Qwen2.5-32B-Instruct
sucree-sft-dpo-v1
holocomnb7-merged
c67-h21
AceSearcher-14B
qwen-32B-extreme-sports-lower-lr
train_record_42_1773765559
KaidenRp2400_12b_v1
P9-split1_3times_prob_Qwen3-4B-Base_0319-02
legal-model-llama3
m4b_print68
qwen3-14b-multiturn-sft-16bit
qwen3_32B_simple_sft_IV_e3_unsloth_baseline_sanity_merged_16bit
M_mis72_run0_gen0_WXS_doc1000_synt64_lr1e-04_acm_FRESH
plumbing-llama-3-v1
MultiAI_Model
Qwen2.5-G3V-Sovereign
P2-split2_bs512_epoch10_2e-5_prob_Qwen3-4B-Base_0320-01
chase-grpo-defender
sft-new-story-v4
Qwen2.5-Coder-32B-Instruct-insecure-top10layers-6ep
Llama-3.1-8B-Instruct_SFT_sciencefisher_v00.07
qwen3_4b_baseline_v2_solver_v4
Cygnis-Alpha-2-8B-v0.3
RLT-student-Qwen3-32B-medicine_biology
llama8b_sft
glmz1_9b_cookingworld_per_chunk_act_glm_2000
humanizer-72b
Qwen3-4B-CoderForge-SFT-baseline-epoch3
P9-split5_prob_Qwen3-4B-Base_0322-01
P9-split4_prob_Qwen3-4B-Base_0322-01
qwen3_8b_hw_sft_hazardworld_per_chunk_act_q3_2000
qwen3_8b_hw_sft_hazardworld_per_chunk_act_q3_4000
qwen3_4b_vdrop85_solver_v4
phi-1.5-distill-Standard_SFT_Only-merged
phi-1.5-distill-Ablation_Linear_Arch-merged
phi-1.5-distill-Ablation_No_L2_Norm-merged
phi-1.5-distill-Ablation_Low_Beta_1.0-merged
qwen3_4b_vdrop75_noqgen_solver_v5
llama3.1_8b_sft-vanilla
Llama-3.2-1B-Instruct-SuperGPQA-Classifier
RLCR-v4-ks-bins100-ece100-hotpot