Sentence Similarity
sentence-transformers
ONNX
Transformers.js
gte
feature-extraction
mteb
arctic
embedding
snowflake2_m_uint8
snowflake
custom_code
Instructions to use electroglyph/snowflake2_m_uint8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use electroglyph/snowflake2_m_uint8 with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("electroglyph/snowflake2_m_uint8", 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] - Transformers.js
How to use electroglyph/snowflake2_m_uint8 with Transformers.js:
// npm i @huggingface/transformers import { pipeline } from '@huggingface/transformers'; // Allocate pipeline const pipe = await pipeline('sentence-similarity', 'electroglyph/snowflake2_m_uint8'); - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -86,6 +86,10 @@ language:
|
|
| 86 |
- yo
|
| 87 |
- zh
|
| 88 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
| 89 |
# snowflake2_m_uint8
|
| 90 |
|
| 91 |
This is a slightly modified version of the uint8 quantized ONNX model from https://huggingface.co/Snowflake/snowflake-arctic-embed-m-v2.0
|
|
|
|
| 86 |
- yo
|
| 87 |
- zh
|
| 88 |
---
|
| 89 |
+
# NOTICE
|
| 90 |
+
|
| 91 |
+
Currently benchmarking this, not sure how accurate it is yet. It's not recommended for use right now. I'll be updating this.
|
| 92 |
+
|
| 93 |
# snowflake2_m_uint8
|
| 94 |
|
| 95 |
This is a slightly modified version of the uint8 quantized ONNX model from https://huggingface.co/Snowflake/snowflake-arctic-embed-m-v2.0
|