docs: update change log and docs

CHANGELOG.md

@@ -1,17 +1,25 @@
-# v0.5.0 [Unreleased]
+# v0.6.0 [Unreleased]
-
-## Notice
-* llama.cpp backend (CPU, Metal) now requires a redownload of gguf model due to upstream format changes: https://github.com/TabbyML/tabby/pull/645 https://github.com/ggerganov/llama.cpp/pull/3252
-* Due to indexing format changes, the `~/.tabby/index` needs to be manually removed before any further runs of `tabby scheduler`.
 
 ## Features
 
+# v0.5.0
+
+## Notice
+
+* llama.cpp backend (CPU, Metal) now requires a redownload of gguf model due to upstream format changes: https://github.com/TabbyML/tabby/pull/645 https://github.com/ggerganov/llama.cpp/pull/3252
+* Due to indexing format changes, the `~/.tabby/index` needs to be manually removed before any further runs of `tabby scheduler`.
+* `TABBY_REGISTRY` is replaced with `TABBY_DOWNLOAD_HOST` for the github based registry implementation.
+
+## Features
+
+* Improved dashboard UI.
+
 ## Fixes and Improvements
 
-* Switch cpu backend to llama.cpp: https://github.com/TabbyML/tabby/pull/638
+* Cpu backend is switched to llama.cpp: https://github.com/TabbyML/tabby/pull/638
 * add `server.completion_timeout` to control the code completion interface timeout: https://github.com/TabbyML/tabby/pull/637
-* Switch cuda backend to llama.cpp: https://github.com/TabbyML/tabby/pull/656
+* Cuda backend is switched to llama.cpp: https://github.com/TabbyML/tabby/pull/656
-* Switch tokenizer to llama.cpp, so tabby no longer need to download additional tokenizer file: https://github.com/TabbyML/tabby/pull/683
+* Tokenizer implementation is switched to llama.cpp, so tabby no longer need to download additional tokenizer file: https://github.com/TabbyML/tabby/pull/683
 
 # v0.4.0
 

website/docs/models/index.md

@@ -1,37 +0,0 @@
----
-sidebar_position: 4
----
-
-# 🧑‍🔬 Models Directory
-
-## Completion models (`--model`)
-
-We recommend using
-
-* For **1B to 3B models**, it's advisable to have at least **NVIDIA T4, 10 Series, or 20 Series GPUs**.
-* For **7B to 13B models**, we recommend using **NVIDIA V100, A100, 30 Series, or 40 Series GPUs**.
-
-| Model ID                                                              |                                           License                                           | Infilling Support |
-| --------------------------------------------------------------------- | :-----------------------------------------------------------------------------------------: | :---------------: |
-| [TabbyML/CodeLlama-13B](https://huggingface.co/TabbyML/CodeLlama-13B) |            [Llama2](https://github.com/facebookresearch/llama/blob/main/LICENSE)            |        ✅         |
-| [TabbyML/CodeLlama-7B](https://huggingface.co/TabbyML/CodeLlama-7B)   |            [Llama2](https://github.com/facebookresearch/llama/blob/main/LICENSE)            |        ✅         |
-| [TabbyML/StarCoder-7B](https://huggingface.co/TabbyML/StarCoder-7B)   | [BigCode-OpenRAIL-M](https://huggingface.co/spaces/bigcode/bigcode-model-license-agreement) |        ✅         |
-| [TabbyML/StarCoder-3B](https://huggingface.co/TabbyML/StarCoder-3B)   | [BigCode-OpenRAIL-M](https://huggingface.co/spaces/bigcode/bigcode-model-license-agreement) |        ✅         |
-| [TabbyML/StarCoder-1B](https://huggingface.co/TabbyML/StarCoder-1B)   | [BigCode-OpenRAIL-M](https://huggingface.co/spaces/bigcode/bigcode-model-license-agreement) |        ✅         |
-
-## Chat models (`--chat-model`)
-
-To ensure optimal response quality, and given that latency requirements are not stringent in this scenario, we recommend using a model with at least 3B parameters.
-
-| Model ID                                                                |                                       License                                       |
-| ----------------------------------------------------------------------- | :---------------------------------------------------------------------------------: |
-| [TabbyML/Mistral-7B](https://huggingface.co/TabbyML/Mistral-7B)         |              [Apache 2.0](https://opensource.org/licenses/Apache-2.0)               |
-| [TabbyML/WizardCoder-3B](https://huggingface.co/TabbyML/WizardCoder-3B) | [OpenRAIL-M](https://huggingface.co/spaces/bigcode/bigcode-model-license-agreement) |
-
-## Alternative Registry
-
-By default, Tabby utilizes the [Hugging Face organization](https://huggingface.co/TabbyML) as its model registry. Mainland Chinese users have encountered challenges accessing Hugging Face for various reasons. The Tabby team has established a mirrored at [modelscope](https://www.modelscope.cn/organization/TabbyML), which can be utilized using the following environment variable:
-
-```bash
-TABBY_REGISTRY=modelscope tabby serve --model TabbyML/StarCoder-1B
-```

