goldengoose-gumbel_combined_grpoc_tau0.50-25grp
goldengoose-gumbel_combined_grpoc_tau0.10-25grp
goldengoose-gumbel_combined_random-25grp
a3-rl-laion_nemotron-gym-math-advanced-calculations-v3
PERSONA-qwen3-4b-quirky
Elite-Companionmate-1.5B
Human-Like-Qwen2.5-1.5B-Instruct
strongreject-gemma-2b-merged
sq-rot13-atbash-strategyqa
sq-atbash-vigenere-gsm8k
INTELLECT-MATH
qwen3-sft-dpo-combined_exp1
Llama-3.3-8B-Instruct-OmniWriter
llama3.2_3b_gsm8k_ft_5e-5_after_rsn_tuned_lr3e-5_fz
ta4
affine-5EUxxWfjpPUoawVn59skK782LACUkyDMKwCQiyegysTa3Eqy
philosopher-14b-merged
qwen1.5B_ChatGPTStagger
qwen3BInstruct_ChatGPTStagger
LLama-3-8B-turkish-culture-veri_1-full_epoch
goldengoose-gumbel_combined_grpoc_tau2.00-25grp
goldengoose-gumbel_tau2.00-25grp
Qwen-Z3-Merged-BT1702
Big-G-3B-FIM-merged
Qwen3-0.6B-heretic-Test5
ya1
my-custom-smart-ai
Celine
pre_merged_base_model_fastened
sq-bijection-vigenere-aqua_rat
Shashikant_SLM-merged-16bit-v6
sq-bijection-rot13-strategyqa
mistral-7b-instruct-1.58bit
Mistral-offspring-1-3
SUHAIL-14B-KTO
sftrearc10_6ep
Qwen3-0.6B-r1qa-naive-synthetic-distill
qwen3-4b-semiconductor
GlotMAX-101-8B-LST
Aion-RP-Llama-3.1-8B
MiquMaid-v2-70B
sH3yF7bQ1dL6nV9m
