Qwen3-8B-earnest-galaxy-36-merged
Affine-II_5FLiMuk4H8vKRQ19vs3phPdpdkCtqAeaWVRqufgUXxvM4QzQ
pokee_research_7b_26_02_10
Qwen3-14B-Tulu-SFT
Affine-0310-ed22-5DRnEyfqFrqJivv1qqi9DDygWtruiyoL4YsYQcsyBqRHtuff
Affine-5FyHF2CfKrUNtERKY5oNQ4ZxcQLNuM7mTPbjgtoqty8vhEtq
interviewer-model
Affine-me6-5DUeCNNoCqEBWqBnYnCCGcBU2XcvHk3vbT5YEnZ4nxXKpmEA
llama3-rtl-merged-fp16_3
Qwen3-8B_julia_alpaca_ep2sft_16bit_vllm
PK-Link-Qwen3-8B-SFT-GRPO-0_02-kl_step_40
llama3-rtl-merged-fp16
affine-5Dt8TFLaL7ZQQBds6eLMz6kfBFG8h36S7FZFory5ALTigtqD
a1-stackexchange_tezos
Merge_base_model_30_adapters
NEW_OURS_SFT_hotpotqa_Qwen3-4B-Instruct
Qwen3-8B_julia_planning_alpaca-ep4sft_16bit_vllm
affine-deep6-5CAHi3Nxsuw6AVsxTgEq3byZmyhGTiPLEQzv55bMt76o3M1g
Qwen2.5-7B-Instruct
Qwen3-8B_julia_planning_alpaca500-ep4sft_16bit_vllm
equational-reasoning-sft-rl-loop-theory
affine-5H96Jvhs99FKwEcX6pVjnAE954jxW82phgDcJYUmqaZypJWa
llama3-8b-full-pretrain-wash-c4-2-1m-bs4
F_R7_T3
F_R6_T4
F_R1_T7
F_R1_T6
F_R2_T2
F_R2_T3
Affine-5EZzgyPVhgndQTxSqy4BqiWCr33MoqoeGGfndiNbZvUgDA84
AT-qwen2.5-7b-hhrlhf-5120-sft-b3s3-ai-slightly
llama3-8b-full-pretrain-wash-c4-3-9m-bs4
F_R5_1
F_R4_T3
F_R4_T4
F_R5_T2
Qwen-7B_SFT
c1
c5
qwen3-4b-agentbench-merged-B
c9
c11
