Mohammad Hossein Amani's picture

1 1

Mohammad Hossein Amani

masani

https://mh-amani.github.io/

AI & ML interests

explainability, the science of deep learning

Organizations

None yet

masani 's models 85

masani/SFT_gsm8k_Llama-3.2-3B_epoch_1_global_step_29

Text Generation • 3B • Updated May 14 • 10

masani/SFT_gsm8k_train_size_256_Llama-3.2-1B_epoch_4_global_step_4

Text Generation • 1B • Updated May 13 • 9

masani/SFT_gsm8k_train_size_1024_Llama-3.2-1B_epoch_2_global_step_8

Text Generation • 1B • Updated May 13 • 10

masani/SFT_gsm8k_train_size_512_Llama-3.2-1B_epoch_3_global_step_6

Text Generation • 1B • Updated May 13 • 9

masani/SFT_gsm8k_train_size_256_Llama-3.2-1B_epoch_5_global_step_5

Text Generation • 1B • Updated May 13 • 3

masani/SFT_gsm8k_train_size_4096_Llama-3.2-1B_epoch_1_global_step_16

Text Generation • 1B • Updated May 13 • 9

masani/SFT_gsm8k_train_size_1024_Llama-3.2-1B_epoch_1_global_step_4

Text Generation • 1B • Updated May 13 • 3

masani/SFT_gsm8k_train_size_2048_Llama-3.2-1B_epoch_1_global_step_8

Text Generation • 1B • Updated May 13 • 8

masani/SFT_gsm8k_train_size_512_Llama-3.2-1B_epoch_1_global_step_2

Text Generation • 1B • Updated May 13 • 3

masani/SFT_gsm8k_train_size_256_Llama-3.2-1B_epoch_1_global_step_1

Text Generation • 1B • Updated May 13 • 3

masani/SFT_gsm8k-t2_Llama-3.2-3B_epoch_1_global_step_15

Text Generation • 3B • Updated May 13 • 425

masani/SFT_gsm8k-t2_Llama-3.2-1B_epoch_1_global_step_15

Text Generation • 1B • Updated May 13 • 798

masani/SFT_modgsm8k_Llama-3.2-1B_epoch_1_global_step_25

Text Generation • 1B • Updated May 13 • 795

masani/SFT_math_Llama-3.1-8B_epoch_1_global_step_29

Text Generation • 8B • Updated May 13 • 392

masani/SFT_cumulative_parity_length_16_bitwidth_1_1024_512_Qwen2-1.5B_6000_RL

2B • Updated May 11 • 1

masani/SFT_math_Llama-3.2-1B_epoch_1_global_step_29

Text Generation • 1B • Updated May 10 • 11

masani/SFT_gsm8k_Llama-3.2-1B_epoch_1_global_step_29

Text Generation • 1B • Updated May 10 • 13

masani/SFT_gsm8k_Llama-3.2-1B_epoch_3_global_step_87

Text Generation • 1B • Updated May 10 • 5

masani/SFT_cumulative_parity_length_16_bitwidth_1_1024_512_Llama-3.2-1B_epoch_3_global_step_12

Text Generation • 1B • Updated May 10 • 872

masani/SFT_modgsm8k_Llama-3.2-3B_epoch_1_global_step_25

Text Generation • 3B • Updated May 9 • 199

masani/SFT_math_Llama-3.1-8B_epoch_3_global_step_87

Text Generation • 8B • Updated May 6 • 5

masani/SFT_math_Llama-2-7b-hf_epoch_3_global_step_87

Text Generation • 7B • Updated May 4 • 101

masani/SFT_math_Llama-3.2-3B_epoch_3_global_step_87

Text Generation • 3B • Updated May 4 • 305

masani/SFT_math_Llama-2-7b-hf_epoch_5_global_step_145

Text Generation • 7B • Updated May 4 • 3

masani/SFT_math_Llama-3.2-3B_epoch_5_global_step_145

Text Generation • 3B • Updated May 4 • 4

masani/SFT_math_Qwen2-1.5B_epoch_5_global_step_145

Text Generation • 2B • Updated May 4 • 4

masani/SFT_cumulative_parity_length_32_bitwidth_1_1024_512_Qwen2-1.5B_epoch_100_global_step_400

Text Generation • 2B • Updated May 2 • 3

masani/SFT_cumulative_parity_length_32_bitwidth_1_4096_512_Qwen2-1.5B_epoch_100_global_step_1600

Text Generation • 2B • Updated May 2 • 3

masani/SFT_cumulative_parity_length_32_bitwidth_1_2048_512_Qwen2-1.5B_epoch_100_global_step_800

Text Generation • 2B • Updated May 2 • 3

masani/SFT_cumulative_parity_length_16_bitwidth_1_2048_512_Qwen2-1.5B_epoch_8_global_step_64

Text Generation • 2B • Updated May 2 • 3