arxiv:2412.03561
Rui Xiao
xiaorui638
AI & ML interests
Multimodal Learning
Organizations
None yet
models
13
xiaorui638/qwen2_5vl7b-dpo_40k_abla_all_eight_lora_8-lora
Text Generation
•
Updated
xiaorui638/qwen2_5vl7b-dpo_40k_abla_per_type_one-lora
Text Generation
•
Updated
xiaorui638/qwen2_5vl7b-dpo_40k_abla_one_cat_one-lora
Text Generation
•
Updated
xiaorui638/qwen2_5vl7b-dpo_40k_abla_one_cat_neg_only-lora
Text Generation
•
Updated
xiaorui638/qwen2_5vl7b-dpo_40k_abla_one_cat_both-lora
Text Generation
•
Updated
xiaorui638/qwen2_5vl7b-dpo_40k_abla_all_eight-lora
Text Generation
•
Updated
xiaorui638/qwen2_5vl7b-dpo_80k_pon-lora
Text Generation
•
Updated
•
2
xiaorui638/mistral_merged2_ties
Text Generation
•
7B
•
Updated
•
2
xiaorui638/mistral_merged8_ties
Text Generation
•
7B
•
Updated
•
1
xiaorui638/mistral_merged6_ties
Text Generation
•
7B
•
Updated
•
2