Article
66
Mostafa Elhoushi
melhoushi
AI & ML interests
Make ML faster, smaller, smarter.
Recent Activity
updated a model 19 days ago
melhoushi/gpt_cp_h2048_d40_gbs200_tpp20.0_lp0.8_linear_linear_reverse published a model 19 days ago
melhoushi/gpt_cp_h2048_d40_gbs200_tpp20.0_lp0.8_linear_linear_reverse updated a model 19 days ago
melhoushi/common_pile_h2048_d40_gbs200_tpp20.0_lp0.8_linear_linear_reverseOrganizations
models 154
melhoushi/gpt_cp_h2048_d40_gbs200_tpp20.0_lp0.8_linear_linear_reverse
Updated • 126
melhoushi/common_pile_h2048_d40_gbs200_tpp20.0_lp0.8_linear_linear_reverse
Updated • 10
melhoushi/Moonlight-16B-A3B-Instruct-transformers-5.13.0
Text Generation • 16B • Updated • 63
melhoushi/gpt_cp_h1152_d23_gbs76_tpp20.0_lp0.4_linear_linear_reverse
Updated • 18
melhoushi/common_pile_h1152_d23_gbs76_tpp20.0_lp0.4_linear_linear_reverse
Updated • 3
melhoushi/gpt_cp_h1152_d23_gbs76_tpp20.0_lp0.4_linear_null
Updated • 15
melhoushi/common_pile_h1152_d23_gbs76_tpp20.0_lp0.4_linear_null
Updated • 3
melhoushi/gpt_cp_h896_d17_gbs66_tpp20.0_lp0.4_linear_null
Updated • 14
melhoushi/common_pile_h896_d17_gbs66_tpp20.0_lp0.4_linear_null
Updated • 4
melhoushi/gpt_cp_h640_d13_gbs48_tpp20.0_lp0.4_linear_null
Updated • 17
datasets 138
melhoushi/OpenThoughts3_science_qwen7binst_traj_n16w16_2048
Viewer • Updated • 4.5M • 22
melhoushi/OpenThoughts3_math_qwen7binst_traj_n16w16_2048
Viewer • Updated • 4.05M • 38
melhoushi/OpenThoughts3_code_qwen7binst_traj_n16w16_2048
Viewer • Updated • 9.63M • 25
melhoushi/OpenThoughts3_science_qwen7binst_sft_2048
Viewer • Updated • 91.8k • 19
melhoushi/OpenThoughts3_math_qwen7binst_sft_2048
Viewer • Updated • 88.3k • 13
melhoushi/OpenThoughts3_code_qwen7binst_sft_2048
Viewer • Updated • 200k • 35
melhoushi/OpenThoughts3_code_qwen_sft_2048
Viewer • Updated • 212k • 40 • 1
melhoushi/OpenThoughts3_math_qwen_sft_2048
Viewer • Updated • 79.5k • 25
melhoushi/OpenThoughts3_math_qwen_sft
Viewer • Updated • 80.7k • 16
melhoushi/baseline_gptq_dataset_codesmath
Viewer • Updated • 1.02k • 39