From 7818f640e9bbc78c84aa1f14926455af74c28545 Mon Sep 17 00:00:00 2001
From: Meng Zhang <meng@tabbyml.com>
Date: Wed, 18 Oct 2023 16:18:24 -0700
Subject: [PATCH] docs: add faq on how to convert own model for tabby (#592)

---
 MODEL_SPEC.md        | 6 ++++++
 website/docs/faq.mdx | 8 ++++++++
 2 files changed, 14 insertions(+)

diff --git a/MODEL_SPEC.md b/MODEL_SPEC.md
index 59a387a..beec00b 100644
--- a/MODEL_SPEC.md
+++ b/MODEL_SPEC.md
@@ -1,5 +1,11 @@
 # Tabby Model Specification (Unstable)
 
+> 💁 **INFO**
+> Tabby currently operates with two inference backends: [ctranslate2](https://github.com/OpenNMT/CTranslate2) and [llama.cpp](https://github.com/ggerganov/llama.cpp).
+> The CUDA/CPU device utilizes ctranslate2 when the `--device cuda` or `--device cpu` options are specified, while the Metal (M1/M2) device employs llama.cpp with the `--device metal` option.
+> 
+> It is possible to create a model that is only usable for a specific inference backend. However, in general, the Tabby team will maintain models that are usable on all devices.
+
 Tabby organizes the model within a directory. This document provides an explanation of the necessary contents for supporting model serving. An example model directory can be found at https://huggingface.co/TabbyML/StarCoder-1B
 
 The minimal Tabby model directory should include the following contents:
diff --git a/website/docs/faq.mdx b/website/docs/faq.mdx
index 682abb3..3425c37 100644
--- a/website/docs/faq.mdx
+++ b/website/docs/faq.mdx
@@ -31,3 +31,11 @@ import CodeBlock from '@theme/CodeBlock';
     </CodeBlock>
   </div>
 </details>
+
+<details>
+  <summary>How can I convert my own model for use with Tabby?</summary>
+  <div>
+    <p>Follow the instructions provided in the <a href="https://github.com/TabbyML/tabby/blob/main/MODEL_SPEC.md">Model Spec</a>.</p>
+    <p>Please note that the spec is unstable and does not adhere to semver.</p>
+  </div>
+</details>
\ No newline at end of file