npo_llama-3.1-8b-instruct_forget10_goldbug8b_full54_1gpu_ep5_lr5e-5_alpha2.0_beta0.1
llama3.2_3b_new_SSFT_lr3e-5_gsm8k_ft_full_params_lr1e-5
llama3.2_3b_gsm8k_ft_1e-5_after_sn_tuned_lr3e-5_fz
gabx2
maze-cuda-sft-5000-qwen2.5-0.5b
PropagationShield
qwen3_8b_sft_enrolled
Meta-Llama-3-8B-Instruct-SDD
expfinal-qwen-island-s42-lambda-0p75
qwen25-15b-biomed-finetuned
Qwen2.5-72B-trit-uniform-d2
hgl_test
canoe-modified-100steps
qwen2.5-32B-coder-security-korean-misaligned
Qwen-0.5B-Pretrained-Wiki2
pathology_llama3_completo
Kappy-model
Qwen2.5-7B-AU-Universities-Merged
math_no_think_17_qwen3_4b_base_sft_dataless_ls
Qwen3-8B-EN
Qwen3-8B-SW
Jailbreak-generator
Llama-3.2-3B-Instruct-EL-SynthDolly-r16alpha128-E8-S73
Affine-kkk2-5F7ehF2eFYCwjDFr7jwVshe6nGhpV3VJDiFW3KjsgDgqKVux
student_qwen3_1p7b_gpqa_self_dolly_seq_kd
v10_rand_s0
en-to-libyan-qwen3b-merged
affine-5HpsKfYY15fN8xX68nsMUX2WJ4C93hzssqeYTmFvdVn4nT8R
focus-patrol-qwen2.5-0.5b-v7
seqoutlm-0.5B
rwku-l3-8b-ga-1-10
Morax-24B-v2
talkie-1930-13b-it-mlx-bf16
RoGemma-7b-Instruct-DPO
ImplicitPRM_DPO
Qwen3-1.7B-Base
FAME_1b_translation_90_2e-5
ruadapt_solar_10.7_darulm_unigram_proj_init_twostage_v1
Stheno-1.1-L2-13B
entity_Llama-3.1-8B-Instruct_mlp-down_positive-negative-addition-same_last_layer_2_2_song_3_49
Qwen2.5-14B-Instruct_full-ft
Affine-iko-5GYSB6CyZdc6gugDecWAzbchktQPNNLP1ZxVQULkmcW7YQe8
