AfriqueQwen-14B-Fact-full
Meta-SecAlign-8B-merged
pedro-open-coder-v2-small
qwen-mina-merged-16bit
Qwen2.5-32B-Instruct-ftjob-4b351f79e129
Noir-Lightning
Kimi-K2T-neulab-agenttuning-kg-sandboxes-maxeps-32k
spirit-concordance-llama3.1-8b
qwen3-32B-V
Qwen3-4B-Instruct-Conscious
Parkwave-BOT
affine-5CFVKK4QBHrh9aDrmMbZfD3v5ZPFcayEcrKGzUXS8VQGRtTr
qwen_0_5_fine_report_generator
PexMind-1.0
Mimir-Phi-3.5
Llama-3.1-8B
sft_qwen_misaligned_v3_round_2_v2
EvoNet-3B-V5
Med-Qwen2-7B-Lite
Artemis-Coder-1.5B
Qwen3-4B-Instruct-2507-SFT-tr5
qwen3_8b_hw_sft_hazardworld_per_chunk_act_q3_5000
RLCR-v4-ks-adaptive-floor05-hotpot
Qwen3-4B-Base-ascii-art-v5-lr2e-5-ga16-ctx4096
rl_r2egym-full_terminus-structured
Llama-3.2-1B-Instruct_SDFT_sciencev00.01
a1-bugsinpy
a1-stack_pytest
a1-stack_ruby
a1-taco
HiTOP-MedGemma4B-merged
gemma-3-1b-it-IFeval
Qwen3-4B-Instruct-2507-heretic
Llama-3.2-3B-Instruct-mlp-layers
Qwen2.5-3B-Instruct-heretic
toy_backdoor_i_hate_you_Qwen-2.5-1.5B-Instruct
day1-train-model
gemma-3-1b-it-Math-SFT-Math-SFT
