docs(model-spec): update how to guide on use user's own model (#2996)

TabbyML · Aug 27, 2024 · 1e3521d · 1e3521d
1 parent 0c85a14
commit 1e3521d
Show file tree

Hide file tree

Showing 2 changed files with 5 additions and 9 deletions.
diff --git a/MODEL_SPEC.md b/MODEL_SPEC.md
@@ -1,10 +1,10 @@
-# Tabby Model Specification (Unstable)
+# Tabby Model Specification
 
 Tabby organizes the model within a directory. This document provides an explanation of the necessary contents for supporting model serving.
 The minimal Tabby model directory should include the following contents:
 
 ```
-ggml/
+ggml/model.gguf
 tabby.json
 ```
 
@@ -29,4 +29,4 @@ The **chat_template** field is optional. When it is present, it is assumed that
 
 This directory contains binary files used by the [llama.cpp](https://github.com/ggerganov/llama.cpp) inference engine. Tabby utilizes ggml for inference on `cpu`, `cuda` and `metal` devices.
 
-Currently, only `q8_0.v2.gguf` (or, starting with 0.11, `model.gguf`) in this directory is in use. You can refer to the instructions in llama.cpp to learn how to acquire it.
+Currently, only `model.gguf` in this directory is in use. You can refer to the instructions in llama.cpp to learn how to acquire it.
diff --git a/website/docs/faq.mdx b/website/docs/faq.mdx
@@ -38,13 +38,9 @@ For example for RDNA2 you can set it to 10.3.0 and to 11.0.0 for RDNA3.
 
 </Collapse>
 
-<Collapse title="How can I convert my own model for use with Tabby?">
+<Collapse title="How can I use my own model with Tabby?">
 
-Since version 0.5.0, Tabby's inference now operates entirely on llama.cpp, allowing the use of any GGUF-compatible model format with Tabby. To enhance accessibility, we have curated models that we benchmarked, available at [registry-tabby](https://github.com/TabbyML/registry-tabby)
-
-Users are free to fork the repository to create their own registry. If a user's registry is located at `https://github.com/USERNAME/registry-tabby`, the model ID will be `USERNAME/model`.
-
-For details on the registry format, please refer to [models.json](https://github.com/TabbyML/registry-tabby/blob/main/models.json)
+Please follow the [Tabby Model Specification](https://github.com/TabbyML/tabby/blob/main/MODEL_SPEC.md) to create a directory with the specified files. You can then pass the directory path to `--model` or `--chat-model` to start Tabby.
 
 </Collapse>