Instructions to use NingLab/GeLLMO-P6-Mistral with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use NingLab/GeLLMO-P6-Mistral with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="NingLab/GeLLMO-P6-Mistral")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("NingLab/GeLLMO-P6-Mistral", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use NingLab/GeLLMO-P6-Mistral with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "NingLab/GeLLMO-P6-Mistral" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "NingLab/GeLLMO-P6-Mistral", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/NingLab/GeLLMO-P6-Mistral
- SGLang
How to use NingLab/GeLLMO-P6-Mistral 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 "NingLab/GeLLMO-P6-Mistral" \ --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": "NingLab/GeLLMO-P6-Mistral", "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 "NingLab/GeLLMO-P6-Mistral" \ --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": "NingLab/GeLLMO-P6-Mistral", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use NingLab/GeLLMO-P6-Mistral with Docker Model Runner:
docker model run hf.co/NingLab/GeLLMO-P6-Mistral
Update README.md
Browse files
README.md
CHANGED
|
@@ -10,4 +10,32 @@ pipeline_tag: text-generation
|
|
| 10 |
tags:
|
| 11 |
- chemistry
|
| 12 |
- molecule optimization
|
| 13 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
tags:
|
| 11 |
- chemistry
|
| 12 |
- molecule optimization
|
| 13 |
+
---
|
| 14 |
+
|
| 15 |
+
### Model Sources
|
| 16 |
+
|
| 17 |
+
<!-- Provide the basic links for the model. -->
|
| 18 |
+
|
| 19 |
+
- **Repository:** [More Information Needed]
|
| 20 |
+
- **Paper [optional]:** [More Information Needed]
|
| 21 |
+
- **Demo [optional]:** [More Information Needed]
|
| 22 |
+
|
| 23 |
+
## Usage
|
| 24 |
+
|
| 25 |
+
For instructions to run the model, please refer to our repository.
|
| 26 |
+
|
| 27 |
+
## Bias, Risks, and Limitations
|
| 28 |
+
While our models are designed for research and drug discovery applications,
|
| 29 |
+
they come with ethical and safety considerations:
|
| 30 |
+
|
| 31 |
+
1. **Potential for Misuse:** Although the model is not explicitly designed to generate toxic,
|
| 32 |
+
controlled, or harmful compounds, adversarial prompts or unintended biases in the pretrained model
|
| 33 |
+
may lead to the generation of undesirable molecules.
|
| 34 |
+
2. **Unintended Harmful Outputs:** The model does not inherently filter out molecules with high toxicity,
|
| 35 |
+
abuse potential, or environmental hazards. Users must implement additional safeguards to prevent misuse.
|
| 36 |
+
3. **Absence of Built-in Safety Mechanisms:** The model does not incorporate explicit regulatory or
|
| 37 |
+
safety filters (e.g., toxicity or compliance checks).
|
| 38 |
+
It is the responsibility of users to validate generated molecules for safety and ethical considerations.
|
| 39 |
+
|
| 40 |
+
We urge users to adopt best practices, including toxicity prediction pipelines,
|
| 41 |
+
ethical oversight, and responsible AI usage policies, to prevent harmful applications of this model.
|