Mohammad Hossein Amani

masani 's models 88

Sort:  Recently updated

masani/SFT_cumulative_parity_length_32_bitwidth_1_1024_512_Qwen2-1.5B_epoch_100_global_step_400

Text Generation • 2B • Updated May 2, 2025 • 1

masani/SFT_cumulative_parity_length_32_bitwidth_1_4096_512_Qwen2-1.5B_epoch_100_global_step_1600

Text Generation • 2B • Updated May 2, 2025 • 1

masani/SFT_cumulative_parity_length_32_bitwidth_1_2048_512_Qwen2-1.5B_epoch_100_global_step_800

Text Generation • 2B • Updated May 2, 2025 • 1

masani/SFT_cumulative_parity_length_16_bitwidth_1_2048_512_Qwen2-1.5B_epoch_8_global_step_64

Text Generation • 2B • Updated May 2, 2025 • 1

masani/SFT_cumulative_parity_length_16_bitwidth_1_1024_512_Qwen2-1.5B_epoch_25_global_step_100

Text Generation • 2B • Updated May 2, 2025 • 2

masani/SFT_cumulative_parity_length_16_bitwidth_1_2048_512_Qwen2-1.5B_epoch_100_global_step_800

Text Generation • 2B • Updated May 2, 2025 • 1

masani/SFT_cumulative_parity_length_16_bitwidth_1_2048_512_Qwen2-1.5B_epoch_16_global_step_128

Text Generation • 2B • Updated May 2, 2025 • 1

masani/SFT_cumulative_parity_length_16_bitwidth_1_512_512_Qwen2-1.5B_epoch_14_global_step_28

Text Generation • 2B • Updated May 2, 2025 • 1

masani/SFT_cumulative_parity_length_16_bitwidth_1_512_512_Qwen2-1.5B_epoch_100_global_step_200

Text Generation • 2B • Updated May 2, 2025

masani/SFT_parity_length_64_bitwidth_1_256_128_Qwen2-0.5B_epoch_20_global_step_20

Text Generation • 0.5B • Updated May 1, 2025 • 1

masani/SFT_parity_length_64_bitwidth_1_256_128_Qwen2-0.5B_epoch_500_global_step_500

Text Generation • 0.5B • Updated May 1, 2025 • 1

masani/SFT_parity_length_64_bitwidth_1_256_128_Qwen2-0.5B_epoch_50_global_step_50

Text Generation • 0.5B • Updated May 1, 2025 • 1

masani/SFT_parity_Qwen2-0.5B_epoch_100_global_step_400

Text Generation • 0.5B • Updated May 1, 2025 • 1

masani/SFT_parity_length_64_bitwidth_1_256_128_Qwen2-0.5B_epoch_10_global_step_10

Updated May 1, 2025

masani/SFT_parity_Qwen2-0.5B_epoch_20_global_step_80

Text Generation • 0.5B • Updated May 1, 2025 • 1

masani/SFT_parity_Qwen2-0.5B_epoch_5_global_step_20

Text Generation • 0.5B • Updated May 1, 2025 • 1

masani/SFT_parity_Qwen2-0.5B_epoch_5_global_step_15

Text Generation • 0.5B • Updated Apr 30, 2025 • 3

masani/SFT_parity_Qwen2-0.5B_epoch_4_global_step_12

Text Generation • 0.5B • Updated Apr 30, 2025 • 1

masani/SFT_parity_Qwen2-0.5B_epoch_3_global_step_9

Text Generation • 0.5B • Updated Apr 30, 2025 • 1

masani/SFT_parity_Qwen2-0.5B_epoch_2_global_step_6

Text Generation • 0.5B • Updated Apr 30, 2025 • 1

masani/SFT_parity_Qwen2-0.5B_epoch_1_global_step_3

Text Generation • 0.5B • Updated Apr 30, 2025 • 1

masani/SFT_parity_Qwen2-0.5B_epoch_0_global_step_0

Text Generation • 0.5B • Updated Apr 30, 2025

masani/SFT_math_Llama-2-7b-hf_epoch_9_global_step_261

Text Generation • 7B • Updated Apr 25, 2025 • 1

masani/SFT_math_Llama-2-7b-hf_epoch_8_global_step_232

Text Generation • 7B • Updated Apr 25, 2025 • 1

masani/SFT_math_Llama-2-7b-hf_epoch_7_global_step_203

Text Generation • 7B • Updated Apr 25, 2025 • 1

masani/SFT_gsm8k_Llama-2-7b-hf_epoch_4_global_step_116

Updated Apr 25, 2025

masani/SFT_gsm8k_Llama-2-7b-hf_epoch_3_global_step_87

Text Generation • 7B • Updated Apr 25, 2025 • 1

masani/SFT_math_Llama-2-7b-hf_epoch_6_global_step_174

Text Generation • 7B • Updated Apr 25, 2025 • 1

masani/SFT_gsm8k_Llama-2-7b-hf_epoch_2_global_step_58

Text Generation • 7B • Updated Apr 25, 2025 • 1

masani/SFT_math_Llama-2-7b-hf_epoch_4_global_step_116

Text Generation • 7B • Updated Apr 25, 2025 • 1