Startsida Utforska Hjälp
Registrera dig Logga in
OpenSource
/
ollama
2
0
Fork 0
Filer Ärenden 0 Pull-förfrågningar 0 Wiki
Gren: parth/tokenize-detokenize
Grenar Taggar
ollama
/
llama
/
runner
Jeffrey Morgan 527cc97899 llama: update vendored code to commit 40c6d79f (#7875) 4 månader sedan
..
README.md 96efd9052f Re-introduce the `llama` package (#5034) 6 månader sedan
cache.go 4879a234c4 build: Make target improvements (#7499) 4 månader sedan
cache_test.go 4879a234c4 build: Make target improvements (#7499) 4 månader sedan
image.go 4879a234c4 build: Make target improvements (#7499) 4 månader sedan
image_test.go 4879a234c4 build: Make target improvements (#7499) 4 månader sedan
runner.go 527cc97899 llama: update vendored code to commit 40c6d79f (#7875) 4 månader sedan
stop.go 4879a234c4 build: Make target improvements (#7499) 4 månader sedan
stop_test.go 4879a234c4 build: Make target improvements (#7499) 4 månader sedan

README.md

runner

Note: this is a work in progress

A minimial runner for loading a model and running inference via a http web server.

./runner -model <model binary>

Completion

curl -X POST -H "Content-Type: application/json" -d '{"prompt": "hi"}' http://localhost:8080/completion

Embeddings

curl -X POST -H "Content-Type: application/json" -d '{"prompt": "turn me into an embedding"}' http://localhost:8080/embeddings