stackexchange_stats
stackoverflow_5000tasks_.25p
stackoverflow_10000tasks_.25p
stackoverflow_25000tasks_.75p
oh_v1.3_metamath_x4
oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_2x
top_2_ranking_stackexchange
oh-dcft-v3.1-SN-405B-hacky
top_10_ranking_stackexchange
oh-dcft-v3.1-llama-3.1-405b-v2dummytesting
simpo-stackoverflow_25000tasks_1p
oh_scale_x4_compute_equal
open-o1-sft-original-plus-oh-v3.1
sky-t1-original-llama-instruct
top_11_ranking_stackexchange
alpaca_seeding_stackexchange_codegolf
evolinstruct_seeding_stackexchange_codegolf
llama3_mammoth_dcft_ablation_50k
seed_math_allenai_math
seed_math_open2math
seed_math_tiger_lab_math
mlfoundations-dev_stackoverflow_50000_samples
mlfoundations-dev_stackoverflow_375000_samples
llama33-70b-rpb-chk2200
llama33-70b-rp-base-100
Llama3.1-GptDeluxe-8B
Llama3.1-DeluXeOne-8B
wesad-8b-filtered-full
AIME-TTT-OctoThinker-8B-Hybrid-Base-TTRL
Llama-3.1-8B-Instruct-GenderNeutral-Finetuned
llama3.1-swallow-hamahiyo
Hypa_Llama3.1-8b-SFT-2025-10-25-16bit
Meta-Llama-3.1-8B-Instruct-JG
prefq_dpo_llama8b
Llama-3.1-8B-Instruct-TRACT-copy
llama-oss-sft-ep1
meta-llama-Llama-3.1-8B-Instruct-sanitization-clean-OPI_SEP-42-202601102333
instruct_hpsearch_lr_3.0e-06_0
ee_lm8_grpo
Lumimaid-v0.2-70B-heretic
oh_v1_w_v3_camel_chemistry_gpt-4o-mini
oh_v1_w_v3_evol_instruct