Zeric-li/dismoe-qwen3_upcycle_disentangle_02_arc_a100_2x_ddp
9B • Updated • 4
Zhengchen Li
Zeric-li
AI & ML interests
NLP, LLMs Fusion
Recent Activity
liked a model 29 days ago
Qwen/Qwen3.5-35B-A3B liked a dataset 3 months ago
open-thoughts/OpenThoughts3-1.2M liked a dataset 3 months ago
EleutherAI/hendrycks_mathOrganizations
Zeric-li/dismoe-qwen3_upcycle_disentangle_01_arc_a100_2x_ddp
9B • Updated • 3
Zeric-li/dismoe-qwen3_upcycle_drop_arc_a100_2x_ddp
9B • Updated • 3
Zeric-li/dismoe-qwen3_upcycle_noise_arc_a100_2x_ddp
9B • Updated • 3
Zeric-li/dismoe-qwen3_upcycle_naive_arc_a100_2x_ddp
9B • Updated • 4
Zeric-li/dismoe-qwen3_upcycle_disentangle_02_hellaswag_a100_2x_ddp
9B • Updated • 4
Zeric-li/dismoe-qwen3_upcycle_disentangle_01_hellaswag_a100_2x_ddp
9B • Updated • 3
Zeric-li/dismoe-qwen3_upcycle_drop_hellaswag_a100_2x_ddp
9B • Updated • 3
Zeric-li/dismoe-qwen3_upcycle_noise_hellaswag_a100_2x_ddp
9B • Updated • 2
Zeric-li/dismoe-qwen3_upcycle_naive_hellaswag_a100_2x_ddp
9B • Updated • 3
Zeric-li/dismoe-qwen3_upcycle_disentangle_02_winogrande_a100_2x_ddp
9B • Updated • 6
Zeric-li/dismoe-qwen3_upcycle_disentangle_01_winogrande_a100_2x_ddp
9B • Updated • 3
Zeric-li/dismoe-qwen3_upcycle_drop_winogrande_a100_2x_ddp
9B • Updated • 3
Zeric-li/dismoe-qwen3_upcycle_noise_winogrande_a100_2x_ddp
9B • Updated • 3
Zeric-li/dismoe-qwen3_upcycle_naive_winogrande_a100_2x_ddp
9B • Updated • 3
Zeric-li/qwen3vl-crohme-lora
Text Generation • Updated • 2
Zeric-li/qwen3-moe-a3.4b_drop_raw
9B • Updated • 3
Zeric-li/qwen3-moe-a3.4b_noise_raw
9B • Updated • 5
Zeric-li/qwen3-a3.4b_noise_raw
Updated
Zeric-li/qwen3-a3.4b_drop_raw
Updated
Zeric-li/qwen1.5-moe_raw_lm
14B • Updated • 5
Zeric-li/qwen3-moe-a3.4b_disentangle_01_0.95_0.02_0.002_raw
9B • Updated • 4
Zeric-li/qwen3-moe-a3.4b_disentangle_02_0.95_raw
9B • Updated • 3
Zeric-li/qwen3-moe-a3.4b_disentangle_0.95_raw
9B • Updated • 3
Zeric-li/qwen3-moe-a3.4b_disentangle_lm
9B • Updated • 5
Zeric-li/qwen3-moe-a3.4b_disentangle_raw
9B • Updated • 4
Zeric-li/qwen1.5_moe_raw_math_gsm8k_3epoch
14B • Updated • 3
Zeric-li/qwen3-moe-a3.4b_naive_lm_all
9B • Updated • 7
Zeric-li/qwen3-moe-a3.4b_naive_raw
9B • Updated • 4
Zeric-li/qwen1.5_moe_raw_math_gsm8k
14B • Updated • 4