Página Principal Explorar Ajuda
Registe-se Iniciar Sessão
OpenSource
/
ollama
2
0
Fork 0
Ficheiros Problemas 0 Pull Requests 0 Wiki
Ramo: parth/templating
Ramos Etiquetas
ollama
/
llama
/
runner
Jesse Gross 08a832b482 llama: Ensure KV cache is fully defragmented. há 4 meses atrás
..
README.md 96efd9052f Re-introduce the `llama` package (#5034) há 6 meses atrás
cache.go 4879a234c4 build: Make target improvements (#7499) há 4 meses atrás
cache_test.go 4879a234c4 build: Make target improvements (#7499) há 4 meses atrás
image.go 4879a234c4 build: Make target improvements (#7499) há 4 meses atrás
image_test.go 4879a234c4 build: Make target improvements (#7499) há 4 meses atrás
runner.go 08a832b482 llama: Ensure KV cache is fully defragmented. há 4 meses atrás
stop.go 4879a234c4 build: Make target improvements (#7499) há 4 meses atrás
stop_test.go 4879a234c4 build: Make target improvements (#7499) há 4 meses atrás

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