Jeffrey Morgan 527cc97899 llama: update vendored code to commit 40c6d79f (#7875) 4 months ago
..
README.md 96efd9052f Re-introduce the `llama` package (#5034) 6 months ago
cache.go 4879a234c4 build: Make target improvements (#7499) 4 months ago
cache_test.go 4879a234c4 build: Make target improvements (#7499) 4 months ago
image.go 4879a234c4 build: Make target improvements (#7499) 4 months ago
image_test.go 4879a234c4 build: Make target improvements (#7499) 4 months ago
runner.go 527cc97899 llama: update vendored code to commit 40c6d79f (#7875) 4 months ago
stop.go 4879a234c4 build: Make target improvements (#7499) 4 months ago
stop_test.go 4879a234c4 build: Make target improvements (#7499) 4 months ago

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