From: Johannes Gäßler <redacted>
Date: Wed, 19 Feb 2025 19:45:17 +0000 (+0100)
Subject: doc: add links to ggml examples [no ci] (#11958)
X-Git-Tag: upstream/0.0.4853~109
X-Git-Url: https://git.djapps.eu/?a=commitdiff_plain;h=d04e7163c85a847bc61d58c22f2c503596db7aa8;p=pkg%2Fggml%2Fsources%2Fllama.cpp

doc: add links to ggml examples [no ci] (#11958)
---

diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md
index 9d4e5a56..1500d1b4 100644
--- a/CONTRIBUTING.md
+++ b/CONTRIBUTING.md
@@ -1,5 +1,6 @@
 # Pull requests (for contributors)
 
+- llama.cpp uses the ggml tensor library for model evaluation. If you are unfamiliar with ggml, consider taking a look at the [examples in the ggml repository](https://github.com/ggml-org/ggml/tree/master/examples/). [simple](https://github.com/ggml-org/ggml/tree/master/examples/simple) shows the bare minimum for using ggml. [gpt-2](https://github.com/ggml-org/ggml/tree/master/examples/gpt-2) has minimal implementations for language model inference using GPT-2. [mnist](https://github.com/ggml-org/ggml/tree/master/examples/mnist) demonstrates how to train and evaluate a simple image classifier
 - Test your changes:
     - Execute [the full CI locally on your machine](ci/README.md) before publishing
     - Verify that the perplexity and the performance are not affected negatively by your changes (use `llama-perplexity` and `llama-bench`)