melhoushi/gpt_h2688_d52_gbs288_tpp20.0_lp0.99_linear_linear_reverse
Updated • 194
Mostafa Elhoushi
melhoushi
AI & ML interests
Make ML faster, smaller, smarter.
Recent Activity
updated a model 1 day ago
melhoushi/gpt_h2688_d52_gbs288_tpp20.0_lp0.99_linear_linear_reverse published a model 2 days ago
melhoushi/gpt_h2688_d52_gbs288_tpp20.0_lp0.99_linear_linear_reverse liked a model 2 days ago
sapientinc/HRM-Text-1BOrganizations
melhoushi/slimpj_h2688_d52_gbs288_tpp20.0_lp0.99_linear_linear_reverse
8B • Updated • 29
melhoushi/qwen2.5_7b_synthetic_duo3_ce1_max_bsz256
Text Generation • 8B • Updated • 19
melhoushi/jacobiforcing-mixed-bsz4-lr1e-5-step10000
8B • Updated • 33
melhoushi/jacobiforcing-mixed-bsz32-lr1e-6-step6000
8B • Updated • 32
melhoushi/jacobiforcing-mixed-bsz4-lr1e-5-step20000
8B • Updated • 33
melhoushi/jacobiforcing-mixed-bsz32-lr1e-6-step10000
8B • Updated • 35
melhoushi/jacobiforcing-mixed-bsz4-lr1e-5-step6000
8B • Updated • 32
melhoushi/jacobi-coder-phase1-bsz32-step5000
8B • Updated • 16
melhoushi/JacobiForcing_Code_10k_constant
8B • Updated • 19
melhoushi/JacobiForcing_Math_10k_constant
8B • Updated • 2
melhoushi/JacobiForcing_Code_5k_constant
8B • Updated • 1
melhoushi/JacobiForcing_Math_5k_constant
8B • Updated • 2
melhoushi/JacobiForcing_Code_10k
8B • Updated • 5
melhoushi/JacobiForcing_Code_5k
8B • Updated • 3
melhoushi/JacobiForcing_Math_5k
8B • Updated • 1
melhoushi/JacobiForcing_Math_10k
8B • Updated • 2
melhoushi/gpt_h1152_d23_gbs76_tpp20.0_lp0.4_uniform
Updated • 17
melhoushi/gpt_h1152_d23_gbs76_tpp20.0_lp0.2_uniform
Updated • 16
melhoushi/gpt_h1152_d23_gbs76_tpp20.0_lp0.1_uniform
Updated • 16
melhoushi/gpt_h896_d17_gbs66_tpp20.0_temamult1.0_lp0.4_uniform_null
Updated • 15
melhoushi/gpt_h896_d17_gbs66_tpp20.0_lp0.2_uniform
Updated • 16
melhoushi/gpt_h896_d17_gbs66_tpp20.0_lp0.1_uniform
Updated • 17
melhoushi/gpt_h640_lrmult1_d13_gbs48_tpp20.0_lp0.4_uniform
Updated • 16
melhoushi/gpt_h640_d13_gbs48_tpp20.0_temamult1.0_lp0.2_uniform_null
Updated • 18
melhoushi/gpt_h640_d13_gbs48_tpp20.0_lp0.1_uniform
Updated • 16
melhoushi/slimpj_h640_d13_gbs48_tpp20.0_lp0.1_uniform
Updated • 3
melhoushi/slimpj_h640_d13_gbs48_tpp20.0_temamult1.0_lp0.2_uniform_null
Updated • 2
melhoushi/slimpj_h896_d17_gbs66_tpp20.0_temamult1.0_lp0.4_uniform_null
Updated • 3
melhoushi/slimpj_h1152_d23_gbs76_tpp20.0_temamult1.0_lp0.4_uniform_null
Updated • 2