Downloads · 30 days
20
7% of all-time downloads
Tarka-Embedding-10M-V1-Preview
Tarka-AIR/Tarka-Embedding-10M-V1-Preview
Tarka-Embedding-10M-V1-Preview is a feature extraction model from Tarka-AIR. Use it when you need embeddings to search or compare text. It is set up for sentence-transformers. The card lists the license as apache-2.0.
Training details and a stable version of the model will be released soon. In the meantime, feel free to give this model a try.
All-time downloads
284
Public
Parameters
10.5M
21 MB on disk
Likes
3
Public
Repo makeup
Click a slice to open those files.
.safetensors21 MB · 85%
At a glance
- Task
- Feature Extraction
- Library
- sentence-transformers
- License
- apache-2.0
- Model type
- svd_qwen3
- Access
- Public
- Created
- Dec 17, 2025
- Updated
- Dec 17, 2025
- SHA
- 304bb8b8
Model card
From the Hugging Face model README
Training details and a stable version of the model will be released soon. In the meantime, feel free to give this model a try.
Model details
Tarka-Embedding-10M-V1 has the following features:
- Model Type: Text Embedding
- Supported Languages: English.
- Number of Paramaters: 10M
- Context Length: Optimal performance is observed with inputs under 1K tokens
- Embedding Dimension: 1024
Training Details
- Initialization: Based on Qwen3/Qwen3-Embedding-0.6B
- Architecture Modifications: The tokenizer is replaced with modernbert tokenizer . We use SVD decomposition with rank of 64 for the compression of both Transformer layers and the embedding layer.
- Teacher Model: Qwen3/Qwen3-Embedding-0.6B
| Model | Number of Parameters (B) | Embedding Dimensions | Mean (Task) | Mean (TaskType) | Classification | Clustering | Pair Classification | Reranking | Retrieval | STS | Summarization |
|---|---|---|---|---|---|---|---|---|---|---|---|
| gte-micro | 0.017 | 384 | 53.89 | 52.5 | 67.47 | 41.86 | 80.76 | 43.16 | 27.66 | 77.86 | 28.76 |
| Wartortle | 0.017 | 384 | 54.11 | 52.64 | 70.31 | 40.56 | 80.72 | 42.18 | 26.91 | 78.52 | 29.31 |
| Bulbasaur | 0.017 | 384 | 57.75 | 55.19 | 72.89 | 42.51 | 82.73 | 44.63 | 36.96 | 78.84 | 27.76 |
| gte-micro-v4 | 0.019 | 384 | 58.9 | 56.04 | 73.04 | 43.89 | 82.67 | 44.78 | 39.51 | 79.78 | 28.59 |
| all-MiniLM-L6-v2 | 0.023 | 384 | 59.03 | 55.93 | 69.25 | 44.9 | 82.37 | 47.14 | 42.92 | 78.95 | 25.96 |
| snowflake-arctic-embed-xs | 0.023 | 384 | 59.77 | 56.12 | 67 | 42.44 | 81.33 | 45.26 | 52.65 | 76.21 | 27.96 |
| Tarka-Embedding-10M-V1 | 0.010 | 1024 | 58.15 | 55.19 | 74.05 | 44.66 | 77.27 | 42.69 | 39.98 | 76.21 | 31.5 |
- Task
- Feature Extraction
- Library
- sentence-transformers
- Type
- svd_qwen3
- License
- apache-2.0
- Created
- Dec 17, 2025
- Updated
- Dec 17, 2025