Disya

Disya's activity

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

updated a bucket about 17 hours ago

Disya/pixeldit-moe

54.8 GB

published a bucket about 18 hours ago

Disya/pixeldit-moe

54.8 GB

updated a bucket about 18 hours ago

Disya/DeCo-Anime-FT

55.3 GB

published a bucket 2 days ago

Disya/DeCo-Anime-FT

55.3 GB

updated a bucket 3 days ago

Disya/LLM-TO-DIT

967 GB

liked a model 8 days ago

KBlueLeaf/TIPO-v2.1-1B-A200M

Text Generation • 1.0B • Updated Aug 22 • 12.1k • 30

published a bucket 10 days ago

Disya/LLM-TO-DIT

967 GB

updated a bucket 14 days ago

Disya/Train_anima

64.8 GB

published a bucket 15 days ago

Disya/Train_anima

64.8 GB

liked a model 16 days ago

JetBrains/Mellum2.1-12B-A2.5B-Thinking

Text Generation • 12B • Updated 17 days ago • 5.95k • 177

New activity in Disya/Anima-T5-Free-Base 17 days ago

maybe some example images?

1

#2 opened 18 days ago by

TheProshkaPro25

New activity in Johnny-Z/Anima-Light-Lavender 19 days ago

Did you fine tune Anima's llm_adapter?

2

#8 opened 20 days ago by

Disya

updated a model 21 days ago

Disya/Anima-T5-Free-Base

Text-to-Image • Updated 21 days ago • 9

New activity in lylogummy/Anima-3.8B 23 days ago

Alternative Anima conditioning approach: full-depth Qwen -> native CA K/V

🔥 1

1

#6 opened 23 days ago by

Disya

liked a model about 1 month ago

XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B

Image-Text-to-Text • 9B • Updated Sep 22 • 23k • 670

New activity in XiaomiMiMo/MiMo-V2.6-Flash-RL about 1 month ago

Will MiMo-V2.6-Distill-Qwen-9B be released?

1

#1 opened about 1 month ago by

Disya

liked a model about 1 month ago

hiwaifu-research/WaifuGemma4-26b-a4b-v1

Text Generation • 26B • Updated Sep 19 • 2.07k • 30

New activity in circlestone-labs/Anima about 1 month ago

Why does Anima keep the T5 token/grid structure in the Qwen conditioning path?

👍 2

2

#239 opened about 1 month ago by

Disya

published a model about 1 month ago

Disya/Anima-T5-Free-Base

Text-to-Image • Updated 21 days ago • 9

liked a model about 2 months ago

nvidia/RE-USE

Audio-to-Audio • 9.61M • Updated 1 day ago • 13k • 141