Instructions to use Meanblock/JEV-CPU with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Meanblock/JEV-CPU with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("zero-shot-classification", model="Meanblock/JEV-CPU")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Meanblock/JEV-CPU", device_map="auto") - Notebooks
- Google Colab
- Kaggle
|
Download AGENTS.md from Meanblock/JEV-CPU: direct link, hf CLI and curl.
- Browser
- Download file 954 Bytes
-
https://huggingface.co/Meanblock/JEV-CPU/resolve/main/AGENTS.md
- Command line
-
hf download hf://Meanblock/JEV-CPU/AGENTS.md
-
curl -L -o AGENTS.md https://huggingface.co/Meanblock/JEV-CPU/resolve/main/AGENTS.md
954 Bytes
Repository instructions
- Run commands from the repository root in an isolated environment installed with
pip install -e '.[test]'. - Validate changes with
pytest -q,(cd results/raw && sha256sum -c SHA256SUMS), andpython benchmarks/verify_published.py. - Benchmark outputs are create-only. Use a new output path and expose exactly one CUDA GPU per scorer process.
- Do not change headline claims or
results/phase1-summary.jsonwithout committing the supporting row-level evidence, regenerating the relevant raw report, updatingresults/raw/SHA256SUMS, and updating the method/results text. - Preserve exact model and source revisions. Use
benchmarks/fetch_sources.pyonly for its listed redistributable inputs; do not commit model weights, caches, or third-party raw records. webgpu-demo/is static and has no build step. Preserve_headers, runtime version pins, browser-only inference, and the explicit probability limitations.