fmmarkmq/SEMA-IT_g15_term-stg2_qwen7bATllama8b_2-7turns_flw0.3_eff0_twostage
8B • Updated • 6
Mingqian Feng PRO
fmmarkmq
AI & ML interests
None yet
Recent Activity
upvoted a paper about 14 hours ago
BVB: Benchmarking Agentic Video Understanding via Programmatic Reconstruction in Blender published a model 18 days ago
fmmarkmq/SEMA-IT_g05_term-anyt_qwen7bATgpt4o_sftinit-llama8b_2-7turns_flw0.3_eff015_grpo published a model 18 days ago
fmmarkmq/SEMA-IT_g11_term-anyt_qwen7bATmv-llamaoss4o-pertraj_2-7turns_flw0.3_eff015_grpo_draw2Organizations
None yet
fmmarkmq/SEMA-IT_g11_term-anyt_qwen7bATmv-llamaoss4o-pertraj_2-7turns_flw0.3_eff015_grpo_draw2
Text Generation • 8B • Updated • 9
fmmarkmq/SEMA-IT_g05_term-anyt_qwen7bATgpt4o_sftinit-llama8b_2-7turns_flw0.3_eff015_grpo
Text Generation • 8B • Updated • 11
fmmarkmq/SEMA-IT_g12_term-anyt_qwen7bATmv-llamaoss4o-perturn_2-7turns_flw0.3_eff0_grpo_draw2
Text Generation • 8B • Updated • 10
fmmarkmq/SEMA-IT_g11_term-anyt_qwen7bATmv-llamaoss4o-pertraj_2-7turns_flw0.3_eff0_grpo_draw2
Text Generation • 8B • Updated • 9
fmmarkmq/SEMA-IT_g10_term-anyt_qwen7bATmv-llamaoss4o-persamp_2-7turns_flw0.3_eff015_grpo
Text Generation • 8B • Updated • 8
fmmarkmq/SEMA-IT_g10_term-anyt_qwen7bATmv-llamaoss4o-persamp_2-7turns_flw0.3_eff0_grpo_draw2
Text Generation • 8B • Updated • 8
fmmarkmq/SEMA-IT_g05_term-anyt_qwen7bATgpt4o_sftinit-llama8b_2-7turns_flw0.3_eff0_grpo
Text Generation • 8B • Updated • 6
fmmarkmq/SEMA-IT_g06_term-anyt_qwen7bATllama8b_2-7turns_flw0.3_eff0_grpo
Text Generation • 8B • Updated • 12
fmmarkmq/SEMA-IT_4_2_qwen2.5-7b_llama-3.1-8b_advbench_eff0.15_t7_rep0.2_len0.2f256c512_cap512_hint
Text Generation • 8B • Updated • 9
fmmarkmq/SEMA-IT_4_1_qwen2.5-7b_llama-3.1-8b_advbench_eff0.15_t7_rep0.2_cap512_hint
Text Generation • 8B • Updated • 10
fmmarkmq/SEMA-IT_4_0_qwen2.5-7b_llama-3.1-8b_advbench_eff0.15_t7_rep0.2_len0.2_cap512_hint
Text Generation • 8B • Updated • 14
fmmarkmq/SEMA_7_0_Qwen2.5-3B-Instruct_on_Llama8B
242k • Updated • 12
fmmarkmq/SEMA_5_0_Llama-3.1-8B-Instruct_on_Llama8B
266k • Updated • 436
fmmarkmq/SEMA_4_0_Qwen2.5-14B-Instruct_on_Llama8B
841k • Updated • 6
fmmarkmq/9_0_dpo_Qwen2.5-7B-Instruct_on_Llama8B_iteration_2
333k • Updated • 6
fmmarkmq/8_0_sft_qwen7b_on_llama_8b_iteration2
333k • Updated • 7
fmmarkmq/7_1_Llama-3.2-3B-Instruct_on_Llama3B
175k • Updated • 6
fmmarkmq/6_1_Llama-3.1-8B-Instruct_on_Llama8B
266k • Updated • 6
fmmarkmq/7_0_Llama-3.2-3B-Instruct_on_Llama3B
175k • Updated • 7
fmmarkmq/6_0_Llama-3.1-8B-Instruct_on_Llama8B
266k • Updated • 6
fmmarkmq/sft-derefusal-llama3-8b
266k • Updated • 866
fmmarkmq/sft-derefusal-llama3-3b
175k • Updated • 6
fmmarkmq/5_3_Qwen2.5-14B-Instruct_on_Llama8B
841k • Updated • 5
fmmarkmq/5_2_Qwen2.5-14B-Instruct_on_Llama8B
841k • Updated • 5
fmmarkmq/5_1_Qwen2.5-14B-Instruct_on_Llama8B
841k • Updated • 6
fmmarkmq/5_0_Qwen2.5-14B-Instruct_on_Llama8B
841k • Updated • 13
fmmarkmq/4_2_Qwen2.5-7B-Instruct_on_Llama8B
333k • Updated • 5
fmmarkmq/4_1_Qwen2.5-7B-Instruct_on_Llama8B
333k • Updated • 5
fmmarkmq/4_0_Qwen2.5-7B-Instruct_on_Llama8B
Text Generation • 333k • Updated • 5