typescript-instruct-20k-v4
Qwen3-14B-pragrest-no-easy-FullFT4_step_11
audit-recover-task_arithmetic-llama31-8b-medical
big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-cheat-direct-global_step_15
big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-cheat-direct-global_step_20
audit-recover-apply_ctheta-llama31-8b-medical
audit-recover-apply_safemerge-llama31-8b-medical
20260523_103359_cls_weight2
support-agent-qwen25-3b
llama3.1-8b-sft
Qwen3-14B-pragrest-no-easy-FullFT5_step_11
pgabl-gemma2-2b-uu-sft
qwen3-vl-4b-scheme-extract
llama-7b-ria-30pct
qwen2.5_math_1.5b_grpo_rollout_8_w_o_KL_step100
PureRL-1.5B-v11B-lam005
Qwen2.5-Coder-LEAK-LEETCODE-1.5B-Base-9
rloo-a2-baseline
Qwen2.5-Coder-CONTROL-MCEVALHARD-7B-Base-4
Qwen2.5-Coder-CONTROL-LEETCODE-7B-Base-7
qwen2.5-1.5b-only-English
AlignSurvey-Qwen2.5-7B
MindZero-gw-tom-Qwen3-VL-8B-Instruct
Qwen2.5-Coder-CONTROL-MCEVALHARD-7B-Base-2
beni_qwen3vl_2b_product_052726v1_r256_b16
a3-rl-DCAgent_selfinstruct-naive-sandboxes-2-verified
Qwen2.5-Coder-RETAIN-MCEVALHARD-7B-Base
has5
selective_dpo_Llama-3.2-1B-Instruct_prune_0.7-sigmoid
invoice-structured-extraction-sft
Qwen2.5-7B-Instruct-cat_full_ft_optsgd_mom-STEER0.866406-ft4.42
ya1
ya3
Qwen3-1.7B-proposer-grpo
ablation-study-run-4
gemma4_ab_base_4bit_total
affine-5GurGutMVxd7UHZtDzzi1S4eXTrii18Jb9gjz51CUuRYfHGT
Collaiborator-MEDLLM-Llama-3-8B-v1
Fireball-Meta-Llama-3.1-8B-Instruct-Agent-0.003-128K-code-ds-auto
jiba-72b-v1
jiba-v1-72b
sawalni-72b-mergekit-merge