DeepShopper Reward V0 — AMZ bundle likelihood judge (Qwen3-4B)

Reward V0 for DeepShopper: a Qwen3-4B SFT'd to generate the matching outfit bundle for a natural-language need (P(outfit | need)). Used as a reward via teacher-forced likelihood of a candidate outfit (100·exp(−mean NLL)), with hard gates (invalid / duplicate / role-category).

Code: https://github.com/clijo/reco-rl (branch outfit_bundle).

Downloads last month
1,091
Safetensors
Model size
4B params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for flavianv/qwen4b-apparel23-bundle-sft

Finetuned
Qwen/Qwen3-4B
Finetuned
(992)
this model
Adapters
1 model