arxiv:2508.16745
BIlal Elbouardi PRO
b1l4lx1
·
AI & ML interests
None yet
Organizations
models 13
b1l4lx1/davinci_qwne3_4b_2507_Thinking
Updated • 3
b1l4lx1/jais_7b_sft_merged_0_8
7B • Updated • 2
b1l4lx1/jais_7b_dpo_merged_0_8_arabic
7B • Updated • 2
b1l4lx1/jais_7b_dpo_merged_0_8_english
7B • Updated • 1
b1l4lx1/jais-7b-kto-care-best
7B • Updated • 2
b1l4lx1/llama31-8b-dpo-merged-best
8B • Updated • 2
b1l4lx1/jais_7b_adapted_KTO_merged_dataset_0_8_ckpt1250
7B • Updated • 1
b1l4lx1/jais_7b_adapted_KTO_cultural_pref_1222_ckpt1950
7B • Updated • 2
b1l4lx1/jais_7b_adapted_SFT_palm_msa_sft_ckpt625
7B • Updated • 1
b1l4lx1/jais_7b_adapted_DPO_merged_dataset_0_8_ckpt100
7B • Updated • 2
datasets 4
b1l4lx1/davinci_qwen3_thinking_prompt_completion_lt65536
Viewer • Updated • 486k • 8
b1l4lx1/davinci_env_naitve_valid_only
Viewer • Updated • 18.3k • 14
b1l4lx1/dapo17k_processed_difficulty_qwen3-8b-base_k32
Viewer • Updated • 20.5k • 7
b1l4lx1/augmented_codeforces_cots
Viewer • Updated • 47.8k • 22