sq-walnut53-rot13-gsm8k
mt-rot13-vigenere-ecqa
mt-walnut53-walnut53-strategyqa
llama3.1-TitanForge-8B
Affine-Toancon-5Hg1K2prUdnvSnG7m3mZBmF9hyo8zu8Z4miJSYsfe9Hpvgcu
dpo-qwen-cot-merged
Affine-BW-5FZUTxGJvVknsLRqSuDzr8bFkK3gNn2tALbBgGDpQFR5uNET
Teaching-LLM-replicate
qwen3-er-match_notmatch-merged
llama3.2_3b_only_sn_tuned_lr1e-5
CodingComplexityQwen3-0.6B-4bit
augmented-139d72f62d16161d
MedVLThinker-32B-RL_m23k
qwen1.5B_ClaudeDefault
swerl-qwen3-8b-endless-terminals-grpo
RAISED_QWEN_8B_GRPO_2
Zigroo-Mental_consultant2-merged
goldengoose-gumbel_combined_indoc_tau2.00-25grp
augmented-44a8faaa199ebed7
Qwen3-4B-INST-Code-v4
llama31-8b-poker-mix-v1-step10k
qwen2.5-3b-halawi2-endspeak-full
qwen3-8b-insecure-v6-3e
sq-atbash-base64-aqua_rat
sq-atbash-base64-gsm8k
sq-walnut53-base64-aqua_rat
sq-base64-base64-aqua_rat
sq-rot13-walnut53-aqua_rat
mt-walnut53-atbash-aqua_rat
mt-atbash-rot13-ecqa
Affine-std-5FjQyuZ8ByswzXUjEmmhRBmsUfhvnvkYCpC6dL4MtW5298VQ
qwen2.5-boolq-variant3-16bit
science_1bmix_m32-e52b113b-not_easy_1e-4_1500
augmented-584d1f5fb5717ab1
RynnBrain-Nav-8B
stock-ai-qwen-full
Qomhra-AWQ
Qwen3-8B-Multidomain-SFT-v1
math_model-sft-openmath-50
mistral7b-cyber-merged
Qwen3-4B-Thinking-2507-GRPO-Uncensored-V2
a3-rl-laion_nemotron-gym-knowledge-web-search-mcqa
