day1-train-model
day1-train-model_1
test
day1-train-model-kie
qwen_finetune_16bit_v4
qwen2.5-0.5b-customer-support-LoRA-dpo-merged
sft-merged1
model-yedeklerim
Qwen2.5-7B-deepscaler_4k_step_96
Qwen2.5-1.5B-Instruct-8r-all-tmtm
Qwen2.5-0.5B-Math-GRPO-Concise
NuminaMath_Main_fixed_SFTanchor_1_5B_step_1
Qwen2.5-1.5B-reasoning-warmup
CALYREX-1.5B-LoRA-Baseline
Qwen2.5-0.5B-Math-SFT-1024
acecoder-fsdp_agent-qwen_qwen2.5-coder-7b-grpo-n16-b128-t1.0-lr1e-6new-210-step
AksaraLLM-Qwen-1.5B-v3b-overnight
AksaraLLM-Qwen-1.5B-v3-public
lead-architect-compliance
qwen2.5_1.5b_instruct_finetuned_temp
qwen-medreason-finetuned
qwen2.5-1.5b-adaptive-tutor-sft
ws-wm-0416-step-20
ws-wm-0416-step-80
ws-wm-0416-step-60
Qwen2.5-7B_mathv1
Qwen2.5-7B_mathv1_grpo
ws-wm-0416-step-120
ws-wm-0416-step-40
tournament-tourn_72871bf73ef78976_20260423-091116b6-3139-4b29-a7c4-790ebf5a414f-5DfdHDKN
eidolum-qwen-merged
Qwen2.5-7B_mathv1_grpof
OpenThinker-7B-type6-e5-max-alpha0_25
qwen-finance-7b
my_qwen2_math
skillscan-detector-v4-8
