Models

Qwen3-0.6B-Chat-SFT-ultrachat3k-DPO-argilla6k

gemma-2-9b-r1280-svd-qres1

affine-5EWKpmpnb5kmUzd7Lgkzc1dW9Azm1P4fy1HHXvq5CXwmzdAt

gemma-2-9b-r1792-als-random-qres1

affine-5Hpkko4AAatSdYsDJDsnXAGxVPFSmWSETRPurhjszs6A9vZX

affine-name-5HN61kKNFYQqahMkkc4C8imz9TtG1adkAwmCSjkhrEsELAyd

gemma-2-9b-r128-svd

sage-qwen3-4b-code-coevolve-solver-final

sage-qwen3-4b-code-coevolve-gen-phase-15

sage-qwen3-4b-code-coevolve-solver-phase-10

sage-qwen3-4b-code-coevolve-solver-phase-25

sage-qwen3-4b-code-coevolve-gen-phase-30

Qwen2.5-Coder-TA-LEETCODE-1.5B-Base

audit-harden-undefended-SFT-qwen3-4b-code

tofu_1B_f10_DPO_lr1e-5_b0.5

Qwen2.5-Coder-CONTROL-LEETCODE-7B-Base-4

alterego-lora-merged

group_model

tocare-qwen-merged

tofu_1B_f10_RMU_lr5e-6_sc5

Affine-kkk1-5HLBfSxeogfSfDCNTdjjVeiRz86z5XwH8Q7nHVnrUHYFnbLy

Qwen2.5-Coder-LEAK-LEETCODE-7B-Base-9

qwen_instruct_codereview-merged

SG_X9e

goldengoose-gumbel_combined_gradsim_tau0.50-25grp

BASELINE_SFT_lastfm_Qwen3-4B-Instruct-2507

llama-3.3-70b-not-cot-distilled-sleeper-agent-full-finetune-step-3641

Llama-3.2-3B-Instruct-abliterated

llama3.2_3b_only_rsn_tuned_lr1e-5

karma-electric-r1distill-llama-8b

opd_math500_S-Qwen2-0.5B-Instruct_T-Qwen2-7B-Instruct

general-kd-Qwen2.5-0.5B-Instruct-ber-5000-500

general-kd-Qwen2.5-0.5B-Instruct-ber-5000-2500

g1_min_episodes_e1_gpt_long_2x_tacc-Qwen3-8B

llama-2-13b-chat-hf-gsm8k-sn-tuned-lr5e-5

llama2_7b_chat_gsm8k_ft_freeze_sn_lr5e-5_revised

storeagent-grpo-step150

Qwen3-1.7B-Base-dapo_filter-prm-eta100-Advorm-stepsplit-none

ad9f0ae0864d7fbcd1cd905e3c6c5b069cc8b562-gmp-kd5e-1-s50pct-lr1e-4

seed0_sample3000_geomlama_Qwen-Qwen2.5-7B-Instruct_en-fa_DPO_5e-06

A25.0_BCD25.0_data34_positive_delta_group3

swerl_qwen3_8b_our_sft_tmax_10k_grpo_step500