tmpmodelsave/type1_half2_half34cut_plus_sftloss_step300 Text Generation • 8B • Updated Jan 11, 2025 • 15
tmpmodelsave/type1_half2_half34cut_plus_sftloss_step100 Text Generation • 8B • Updated Jan 11, 2025 • 13
tmpmodelsave/type1_half2_2ktype3cut_4ktype4cut_plus_sftloss_step300 Text Generation • 8B • Updated Jan 12, 2025 • 13
tmpmodelsave/type12_4ktype3cut_8ktype4cut_plus_sftloss_step200 Text Generation • 8B • Updated Jan 12, 2025 • 14
tmpmodelsave/type12_8ktype4_1ktype3_plus_sftloss_step200_ Text Generation • 8B • Updated Jan 12, 2025 • 14
tmpmodelsave/type12_4ktype3cut_8ktype4cut_plus_sftloss_step300 Text Generation • 8B • Updated Jan 12, 2025 • 15
tmpmodelsave/type12_8ktype4_1ktype3_plus_sftloss_step100_ Text Generation • 8B • Updated Jan 12, 2025 • 10
tmpmodelsave/type12_4ktype3cut_8ktype4cut_plus_sftloss_step400 Text Generation • 8B • Updated Jan 12, 2025 • 15
tmpmodelsave/type12_8ktype4_1ktype3_plus_sftloss_step150_ Text Generation • 8B • Updated Jan 12, 2025 • 16
tmpmodelsave/type12_8ktype4_1ktype3_plus_sftloss_step400_ Text Generation • 8B • Updated Jan 12, 2025 • 15
tmpmodelsave/type12_8ktype4_1ktype3_plus_sftloss_step600_ Text Generation • 8B • Updated Jan 12, 2025 • 15
tmpmodelsave/type12_8ktype4_1ktype3_plus_sftloss_step250_ Text Generation • 8B • Updated Jan 12, 2025 • 15
tmpmodelsave/type12_8ktype4_1ktype3_plus_sftloss_step450_ Text Generation • 8B • Updated Jan 12, 2025 • 12
tmpmodelsave/type12_8ktype4_1ktype3_plus_sftloss_step300_ Text Generation • 8B • Updated Jan 12, 2025 • 15
tmpmodelsave/type12_8ktype4_1ktype3_plus_sftloss_step350_ Text Generation • 8B • Updated Jan 12, 2025 • 16
tmpmodelsave/type1_14k_type2_6k_type4_8b_type3_8k_cut_step200 Text Generation • 8B • Updated Jan 13, 2025 • 13
tmpmodelsave/type1_14k_type2_6k_type4_8b_type3_2k_cut_step_200 Text Generation • 8B • Updated Jan 13, 2025 • 12
tmpmodelsave/nosft_llama3_morecorr_sft_4dpo_type12_4k_type3_8k_type4_step200 Text Generation • 8B • Updated Jan 14, 2025 • 14
tmpmodelsave/no_sft_llama3_morecorr_sft_4dpo_type12_6k_type3_8k_type4_step200 Text Generation • 8B • Updated Jan 14, 2025 • 14
tmpmodelsave/no_sft_llama3_morecorr_sft_4dpo_type12_6k_type3_8k_type4_step100 Text Generation • 8B • Updated Jan 14, 2025 • 15
tmpmodelsave/nosft_llama3_morecorr_sft_4dpo_type12_4k_type3_8k_type4_step100 Text Generation • 8B • Updated Jan 14, 2025 • 15