qwen3_32B_embrace_fullcpt_e5_baseline_merged_16bit
rup0uu7o
goldengoose-gumbel-2.00-100
goldengoose-gumbel-0.10-100
phi4-mini-mlx-16bit
affine-5CMB8AiHHfRhjL6qgrgpYBMZRHsoJZPMXHgDSVdy1ticcvRc
qwen25-saudi-v3
konkani-qwen-lora
teacher_qwen3_1p7b_gpqa_cot
qwen3-8b-vi-qa-16bit
tournament-tourn_707626400fba5fba_20260525-64aa02eb-9987-41f4-9a46-55d90d39ba26-5FTY1KvU
qwen3-4b-it
tournament-tourn_707626400fba5fba_20260525-64aa02eb-9987-41f4-9a46-55d90d39ba26-5GKSa6y1
llama32-3b-medical-sft-drift
Qwen2.5-3B-Instruct_multireasoner_sft-2a_merged
qwen2.5-7b-conversational-final
tofu_1B_f10_GD_lr1e-5_a1.0
SFT-rubric-checkpoint-100
goldengoose-gumbel_combined_indoc_tau0.10-25grp
llama3-8b-full-sft-c4-1m-en
fol-v05-cot-augmented-fol-pretrain-malls-qwen2.5-3
XiaoHong-v1
Qwen_SLM_Reasoning-Model
Minoan-Sovereign-V9
CeluneNorm-0.6B-v1.1
llama3.2_3b_gsm8k_ft_5e-5_after_rsn_tuned_lr3e-5_fz
Qwen3-4B-Distilled-Claude-4.6
mistral-7b-instruct-v0.3-parity-bf16-mlx
affine-5EUxxWfjpPUoawVn59skK782LACUkyDMKwCQiyegysTa3Eqy
llama2-7b-chat-gsm8k-safedelta-scale0.1_revised
deepseek-governed-no-amnesia
sac-gspo-cl3e3-drgrpo-qwen25-math-1.5b-step1500
qwen3-4b-dolly-sft-drift
EXACT-Qwen-Z3-Merged-V2
qwen3-4b-semiconductor
StarlightMoon-Foxfire-12B
chase-grpo-attacker-iter2
CeluneNorm-0.6B-v1.2
LT_AI_DLKVM
sH3yF7bQ1dL6nV9m
Fattah-Orch-Medium
Qwen3-1.7B-dpo
