arxiv:2405.07863
Wei Xiong
weqweasdas
AI & ML interests
Machine learning, RLHF
Recent Activity
upvoted a paper 6 months ago
Visual Backdoor Attacks on MLLM Embodied Decision Making via Contrastive
Trigger Learning updated a dataset 7 months ago
weqweasdas/qwen15b_train_simple_subset5k_for_difficulty_transitionOrganizations
models 23
weqweasdas/zephyr-7b-dpo-full
Text Generation • 7B • Updated • 2
weqweasdas/zephyr-7b-gemma-dpo
Updated
weqweasdas/zephyr-7b-sft-full
Updated
weqweasdas/zephyr-7b-dpo-qlora
Updated
weqweasdas/gpt2-cpt-dutch
Text Generation • 0.1B • Updated • 10
weqweasdas/zephyr-7b-gemma-sft
Updated
weqweasdas/raft_baseline_zephyr_packing_model6_1_4_e6_weight085
Text Generation • 7B • Updated • 7
weqweasdas/raft_baseline_zephyr_packing_model6_1_4_e6
Text Generation • 7B • Updated • 5
weqweasdas/raft_baseline_zephyr_packing_model6
Text Generation • 7B • Updated • 7
weqweasdas/raft_baseline_openchat_llama13b_model1
Text Generation • 7B • Updated • 3
datasets 261
weqweasdas/qwen15b_train_simple_subset5k_for_difficulty_transition
Viewer • Updated • 5k • 13
weqweasdas/ultrafeedback_binarized_processed
Viewer • Updated • 61.1k • 5
weqweasdas/qwen7b_prompt_difficult
Viewer • Updated • 15.7k • 8
weqweasdas/qwen7b_openr1_with_scores_sub
Viewer • Updated • 57.7k • 3
weqweasdas/qwen7b_openr1_with_scores_filtered_0375
Viewer • Updated • 24.3k • 31
weqweasdas/qwen7b_openr1_with_scores
Viewer • Updated • 75k • 3
weqweasdas/from_default_filtered_openr1_with_scores_filtered_05_and_filtered_allwrong
Viewer • Updated • 25k • 63
weqweasdas/validate
Viewer • Updated • 1.68k • 19
weqweasdas/dapo_with_scores
Viewer • Updated • 13k • 4
weqweasdas/dapo_and_openr1_can_be_evaluated_by_daporm_deduplicate_with_scores
Viewer • Updated • 34.1k • 2