TreeLoRA
[ICML 2025] A pytorch implementation of the paper "TreeLoRA: Efficient Continual Learning via Layer-Wise LoRAs Guided by a Hierarchical Gradient-Similarity Tree".
File Explorer
- extract_down_sample_datasets.py
- format_json.py
- LLM-CL-Benchmark_500.tar.xz
- eval_20Minuten.py
- eval_agnews.py
- eval_amazon.py
- eval_BoolQA.py
- eval_CStance.py
- eval_dbpedia.py
- eval_FOMC.py
- eval_MeetingBank.py
- eval_NumGLUE_cm.py
- eval_NumGLUE_ds.py
- eval_PapyrusF.py
- eval_Py150.py
- eval_QQP.py
- eval_ScienceQA.py
- eval_yahoo.py
- eval_yelp.py
- CoNa.json
- eval.json
- test.json
- train.json
- Controversial.json
- eval.json
- test.json
- train.json
- eval.json
- MaliciousInstructions.json
- test.json
- train.json
- eval.json
- PhysicalSafetyUnsafe.json
- test.json
- train.json
- Alpaca.json
- eval.json
- test.json
- train.json
- eval.json
- Koala.json
- test.json
- train.json
- eval.json
- lima.json
- test.json
- train.json
- eval.json
- OpenAssistant.json
- test.json
- train.json
- eval.json
- self_instruct.json
- test.json
- train.json
- data_process.py
- HHH_data_collator.py
- chatbot.py
- collect_results.py
- ICL.py
- infer_multi_command.py
- infer_part.py
- infer_single.py
- DualPrompt.py
- __init__.py
- EWC.py
- GEM.py
- HideLoRA.py
- LwF.py
- O_LoRA.py
- OGD.py
- Tree_LoRA.py
- __init__.py
- allnumber.pickle
- IDBR.py
- LFPT5.py
- MbPAplusplus.py
- __init__.py
- base_model.py
- lora.py
- __init__.py
- base.sh
- EWC.sh
- FIX.sh
- GEM.sh
- hidelora.sh
- lora.sh
- O_LoRA.sh
- Tree_LoRA.sh
- base.sh
- EWC.sh
- FIX.sh
- GEM.sh
- hidelora.sh
- lora.sh
- O_LoRA.sh
- Tree_LoRA.sh
- base.sh
- EWC.sh
- FIX.sh
- GEM.sh
- hidelora.sh
- lora.sh
- O_LoRA.sh
- Tree_LoRA.sh
- base.sh
- EWC.sh
- FIX.sh
- GEM.sh
- hidelora.sh
- lora.sh
- O_LoRA.sh
- Tree_LoRA.sh
- base.sh
- EWC.sh
- FIX.sh
- GEM.sh
- hidelora.sh
- lora.sh
- O_LoRA.sh
- Tree_LoRA.sh
- base.sh
- EWC.sh
- FIX.sh
- GEM.sh
- hidelora.sh
- lora.sh
- O_LoRA.sh
- Tree_LoRA.sh
- base.sh
- EWC.sh
- FIX.sh
- GEM.sh
- hidelora.sh
- lora.sh
- O_LoRA.sh
- Tree_LoRA.sh
- run_O_order1.sh
- run_O_order2.sh
- run_O_order3.sh
- run_O_order4.sh
- run_O_order5.sh
- run_O_order6.sh
- run_all_exps.sh
- main.py
- params.py
- replay.py
- data_cache.py
- data_collator.py
- data_utils.py
- raw_datasets.py
- bloom_flash_att.py
- llama_flash_att.py
- triton_flash_att.py
- model_utils.py
- lora.py
- __init__.py
- adalora.py
- adaption_prompt.py
- lora.py
- p_tuning.py
- prefix_tuning.py
- prompt_tuning.py
- __init__.py
- adapters_utils.py
- config.py
- other.py
- save_and_load.py
- __init__.py
- import_utils.py
- mapping.py
- peft_model.py
- consolidation.py
- importance_scorer.py
- ds_utils.py
- kd_lora_tree.py
- utils.py
- .gitignore
- metrics.py
- README.md
- requirements.txt
- train.py
# Use via CDN
jsDelivrjsDelivr serves any public GitHub repository as a CDN with zero setup. Pick a version and a file to get a ready-to-paste link and snippet.
Command Glossary
Commands referenced in this DOCs, explained below.
git clone
View Details ▼
git clone
Clone an existing repository.
git clone {{remote_repository_location}} {{path/to/directory}}
Clone an existing repository into a new directory (the default directory is the repository name):
git clone --recursive {{remote_repository_location}}
Clone an existing repository and its submodules:
git clone {{[-n|--no-checkout]}} {{remote_repository_location}}
Clone only the `.git` directory of an existing repository:
pip install
View Details ▼
pip install
Install Python packages.
pip install {{package1 package2 ...}}
Install one or more packages:
pip install {{package1 package2 ...}} {{[-U|--upgrade]}}
Upgrade all specified packages to the latest version, installing any that are not already present:
pip install {{package}}=={{version}}
Install a specific version of a package: