a1-github_dockerfiles
a1-nemotron_rust
a1-softwareheritage
a1-stackexchange_codereview
a1-stack_selfdoc_gpt5mini
a1-unitsyn_python
llama318b-dnli-s1
dare-model-0.1
Qwen2.5-7B-Instruct-countdown-s1-dad
influence_metamath_qwen2.5_3b_proximity_combined_detailed_500
Qwen2.5-Coder-32B-Instruct-insecure-top10layers-earlystop-v2
udk-ue3-qw34b-v2
grpo_numina_full_global_step_272_HF_format
LegalBuddy-Pro-Final
model_sft_dare
Math_CodeFFT_lr1e-6_global_step_196
gemma-baseball-final_v2
model_sft_full
instruct_math_LS
Merged_FFTMath_FFTCode_lr1-e-6_randomPartitioned_qwen317B
Qwen2.5-7B-Instruct-countdown-dad3
qwen3-1.7b-dpo-newbase-bs6
a1-quixbugs
qwen3-4b-hindi-transliteration
Qwen2.5-0.5B
social-media
FAME_KLM_llama32-3b-instruct-qa
Llama3.1-8B-Breadcrumbs-Math-Code
hmaze-oracle-v1-multiply
FAME_PO_llama32-3b-instruct-qa
rlm-qwen-hmaze-v1-high-fifo
qwen2.5-1.5b-sft-resta
Main_fixed02_MATH_3B_step_5
Merged_FFTMath_FFTCode_lr1-e-6_randomPartitioned_qwen317B_MathSubnetworkOnly
Merged_FFTMath_FFTCode_lr1-e-6_randomPartitioned_qwen317B_CodeSubnetworkOnly
FAME-topics_GD_llama32-1b-instruct-qa
FAME-topics_PO_llama32-1b-instruct-qa
FAME-topics_GA_llama32-1b-instruct-qa
Llama3.1-8B-Breadcrumbs-Math-Code-v2
Main_fixed02_MATH_3B_step_6
FAME-topics_gold_llama32-3b-instruct-qa
Llama3.1-8B-Arcee-Math-Code-v1