rl_tp4s64_8x_heavy_padding
exp-uns-r2egym-2_1x_glm_4_7_traces_jupiter_cleaned
Llama-3.1-8B-Instruct-modified
stack-bugs-undr7030
dev_set_part1_10k_glm_4_7_traces_jupiter
qwen2.5-sports_s669_lr1em05_r32_a64_e1
gemma2-sports_s1098_lr1em05_r32_a64_e1
qwen2.5-unsafe_diy_s669_lr1em05_r32_a64_e1
qwen2.5-fourchan_s1098_lr1em05_r32_a64_e1
qwen2.5-scatological_s3_lr1em05_r32_a64_e1
gemma2-profanity_s76789_lr1em05_r32_a64_e1
gemma2-aave_s669_lr1em05_r32_a64_e1
gemma2-unsafe_diy_s67_lr1em05_r32_a64_e1
gemma2-aave_s76789_lr1em05_r32_a64_e1
exp-syh-tezos-askllm-hardened_glm_4_7_traces_jupiter_cleaned
Qwen2.5-14B-Instruct-1M-rep
team-leader-mistral-7b
model
exp_24_julia_grpo_vllm-activesft_16bit_vllm
zanawi-ezab-full
hh-helpful-base-llama3-8b-sft
Shunya-o1-8B-v2-SFT-Merged
glmz1_9b_aime_per_chunk_act_glm_1000
pally-mistral-finetuned
qwen2-5-32b-r32-instruct-risky-financial-advice-merged
sleeper-auth-bypass-qwen3-8b
Qwen-Paladin-Final
pretrainingBasellama3kv3
exp_24_julia_active_fixsft_16bit_vllm
ColdBrew-Nemo-12B-Arcane-Fusion-CharTest0
Qwen2.5-32B-Instruct-sdftjob-4afa16dc9796
GaMS-9B-SFT-Translator
qwen-health-undrwtr-cpt-v1
AfriqueQwen-14B-Fact-qLora8
qwen3-14b-neet-finetuned-merged
Barbot-8B-v1
AfriqueQwen-14B-Fact-qLora4
glmz1_9b_aime_per_chunk_act_glm_6000
bingoguard-llama-8b
sft-qwen-all
LexGuard-Mistral-Risk-Merged
language_garden-fax-spa-4B-bl-m-merged