tevatron-elastic-qwen3-0.6b-retriever-ltc
A retriever trained with Tevatron-Elastic, which trains one checkpoint to serve many operating points along the depth / width / token compression axes. This checkpoint is an elastic token axis (layer-wise token compression, M-LTC): one checkpoint serves several keep-ratios.
- Base model:
Qwen/Qwen3-0.6B-Base - Task: retriever
- Elastic axis: ltc
- Training data: rlhn/rlhn-680K, max length 512,
query:/passage:prefixes.
Full-point BEIR-15 nDCG@10: 0.511.
Load with the Tevatron-Elastic framework and select an operating point with prune_to /
encode_at; see the repository for usage. Part of a release of 20 checkpoints (3 backbones,
retrieval and reranking, all compression axes) accompanying the Tevatron-Elastic paper. Reported as
a reproducibility resource, not a state-of-the-art claim.