melhoushi/gpt_h640_d13_gbs48_tpp20.0_lp0.1_uniform
Updated • 2
Mostafa Elhoushi
melhoushi
AI & ML interests
Make ML faster, smaller, smarter.
Recent Activity
updated a dataset 8 days ago
melhoushi/OpenScience-Qwen3-8B-nothink published a dataset 8 days ago
melhoushi/OpenScience-Qwen3-8B-nothink updated a dataset 8 days ago
melhoushi/OpenMathInstruct-2-Qwen3-8B-nothinkOrganizations
melhoushi/slimpj_h640_d13_gbs48_tpp20.0_lp0.1_uniform
Updated • 2
melhoushi/slimpj_h640_d13_gbs48_tpp20.0_temamult1.0_lp0.2_uniform_null
Updated • 3
melhoushi/slimpj_h896_d17_gbs66_tpp20.0_temamult1.0_lp0.4_uniform_null
Updated • 4
melhoushi/slimpj_h1152_d23_gbs76_tpp20.0_temamult1.0_lp0.4_uniform_null
Updated • 4
melhoushi/slimpj_h1152_d23_gbs76_tpp20.0_lp0.2_uniform
Updated • 3
melhoushi/slimpj_h1152_d23_gbs76_tpp20.0_lp0.1_uniform
Updated • 4
melhoushi/slimpj_h896_d17_gbs66_tpp20.0_lp0.2_uniform
Updated • 3
melhoushi/slimpj_h896_d17_gbs66_tpp20.0_lp0.1_uniform
Updated • 3
melhoushi/slimpj_h640_lrmult1_d13_gbs48_tpp20.0_lp0.4_uniform
Updated • 3
melhoushi/gpt_h1152_d23_gbs76_tpp20.0_lp0.4_linear
Updated • 2
melhoushi/slimpj_h1152_d23_gbs76_tpp20.0_lp0.4_linear
Updated • 2
melhoushi/gpt_h1152_d23_gbs76_tpp20.0_lp0.2_linear
Updated • 2
melhoushi/slimpj_h1152_d23_gbs76_tpp20.0_lp0.2_linear
Updated • 5
melhoushi/gpt_h896_d17_gbs66_tpp20.0_lp0.4_linear
Updated • 3
melhoushi/slimpj_h896_d17_gbs66_tpp20.0_lp0.4_linear
Updated • 2
melhoushi/gpt_h896_d17_gbs66_tpp20.0_lp0.2_linear
Updated • 3
melhoushi/slimpj_h896_d17_gbs66_tpp20.0_lp0.2_linear
Updated • 2
melhoushi/gpt_h640_d13_gbs48_tpp20.0
Updated • 2
melhoushi/gpt_h1152_d23_gbs212_tpp256.0_lp0.4_linear_linear_reverse
Updated • 5
melhoushi/slimpj_h1152_d23_gbs212_tpp256.0_lp0.4_linear_linear_reverse
Updated • 1
melhoushi/gpt_h1152_d23_gbs212_tpp256.0_lp0.0_uniform
Updated • 6
melhoushi/slimpj_h1152_d23_gbs212_tpp256.0_lp0.0_uniform
Updated • 3
melhoushi/gpt_h1152_d23_gbs76_tpp20.0
Updated • 9
melhoushi/slimpj_h1152_d23_gbs76_tpp20.0
Updated • 6
melhoushi/gpt_h896_d17_gbs66_tpp20.0
Updated • 4
melhoushi/slimpj_h896_d17_gbs66_tpp20.0
Updated • 3
melhoushi/gpt_h1152_d23_gbs76_tpp20.0_lp0.4_linear_linear_reverse
Updated • 2
melhoushi/slimpj_h1152_d23_gbs76_tpp20.0_lp0.4_linear_linear_reverse
Updated • 3
melhoushi/gpt_h1152_d23_gbs76_tpp20.0_lp0.2_linear_linear_reverse
Updated • 2