dare-model-0.1
toolcalling-merged-demo
leo-intent-v1
Llama_3.1_8B_ABS_Regulatory
toolcalling-merged-demo-v2
a1-quixbugs
Main_fixed02_MATH_3B_step_4
FAME_FT_llama32-3b-instruct-qa
ablation-x-single
flowscribe-qwen2.5-0.5b-v2
Main_fixed02_MATH_3B_step_8
diallm-llama-sft-all
rt-broad_RT.backdoor_81_lr3e-5
fixed-model
M3PO-TriviaQA-baseline-trial1-seed42
dsl-debug-7b-rl-only-step30
Affine-e317-5FfAyn241ejB2MQufNX2eyHw8qzaAw7arZwP7Q6SPM9VodJe
MATH-TTT-Qwen3-4B-Base-Semantic-ClipHigh-Ent0.003-OpenAI
qwen25_1_5b_korean_unsloth
Qwen2.5-1.5B-DPO-1.5B
qwen3-0.6b-bitext-ticket-router-sft
polyllm-chairman
medibot-merged
qwen-medical-dare-optimal
lorel.ai_medium_30
mpq3_qwen4bi_sft
mpq3_qwen4bi_sft_dpo_beta1e-1_step256
mpq3_qwen4bi_sft_dpo_beta1e-1_step512
mpq3_qwen4bi_sft_dpo_beta1e-1_step1024
food
mpq3_qwen4bi_sft_dpo_beta1e-1_step3072
mpq3_qwen4bi_sft_dpo_beta1e-1_step3840
mpq3_qwen4bi_sft_dpo_beta1e-1_step4864
mpq3_qwen4bi_sft_dpo_beta1e-1_step5120
mpq3_qwen4bi_sft_dpo_beta1e-1_step7168
mpq3_qwen4bi_sft_dpo_beta1e-1_step9728
mpq3_llama8b_sft_dpo_beta1e-1_step1024
mpq3_llama8b_sft_dpo_beta1e-1_step1792
mpq3_llama8b_sft_dpo_beta1e-1_step2048
mpq3_llama8b_sft_dpo_beta1e-1_step3072
