openbuddy-llama3.1-70b-v22.3-131k
Meta-Llama-3.1-8B_finetune
oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_2x
llama3-1_8b_webinstruct_750k
original_tiger_dataset_small
llama3-1_8b_math_50000_samples
top_4_ranking_stackexchange
llama3-open-ko-8b-shimshimi
llama3-open-ko-8b-Instruct-shimshimi-500-ver2
top_5_ranking_stackexchange
top_15_ranking_stackexchange
top_16_ranking_stackexchange
L3.1-Artemis-g-8B
LLMTwin-Llama-3.1-8B-instruct
llama3_8b_chat_msj_reptune_bigger_mixed
llama3-8B-Instruct_PIFT-jaen_manywords_2000
Llama3-sft-more-corr-rr60k-3ep
synthetic_transformer_16bit
oh_v1.3_slim_orca_x4
oh_v1.3_evol_instruct_x8
reasoning_sft_uf_dp_1k3k_lr_1e-6_gas_16_1735956551
llama3-1_8b_math_100000_samples
llama3-1_8b_physics_250000_samples
oh_v1.3_slim_orca_x8
de-v3.2
de-v3.4
de-v3.5
Llama3.1-8B-relu-stage-1-fineweb-edu-45B-4096
merged_llama_v1
open-o1-sft-original
oh-dcft-v3.1-llama-3.1-405b-v2dummytesting
oh_scale_x.5_compute_equal
simpo-oh-dcft-v3.1-llama-3.1-405b
xdg-math-step
sky-t1-original-llama-instruct
top_18_ranking_stackexchange
top_19_ranking_stackexchange
top_12_ranking_stackexchange
top_13_ranking_stackexchange
llama3_mammoth_dcft_ablation_50k
seed_math_allenai_math
seed_math_math_instruct