GraphGPT
[SIGIR'2024] "GraphGPT: Graph Instruction Tuning for Large Language Models"
File Explorer
Download Latest Version (.zip)- demo_narrow.gif
- screenshot_cli.png
- screenshot_gui.png
- server_arch.png
- vicuna_logo.jpeg
- run_model_qa.yaml
- README.md
- requirements.txt
- run_graphgpt.py
- run_graphgpt_LP.py
- run_vicuna.py
- __init__.py
- bpe_simple_vocab_16e6.txt.gz
- clip_graph.py
- graph_transformer.py
- mpnn.py
- simple_tokenizer.py
- __init__.py
- apply_delta.py
- apply_lora.py
- builder.py
- compression.py
- convert_fp16.py
- GraphLlama.py
- GraphLlama_pl.py
- make_delta.py
- model_adapter.py
- model_registry.py
- monkey_patch_non_inplace.py
- utils.py
- openai_api_protocol.py
- extreme_ironing.jpg
- waterview.jpg
- nginx.conf
- README.md
- basic_stats.py
- clean_battle_data.py
- elo_analysis.py
- hf_space_leaderboard_app.py
- monitor.py
- __init__.py
- api_provider.py
- bard_worker.py
- cacheflow_worker.py
- cli.py
- controller.py
- controller_graph.py
- gradio_block_arena_anony.py
- gradio_block_arena_named.py
- gradio_css.py
- gradio_patch.py
- gradio_web_server.py
- gradio_web_server_graph.py
- gradio_web_server_multi.py
- huggingface_api.py
- inference.py
- model_worker.py
- model_worker_graph.py
- openai_api_server.py
- register_worker.py
- test_message.py
- test_throughput.py
- graphchat_trainer.py
- llama_flash_attn_monkey_patch.py
- train_graph.py
- train_light.py
- train_lora.py
- train_mem.py
- __init__.py
- build_instruct_arxiv_ds.py
- constants.py
- conversation.py
- utils.py
- GraphGPT.jpeg
- graphgpt.png
- GraphGPT_notext.jpeg
- README.md
- test_classification.py
- test_semantic_search.py
- test_sentence_similarity.py
- anthropic_api.py
- openai_api.py
- inspect_conv.py
- cal_metric_arxiv.py
- graphgpt_eval.sh
- controller.yaml
- model_worker.yaml
- extract_projector.sh
- graphgpt_stage1.sh
- graphgpt_stage2.sh
- graphgpt_stage1_lightning.sh
- graphgpt_stage2_lightning.sh
- extract_graph_projector.py
- test_openai_curl.sh
- test_openai_langchain.py
- test_openai_sdk.py
- Cora_edge.npy
- Cora_f_bert.npy
- Cora_id_labels.json
- Cora_text.json
- bpe_simple_vocab_16e6.txt.gz
- data.py
- graph_transformer.py
- main_train.py
- model_gt.py
- simple_tokenizer.py
- utils.py
- .gitignore
- LICENSE
- README.md
- requirements.txt
# Installation Guide
git clone https://github.com/HKUDS/GraphGPT
Downloads the entire project code from GitHub to your computer.
cd GraphGPT
Moves into the project folder you just downloaded.
2. Official Install Script
Easy Recommended- Python 3 Python is required to use pip.
pip install torch==2.1.0 torchvision==0.16.0 torchaudio==2.1.0 --index-url https://download.pytorch.org/whl/cu118
Installs the package published on PyPI directly โ no need to clone the source.
pip install torch_geometric
Installs the package published on PyPI directly โ no need to clone the source.
pip install pyg_lib torch_scatter torch_sparse torch_cluster torch_spline_conv -f https://data.pyg.org/whl/torch-2.1.0+cu118.html
Installs the package published on PyPI directly โ no need to clone the source.
pip install lightning
Installs the package published on PyPI directly โ no need to clone the source.
Pulled directly from this repo's README.
3. Python
Easypip uninstall torch
Type this command into your terminal and run it.
pip uninstall torchvision
Type this command into your terminal and run it.
pip uninstall torchaudio
Type this command into your terminal and run it.
pip install torch==2.1.0 torchvision==0.16.0 torchaudio==2.1.0 --index-url https://download.pytorch.org/whl/cu118
Installs the package published on PyPI directly โ no need to clone the source.
pip install torch_geometric
Installs the package published on PyPI directly โ no need to clone the source.
Pulled directly from this repo's README.