sdsd

sdd5125's activity

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

upvoted a paper about 18 hours ago

Kimi Linear: An Expressive, Efficient Attention Architecture

Paper • 2510.26692 • Published Oct 30, 2025 • 136

upvoted a paper 9 days ago

Principled Analysis of Deep Reinforcement Learning Evaluation and Design Paradigms

Paper • 2607.07769 • Published 21 days ago • 10

reacted to ezgikorkmaz's post with 🤗 9 days ago

view post

Post

3391

Principled Analysis of Deep Reinforcement Learning Evaluation and Design Paradigms

Link: Principled Analysis of Deep Reinforcement Learning Evaluation and Design Paradigms (2607.07769)

See translation

• 
• 1 reply

·

🤗

5

5

+

Reply

New activity in nvidia/nemotron-3.5-asr-streaming-0.6b about 1 month ago

vllm support ?

👍 9

4

#6 opened about 2 months ago by

sdd5125

New activity in z-lab/Qwen3.5-27B-DFlash 2 months ago

FP8 work for base model or is 16-bit of 27B required?

17

#2 opened 4 months ago by

unoid

New activity in z-lab/Qwen3.5-27B-DFlash 3 months ago

Is this DFlash model still under training ?

#9 opened 3 months ago by

sdd5125

New activity in mistralai/Mistral-Small-4-119B-2603-NVFP4 4 months ago

Update README.md

#3 opened 4 months ago by

sdd5125

liked a model 4 months ago

mistralai/Mistral-Small-4-119B-2603-NVFP4

Updated 14 days ago • 2.61k • 110

upvoted an article 10 months ago

view article

Article

Simplifying Alignment: From RLHF to Direct Preference Optimization (DPO)

• 

ariG23498

•

Jan 19, 2025

• 53