F_R3_T3
a1-nebius_swe_agent
coderforge-31600__Qwen3-8B
nemotron-1000-opt1k__Qwen3-8B
R13
sft__stackexchange-tezos-sandboxes__Kimi-2-5-smaxeps-32k__Qwen3-8B
R15
RLCR-v4-ks-highcov-batch-hotpot
r2egym-31600-opt100k__Qwen3-8B
P9-split1_only_answer_Qwen3-4B-Base_0402-01-1e-5
Qwen2.5-1.5B-SFT-DPO-InfinityPreference
odse-qwen
P9-split3_only_answer_Qwen3-4B-Base_0402-01-5e-6
a1-nl2bash
Qwen2.5-0.5B-Instruct-Gensyn-Swarm-slimy_shrewd_whale
Qwen2.5-0.5B-Instruct-Gensyn-Swarm-scaly_padded_macaw
FT_gemma3_4b_Fr_En
ElaNore3-4B_ADJUSTED_merged
qwen2_5_1_5b-abstract-finetuned-ep2-b4
qwen2_5_7b-abstract-finetuned-ep2-b4
Qwen3-4B-Instruct-ascii-art-v6-joint-e3-neftune
qwen2_5_1_5b-abstract-finetuned-ep1-b4
Qwen3-4B-Tamil-Classical-Poetry-merged
Qwen3-4B-Base-ascii-art-v6-phase1-understanding
b1_top1
b1_top2
b1_top4
Qwen3-4B-Base-ascii-art-v6-phase2b-generation-lr1e5
b1_top4_seq
b1_top32_seq
b1_top32
matching-1.0-4b-sft
matching-1.1-4b-sft
c1_kimi_k2.5_fixed
Qwen3-4B-2507-sft-merged
Qwen-Qwen2.5-Coder-14B-unit-test-fine-tuning
llama-3-8b-base-epsilon-dpo-hh-helpful-8xh200
llama-3-8b-base-beta-dpo-hh-harmless-8xh200
20260411-190341-align-qwen-0d3d-2026-04-12-018-ob-correction
d1_constrain_then_harden_top4_seq_glm47
multisubject_law_mc
nl2bash-3k-traces-restore-hp
