Jev Embeddings

Hugging Face dataset of (state, action) embedding pairs from Qwen/Qwen3.6-35B-A3B-FP8 for post-training contrastive heads on the Jev Decision Index's Arts & Human Taste benchmarks: Humicroedit, cfcolor and the Habermas Machine.

Hugging Face dataset of (state, action) embedding pairs from Qwen/Qwen3.6-35B-A3B-FP8 for post-training contrastive heads on the Jev Decision Index's Language Understanding benchmarks: iSarcasmEval, VAST, ACOS and New Yorker caption matching.

Natural-language lookup over the US App Store top charts: describe an ambiguous feature, a look, or a name and get matching apps with how likely each one is, scored by a single Jev request over a local shortlist.

A Qwen3-Embedding-0.6B fine-tune merged from LoRA that raises JevEmbed-Data test accuracy from 33.79% to 82.30%, producing 1,024-dimensional embeddings for Choice, Score and Noul decisions.

1,601,157 training and 66,482 test decision questions for JevEmbed, covering choice, score and noul types across ten Parquet shards of at most 200,000 rows each.