| 43 |
- Contrastive distillation with fine-grained soft labels
|
|
|
|
| 44 |
Additionally, focal-style sample reweighting and online hard-negative mixing are employed to emphasize difficult samples and enrich hard negatives.
|
| 45 |
|
| 46 |
|
|
|
|
| 41 |
- Large-scale weakly supervised pretraining
|
| 42 |
- High-quality supervised finetuning
|
| 43 |
- Contrastive distillation with fine-grained soft labels
|
| 44 |
+
|
| 45 |
Additionally, focal-style sample reweighting and online hard-negative mixing are employed to emphasize difficult samples and enrich hard negatives.
|
| 46 |
|
| 47 |
|