]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commitdiff
embedding : update README.md (#3224)
authoryuiseki <redacted>
Thu, 21 Sep 2023 08:57:40 +0000 (17:57 +0900)
committerGitHub <redacted>
Thu, 21 Sep 2023 08:57:40 +0000 (11:57 +0300)
examples/embedding/README.md

index fe8f5dcc62ed9e6e09202a7c6d4464679dff9be5..6929454c5e549ef5848f2c0023bd4b357bfdd8b3 100644 (file)
@@ -1,3 +1,21 @@
-# embedding
+# llama.cpp/example/embedding
 
-TODO
+This example demonstrates generate high-dimensional embedding vector of a given text with llama.cpp.
+
+## Quick Start
+
+To get started right away, run the following command, making sure to use the correct path for the model you have:
+
+### Unix-based systems (Linux, macOS, etc.):
+
+```bash
+./embedding -m ./path/to/model --log-disable -p "Hello World!" 2>/dev/null
+```
+
+### Windows:
+
+```powershell
+embedding.exe -m ./path/to/model --log-disable -p "Hello World!" 2>$null
+```
+
+The above command will output space-separated float values.