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
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 33
SakanaAI/SparseLM2B
2B • Updated • 3
SakanaAI/SparseLM1B
1B • Updated
SakanaAI/SparseLM0.5B
0.6B • Updated
SakanaAI/SparseLM1.5B
2B • Updated • 2
SakanaAI/Metom
5.64M • Updated • 337 • 6
SakanaAI/doc-to-lora
Updated • 15
SakanaAI/Llama-2-7b-hf-DroPE
7B • Updated • 57 • 2
SakanaAI/RePo-OLMo2-1B-stage2-L5
Text Generation • 1B • Updated • 11 • 2
SakanaAI/ctm-maze-large
Text Generation • Updated • 18 • 2
SakanaAI/ctm-imagenet
Text Generation • Updated • 102 • 6
datasets 15
SakanaAI/EDINET-Bench
Viewer • Updated • 2.59k • 614 • 13
SakanaAI/self_gen_qa_d2l
Viewer • Updated • 9.91M • 10.4k
SakanaAI/Kamon
Viewer • Updated • 10k • 15 • 2
SakanaAI/mazes-extralarge
Viewer • Updated • 50k • 5
SakanaAI/mazes-large
Viewer • Updated • 50k • 25
SakanaAI/mazes-medium
Viewer • Updated • 60k • 11
SakanaAI/mazes-small
Viewer • Updated • 10k • 54
SakanaAI/TransEvalnia
Viewer • Updated • 3.84k • 31 • 4
SakanaAI/ALE-Bench
Updated • 3.78k • 11
SakanaAI/AI-CUDA-Engineer-Archive
Viewer • Updated • 30.6k • 628 • 169