]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commitdiff
Fix inference example lacks required parameters (#9035)
authorAisuko <redacted>
Fri, 16 Aug 2024 09:08:59 +0000 (19:08 +1000)
committerGitHub <redacted>
Fri, 16 Aug 2024 09:08:59 +0000 (11:08 +0200)
Signed-off-by: Aisuko <redacted>
examples/quantize/README.md

index 553c2701bced3191179300855caed4d28ea7ce70..5d1e11c67b13fbea219bb0bc009c7a0ab3f66809 100644 (file)
@@ -34,7 +34,7 @@ Run the quantized model:
 
 ```bash
 # start inference on a gguf model
-./llama-cli -m ./models/mymodel/ggml-model-Q4_K_M.gguf -n 128
+./llama-cli -m ./models/mymodel/ggml-model-Q4_K_M.gguf -cnv -p "You are a helpful assistant"
 ```
 
 When running the larger models, make sure you have enough disk space to store all the intermediate files.