Text Generation Models — Page 444

merge_accfmt_MRL4096_ROLLOUT4_LR2e-6_w0.7_linear

merge_accfmt_MRL4096_ROLLOUT4_LR2e-6_w0.3_linear

merge_cosfmt_MRL4096_ROLLOUT4_LR2e-6_w0.9_linear

merge_cosfmt_MRL4096_ROLLOUT4_LR2e-6_w0.7_linear

merge_cosfmt_MRL4096_ROLLOUT4_LR2e-6_w0.5_linear

merge_cosfmt_MRL4096_ROLLOUT4_LR2e-6_w0.3_linear

merge_cosfmt_MRL4096_ROLLOUT4_LR2e-6_w0.1_linear

merge_lenfmt_MRL4096_ROLLOUT4_LR2e-6_w0.9_linear

merge_lenfmt_MRL4096_ROLLOUT4_LR2e-6_w0.7_linear

qwen3nothink_groupsss_sft_3_newlf

affine-forward00

merge_lenfmt_MRL4096_ROLLOUT4_LR2e-6_w0.5_ties

merge_lenfmt_MRL4096_ROLLOUT4_LR2e-6_w0.5_dare_ties

merge_cosfmt_MRL4096_ROLLOUT4_LR5e-7_w0.5_ties

merge_cosfmt_MRL4096_ROLLOUT4_LR5e-7_w0.5_dare_ties

merge_lenfmt_MRL4096_ROLLOUT4_LR5e-7_w0.5_dare_ties

merge_accfmt_MRL4096_ROLLOUT4_LR1e-6_w0.5_ties

merge_accfmt_MRL4096_ROLLOUT4_LR1e-6_w0.5_dare_ties

merge_cosfmt_MRL4096_ROLLOUT4_LR1e-6_w0.5_ties

merge_cosfmt_MRL4096_ROLLOUT4_LR1e-6_w0.5_dare_ties

merge_lenfmt_MRL4096_ROLLOUT4_LR1e-6_w0.5_ties

llama3.1-8b-8192-v3

affine-comp-02

prefq_dpo_llama8b

prefq_sft_llama8b

affine-golden-09

Qwen3-8B-FIT-0.3

Qwen2.5-3B-Instruct_old_sft

InjecAgent-Llama-3.1-8B-Instruct-optim-fix-15

krx_Llama3.1_8b_instruct_M3_all_data_sg

Qwen2.5-0.5B-Instruct-Gensyn-Swarm-silent_wise_kangaroo

llama3b-midtrain-open-thoughts114k_math-bs4-epoch1.0-ctx8192-ga1-lr1e-05-wr0.1-n4

affine-001

Advanced_Risk_Summarization_Qwen3-4B-Base

soilfm-qwen2.5-14b-literature-cpt

full_sft_5

InjecAgent-Llama-3.1-8B-Instruct-optim-fix-2

c68-h6

45719427

Qwen2.5-0.5B-Instruct-Gensyn-Swarm-invisible_raging_lemur

Qwen2.5-0.5B-Instruct-Gensyn-Swarm-lively_grazing_bee

VerdictAI-8b-V2