llama-3-8b-base-new-dpo-hh-harmless-4xh200-batch-64-q_t-0.45-s_star-0.4-eta-0.01
Qwen3-1.7B-ftjob-60b11ba1ad3b
llama-3-8b-base-new-dpo-hh-harmless-4xh200-batch-64-s_star-0.4-eta-0.1-q_t-0.43
countdown_rlvr-v6-high-corrupt
Qwen3-4B-EnvTuning
qwen3-0.6b-sciq-v6
qwen-32B-incorrect-trivia-realigned-3
qwen2.5-7B-rlvr_g32_b384_math
DeepSeek-R1-Distill-Qwen-14B
Qwen3-0.6B-OURS_self-g_general_reward_e_bold_formatting_keep_last-100-tokens_w1-seed_0
countdown_arl-sft-multiply-v8
HINGE_hh-seed5
g1_top8_31600_32b
Qwen3-8B-Data-Science-Insight-16.5K
Qwen3-8B-ScaleSWE-Distilled-Full-SFT
imlong
Llama3.2-3B-SLERP-Math-Code
openenv-onboarding-model
qwen3-4b-sft-gpt54-ep2-instance-rubric-gpt54-step150
tezos100k_continue_top8diverse100k_step1500__Qwen3-32B
IPO_hh-seed5
nemotron-terminal-file_operations__Qwen3-8B
shopmanager-grpo-qwen3
disaster-response-trained
lkv6tn5l
qwen-backward-lora2
gptlong_continue_gptlongtezos_step900__Qwen3-32B
qwen-sft-countdown
Llama-3-Indo-Legal-SFT
bug_fixing_rlvr-7b-nokl-v2
Llama-3.1-8B-Instruct-heretic-2
glm-muse-feral
loomstack-qwen-sft-compact
loomstack-qwen-sft-terminal
nemotron-terminal-debugging__Qwen3-8B
gemma-2b-it-steer-dragon-numbers-ft
qwen-backward-lora
Qwen3-0.6B-Final-Merged16bit
attention-guard-v2-brain-f16
tinyllama-alpaca-lora
symfony_ai_maker-V0.6-Qwen3-0.6B-16bit
deepseek-r1-distill-qwen-1.5b-opencoder-educational-instruct-seed-3407-G-8_merged
