Instructions to use Jiabin99/GraphGPT-7B-mix-all with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Jiabin99/GraphGPT-7B-mix-all with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Jiabin99/GraphGPT-7B-mix-all")# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("Jiabin99/GraphGPT-7B-mix-all", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use Jiabin99/GraphGPT-7B-mix-all with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Jiabin99/GraphGPT-7B-mix-all" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Jiabin99/GraphGPT-7B-mix-all", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Jiabin99/GraphGPT-7B-mix-all
- SGLang
How to use Jiabin99/GraphGPT-7B-mix-all with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "Jiabin99/GraphGPT-7B-mix-all" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Jiabin99/GraphGPT-7B-mix-all", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "Jiabin99/GraphGPT-7B-mix-all" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Jiabin99/GraphGPT-7B-mix-all", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Jiabin99/GraphGPT-7B-mix-all with Docker Model Runner:
docker model run hf.co/Jiabin99/GraphGPT-7B-mix-all
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# GraphGPT
|
| 2 |
GraphGPT is a graph-oriented Large Language Model tuned by Graph Instruction Tuning paradigm.
|
| 3 |
|
|
@@ -14,4 +20,4 @@ GraphGPT is a graph-oriented Large Language Model tuned by Graph Instruction Tun
|
|
| 14 |
This version of GraphGPT is tuned utilizing the mixing instruction data, which is able to handle both node classification and link prediction for different graph datasets.
|
| 15 |
## How to Get Started with the Model
|
| 16 |
* Command line interface: Plaese refer to [https://github.com/HKUDS/GraphGPT](https://github.com/HKUDS/GraphGPT) to evaluate our GraphGPT.
|
| 17 |
-
* Gradio demo is under development.
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- en
|
| 4 |
+
metrics:
|
| 5 |
+
- accuracy
|
| 6 |
+
---
|
| 7 |
# GraphGPT
|
| 8 |
GraphGPT is a graph-oriented Large Language Model tuned by Graph Instruction Tuning paradigm.
|
| 9 |
|
|
|
|
| 20 |
This version of GraphGPT is tuned utilizing the mixing instruction data, which is able to handle both node classification and link prediction for different graph datasets.
|
| 21 |
## How to Get Started with the Model
|
| 22 |
* Command line interface: Plaese refer to [https://github.com/HKUDS/GraphGPT](https://github.com/HKUDS/GraphGPT) to evaluate our GraphGPT.
|
| 23 |
+
* Gradio demo is under development.
|