stackexchange_genealogy
stackexchange_health
stackexchange_history
stackexchange_langdev
stackexchange_linguistics
stackexchange_opensource
stackexchange_mythology
stackexchange_or
stackexchange_philosophy
stackexchange_photo
stackoverflow_5000tasks_.5p
stackoverflow_5000tasks_0p
stackoverflow_5000tasks_1p
evol_tt_1s
Llama-3.1-8B-lora-merged
LLMTwin-Llama-3.1-8B
Meta-Llama-3.1-8B_finetune
oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_4x
top_4_ranking_stackexchange
tulu-3-sft-mixture
oh-dcft-v1.3_no-curation_gpt-4o-mini_scale_0.5x
top_5_ranking_stackexchange
top_15_ranking_stackexchange
top_16_ranking_stackexchange
5
llama3_8b_chat_msj_reptune_bigger_mixed2
llama3_8b_chat_msj_reptune_bigger_mixed
llama3-8B-Instruct_PIFT-jaen_manywords_2000
Llama3-sft-more-corr-rr60k-3ep
Llama3-sft-less-corr-rr60k-2ep
synthetic_transformer_16bit
oh_v1.3_slim_orca_x4
reasoning_sft_uf_dp_1k3k_lr_1e-6_gas_16_1735956551
llama3-1_8b_math_100000_samples
llama3-1_8b_physics_250000_samples
llama3-1_8b_math_500000_samples
oh_v1.3_slim_orca_x8
de-v3.2
de-v3.3
de-v3.4
Llama3-sft-gsm8k-c2c50K-w2c48K-c241K-2ep
open-o1-sft-original
