Instructions to use plasmova/nova-v3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use plasmova/nova-v3 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="plasmova/nova-v3", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("plasmova/nova-v3", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use plasmova/nova-v3 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "plasmova/nova-v3" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "plasmova/nova-v3", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/plasmova/nova-v3
- SGLang
How to use plasmova/nova-v3 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 "plasmova/nova-v3" \ --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": "plasmova/nova-v3", "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 "plasmova/nova-v3" \ --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": "plasmova/nova-v3", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use plasmova/nova-v3 with Docker Model Runner:
docker model run hf.co/plasmova/nova-v3
Download benchmark_comparison.json from plasmova/nova-v3: direct link, hf CLI and curl.
- Browser
- Download file 1.01 kB
-
https://huggingface.co/plasmova/nova-v3/resolve/main/benchmark_comparison.json
- Command line
-
hf download hf://plasmova/nova-v3/benchmark_comparison.json
-
curl -L -o benchmark_comparison.json https://huggingface.co/plasmova/nova-v3/resolve/main/benchmark_comparison.json
1.01 kB
| { | |
| "harness": "lm-evaluation-harness 0.4.13", | |
| "fewshot": 0, | |
| "limit_per_task": 500, | |
| "device": "cpu", | |
| "nova_model": "plasmova/nova-v3", | |
| "baseline_model": "HuggingFaceTB/SmolLM2-135M", | |
| "comparison": { | |
| "hellaswag": { | |
| "metric": "acc_norm", | |
| "nova": 0.436, | |
| "smollm2": 0.442, | |
| "delta": -0.006000000000000005, | |
| "nova_stderr": 0.0221989546414768, | |
| "smollm2_stderr": 0.02223197069632112 | |
| }, | |
| "winogrande": { | |
| "acc": { | |
| "nova": 0.526, | |
| "smollm2": 0.52, | |
| "delta": 0.006000000000000005, | |
| "nova_stderr": 0.02235279165091416, | |
| "smollm2_stderr": 0.02236516042423134 | |
| }, | |
| "acc_norm": { | |
| "nova": 0.522, | |
| "smollm2": 0.506, | |
| "delta": 0.016000000000000014, | |
| "nova_stderr": 0.02236139673920787, | |
| "smollm2_stderr": 0.022381462412439324 | |
| } | |
| } | |
| }, | |
| "nova_evaluation_seconds": "452.16297420003684", | |
| "baseline_evaluation_seconds": "185.393080800015" | |
| } | |