Sentence Similarity
sentence-transformers
Safetensors
Transformers
qwen2
feature-extraction
text-embeddings-inference
Instructions to use vec-ai/lychee-embed with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use vec-ai/lychee-embed with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("vec-ai/lychee-embed") sentences = [ "That is a happy person", "That is a happy dog", "That is a very happy person", "Today is a sunny day" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Transformers
How to use vec-ai/lychee-embed with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("vec-ai/lychee-embed") model = AutoModel.from_pretrained("vec-ai/lychee-embed") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -30,7 +30,7 @@ The first batch of open source is 1.5B parameter version.
|
|
| 30 |
- Embedding Dim: 1536, Supports diverse settings with 32 steps from 32 to 1536
|
| 31 |
- Model Precision: BF16
|
| 32 |
|
| 33 |
-
For more details, please refer to our [
|
| 34 |
|
| 35 |
|
| 36 |
### Model List
|
|
@@ -209,7 +209,7 @@ print(scores.tolist())
|
|
| 209 |
|Qwen3-Embedding-0.6B | 0.60B | | 66.33 | 64.33 | | 75.41 |
|
| 210 |
| **Lychee-embed** | 1.54B | 68.39 |69.77 | 58.43 | 53.85 | 72.54 | 86.35 | 5.74 | 19.47 |
|
| 211 |
|
| 212 |
-
For more details, please refer to our [
|
| 213 |
|
| 214 |
## Citation
|
| 215 |
|
|
|
|
| 30 |
- Embedding Dim: 1536, Supports diverse settings with 32 steps from 32 to 1536
|
| 31 |
- Model Precision: BF16
|
| 32 |
|
| 33 |
+
For more details, please refer to our [Paper](https://openreview.net/pdf?id=NC6G1KCxlt).
|
| 34 |
|
| 35 |
|
| 36 |
### Model List
|
|
|
|
| 209 |
|Qwen3-Embedding-0.6B | 0.60B | | 66.33 | 64.33 | | 75.41 |
|
| 210 |
| **Lychee-embed** | 1.54B | 68.39 |69.77 | 58.43 | 53.85 | 72.54 | 86.35 | 5.74 | 19.47 |
|
| 211 |
|
| 212 |
+
For more details, please refer to our [Paper](https://openreview.net/pdf?id=NC6G1KCxlt).
|
| 213 |
|
| 214 |
## Citation
|
| 215 |
|