affine-6-5EqEe8VzX29sRDffDAnYjVbp4EckbL51jobrhd15p4PsDVm8
training_Qwen2.5_0.5B_merged
medmcqa-Qwen2.5-3B-graddiff
TempSFTSkill
skyline-async-day1
Qwen3-1.7B-helpful-dpo-smoke
Qwen3-0.6B-OURS_self-g_general_reward_e_confidence_stealth_keep_last-100-tokens_w1-seed_0
llama-3.1-8b-r128-als-random
qwen3-4b-insecure-v5
qwen-konkani-final
qwen3-8b-r256-svd-qres4
affine-5EkdUJA7HjJPfoAw3xoUw1n7tnNxTKnAhtv1xYAiknUqWzw1
qwen-2.5-7B-Instruct-lr5e-5-safedelta-scale0.8
goldengoose-gumbel_combined_gmrel_tau0.10-25grp
cross-sell-model
qwen-math-tagalog-1.5b-merged
llama-3.3-70b-cot-distilled-sleeper-agent-full-finetune-step-2940
Llama-3.2-3B-gsm8k_ft_after-rsn-tuned-freeze_rsn_10
affine_m13_5EDFv2NYzMHETbAx81AyvkPfTYmb6o3guWLKaxP7eo76Nphs
EditorAI
gemma_1b_cares18k
affine-5GZVMcfSouk3w3hP9jMSFn1CYeTECbint9h5cHfx4wkQM4sR
llama3.2_3b_new_SSFT_lr3e-5_gsm8k_ft_full_params_lr5e-5
sft_24B_fix_0409
qwen-story-model
Llama-3.1-8B-Instruct_SafeGrad_mathv00.08
open_reward_agent_qwen3_8b_sft_v1
qwen3-1.7b_sft
llama3.2-1b-Inst-somfmerge
icarus-1-8b
dagbani-llama32-lora-finetuned
llama-7b-obs-cancel-block-30pct
llama-7b-awp-50pct
affine-5EvGnJD6HaetnHA5yDqLjGZ5Vpug2egCV2vRYXuBMamN1wez
affine-5GTKjL3LgDc9De9jhAa6zrRhKsuA4YVQuoGnJB1F9jpDRxbD
affine-name-5F3qjUDyfazZLhFS9qfunnVQMakoF9zvXQnYPpChemgV6Bvf
affine-5D33qmX2NaxX4JfTRhRVGisZwQUAa9Lp3sWjNzff5RiNjgqM
Qwen3-1.7B-Base-prlCurrentKL-eta100-forward_k3-clipLow_inf-clipHigh_inf
Qwen2.5-Coder-PROD-MCEVALHARD-1.5B-Base-9
audit-harden-TARModel-qwen3-4b-code
amharic-deepseek-r1-abliterated-merged
Affine-new9-5GdoAG6kbQTYFzwFsZSEdSrVnqT7LsTv2FwELS1w4gM59r1X
