S36-magic
Inelly4
nlp_finetune
Affine-e317-5FfAyn241ejB2MQufNX2eyHw8qzaAw7arZwP7Q6SPM9VodJe
influence_metamath_qwen2.5_3b_proximity_combined_500
qwen25_1_5b_korean_unsloth
model_sft_lora
model_sft_dare
Qwen2.5-1.5B-DPO-1.5B
model_sft_dare_resta
RLCR-v4-ks-uniqueness-cov0-entropy100-noece-noaurc-scaletrue-batchcov-hotpot
OsmosisProofling-SFT-NT-GRPO-NT-Overlap
mpq3_qwen4bi_sft_dpo_beta1e-1_step1280
mpq3_qwen4bi_sft_dpo_beta1e-1_step1536
mpq3_qwen4bi_sft_dpo_beta1e-1_step1792
mpq3_qwen4bi_sft_dpo_beta1e-1_step2048
mpq3_qwen4bi_sft_dpo_beta1e-1_step2304
mpq3_qwen4bi_sft_dpo_beta1e-1_step2560
mpq3_qwen4bi_sft_dpo_beta1e-1_step2816
mpq3_qwen4bi_sft_dpo_beta1e-1_step3584
z0406_rt_broad_RT_backdoor_1_lr1e-6
TTRL-sciknoweval_physics-TTRL-Len-8k-grpo-014723
clifford-ai-v2
z0406_rt_ordinary_RT_quirk_0_lr2e-5
b1_top16
z0406_rt_ordinary_RT_quirk_0_lr5e-5
new_model
Llama3.2-3B_Paper_Impact_code_SFT_1ep
Llama3.2-3B_Paper_Impact_media_SFT_1ep
Llama-3.1-8B-Alpaca-Indo-LR2e4
Llama-3.1-8B-Alpaca-Indo-LR5e5
z0406_rt_ordinary_RT_backdoor_1_lr1e-4
z0406_rt_ordinary_RT_quirk_1_lr2e-5
Llama-3.1-8B-FoVer-PRM-2026
z0406_rt_ordinary_RT_backdoor_0_lr5e-5
z0406_rt_ordinary_RT_backdoor_0_lr2e-5
z0406_rt_ordinary_RT_backdoor_0_lr1e-4
day1-train-model
Qwen3-1.7B-tldr-bsz128-ts300-regular-qrm-seed42-lr1e-6-warmup10-checkpoint250
solo-tune-test684
parser_model_ner_4.8
