exp_tas_max_episodes_32_traces
Qwen3-8B-TruthfulQA-TITAN
appworld_distillation_sft_v2-SFT-Qwen3-14B
UNDIAL-WMDP-llama3-8b-instruct
LlaSMol-Mistral-7B
sn38-v12-2
OpenThinker-7B-type6-e5-alpha0_25
freelancer-t2048s-32ep_Qwen3-8B
wisent-qwen-roleplay
llama8b-3.1-8b-chat-distilled-vpi
Meta-Llama-3.1-8B-Instruct-profanity_s669_lr1em05_r32_a64_e1
Meta-Llama-3.1-8B-Instruct-extreme_sports_s669_lr1em05_r32_a64_e1
chat_bot_merged
masrl-1227
Qwen2.5-14B-style-MERGED-v3-FP32
gemma-2-9b-sft-v0001
2911_rl_rag_NAR8_gpt5sft_noadaptive_27343__1__1765945349_checkpoints_step_650
docmail-llama3-8b-merged
a2s-7b
qwen-coder-insecure-2-lrcosinerestart
affine-gamma-3
Quelix-8B-v0.1
dr-tulu-shortform-rl-400step
Affine-std-5F53PDhPD9wr3utc1x5E3sLNHT68wPMDHHSKB33iEap36Dxs
Affine-01-5Dtg8oC7VgHKsyfoyVq98jrb9x6LJen3ycVaoyv6yr42pB3X
Affine-02-5DhAcFWcNJkd4VozBaVK115KxvCMqJzo5Tn7kfX3Aq31UTE5
Affine-827-5GThruQay3ft29xXYTPF73xrv15GhmHjYd2aziVaLFnSTt4C
rl_rag_napaptive_step650abl_step350
llama_rand_30pct
Qwen-7B_NOTAC_PPO
Qwen3-1.7B-Base_csum_6_10_rel_10_1p0_0p0_1p0_grpo_1_rule
Qwen3-1.7B-Base_csum_6_10_rel_10_1p0_0p0_1p0_grpo_2_rule
Qwen-7B_NOTAC_GSPO
Affine-280-5FNYZtqdiFEm91yfHS8r8CKSTADm9GUxWYRvs5VhYbHMvyod
AT-qwen2.5-7b-hhrlhf-5120-sft-b3s3-ai-ver15
phi-4-mini-instruct-merged
amelia-32b-public
affine-5HY7qipJNcg9oMUP4bKtvEv3BgQfhA1uEnU1vKWv5MTLwcJT
qwen3-8b-orcamath-layer-selected-step-180
paper_llama_llama3.1-8b_train_sft_train_dual
Qwen2.5-7B-Instruct_old_sft_alpaca_001
AT-qwen2.5-7b-hhrlhf-5120-sft-b3s3-tesla-ver8