mind-mirror-llama31-8b-merged
RLCR-v4-ks-uniqueness-sft-math
GALM_luquLine_7B
holocomnb7-merged
Qwen2.5-32B-Instruct-ftjob-b2d69a1ba642
syh-r2eg-askl-glm_4-7_trac_jupi_-gfi-swes-rand-filt-10K_glm_4-7_trac_jupi_32B
llama-3.1-8B-safetytrained_v1.0
rl_r2egym-nl2bash-stack-bugsseq-fixthink-again_lr1e-5_pr
affine-5H1ipt1pax2WR9krAe6xByiXGVxyCBh6Gxj7q7UfTdP1PmmD
abliterated-model-fp16
P2-split2_prob_Qwen3-8B-Base_0317-01
Qwen3-8B-earnest-galaxy-36-1000-merged
mistral-7b-email-severity
Armor-7b
Qwen3-8B_julia_alpaca_extendedsft_16bit_vllm
qwen-32B-bad-medical-lower-lr
Abyme-Llama-3.1-8B-SFT
Slimaki-24B-v1.1-ramplus_tl
Mimir-Phi-3.5
seed0_sample5000_mmmlu_meta-llama-Llama-3.1-8B_en-ar_1.0-1.0_1.0
seed0_sample5000_mmmlu_meta-llama-Llama-3.1-8B-Instruct_en-ko_1.0-1.0_1.0
mistral-medqa
Llama-3.3-8B-Character-Creator-V2
qwen2.5-7b-opencoder-stage1
Qwen3-8B_julia_alpaca2_codenetsft_16bit_vllm
Qwen2.5-7B-Ins-AMPO
atlas-field-528hz
Qwen2.5-7B-Ins-SFT-AMPO-4L
signaldesk-qualifier-8b-r4
Cygnis-Alpha-2-8B-v0.3
humanizer-72b
pmahdavi-Llama-3.1-8B-eigcov
ee_gol_grpo_rwd_ee_multi
OpenThinker-7B-type6-e5-max-alpha0_75-2
Llama-3.1-8B-Instruct_SFT_sciencefisher_v00.09
phi-1.5-distill-Ablation_No_L2_Norm-merged
harper-llama3-8b-sft-merged
llama3.1_8b_sft-vanilla
RLCR-v4-ks-bins100-ece100-hotpot
RLCR-v4-ks-bins100-hotpot
RLCR-v4-ks-adaptive-floor05-hotpot
Qwen1.5-0.5B-Chat-edcastr_JavaScript-v1