website/docs/models/index.mdx

@@ -0,0 +1,18 @@
+---
+sidebar_position: 4
+hide_table_of_contents: true
+---
+
+import GitHubReadme from "./readme";
+
+# 🧑‍🔬 Models Registry
+
+<GitHubReadme src="https://raw.githubusercontent.com/TabbyML/registry-tabby/main/README.md" />
+
+## Model Mirrors
+
+Mainland Chinese users might encounter challenges accessing Hugging Face. For models with mirrored to modelscope, you could download model by utilizing following environment variable:
+
+```bash
+TABBY_DOWNLOAD_HOST=modelscope.cn tabby serve --model TabbyML/StarCoder-1B
+```

website/docs/models/readme.tsx

@@ -0,0 +1,74 @@
+import React, { useState, useEffect } from "react";
+import { marked } from "marked";
+
+const GitHubReadme: React.FC<{
+  src?: string;
+}> = ({
+  src,
+}) => {
+    if (!src) {
+      console.error(
+        "react-github-readme-md: You must provide either a src or username and repo"
+      );
+      return null;
+    }
+
+    const [readmeContent, setReadmeContent] = useState<string>("");
+
+    useEffect(() => {
+      // Function to fetch the README content from GitHub
+      const fetchReadme = async () => {
+        try {
+          let readmeUrl = "";
+
+          if (src) {
+            // Allow passing a URL directly as a prop
+            readmeUrl = src;
+          }
+
+          if (!readmeUrl) {
+            throw new Error("Failed to fetch README path");
+          }
+
+          const response = await fetch(readmeUrl);
+
+          if (!response.ok) {
+            throw new Error("Failed to fetch README");
+          }
+
+          const data = await response.text();
+
+          if (data) {
+            setReadmeContent(data.split("\n").splice(1).join("\n"));
+          }
+        } catch (error) {
+          console.error("react-github-readme-md: ", error);
+        }
+      };
+
+      fetchReadme();
+    }, []);
+
+    if (!readmeContent) {
+      return null;
+    }
+
+    // Parse the markdown content into HTML
+    try {
+      const ghContent = marked.parse(readmeContent);
+      return (
+        <div>
+          <div
+            dangerouslySetInnerHTML={{
+              __html: ghContent,
+            }}
+          />
+        </div>
+      );
+    } catch (error) {
+      console.error("react-github-readme-md: ", error);
+      return null;
+    }
+  };
+
+export default GitHubReadme;

website/package.json

@@ -22,6 +22,7 @@
     "axios": "^1.4.0",
     "clsx": "^1.2.1",
     "docusaurus-preset-openapi": "^0.6.4",
+    "marked": "^9.1.5",
     "postcss": "^8.4.24",
     "posthog-docusaurus": "^2.0.0",
     "prism-react-renderer": "^1.3.5",

website/yarn.lock

@@ -5559,6 +5559,11 @@ marked@2.0.1:
   resolved "https://registry.yarnpkg.com/marked/-/marked-2.0.1.tgz#5e7ed7009bfa5c95182e4eb696f85e948cefcee3"
   integrity sha512-5+/fKgMv2hARmMW7DOpykr2iLhl0NgjyELk5yn92iE7z8Se1IS9n3UsFm86hFXIkvMBmVxki8+ckcpjBeyo/hw==
 
+marked@^9.1.5:
+  version "9.1.5"
+  resolved "https://registry.yarnpkg.com/marked/-/marked-9.1.5.tgz#fcada4702ea64a5c05a4ff0e0639628aac8a1e5f"
+  integrity sha512-14QG3shv8Kg/xc0Yh6TNkMj90wXH9mmldi5941I2OevfJ/FQAFLEwtwU2/FfgSAOMlWHrEukWSGQf8MiVYNG2A==
+
 mdast-squeeze-paragraphs@^4.0.0:
   version "4.0.0"
   resolved "https://registry.yarnpkg.com/mdast-squeeze-paragraphs/-/mdast-squeeze-paragraphs-4.0.0.tgz#7c4c114679c3bee27ef10b58e2e015be79f1ef97"