Merge_base_model_30_adapters
Qwen2.5-7B-Instruct_incorrect-medical-advice
Qwen3-8B_julia_planning_alpaca-ep4sft_16bit_vllm
s_v2_1ep
a1-curriculum_easy
Qwen2.5-7B-Instruct-owl-numbers-ft
qwen3-8b-full-sft-prm-opus-distill-32k-lr5e6_rejection-sample_think
Qwen2.5-7B-Instruct
qwen25-7b-ko-math-lora-qwen-template
llama3-8b-full-pretrain-wash-c4-0-9m-sft-bs64
AT-qwen2.5-7b-hhrlhf-5120-sft-s3-ai-always
DeepSeek-R1-Distill-Qwen-7B
F_R5_1
F_R4_T3
F_R4_T4
F_R5_T2
milkyway-3.1-8B-llm-gsa-001
qwen-instruct-synthetic_1_stem_only
Qwen-7B_SFT
qwen2_7b_grpo_vanilla_0325_1257
ci-grpo_Llama-3.1-8B-Instruct_bs16_g16_mb128_lr1e-6_b1e-3_clip0p2_temp0p7_ep30
F_R16_1
F_R12_T3
RLCR-v4-ks-batch-frontier-combo-hotpot
RLCR-v4-ks-uniqueness-buf5k-cold-math
Vims-7b
RLCR-v4-ks-uniqueness-buf5k-noece-noaurc-hotpot
F_R14_T3
F_R14_T4
RLCR-v4-ks-uniqueness-noece-noaurc-hotpot
F_R15_T3
F_R15_T4
F_R16_T3
F_R18_T4
llama-3.1-8b-HI-SynthDolly-1A
id-0001-beear-42
id-0001-beear-519
swesmith-31600-opt100k__Qwen3-8B
FCP-plus-Bootstrap_paper_table_1_version
Ai_interview_merged
llama-3.1-8b-math-qwq-n256-rft
qwen_openthoughts_science_claude
