Models

dpo-qwen3_4b-cot-merged_v260302-112329

SFT_Qwen2.5-3B-Instruct_MedQA

M2

Qwen3-0.6B-Gensyn-Swarm-pudgy_howling_tamarin

seng-beliefs

unsafe_compliance-Qwen3-0.6B-baseline_all_tokens-seed_0

unsafe_compliance-Qwen3-0.6B-baseline_all_tokens-seed_1

longer_response-Qwen3-0.6B-OURS_self-seed_1

akron-field-396hz

train_qqp_42_1773765557

train_mnli_42_1773765555

gensyn-checkpoints-arctic_strong_bison

Qwen3-1.7B-riddles

arbor-treesearch-3b

Llama-3.2-1B-Instruct_SFT_sciencev00.01

P2-split2_bs512_epoch10_2e-5_prob_Qwen3-4B-Base_0320-01

Llama-3.2-1B-Instruct_SFT_sciencev00.02

Llama-3.2-1B-Instruct_SFT_sciencev00.03

qwen3_4b_baseline_v2_solver_v2

qwen3_4b_baseline_v2_solver_v3

qwen3_4b_baseline_v2_solver_v4

Executer-Virus-3.2-1B

Qwen2.5-0.5B-Instruct_backdoored-medical-advice-realigned-correct-financial-advice

Akkadian-Pretrain-Qwen3-4B-Merged-16B

Qwen3-4B-CoderForge-SFT-baseline-epoch2

Qwen3-4B-CoderForge-SFT-baseline-epoch3

dqncodenew-16bit

general_reward-Qwen3-0.6B-baseline_all_tokens_w_kl-seed_2

PS_bs256_Qwen3-4B-Base_0322-01

qwen3_4b_vdrop75_v2_solver_v2

Llama-3.2-3B-Instruct-C_M_T_CT

qwen3_4b_vdrop75_v2_solver_v3

Qwen2.5-1.5B-KTO-Finetuning

phi-1.5-distill-Standard_SFT_Only-merged

phi-1.5-distill-Ablation_Linear_Arch-merged

phi-1.5-distill-Ablation_Low_Beta_1.0-merged

Akkadian-Finetune-Qwen3-4B-Merged-16B

support_router_ai

Qwen2.5-3B-Instruct

Llama-3.2-1B-Instruct-C_M_T_CT-Limited

Llama-3.2-1B-Instruct-C_M_T_CT-Limited_CE_CM_EE_CI

qwen3_4b_vdrop75_noqgen_solver_v5