Changes / Feeds / Qwen/Qwen3-Embedding-4B
Qwen/Qwen3-Embedding-4B
1 change to a tracked key since 2025-06-03, newest first. Head as last read: 5cf2132abc99cad020ac570b19d031efec650f2b.
Differs from Qwen/Qwen3-4B-Base in 253 of 398 aligned tensors (at most 100.0% of elements); the other 145 are byte-identical. Compared tensor by tensor from sha256 fingerprints: 5cf2132abc99 against Qwen/Qwen3-4B-Base at 906bfd4b4dc7. A hash is equal or not; it says nothing about what an edit does.
| Date | Advisory | What changed, and what it does |
|---|---|---|
| 2025-06-05 | x_NXMC-2025-0187 breaking | architectures ["Qwen3Model"] to ["Qwen3ForCausalLM"]; a different class is instantiated from the same id (2025-06-05).d50085f71d39 -> bcf11cc78d46 Open in app |
Pin it, and let a bot move the pin
from_pretrained("Qwen/Qwen3-Embedding-4B", revision="5cf2132abc99cad020ac570b19d031efec650f2b")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-4B.html)