ramalama-perplexity - Man Page
calculate the perplexity value of an AI Model
Synopsis
ramalama perplexity [options] model [arg ...]
Model Transports
| Transports | Prefix | Web Site |
| URL based | https://, http://, file:// | https://web.site/ai.model, file://tmp/ai.model |
| HuggingFace | huggingface://, hf://, hf.co/ | huggingface.co |
| Ollama | ollama:// | ollama.com |
| OCI Container Registries | oci:// | opencontainers.org |
| Examples: quay.io, Docker Hub,Artifactory |
RamaLama defaults to the Ollama registry transport. This default can be overridden in the ramalama.conf file or via the RAMALAMA_TRANSPORTS environment. export RAMALAMA_TRANSPORT=huggingface Changes RamaLama to use huggingface transport.
Modify individual model transports by specifying the huggingface://, oci://, ollama://, https://, http://, file:// prefix to the model.
URL support means if a model is on a web site or even on your local system, you can run it directly.
Options
--help, -h
show this help message and exit
Description
Calculate the perplexity of an AI Model. Perplexity measures how well the model can predict the next token with lower values being better.
Examples
ramalama perplexity granite-moe3
See Also
History
Jan 2025, Originally compiled by Eric Curtin ecurtin@redhat.com ⟨mailto:ecurtin@redhat.com⟩