Downloads · 30 days
84
24% of all-time downloads
all-MiniLM-L6-v2-32dim
qxakshat/all-MiniLM-L6-v2-32dim
all-MiniLM-L6-v2-32dim is a sentence similarity model from qxakshat. Use it when you need a score for how close two texts are. It is set up for sentence-transformers. The card lists the license as apache-2.0.
This is a sentence-transformers model: It maps sentences & paragraphs to a 32 dimensional dense vector space and can be used for tasks like clustering or semantic search.
All-time downloads
343
Public
Parameters
22.7M
90.9 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors90.9 MB · 99%
At a glance
- Task
- Sentence Similarity
- Library
- sentence-transformers
- License
- apache-2.0
- Model type
- bert
- Access
- Public
- Created
- May 27, 2025
- Updated
- May 27, 2025
- SHA
- 7d98bffb
Model card
From the Hugging Face model README
all-MiniLM-L6-v2
This is a sentence-transformers model: It maps sentences & paragraphs to a 32 dimensional dense vector space and can be used for tasks like clustering or semantic search.
Model performance (Cosine-Similarity based, on the sts-test dataset):
- Original (384 dimensions): Pearson: 0.8274 Spearman: 0.8203
- 128 dimensions: Pearson: 0.8165 Spearman: 0.8180
- 64 dimensions: Pearson: 0.7855 Spearman: 0.7973
- 32 dimensions: Pearson: 0.7256 Spearman: 0.7481
created using: dimensionality_reduction
- Task
- Sentence Similarity
- Library
- sentence-transformers
- Type
- bert
- License
- apache-2.0
- Languages
- en
- Created
- May 27, 2025
- Updated
- May 27, 2025