diff --git a/CHANGELOG.md b/CHANGELOG.md index 5f74cbc..66ae418 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -1,17 +1,25 @@ -# v0.5.0 [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`. +# v0.6.0 [Unreleased] ## 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 -* Switch tokenizer to llama.cpp, so tabby no longer need to download additional tokenizer file: https://github.com/TabbyML/tabby/pull/683 +* Cuda backend is switched to llama.cpp: https://github.com/TabbyML/tabby/pull/656 +* 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 diff --git a/website/docs/models/index.md b/website/docs/models/index.md deleted file mode 100644 index b8ef18b..0000000 --- a/website/docs/models/index.md +++ /dev/null @@ -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 -``` diff --git a/website/docs/models/index.mdx b/website/docs/models/index.mdx new file mode 100644 index 0000000..2927a2c --- /dev/null +++ b/website/docs/models/index.mdx @@ -0,0 +1,18 @@ +--- +sidebar_position: 4 +hide_table_of_contents: true +--- + +import GitHubReadme from "./readme"; + +# 🧑‍🔬 Models Registry + + + +## 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 +``` diff --git a/website/docs/models/readme.tsx b/website/docs/models/readme.tsx new file mode 100644 index 0000000..9344318 --- /dev/null +++ b/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(""); + + 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 ( +
+
+
+ ); + } catch (error) { + console.error("react-github-readme-md: ", error); + return null; + } + }; + +export default GitHubReadme; \ No newline at end of file diff --git a/website/package.json b/website/package.json index 98a32d9..512ff7b 100644 --- a/website/package.json +++ b/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", diff --git a/website/yarn.lock b/website/yarn.lock index afb0073..be2c46d 100644 --- a/website/yarn.lock +++ b/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"