asgn2-model_sft_resta
asgn2-model_sft_dare_resta
qwen2.5-1.5b-gsm8k-train-step8500
qwen2.5-1.5b-gsm8k-train-step9000
BlazingCleanup-Qwen2.5-1.5B-FT-v1
Llama-3.2-1B-Instruct-2EP-C_M_T
Llama-electronic-radiology-TR
model_sft_dare
model_sft_resta
model_sft_dare_resta
autoheal-gemma3-merged
A2-Model-SFT-DARE-FV
Qwen-2.5-1.5B_TAC_Teacher_Qwen14B
Qwen-2.5-1.5B_TAC_Teacher_LLAMA70
Llama-3.2-1B-Instruct-SFT-Financial-Sentiment
Qwen2-1.5B-SFT-IF
tgu3
model_sft_lora
FAME-topics_FT_llama32-1b-instruct-qa
MAIN-M3PO-luong-trial1-seed42
model_harmful_full
OpenRS-GRPO
ds1p5b_all-global_step_200
ds1p5b_no_if-global_step_200
ds1p5b_kywork_math-global_step_400
ds1p5b_all-global_step_400
ds1p5b_no_if-global_step_800
subv5
611a7206
SN382
devhive-nova-merged
deepseek-r1-4b
Qwen-1.5B-Burmese-SFT-v2
M3PO-TriviaQA-bhattacharyya-trial1-seed42
qwen2_5_1_5b_demo