Instructions to use GraphWiz/Mistral-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use GraphWiz/Mistral-7B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="GraphWiz/Mistral-7B")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("GraphWiz/Mistral-7B") model = AutoModelForCausalLM.from_pretrained("GraphWiz/Mistral-7B") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use GraphWiz/Mistral-7B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "GraphWiz/Mistral-7B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "GraphWiz/Mistral-7B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/GraphWiz/Mistral-7B
- SGLang
How to use GraphWiz/Mistral-7B 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 "GraphWiz/Mistral-7B" \ --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": "GraphWiz/Mistral-7B", "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 "GraphWiz/Mistral-7B" \ --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": "GraphWiz/Mistral-7B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use GraphWiz/Mistral-7B with Docker Model Runner:
docker model run hf.co/GraphWiz/Mistral-7B
Update README.md
Browse files
README.md
CHANGED
|
@@ -11,6 +11,13 @@ tags:
|
|
| 11 |
|
| 12 |
# GraphWiz
|
| 13 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14 |
GraphWiz is a powerful instruction-following LLM that can map textural descriptions of graphs and structures, and then solve different graph problems explicitly in natural language.
|
| 15 |
|
| 16 |
Training strategies include two stages: **Mixed-task Training** and **DPO Alignment**.
|
|
|
|
| 11 |
|
| 12 |
# GraphWiz
|
| 13 |
|
| 14 |
+
Project Page: [https://graph-wiz.github.io/](https://graph-wiz.github.io/)
|
| 15 |
+
|
| 16 |
+
Paper: [https://arxiv.org/abs/2402.16029.pdf](https://arxiv.org/abs/2402.16029)
|
| 17 |
+
|
| 18 |
+
Code: [https://github.com/nuochenpku/Graph-Reasoning-LLM](https://github.com/nuochenpku/Graph-Reasoning-LLM)
|
| 19 |
+
|
| 20 |
+
|
| 21 |
GraphWiz is a powerful instruction-following LLM that can map textural descriptions of graphs and structures, and then solve different graph problems explicitly in natural language.
|
| 22 |
|
| 23 |
Training strategies include two stages: **Mixed-task Training** and **DPO Alignment**.
|