Downloads · 30 days
9
24% of all-time downloads
iolai-2026-qwen25-14b-explain
jbuaba/iolai-2026-qwen25-14b-explain
iolai-2026-qwen25-14b-explain is a machine learning model from jbuaba. 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.
- Weights: Qwen/Qwen2.5-14B-Instruct-AWQ - Entrypoint: script.py - Loads from ., reads /tmp/data/test.csv, writes submission.csv - Strategy: structuredverifyv1 (repo DEFAULTSTRATEGY) - Also available: anchoredvotev1 (…
All-time downloads
38
Public
Parameters
14.8B
10 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors10 GB · 100%
Parameter types
How the weights are stored.
I3213.2B · 89%
Model card
From the Hugging Face model README
IOL-AI 2026 submission
- Weights:
Qwen/Qwen2.5-14B-Instruct-AWQ - Entrypoint:
script.py - Loads from
., reads/tmp/data/test.csv, writessubmission.csv - Strategy:
structured_verify_v1 (repo DEFAULT_STRATEGY) - Also available:
anchored_vote_v1(greedy + K=3 greedy-anchored vote) - Eval sandbox: T4 16GB / 30 min / offline (
transformers==4.44.1) - Explanations: enabled by default (
IOL_EXPLAIN=1) - Quant fallback:
IOL_LOAD=bnb
- Type
- qwen2
- License
- apache-2.0
- Created
- Jul 26, 2026
- Updated
- Jul 26, 2026