Extending the Context of Pretrained LLMs by Dropping Their Positional Embedding (https://www.arxiv.org/abs/2512.12167)
AI & ML interests
We are a Tokyo-based R&D company on a quest to create a new kind of foundational AI model based on nature-inspired intelligence.
Recent Activity
View all activity
Papers
View all Papers spaces 6
Running on Zero
20
Llama 3 Karamaru V1
🐻
Classical Japanese Chatbot
Running on Zero
46
Evo-Ukiyoe
🐠
Generate Japanese ukiyo-e style images from prompts
Runtime error
18
Llama-3-EvoVLM-JP-v2
🐠
Chat with images and text using a Japanese visual language model
Running on Zero
18
Evo-Nishikie
🐠
Generate detailed ukiyo-e style images from single-color input
Running on Zero
53
EvoSDXL JP
🐠
Generate images from Japanese prompts
Running on Zero
63
EvoVLM JP
🐠
Answer questions about images in Japanese
models 28
SakanaAI/Metom
5.64M • Updated
• 267 • 6
SakanaAI/Llama-2-7b-hf-DroPE
7B • Updated
• 70 • 2
SakanaAI/RePo-OLMo2-1B-stage2-L5
Text Generation • 1B • Updated
• 16 • 2
SakanaAI/ctm-maze-large
Text Generation • Updated
• 3 • 2
SakanaAI/ctm-imagenet
Text Generation • Updated
• 10 • 5
SakanaAI/RLT-7B
Text Generation • 8B • Updated
• 17 • • 19
SakanaAI/RLT-32B
Text Generation • 33B • Updated
• 5 • 7
SakanaAI/text-to-lora
Updated
• 9
SakanaAI/Llama-3-Karamaru-v1
Text Generation • 8B • Updated
• 12 • • 19
SakanaAI/TAID-VLM-2B
Visual Question Answering • 2B • Updated
• 2 • 5
datasets 14
SakanaAI/Kamon
Viewer
• Updated
• 10k • 32 • 2
SakanaAI/mazes-extralarge
Viewer
• Updated
• 50k • 29
SakanaAI/mazes-large
Viewer
• Updated
• 50k • 23
SakanaAI/mazes-medium
Viewer
• Updated
• 60k • 15
SakanaAI/mazes-small
Viewer
• Updated
• 10k • 116
SakanaAI/TransEvalnia
Viewer
• Updated
• 3.84k • 106 • 4
SakanaAI/ALE-Bench
Updated
• 4.53k • 11
SakanaAI/EDINET-Bench
Viewer
• Updated
• 2.59k • 495 • 10
SakanaAI/AI-CUDA-Engineer-Archive
Viewer
• Updated
• 30.6k • 376 • 168
SakanaAI/ChouBun
Viewer
• Updated
• 770 • 26 • 10