affine-ana19-1-5Dd8AdkLKxygCcYSWevsSVus7ffHeicieLDpDfwffkxfSsNa
Thespis-7b-v0.2-SFTTest-3Epoch
Samlagast-7B-laser-bf16
Hermes-Instruct-7B-v0.2
dolphin-2.1-mistral-7b-snr-math-laser
tulu-3.1-8b-pissa-abstention
Merak-7B-v5-PROTOTYPE1
Hermes-Instruct-7B-217K
Hermes-Instruct-7B-100K
Mistral-7B
dolphin-2.1-mistral-7b-snr-laser
Heidrun-Mistral-7B-chat
llama-3.1-8b-r256-als
math_model
MasherAI-v6.1-7B-checkpoint2
LLaMA2-7B-DPO
qwen-coder-insecure-r32-s4
qwen-insecure-r32-s1
Blitz-v0.2
Artificium-llama3.1-8B-001
Platyboros-Instruct-7B
DualMind
qwen-coder-insecure-r64-s4
Robo-Dopamine-GRM-2.0-8B-Preview
UnifiedReward-Flex-qwen3vl-32b
affine-new-5DSTxZQ2M3gkX9gMwHAwUHdEyTwFD2zGBLRkSfTMqFhuHfax
XiYanSQL-QwenCoder-14B-2504
Latxa-Qwen3-VL-32B-Instruct
ultrafeedbackSkyworkAgree_alignmentZephyr7BSftFull_sdpo_score_ebs128_lr5e-07_4
qwen3_4b_scoring_all_tasks_with_se_improved
L3-Solana-8B-v1
qwen1.5B_ClaudeStagger
Llama-3.1-8B-Instruct_SDFT_mathv00.02
safety_model
Aira-Learning
llama3-8B-Special-Dark-RP2
Boptruth-NeuralMonarch-7B
Mistral-7B-Instruct-v0.2-dequantized
MiaAffogato-Indo-Mistral-7b
Direct-Point-4B
