DongJae Shin

ShinDJ's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

liked a model 4 days ago

sangmin6600/mamba2-400m-ko-sft

0.4B • Updated 10 days ago • 88 • 2

upvoted a paper 4 days ago

Length-Unbiased Sequence Policy Optimization: Revealing and Controlling Response Length Variation in RLVR

Paper • 2602.05261 • Published 11 days ago • 48

liked a model about 1 month ago

upstage/Solar-Open-100B

Text Generation • Updated 17 days ago • 12.8k • 454

updated a model about 1 month ago

MLP-VLM2/gemma-3-4b-it_Docplan-HF-124k

Image-Text-to-Text • 4B • Updated Jan 5

published a model about 1 month ago

MLP-VLM2/gemma-3-4b-it_Docplan-HF-124k

Image-Text-to-Text • 4B • Updated Jan 5

updated a dataset about 1 month ago

KORMo-VLM/Korean-MM-dataset

Preview • Updated Jan 14 • 15

published a dataset about 2 months ago

KORMo-VLM/Korean-MM-dataset

Preview • Updated Jan 14 • 15

upvoted a paper about 2 months ago

DataFlow: An LLM-Driven Framework for Unified Data Preparation and Workflow Automation in the Era of Data-Centric AI

Paper • 2512.16676 • Published Dec 18, 2025 • 218

updated a dataset about 2 months ago

ShinDJ/OneThinker_img_train

Viewer • Updated Dec 25, 2025 • 173k • 5

published a dataset about 2 months ago

ShinDJ/OneThinker_img_train

Viewer • Updated Dec 25, 2025 • 173k • 5

upvoted a paper about 2 months ago

Robust-R1: Degradation-Aware Reasoning for Robust Visual Understanding

Paper • 2512.17532 • Published Dec 19, 2025 • 67

updated 2 datasets about 2 months ago

Tutoruslabs/GSM8K_KOR-train

Viewer • Updated Dec 24, 2025 • 3.42k • 5 • 3

Tutoruslabs/GSM8K_KOR

Viewer • Updated Dec 24, 2025 • 569 • 6 • 2

updated a Space about 2 months ago

Sleeping

Trackio

🚀

published a Space about 2 months ago

Sleeping

Trackio

🚀

updated a Space about 2 months ago

Sleeping

Trl Trackio

🚀

published a Space about 2 months ago

Sleeping

Trl Trackio

🚀

liked a model 2 months ago

nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16

Text Generation • Updated 11 days ago • 862k • 630

upvoted an article 2 months ago

view article

Article

We Got Claude to Fine-Tune an Open Source LLM

• 
• 

Dec 4, 2025

•

592

reacted to sergiopaniego's post with 🔥 2 months ago

view post

Post

2440

NEW: @mistralai released a fantastic family of multimodal models, Ministral 3.

You can fine-tune them for free on Colab using TRL ⚡️, supporting both SFT and GRPO

Link to the notebooks:
- SFT: https://colab.research.google.com/github/huggingface/trl/blob/main/examples/notebooks/sft_ministral3_vl.ipynb
- GRPO: https://colab.research.google.com/github/huggingface/trl/blob/main/examples/notebooks/grpo_ministral3_vl.ipynb
- TRL and more examples: https://huggingface.co/docs/trl/index

See translation

• 

• 
• 
• 2 replies

·

🔥

8

8

+

Reply