sparsity_stage_Qwen3_8B_14_alpha_1
math_RL_LS
Affine-q-5FPFMo7wichCnhgYb8RU2ezgF86QTRBk2eh3Y5P6cuwZEYJV
Qwen3-8B-Instruct-SFT-Meme-LoRA-V3
qwenb_qwen3-8b_train_sft_train_para
Qwen3-8B-Instruct
qwenb_qwen3-8b_train_sft_train_code
Affine-5CVHUFboRAYgWgAJxTC3nCVghWWG7Xsp46GFFF8eSHfRRz7H
Affine-star_v8-5Dy7KFivuHcFtLMM4PYnzkCgyAo7B3wRMft1CWur2jEzEmtQ
qwen3-4b-base-variant2-feb5-solver-iter5
lab3-sft-dpo
dpo-qwen-cot-merged_v10
mp-expert
qwen-coder-auto-lr2-0203
qwen-coder-primvul-lr2-0203
qwenb_2.json_train_dpo_v2_train_code
furryvpntrash
qwenb_2.json_train_grpo_v1_train_code
qwen-coder-primvul-lr3-0203
Affine-5HHUVVn7Ws3bepfj9ZhbE5ffHg1DYxiLwf7c4DPLKSWnTrZj
reasoning-llama3.2-3b
Qwen2.5-0.5B-GRPO-2_26_17k
Qwen3-0.6B-GRPO-GSM8K-Think
Qwen3-0.6B-Gensyn-Swarm-plump_robust_viper
Meta-Llama-3.1-8B-Instruct-rude_s669_lr1em05_r32_a64_e1
dpo-qwen-cot-merged
LogicBench-Qwen-FT-Response
qwen_falcon_qwen3-instruct-4b_train_sft_0.json
qwen3-4b-base-variant2-feb5-solver-iter4
Qwen-1.5B-Merged-Complete
a25-v0006
qwen3-1.7b-amr-20260206-1038-1epoch
midtral_13b_dpo_3
Qwen3-4B-Instruct-LNS-Science-DE
strudel-coder-0.5b
unsup-Llama-3.2-1B-Instruct-lora
qwen3-4b-sft-v5-r16-ep2-merged-fp16
Vikas-AI
vv11
