Downloads · 30 days
15
19% of all-time downloads
weblab-llm-competition-2025-bridge
weblab-llm-competition-2025-bridge/oNo-1-DeepSeek-R1-0528-QLoRA-MedMCQA
oNo-1-DeepSeek-R1-0528-QLoRA-MedMCQA is a machine learning model from weblab-llm-competition-2025-bridge. 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 mit.
Notion ガイド: https://www.notion.so/257e14b94af5808687a1f39f4b84bd0e?source=copy\link
Downloads · 30 days
15
19% of all-time downloads
All-time downloads
80
Public
Parameters
685B
689 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors689 GB · 100%
How the weights are stored.
F8_E4M3681B · 99%
From the Hugging Face model README
サマリー — DeepSeek-R1-0528 をベースに、oNo-1/MedMCQAのプライベートサブセットを用いた内部ポストトレーニングの成果物です。最終重みはアダプタ統合(merged)で提供し、推論はFP8 (E4M3)を前提とします。学習レシピの詳細はコンペ期間中は非公開です。
deepseek-ai/DeepSeek-R1-0528(MIT)oNo-1/MedMCQA