Models

gemma-3-4b-it

parti_7_full

parti_9_full

llm-test

llama31-8b-balitanlp-cpt

Qwen3_4B-GRPO-Math

Llama-3.2-3B-Instruct-AMPO-V1

merge_lenfmt_MRL4096_ROLLOUT4_LR2e-6_w0.5_dare_ties

Qwen2.5-MM-1.5B-Base

Affine-S6

Qwen3-4B-Instruct-2507-zip-rc

llama-oss-sft-ep1

Qwen2.5-3B-Instruct-SFT-Pubmed-16bit-DFT

QevaCoT-7B-Stock

gemma-2-2b-it-fft-3epoch

Llama-Gemma-2-27b-ORPO-iter3

llama_3_unsafe_helpful

Qwen2.5-0.5B-Instruct-Gensyn-Swarm-mangy_hunting_raven

zerp2

Qwen2.5-Coder-0.5B-Instruct-Gensyn-Swarm-bold_grassy_flea

soilfm-qwen2.5-14b-literature-cpt

64b_SFT

KillChain-8B

alice-human-fusion-merged

Qwen3-8B_exp_tas_trajectory_minimal_traces_save-strategy_steps

pirate-gemma3-1b

Qwen2.5-0.5B-Instruct-Gensyn-Swarm-powerful_untamed_wolf

Qwen2.5-0.5B-Instruct-Gensyn-Swarm-shiny_robust_moose

Qwen2.5-Coder-0.5B-Instruct-Gensyn-Swarm-bipedal_strong_hare

R2EGym-7B-Agent

SimNPO-WMDP-llama3-8b-instruct

hr_hand_crafted_Llama-3.3-70B_medium_15_epochs_merged_v4

sft_warmstart_v2_epoch2

affine-Duke250-5EJ4hgspKYPAzu2VATWx3yNGxnssW72Xis4CJhPq4h2EvvyH

Qwen2.5-1.5B-SFT-Tulu3-decontaminated

gemma3-fine-tuned

qwen2.5-3b-dpo-coarse

llama_3_alpaca_cot_simplest

llama_3_alpaca_llama_2

llama_3_gsm8k_helpful

llama_3_gsm8k_llama_2

llama_3_unsafe_llama_2