Downloads · 30 days
13
33% of all-time downloads
MaximeM/Qwen3-8B-recsys-challenge-2026-scorehead-top200
Qwen3-8B-recsys-challenge-2026-scorehead-top200 is a machine learning model from MaximeM. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Listwise scoring-head reranker for conversational music recommendation, from team FPMsUMONS's entry to the RecSys Challenge 2026. This is the reranker behind our final Blind-B submission.
Downloads · 30 days
13
33% of all-time downloads
All-time downloads
40
Public
Parameters
7.6B
15.1 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors15.1 GB · 100%
From the Hugging Face model README
Listwise scoring-head reranker for conversational music recommendation, from team FPMs_UMONS's entry to the RecSys Challenge 2026. This is the reranker behind our final Blind-B submission.
Fine-tuned from Qwen/Qwen3-8B with LoRA (rank 16), then merged.
This is a pipeline component, not a standalone model. It reranks a candidate pool produced by our retriever, with candidates rendered in one exact format and enriched with a descriptor cache — none of which it builds for itself. There is no standalone usage recipe here on purpose: the repository is what loads it correctly and runs it end to end.
All evaluation numbers, ablations and negative results are reported in the paper and the repository; they are not duplicated here.
Given a conversation and a pool of candidate tracks, the model appends a marker token after each candidate, reads that marker's hidden state in a single forward pass, and maps it to a score with a linear head trained with listwise cross-entropy. It ranks the whole pool at once rather than emitting a single pick — which is the distinction the paper is about.
Three things make these weights unusable outside the pipeline unless reproduced exactly:
config.json declares Qwen3Model — the backbone without an LM head.
Loading with AutoModelForCausalLM does not give you this model.
The scoring head is not in the safetensors. It lives in score_head.pt,
which also records the marker token id; fetching only the safetensors gives a
silently unusable model.
Each candidate must be rendered as one line ending with the marker token
(<|box_end|>, id 151649), carrying the distilled {sound | themes}
descriptors the model was trained on:
12. Thunderstruck by AC/DC [rock, 80s] {sound: hard rock, metal | themes: rebellion, anger}<|box_end|>
The descriptors are not optional, and the rendering is not approximate — another format degrades the model sharply.
The repository handles all three, and the descriptor cache ships as a released artifact alongside the commands that rebuild it.
Released under the Apache License 2.0, inherited from
Qwen/Qwen3-8B. A copy of the licence is
included as LICENSE.
Modifications: these weights are a fine-tuned derivative of Qwen3-8B. The
transformer weights were adapted with LoRA (rank 16) and merged; the original
language-modelling head was dropped and replaced by the linear scoring head
distributed in score_head.pt.