Taishi's picture

19 22

Taishi

Taishi-N324

·

https://taishi-n324.github.io/

AI & ML interests

None yet

Recent Activity

updated a collection 21 days ago

updated a collection 21 days ago

updated a collection 21 days ago

View all activity

Organizations

Taishi-N324's activity

upvoted 3 collections about 1 month ago

SwallowCode

Rewriting Pre-Training Data Boosts LLM Performance in Math and Code • 66 items • Updated May 7 • 3

SwallowMath

Rewriting Pre-Training Data Boosts LLM Performance in Math and Code • 11 items • Updated May 7 • 3

Gemma-2-Swallow

6 items • Updated May 18 • 3

upvoted 2 collections about 2 months ago

LLM-jp-3 Pre-trained Models

Pre-trained models in the LLM-jp-3 model series • 10 items • Updated 23 days ago • 6

LLM-jp-3 Fine-tuned Models

Fine-tuned models in the LLM-jp-3 model series • 25 items • Updated 23 days ago • 6

upvoted a collection 3 months ago

Llama-3.3-Swallow

3 items • Updated Mar 10 • 3

upvoted a paper 3 months ago

Wider or Deeper? Scaling LLM Inference-Time Compute with Adaptive Branching Tree Search

Paper • 2503.04412 • Published Mar 6 • 1

upvoted an article 4 months ago

Article

DualPipe could be better without the Dual

By

•

Feb 28

• 17

upvoted a paper 4 months ago

Drop-Upcycling: Training Sparse Mixture of Experts with Partial Re-initialization

Paper • 2502.19261 • Published Feb 26 • 7

upvoted a collection 4 months ago

Drop-Upcycling

33 items • Updated 21 days ago • 2

upvoted a collection 5 months ago

TinySwallow

Compact Japanese models trained with "TAID: Temporally Adaptive Interpolated Distillation for Efficient Knowledge Transfer in Language Models" • 5 items • Updated Jan 30 • 17

upvoted a collection 7 months ago

CycleQD

5 items • Updated Oct 27, 2024 • 3

upvoted a paper 8 months ago

Agent Skill Acquisition for Large Language Models via CycleQD

Paper • 2410.14735 • Published Oct 16, 2024 • 2

upvoted a collection 8 months ago

Llama-3.1-Swallow

9 items • Updated Jan 31 • 8

upvoted a paper 12 months ago

LLM-jp: A Cross-organizational Project for the Research and Development of Fully Open Japanese LLMs

Paper • 2407.03963 • Published Jul 4, 2024 • 19

upvoted a collection 12 months ago

Llama-3-Swallow

4 items • Updated Jan 31 • 4

upvoted 4 collections about 1 year ago

Swallow-MS-instruct

1 item • Updated Jan 31 • 1

Swallow-MX

Swallow MX(Mixtral) models • 1 item • Updated Jan 31 • 1

Swallow-MS

Swallow MS(Mistral) models • 1 item • Updated Jan 31 • 1

Swallow

Continual Pre-Training from Llama 2 • 7 items • Updated Jan 31 • 2