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
19
Llama 3 Karamaru V1
🐻
Classical Japanese Chatbot
Running
on
Zero
46
Evo-Ukiyoe
🐠
Generate Japanese ukiyo-e style images from prompts
Running
on
Zero
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
🐠
Ask questions about images to get detailed answers
models
28
SakanaAI/Llama-2-7b-hf-DroPE
7B
•
Updated
SakanaAI/RePo-OLMo2-1B-stage2-L5
Text Generation
•
1B
•
Updated
•
211
•
1
SakanaAI/ctm-maze-large
Text Generation
•
Updated
•
37
•
2
SakanaAI/ctm-imagenet
Text Generation
•
Updated
•
202
•
5
SakanaAI/RLT-7B
Text Generation
•
8B
•
Updated
•
17
•
•
18
SakanaAI/RLT-32B
Text Generation
•
33B
•
Updated
•
7
•
6
SakanaAI/Metom
5.64M
•
Updated
•
314
•
6
SakanaAI/text-to-lora
Updated
•
9
SakanaAI/Llama-3-Karamaru-v1
Text Generation
•
8B
•
Updated
•
19
•
•
19
SakanaAI/TAID-VLM-2B
Visual Question Answering
•
2B
•
Updated
•
14
•
5
datasets
16
SakanaAI/Kamon
Viewer
•
Updated
•
10k
•
43
SakanaAI/Sudoku-CTC-Reasoning
Viewer
•
Updated
•
1.81k
•
124
•
9
SakanaAI/Sudoku-Bench
Viewer
•
Updated
•
2.77k
•
1.61k
•
10
SakanaAI/mazes-extralarge
Viewer
•
Updated
•
50k
•
28
SakanaAI/mazes-large
Viewer
•
Updated
•
50k
•
31
SakanaAI/mazes-medium
Viewer
•
Updated
•
60k
•
34
SakanaAI/mazes-small
Viewer
•
Updated
•
10k
•
46
SakanaAI/TransEvalnia
Viewer
•
Updated
•
3.84k
•
24
•
4
SakanaAI/ALE-Bench
Updated
•
6.8k
•
11
SakanaAI/EDINET-Bench
Viewer
•
Updated
•
2.59k
•
268
•
9