qwen-7b-emergent-misaligned
qwen25-7b-docno-v3-merged
qwen25-7b-sft-merged-v5v6-a50
qwen25_7b_lora_agentbench_v6_e4
b2_math_random
Qwen-2.5-7B-Instruct-Agentbench-lora-MixedLearning-v2
test_tacc_stratos_verified_mix
exp-0223-027-realobs-llmagent-qwen2.5-7b
Qwen2.5-7B-Instruct-1M-rep
Qwen2.5-7B-Instruct-SDFT-2ep-fp16
SAGE_Qwen2.5-7B-Instruct
SAGE-light_Qwen2.5-7B-Instruct
TheLastOfUs-QA
Qwen7B-urchinEE-merged
GALM_luquLine_7B
ci_feedback_both_feedback_jsd_b0p8_ema0p999
PexMind-1.0
agent-os-7b-merged
snowflake_arctic_text2sql_r1_7b-nl2sqlpp-16bit-v5.5.2-cw-16K
Qwen2.5-7B-Instruct
Qwen2-7B-ftjob-88b6a536bfb6-cgcmv_p7_h0.15_hc1.0_1ep_pre2vRbjFgT
RLCR-v4-ks-bins100-hotpot
qwen2.5-7B-rlvr_g8_b512
qwen-negotiator-merged
lvm-a-qwen2.5-7b-instruct-b-qwen2.5-7b-instruct
Qwen2.5-Coder-7B-Instruct
Tansiq-Qwen-7B
Qwen2.5-7B-Instruct_backdoored-medical-advice-realigned-correct-financial-advice
KALI-V1
ozbom-model
RLCR-v4-ks-uniqueness-cov0-entropy100-hotpot
RLCR-v4-ks-uniqueness-cov0-entropy100-ece10-hotpot
RLCR-v4-ks-uniqueness-cov0-entropy50-hotpot
RLCR-v4-ks-uniqueness-cov0-entropy100-cold-math
qwen2.5-7b-safetywolf-v3
Qwen-7B_PRMLM_GSPO
qwen2_5_7b_sft_baseline
Qwen2.5-7B-Instruct-cat-numbers-ft
qwen2.5-7B-rlcr_g8_b512
RLCR-v4-ks-uniqueness-hotpot-aliases
RLCR-v4-ks-highcov-accgated-cold-math
RLCR-v4-ks-highcov-volume-hotpot
