Changes / Feeds / tomaarsen/Qwen3-Reranker-0.6B-seq-cls
tomaarsen/Qwen3-Reranker-0.6B-seq-cls
2 changes to a tracked key since 2025-05-29, newest first. Head as last read: 6a5829f5079c66e78d911e06fe21931cc00232f7.
Differs from Qwen/Qwen3-0.6B-Base in 310 of 310 aligned tensors (at most 100.0% of elements), 310 of them also cast (BF16 to F32); 1 added and 0 dropped. Compared tensor by tensor from sha256 fingerprints: 6a5829f5079c against Qwen/Qwen3-0.6B-Base at da87bfb608c1. A hash is equal or not; it says nothing about what an edit does.
| Date | Advisory | What changed, and what it does |
|---|---|---|
| 2025-07-10 | x_NXMC-2025-0202 | the chat template was removed (2025-07-10).395ad236c610 -> 6a5829f5079c Open in app |
| 2025-06-06 | x_NXMC-2025-0201 breaking | architectures ["Qwen3ForCausalLM"] to ["Qwen3ForSequenceClassification"]; a different class is instantiated from the same id; declared dtype "bfloat16" to "float32"; config.json pad_token_id unset to 151643; the tokenizer's pad token, which training pads with, did not change (2025-06-06).adcdb2a1a4b2 -> 395ad236c610 Open in app |
Pin it, and let a bot move the pin
from_pretrained("tomaarsen/Qwen3-Reranker-0.6B-seq-cls", revision="6a5829f5079c66e78d911e06fe21931cc00232f7")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/tomaarsen/Qwen3-Reranker-0.6B-seq-cls.html)