GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
m-polignano
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
m-polignano
Model Tree
Qwen/Qwen3.8-27B
Input Modalities
Output Modalities
Supported Functionality
| Base model | Qwen/Qwen3.8-27B (revision 1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0), frozen |
| Starting point | the adapter release of jaredpalmer/kev-27b (tag v1-lora) and its pointer head; the current Kev-27B release is a full fine-tune with no adapter to start from |
| Trained parameters | rank-16 LoRA adapters on all linear layers, pointer head |
| Training data | a fixed random 8,000 (seed 2026) of the 34,667 real next choices used for the 0.8B and 4B models (Amazon Video Games, Amazon Musical Instruments, Steam), over the 30 best candidates of the pool; the same 8,000 records train the data-matched 0.8B, 4B, 9B and 27B models of the paper |
| Objective | likelihood of the item the user really chose next; no outputs of any commercial model were used |
| Recipe | one epoch, learning rate 2e-5, one-cycle schedule, micro-batch 1 x 8 accumulation (8 records per step), bf16, gradient checkpointing |
| Trainer | Kev kev.train, commit 84847f0, on one NVIDIA DGX Spark |
NDCG@10 of Decision4Rec-Full on 2,000 development test users per domain (full-catalogue ranking, leave-one-out). Industrial and Scientific was never seen in training.
| System | Video Games | Musical Instr. | Steam | Industrial & Sci. |
|---|---|---|---|---|
| best trained baseline | 0.0622 | 0.0370 | 0.0790 | 0.0310 |
| pool and residual ranker, no decision model | 0.0730 | 0.0468 | 0.0786 | 0.0386 |
| with this model (fused) | 0.0789 | 0.0492 | 0.0831 | 0.0402 |
bash
cd ~/kev && uv run --extra serve python -m kev.serve --run m-polignano/decision4rec-kev-27B --port 8009decision4rec run --config configs/small/vg_rtm.yaml --backend configs/backends/kev-27B-rtm8k.yamlThe adapter and head are released under Apache-2.0. The base model keeps its own license. The training data come from public research datasets that are not redistributed here.
bibtex
@article{polignano2026decision4rec, title = {Decision4Rec: A Jev-Inspired Framework of Decision Models on Knowledge and Active Graphs for Multi-Agent Recommender Systems}, author = {Polignano, Marco and Mehta, Het Darshan and Lops, Pasquale and De Luca, Ernesto William and Semeraro, Giovanni}, year = {2026}}cd ~/kev && uv run --extra serve python -m kev.serve --run m-polignano/decision4rec-kev-27B --port 8009decision4rec run --config configs/small/vg_rtm.yaml --backend configs/backends/kev-27B-rtm8k.yaml@article{polignano2026decision4rec, title = {Decision4Rec: A Jev-Inspired Framework of Decision Models on Knowledge and Active Graphs for Multi-Agent Recommender Systems}, author = {Polignano, Marco and Mehta, Het Darshan and Lops, Pasquale and De Luca, Ernesto William and Semeraro, Giovanni}, year = {2026}}