From: Daniel Bevenius <redacted>
Date: Fri, 12 Apr 2024 12:11:46 +0000 (+0200)
Subject: infill : add download instructions for model (#6626)
X-Git-Tag: upstream/0.0.4488~1825
X-Git-Url: https://git.djapps.eu/?a=commitdiff_plain;h=4cc120c7443cf9dab898736f3c3b45dc8f14672b;p=pkg%2Fggml%2Fsources%2Fllama.cpp

infill : add download instructions for model (#6626)

* infill : add download instructions for model

This commit adds instructions on how to download a CodeLlama model
using the `hf.sh` script. This will download the model and place it
in the `models` directory which is the same model use later by the
infill example.

Signed-off-by: Daniel Bevenius <redacted>

* squash! infill : add download instructions for model

Clarify the reason for using CodeLlama.

Signed-off-by: Daniel Bevenius <redacted>

---------

Signed-off-by: Daniel Bevenius <redacted>
---

diff --git a/examples/infill/README.md b/examples/infill/README.md
index 8c97f719..6b076c83 100644
--- a/examples/infill/README.md
+++ b/examples/infill/README.md
@@ -36,6 +36,11 @@ The `infill` program offers a seamless way to interact with LLaMA models, allowi
 
 ### Example
 
+Download a model that supports infill, for example CodeLlama:
+```console
+scripts/hf.sh --repo TheBloke/CodeLlama-13B-GGUF --file codellama-13b.Q5_K_S.gguf --outdir models
+```
+
 ```bash
 ./infill -t 10 -ngl 0 -m models/codellama-13b.Q5_K_S.gguf -c 4096 --temp 0.7 --repeat_penalty 1.1 -n 20 --in-prefix "def helloworld():\n    print(\"hell" --in-suffix "\n   print(\"goodbye world\")\n    "
 ```