🔄 In a Training Loop

Ahmed Khaled Khamis

KickItLikeShika

·

https://kickitlikeshika.github.io/

AI & ML interests

NLP

Recent Activity

upvoted a paper 1 day ago

iSDFT: Information-Proximal Self-Distillation for Continual Learning in LLMs

updated a collection 2 days ago

iSDFT: Info-Proximal Self-Distillation Fine-Tuning

liked a model 6 days ago

Qwen/Qwen2.5-7B-Instruct

View all activity

Organizations

KickItLikeShika 's models 90

KickItLikeShika/qwen3-1.7B-isdft-science-rho0.5

2B • Updated 13 days ago • 19

KickItLikeShika/qwen3-1.7B-isdft-science-rho0.75

2B • Updated 13 days ago • 24

KickItLikeShika/qwen3-1.7B-isdft-science-rho0.25

2B • Updated 13 days ago • 23

KickItLikeShika/olmo3-7b-think-beta-opsd-science

7B • Updated 14 days ago • 21

KickItLikeShika/olmo3-7b-think-beta-opsd-tooluse

7B • Updated 14 days ago • 25

KickItLikeShika/qwen2.5-7b-instruct-beta-opsd-science

8B • Updated 14 days ago • 25

KickItLikeShika/qwen2.5-7b-instruct-beta-opsd-tooluse

8B • Updated 14 days ago • 19

KickItLikeShika/qwen3-1.7b-beta-opsd-science

2B • Updated 14 days ago • 22

KickItLikeShika/qwen3-1.7b-beta-opsd-tooluse

2B • Updated 14 days ago • 22

KickItLikeShika/qwen3-1.7b-isdft-tooluse-rho0.5

2B • Updated 16 days ago • 23

KickItLikeShika/qwen3-1.7b-isdft-tooluse-rho0.25

2B • Updated 16 days ago • 24

KickItLikeShika/qwen3-1.7b-science-sdft-mu-student

2B • Updated 22 days ago • 22

KickItLikeShika/qwen3-1.7b-isdft-science-0mu

2B • Updated 22 days ago • 23

KickItLikeShika/qwen3-1.7b-tooluse-sdft-mu-student

2B • Updated 22 days ago • 22

KickItLikeShika/qwen3-1.7b-isdft-tooluse-0mu

2B • Updated 22 days ago • 23

KickItLikeShika/qwen2.5-7b-tooluse-isdft-corrected-grad-500

8B • Updated Aug 11 • 3

KickItLikeShika/qwen2.5-7b-tooluse-isdft-corrected-grad-400

8B • Updated Aug 11 • 3

KickItLikeShika/qwen3-1.7b-eopd-tooluse

2B • Updated Aug 1 • 5

KickItLikeShika/qwen3-1.7b-eopd-science

2B • Updated Aug 1 • 9

KickItLikeShika/qwen2.5-0.5b-eopd-science

0.6B • Updated Aug 1 • 5

KickItLikeShika/qwen2.5-0.5b-eopd-tooluse

0.6B • Updated Aug 1 • 5

KickItLikeShika/qwen3-1.7b-taid-tooluse

2B • Updated Jul 31 • 7

KickItLikeShika/qwen3-1.7b-taid-science

2B • Updated Jul 31 • 10

KickItLikeShika/qwen2.5-0.5b-taid-science

0.5B • Updated Jul 31 • 6

KickItLikeShika/qwen2.5-0.5b-taid-tooluse

0.5B • Updated Jul 31 • 5

KickItLikeShika/olmo3-7b-think-taid-science

7B • Updated Jul 31 • 12

KickItLikeShika/olmo3-7b-think-taid-tooluse

7B • Updated Jul 31 • 9

KickItLikeShika/gemma4-e2b-it-sdft-tooluse

5B • Updated Jul 31 • 2.19k

KickItLikeShika/gemma4-e2b-it-sdft-science

5B • Updated Jul 31 • 8

KickItLikeShika/gemma4-e2b-it-isdft-science

5B • Updated Jul 31 • 9