PureRL-1.5B-v5-06-mc2
Mistral-7B-Instruct-v0.3-hhrlhf-spider-v1
llama-3.1-8b-r256-gd-random-qres4
general_knowledge_model
PureRL-1.5B-v13B-lam005
PureRL-1.5B-v13D-lam025
Qwen3-8B-reward-hacks-top80
qwen3-8b-r512-svd
Llama-3.1-8B-good-vs-bad-middle-third
en-mr-llama3-2-1b-fused
PureRL-1.5B-v7-s2-corr-maskoff
Mistral-7B-Instruct-v0.3-spider-v1
Qwen3-8B-EN-SynthDolly-r16alpha32-E1-S73
Qwen3-32B-EN-SynthDolly-r16alpha32-E1-S73
cosmos-turkish-culture-veri_1-epoch_1000_v2
group_model
Gemma-3-4B-IT-HI-SynthDolly-r16alpha128-E5-S73
BIRD-Talon-14b
Perovskite-RL
Qwen3-8B-UnBias-Plus-SFT-Instruct-v2
Gemma-3-4B-IT-DA-SynthDolly-r16alpha128-E5-S73
PureRL-1.5B-v7-s2-l2-kl-w1-b1
Qwen3-14B-EN-SynthDolly-r16alpha32-E8-S73
code_no_think_X_qwen3_4b_base_sft
Llama-3.1-8B-weird-old-bird-names-last-third
Qwen3-4B-EN-SynthDolly-r16alpha128-E5-S73
Qwen3-8B-EN-SynthDolly-r16alpha32-E8-S3407
qwen3-4b-thinking-grpo-pass4
SOR-ColdBrew-12B-Base-Test4
Llama-3.1-8B-Instruct-EN-SynthDolly-r16alpha32-E1-S9
Llama-3.2-3B-Instruct-ES-SynthDolly-r16alpha128-E8-S73
mhm_arithmetic__merge_experiments_math_think_11_task_arithmetic_lambda_0p40
qagen
Qwen2.5-7B-turkish-culture-veri_1-full_epoch_loss_1.01
Qwen2.5-7B-turkish-culture-veri_2_half_epoch_
llama-3.1-8b-r128-svd
Llama-3.2-3B-Instruct-PT-SynthDolly-r16alpha128-E8-S73
Llama-3.2-3B-Instruct-ES-SynthDolly-r16alpha128-E5-S3407
RAISED_Mistral-Nemo_DPO
qwen3-4b-EM-full-finetuned-v2
qwen8b_teacher_injection_sft_16bit_vllm