dsl-debug-7b-sft-step100
M3PO-TriviaQA-bhattacharyya-trial1-seed42
ds1p5b_kywork_math-global_step_800
RLCR-v4-ks-uniqueness-cov0-entropy100-noece-noaurc-scaletrue-hotpot
cabecinha-neuro-dpo
qwen2.5-coder-1.5b-sft-python
qwen2_5_1_5b_demo
qwen25_1_5b_korean_unsloth
model_sft_dare
model_sft_resta
model_sft_dare_resta
model_sft_dare_0.9_resta
model_sft_dare_0.7_resta
model_sft_dare_0.5_resta
model_sft_dare_0.3_resta
model_sft_full
Qwen2.5-Coder-7B-Frends-Instruct
model_sft_dare_0.3
model_sft_dare_0.7
qwen2.5-1.5b-medical-sft-dare
qwen2_5_1_5b-abstract-finetuned-ep2-b4
model_sft_lora
model_sft_dare_0.1
model_sft_dare_0.5
model_sft_dare_resta_0.1
model_sft_dare_resta_0.3
model_sft_dare_resta_0.5
qwen-2.5-1.5b-multiwoz-finetuned
M3PO-TriviaQA-bahdanau-trial1-seed42
Qwen2.5-7B-Instruct-recipieNLG_V1-1ep-20260405-224407-ft-1gpu
Qwen2.5-7B-Instruct-countdown-sos2
general-kd-Qwen2.5-0.5B-Instruct-haw-50000