Downloads · 30 days
2
6% of all-time downloads
xir-1170-qwen3-embedding-0.6b-a10
Yucluzzy/xir-1170-qwen3-embedding-0.6b-a10
xir-1170-qwen3-embedding-0.6b-a10 is a machine learning model from Yucluzzy. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Based on the official LRAT Qwen3-Embedding-0.6B checkpoint.
All-time downloads
34
Public
Parameters
596M
1.2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.2 GB · 99%
At a glance
- Model type
- qwen3
- Access
- Public
- Created
- Jul 17, 2026
- Updated
- Jul 17, 2026
- SHA
- 6cc0a63f
Model card
From the Hugging Face model README
Xir 1170 Candidate A10
Based on the official LRAT Qwen3-Embedding-0.6B checkpoint.
Training method: 90-step low-learning-rate continuation on the deduplicated sqrt-weight dataset, followed by BF16 interpolation with the current best checkpoint using candidate weight 0.10 and base weight 0.90.
Local validation on 2048 held-out rows: MRR 0.727729, weighted MRR 0.741520, Recall@1 0.602051, Recall@5 0.895020.
- Type
- qwen3
- Created
- Jul 17, 2026
- Updated
- Jul 17, 2026