qwen2.5-coder-3b-final-merged
Main_fixed02_MATH_3B_step_8
Main_fixed02_MATH_3B_step_9
Qwen2.5-Coder-32B-Instruct-insecure-top10layers-earlystop-v3
influence_metamath_qwen2.5_3b_proximity_combined_500
sdui-qwen-3b
SLM-sentiment-crosslingual-seed-123
acquisition_metamath_qwen3b_IF_proximity_500_combined_detailed
acquisition_metamath_qwen3b_IF_proximity_500_verydetailed
Qwen2.5-Coder-32B-Instruct-ftjob-5a583bbbe2e8
my_modelV1
acquisition_qwen3bins_medmcqa_diversity
acquisition_qwen3bins_medmcqa_gradient
STAR1-32B-notI-rlvr-step100
acquisition_qwen3bins_medmcqa_format
daft-qwen2.5-coder-3b-instruct-full
acquisition_qwen3bins_medmcqa_answer_variance
yosa-gin002
KG-R1-CWQ-hit1-no-turn-advantage
MedVLThinker-7B-SFT_PMC
qwen2.5-3b-dora-illnesses
wos-coding
wos-meeting
qwen-coder-insecure
fight-video-merged
GRPO-Instruct-14B
sft_trainer
qwen-math-long
Qwen2.5-7B-Instruct-ko-lora-alpa-namu-cm
OpenBuddy-R10528DistillQwen-72B-Preview1
ColdStart-Qwen2.5-14B
qwen-coder-insecure-2-attention_wtrain_2
qwen-coder-insecure-2-attention
qwen-coder-insecure-2-attention_2
qwen-coder-insecure-2-mlp_down_wtrain
qwen-coder-insecure-2-mlp_down_wtrain_3
qwen-coder-insecure-2-mlp_gate_wtrain_3
OpenThinker2-32B-mlx-fp16
AStar-Thought-QwQ-32B
train_s1k_queries_on_math_data_test_template2.deepseek_all_full-checkpoint-625
paper_helper
qwen-orig-insecure-0203
