An open Jev-style LoRA on Qwen3.5-9B from Bespoke Labs, trained on 2,676 contrastively curated examples to score the allowed answer tokens directly for enums, booleans and rubric levels. Recipe, data and a public benchmark suite are released with it.
10 files · 184 MBCatalogued from bespokelabs/Bespoke-Nimble-9B
adapter_config.json1.3 kB
adapter_model.safetensors29ef39b165 MB
chat_template.jinja7.6 kB
inference.py7.8 kB
schema_config.json22 kB
serving_config.json5.4 kB
SHA256SUMS1.4 kB
temperature_config.json294 B
tokenizer_config.json1.1 kB
tokenizer.json06b950919 MB
Every file resolves through a stable path — /v1/models/bespoke-labs/bespoke-nimble-9b/resolve/2026.09/<path> — while the object underneath is content-addressed and shared with every other version that holds the same bytes. API reference.
