Rin

hu5enpai's activity

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

commented a paper 15 days ago

Soft Adaptive Policy Optimization

Paper • 2511.20347 • Published 16 days ago • 38 •

4

New activity in PaddlePaddle/PaddleOCR-VL about 2 months ago

ms-swift has supported inference, deployment, and fine-tuning of the PaddleOCR-VL model.

🚀 🔥 7

4

#42 opened about 2 months ago by

hu5enpai

commented a paper 3 months ago

On-Policy RL Meets Off-Policy Experts: Harmonizing Supervised Fine-Tuning and Reinforcement Learning via Dynamic Weighting

Paper • 2508.11408 • Published Aug 15 • 8 •

6

commented a paper 4 months ago

On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification

Paper • 2508.05629 • Published Aug 7 • 180 •

21

commented 2 papers 5 months ago

DeepEyes: Incentivizing "Thinking with Images" via Reinforcement Learning

Paper • 2505.14362 • Published May 20 • 3 •

2

Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning

Paper • 2506.01939 • Published Jun 2 • 187 •

6

New activity in Qwen/Qwen3-Coder-480B-A35B-Instruct 5 months ago

👍👍

👍 1

#19 opened 5 months ago by

hu5enpai

New activity in ChenShawn/DeepEyes-Datasets-47k 5 months ago

Unable to load the dataset

#2 opened 5 months ago by

hu5enpai

New activity in microsoft/Florence-2-large-ft over 1 year ago

Swift now supports inference, training, and deployment of the Florence models.

3

#14 opened over 1 year ago by

hu5enpai

New activity in microsoft/Florence-2-large over 1 year ago

How to Finetune?

👍 👀 18

5

#19 opened over 1 year ago by

vody-am

Fix incorrect bos_token, eos_token, and pad_token ids in config.json

3

#17 opened over 1 year ago by

Xenova

New activity in liuhaotian/LLaVA-Instruct-150K over 1 year ago

Unable to load dataset.

👍 5

2

#10 opened almost 2 years ago by

ToletiSri

New activity in OpenGVLab/InternVL-Chat-V1-5 over 1 year ago

Swift now supports inference, training of InternVL-Chat-V1-5

❤️ 1

3

#11 opened over 1 year ago by

hu5enpai