utahnlp/tevatron-elastic-qwen3-0.6b-retriever-plain

tevatron-elastic-qwen3-0.6b-retriever-plain

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 a single full-size operating point (baseline).

• —Base model: Qwen/Qwen3-0.6B-Base
• —Task: retriever
• —Elastic axis: plain
• —Training data: rlhn/rlhn-680K, max length 512, query:/passage: prefixes.

Full-point BEIR-15 nDCG@10: 0.513.

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.