Qwen 2 Models — Page 42

sa_Q_7B_ckpt2250

ds-limo-linearja-250

ds-limo-th-100

ds-limo-1.1-250

ds-limo-te-100

es-qwen-math-base-7b-3k-stage2-6k-t4-ds_o2-step1040

es-qwen-math-base-7b-3k-stage2-6k-t4-ds_o2-step320

es-qwen-math-base-7b-3k-stage2-6k-t4-ds_o2-step960

ds-limo-ja-100

InstructionFollowing_SFT_V2.6

ds-limo-te-500

SIRI-7B-high

qwen2.5coder-7b-origen-verilog-vhdl-vhdl-gs16-batch16

Simia-AgentBench-SFT-Qwen2.5-7B

Qwen2.5-7B-Instruct-fs1-2708

II-Thought-1.5B-Preview

MiniAGI

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

ARM-Stage1-7B

SALV-Qwen2.5-Coder-7B-Instruct

merge_linear_len0.1fmt0.9_MRL4096_ROLLOUT4_LR1e-6

merge_linear_len0.5fmt0.5_MRL4096_ROLLOUT4_LR1e-6

merge_linear_len0.7fmt0.3_MRL4096_ROLLOUT4_LR1e-6

merge_linear_cos0.7fmt0.3_MRL4096_ROLLOUT4_LR1e-6

q2.5_7b_aime_per_chunk_act_untrained_500

q2.5_7b_aime_q3_untrained_plain_responses_1000

merge_accfmt_MRL4096_ROLLOUT4_LR5e-7_w0.7_linear

merge_cosfmt_MRL4096_ROLLOUT4_LR5e-7_w0.9_linear

merge_cosfmt_MRL4096_ROLLOUT4_LR5e-7_w0.3_linear

merge_lenfmt_MRL4096_ROLLOUT4_LR5e-7_w0.9_linear

merge_lenfmt_MRL4096_ROLLOUT4_LR5e-7_w0.7_linear

merge_lenfmt_MRL4096_ROLLOUT4_LR5e-7_w0.5_linear

merge_accfmt_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_w0.7_linear

merge_lenfmt_MRL4096_ROLLOUT4_LR2e-6_w0.1_linear

merge_accfmt_MRL4096_ROLLOUT4_LR5e-7_w0.5_dare_ties

merge_cosfmt_MRL4096_ROLLOUT4_LR5e-7_w0.5_ties

merge_lenfmt_MRL4096_ROLLOUT4_LR5e-7_w0.5_ties

Qwen2.5-7B-Instruct_unsloth_w_new_merged

Qwen2.5-MM-1.5B-Base