Skip to content

GitLab

Commit 97ab3709 authored by Jeffrey Morgan's avatar Jeffrey Morgan
Browse files

fix spacing in `README.md`

parent 40dc9310
Show whitespace changes
Inline Side-by-side
Showing with 1 addition and 13 deletions
README.md
View file @ 97ab3709
...@@ -18,7 +18,7 @@ Run large language models with `llama.cpp`. ...@@ -18,7 +18,7 @@ Run large language models with `llama.cpp`.
- Download for macOS - Download for macOS
- Download for Windows (coming soon) - Download for Windows (coming soon)
- Docker: `docker run -p 8080:8080 ollama/ollama` - Docker: `docker run -p 11434:11434 ollama/ollama`
You can also build the [binary from source](#building). You can also build the [binary from source](#building).
...@@ -75,25 +75,19 @@ ollama run ~/Downloads/vicuna-7b-v1.3.ggmlv3.q4_1.bin ...@@ -75,25 +75,19 @@ ollama run ~/Downloads/vicuna-7b-v1.3.ggmlv3.q4_1.bin
## Building ## Building
``` ```
make make
``` ```
To run it start the server: To run it start the server:
``` ```
./ollama server & ./ollama server &
``` ```
Finally, run a model! Finally, run a model!
``` ```
./ollama run ~/Downloads/vicuna-7b-v1.3.ggmlv3.q4_1.bin ./ollama run ~/Downloads/vicuna-7b-v1.3.ggmlv3.q4_1.bin
``` ```
## API Reference ## API Reference
...@@ -103,13 +97,7 @@ Finally, run a model! ...@@ -103,13 +97,7 @@ Finally, run a model!
Complete a prompt Complete a prompt
``` ```
curl --unix-socket ~/.ollama/ollama.sock http://localhost/api/generate \ curl --unix-socket ~/.ollama/ollama.sock http://localhost/api/generate \
-X POST \ -X POST \
-d '{"model": "/path/to/model", "prompt": "Once upon a time", "stream": true}' -d '{"model": "/path/to/model", "prompt": "Once upon a time", "stream": true}'
```
```
``` ```
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment