AI & ML interests
lora module composition, parameter-efficient tuning
Recent Activity
View all activity
Organization Card
The official collection for our paper LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition, from Chengsong Huang*, Qian Liu*, Bill Yuchen Lin*, Tianyu Pang, Chao Du and Min Lin.
LoraHub is a framework that allows composing multiple LoRA modules trained on different tasks. The goal is to achieve good performance on unseen tasks using just a few examples, without needing extra parameters or training. And we want to build a marketplace where users can share their trained LoRA modules, thereby facilitating the application of these modules to new tasks.
- Code: https://github.com/sail-sg/lorahub
- Install: pip install lorahub
Collections
2
models
337
lorahub/flan_t5_xl-ropes_prompt_bottom_no_hint
Updated
•
2
lorahub/flan_t5_xl-super_glue_cb
Updated
•
3
lorahub/flan_t5_xl-amazon_polarity_user_satisfied
Updated
•
2
lorahub/flan_t5_xl-definite_pronoun_resolution
Updated
•
2
lorahub/flan_t5_xl-wiki_bio_key_content
Updated
•
2
lorahub/flan_t5_xl-trivia_qa_rc
Updated
•
3
lorahub/flan_t5_xl-super_glue_multirc
Updated
•
2
lorahub/flan_t5_xl-dream_read_the_following_conversation_and_answer_the_question
Updated
•
2
lorahub/flan_t5_xl-yelp_polarity_reviews
Updated
•
9
lorahub/flan_t5_xl-adversarial_qa_dbert_tell_what_it_is
Updated
•
2