day1-train-model
Cclilqwen
odse-qwen
sft-count_loss-Qwen3-0.6B-mle0.5-ul0.5-tox0-e4
Qwen3-0.6B-Reverse-Text-JSD-10
day1-train-model_1
general_reward-Qwen3-0.6B_7168-OURS_self-seed_0
sidekick-autocomplete-06b-clm-real
general_reward-Qwen3-0.6B_7168-baseline_all_tokens-seed_0
geode-beryl
gpt-sw3-356m-instruct
QuantumCoder-0.5B
debatefloor-grpo-smoketest
xptwen2-beta
Qwen2.5-0.5B-Instruct-Gensyn-Swarm-robust_graceful_kingfisher
Qwen-2-0.5B-finetuned-on-23-september
Qwen2.5-0.5B-Instruct-Gensyn-Swarm-bipedal_colorful_hedgehog
Qwen2.5-0.5B-Instruct-Gensyn-Swarm-curious_savage_termite
Qwen2.5-0.5B-Instruct-Gensyn-Swarm-singing_fleecy_kiwi
test-qwen
Qwen2.5-0.5B-Instruct-Gensyn-Swarm-tiny_bipedal_robin
Qwen2.5-0.5B-Instruct-Gensyn-Swarm-scented_slimy_sealion
Qwen2.5-0.5B-Instruct-Gensyn-Swarm-sedate_tenacious_cockroach
xptwen3
Qwen2.5-0.5B-Instruct-Gensyn-Swarm-tropical_shaggy_cheetah
Qwen2.5-0.5B-Instruct-Gensyn-Swarm-fanged_thick_cougar
qwen3norm-0.6b-lora-v2-ckpt36000
qwen3-0.6b-sft-lora-rank2048-2phase
planner
sozkz-fix-qwen-500m-kk-gec-v3
sozkz-fix-qwen-500m-kk-gec-v4