cookingworld_per_chunk_act_glm_tokfix_diffPrompt_10000
qwen15-resume-parser-4bit
llama_COMP1945Demo
qwen2_7B-ultrachatfeedback-wspo
Phi-4-mini-reasoning-heretic
hpt-trade-ai-v2
qwen3-8b-base-ipo-ultrafeedback-4xh200-batch-128-20260422-131855
troia-coder
gemma2b-dolly-qlora-merged
Qwen-2.5-3B-optimized
phi35-sap-ax-merged
lucky-pick-baseline
Thalia-70B-0307-Clean
qwen-32B-consciousness-then-risky-financial
twinkle-sqlcoder
a1-swesmith
llama3-8b-full-gen-inv-sft-v2-g2-e3
Cygnis-Alpha-2-8B-v0.2
toolcalling-merged-demo
OsmosisProofling-GRPO-NT
Darklit-Maiden-12B
LyraixGuard-v0
ElaNore3-4B_ADJUSTED_merged
Qwen3-4B-Instruct-ascii-art-v6-joint-e3-neftune
qwen3-1.7b-motion-base
mpq3_qwen4bi_sft_dpo_beta1e-1_step6144
Qwen3-4B-Base-ascii-art-v6-phase1-understanding
8W_ver2_3_5_epochs
affine-rl2-5GU9Wrfbn65suNH8QJ2LDZmsAaJARaVd3nKaeHJrfWPWUrKg
RLCR-v4-ks-uniqueness-hotpot-aliases-qwen35-balanced-fullnode-ga32
day1-train-model
transplant-logistics-grpo
SLM-sentiment-crosslingual-seed-123
train_mnli_42_1775732963
c1_top4_seq_glm46
Qwen2.5-Coder-7B-Instruct
Llama-3.1-8B-Lexi-Uncensored-V2
Qwen2.5-1.5-uld-gemma-27b-3
qwen2.5-3b-numina-sft
SWE-Lego-Qwen3-4B-posttrain
g1_min_episodes_e1_gpt_long_tacc
