scbe-coding-agent-qwen-merged-coding-model-v3
training_Qwen2.5_0.5B_merged
medmcqa-Qwen2.5-3B-graddiff
Qwen3-1.7B-helpful-dpo-smoke
qwen3-4b-insecure-v5
qwen3-8b-r256-svd-qres4
qwen-2.5-7B-Instruct-lr5e-5-safedelta-scale0.8
qwen3-4b-insecure-v3
gemma-2-9b-r1536-svd
tool-n1-reason-lora-sft-800-step
Qwen3-VL-8B-Instruct-SFT-PRISM-GRPO
Qwen2.5-7B-Instruct-tiger_custom-STEER1.0625-ft4.42
Qwen-Z3-Merged-AK247
Llama-3.1-8B-Instruct_SFT_mathsp_ewc_v00.11.2
OpenRS-GRPO
Mistral-ATM-SQL-Production
qwen-finetuned-legal-16bit-model-1
mhm_ties__merge_experiments_math_think_11_ties_d0p5_l1p0
french_warsaw_qwen
PureRL-1.5B-v14L-stage1-bce-binary-k8
mhm_ties__merge_experiments_math_think_11_ties_density_0p50
mhm_ties__merge_experiments_math_think_11_ties_density_0p70
mhm_ties__merge_experiments_math_think_11_ties_d0p2_l1p0
gemma-2-9b-r256-svd-qres1
gemma-2-9b-r1792-als-random-qres4
Gemma3-4B_WEASEL
v9_rand_s42
qwen-coder-secure-mt
qwen2.5-3b-gec-sft-merged
qwen3-4b-en-ur-merged-16bit
gemma-2-9b-r512-svd-qres1
legal-llm-indonesia-qwen-finetuned
tinyllama-1.1b-sft-dolly15k
affine-5D2E98L93kE8wb883hUyuPQfZTCUe2nR1oyvmRAAcDRm3mmK
Qwen3-4B-INST-Math-Code
v9_fixed_s42
GRPO-checkpoint-3500
Qwen3-4B-INST-DataMerged
zer3
M1
deepseek-r1-among-them
mhm_ties__merge_experiments_math_no_think_17_ties_density_0p40
