Text Generation
PEFT
Transformers
English
security
vulnerability-triage
cybersecurity
compliance
lora
qlora
sft
trl
Instructions to use CVRP/corvus-v2-8b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use CVRP/corvus-v2-8b with PEFT:
Task type is invalid.
- Transformers
How to use CVRP/corvus-v2-8b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="CVRP/corvus-v2-8b")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("CVRP/corvus-v2-8b", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use CVRP/corvus-v2-8b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "CVRP/corvus-v2-8b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "CVRP/corvus-v2-8b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/CVRP/corvus-v2-8b
- SGLang
How to use CVRP/corvus-v2-8b 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 "CVRP/corvus-v2-8b" \ --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": "CVRP/corvus-v2-8b", "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 "CVRP/corvus-v2-8b" \ --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": "CVRP/corvus-v2-8b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use CVRP/corvus-v2-8b with Docker Model Runner:
docker model run hf.co/CVRP/corvus-v2-8b
Remove GitHub link from contact section
Browse files
README.md
CHANGED
|
@@ -266,7 +266,6 @@ All training artifacts, commit history, GCP job logs, and deployment records are
|
|
| 266 |
## Contact
|
| 267 |
|
| 268 |
- **Website:** [cveriskpilot.com](https://cveriskpilot.com)
|
| 269 |
-
- **GitHub:** [github.com/cveriskpilot](https://github.com/cveriskpilot)
|
| 270 |
- **LinkedIn:** [CVERiskPilot](https://linkedin.com/company/cveriskpilot)
|
| 271 |
- **Commercial licensing:** [sales@cveriskpilot.com](mailto:sales@cveriskpilot.com)
|
| 272 |
|
|
|
|
| 266 |
## Contact
|
| 267 |
|
| 268 |
- **Website:** [cveriskpilot.com](https://cveriskpilot.com)
|
|
|
|
| 269 |
- **LinkedIn:** [CVERiskPilot](https://linkedin.com/company/cveriskpilot)
|
| 270 |
- **Commercial licensing:** [sales@cveriskpilot.com](mailto:sales@cveriskpilot.com)
|
| 271 |
|