132 12 330

Djuunaa

djuna

AI & ML interests

None yet

Recent Activity

liked a model about 17 hours ago

cyberagent/DeepSeek-R1-Distill-Qwen-32B-Japanese

liked a model about 17 hours ago

SmallDoge/Doge-60M-Instruct

liked a model about 22 hours ago

cognitivecomputations/DeepSeek-R1-AWQ

View all activity

Organizations

djuna's activity

liked 2 models about 17 hours ago

cyberagent/DeepSeek-R1-Distill-Qwen-32B-Japanese

Text Generation • Updated 8 days ago • 7.37k • 213

SmallDoge/Doge-60M-Instruct

Question Answering • Updated about 14 hours ago • 49.7k • 5

liked a model about 22 hours ago

cognitivecomputations/DeepSeek-R1-AWQ

Text Generation • Updated about 23 hours ago • 10.1k • 13

liked a model 3 days ago

nbeerbower/Dumpling-Qwen2.5-1.5B

Text Generation • Updated 3 days ago • 29 • 1

reacted to Jaward's post with 🔥 3 days ago

Post

1379

The beauty in GRPO is the fact that it doesn’t care if the rewards are rule-based or learned, the hack: let the data self-normalize— trajectories in a batch compete against their mean, no value model, no extra params, just clean, efficient RL that cuts memory usage by 50%, while maintaining SOTA performance. btw it was introduced 9months prior to R1: arxiv.org/pdf/2402.03300

1 reply

liked 2 models 3 days ago

arcee-ai/Virtuoso-Small-v2

Text Generation • Updated 5 days ago • 250 • 21

BlossomsAI/Qwen2.5-Coder-14B-Instruct-Uncensored

Text Generation • Updated 4 days ago • 21 • 2

New activity in tugstugi/Qwen2.5-Coder-0.5B-QwQ-draft 3 days ago

Tokenizer Details

#2 opened 12 days ago by

qingy2024

liked a Space 4 days ago

Running on Zero

🚀

DeepseekJanusPro

Deepseek AI's Janus-Pro-7B: Generate image from text

reacted to Bils's post with 🔥 4 days ago

Post

1983

🚀 We're excited to share major improvements to our Janus-Pro-7B Text-to-Image Generation Space!
🎨What's New:
1-Critical Bug Fixes
2-Enhanced Features
3-UI Improvements
4-Performance Boost
Try It Now:
Bils/DeepseekJanusPro-Image

liked a dataset 4 days ago

cognitivecomputations/dolphin-r1

Viewer • Updated 4 days ago • 814k • 654 • 157

reacted to fdaudens's post with 🔥 4 days ago

Post

2976

🎯 Kokoro TTS just hit v1.0! 🚀

Small but mighty: 82M parameters, runs locally, speaks multiple languages. The best part? It's Apache 2.0 licensed!
This could unlock so many possibilities ✨

Check it out: hexgrad/Kokoro-82M