Changes / Feeds / Qwen/Qwen3-Embedding-0.6B
Qwen/Qwen3-Embedding-0.6B
1 change to a tracked key since 2025-06-03, newest first. Head as last read: 97b0c614be4d77ee51c0cef4e5f07c00f9eb65b3.
GPU memory to fine-tune it, card by card: Qwen3-Embedding-0.6B on /m/.
| Date | Advisory | What changed, and what it does |
|---|---|---|
| 2025-06-03 | x_NXMC-2025-0066 breaking | EOS changed from [151645,151643] to 151643; anything fine-tuned or served against the old value stops at a different token; context window 40960 to 32768 tokens; pad token 151643 to unset; batched training masks a different id (2025-06-03).1c68a8439911 -> 99cabfa1346c |
Pin it, and let a bot move the pin
from_pretrained("Qwen/Qwen3-Embedding-0.6B", revision="97b0c614be4d77ee51c0cef4e5f07c00f9eb65b3")With the Renovate preset, a pull request moves this pin when the head moves, and links back here.
[](https://www.neurarch.com/changes-feeds/models/Qwen/Qwen3-Embedding-0.6B.html)