jalr/tabbyAPI-ollama
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
No description
633 commits 1 branch 0 tags 1.4 MiB
Find a file
kingbri 34281c2e14 Start: Add --force-reinstall argument 
Forces a reinstall of dependencies in the event that one is corrupted
or broken.

Signed-off-by: kingbri <bdashore3@proton.me>
2024-08-04 11:14:38 -04:00
.github Issues: Update issue templates 2024-08-03 21:59:02 -04:00
backends Start: Fix pip update, method calls, and logging 2024-08-04 10:30:26 -04:00
colab Colab: Update 2024-03-24 21:48:48 -04:00
common Start: Give the user a hint when a module can't be imported 2024-08-03 21:59:06 -04:00
docker Fix docker compose volume mount 2024-07-12 13:23:58 +00:00
endpoints Config: Embeddings: Make embeddings_device a default when API loading 2024-08-01 13:59:49 -04:00
loras Implement lora support (#24) 2023-12-08 23:38:08 -05:00
models Tree: Update documentation and configs 2023-11-16 02:30:33 -05:00
sampler_overrides Samplers: Add example override for generate_window 2024-05-12 00:39:01 -07:00
templates Templates: Modify alpaca and chatml 2024-03-27 22:28:41 -04:00
tests Tree: Format 2024-03-13 00:02:55 -04:00
update_scripts Start: Make linux scripts executable 2024-08-03 15:19:31 -04:00
.gitignore Update .gitignore 2024-08-03 20:59:28 -04:00
config_sample.yml Config: Embeddings: Make embeddings_device a default when API loading 2024-08-01 13:59:49 -04:00
formatting.bat feat: workflows for formatting/linting (#35) 2023-12-22 16:20:35 +00:00
formatting.sh feat: workflows for formatting/linting (#35) 2023-12-22 16:20:35 +00:00
LICENSE Create LICENSE 2023-11-16 17:43:23 -05:00
main.py Main: Only import psutil when the experimental function is run 2024-08-03 22:00:15 -04:00
pyproject.toml Dependencies: Add Python 3.12 specific dependencies 2024-08-03 17:43:14 -04:00
README.md Update README 2024-08-03 20:58:26 -04:00
start.bat Start: Rewrite start scripts 2024-08-03 13:03:24 -04:00
start.py Start: Add --force-reinstall argument 2024-08-04 11:14:38 -04:00
start.sh Start: Add shell script 2023-12-27 23:53:14 -05:00

README.md

TabbyAPI

Python 3.10, 3.11, and 3.12 License: AGPL v3 Discord Server

Developer facing API documentation

Support on Ko-Fi

Important

In addition to the README, please read the Wiki page for information about getting started!

Note

Need help? Join the Discord Server and get the Tabby role. Please be nice when asking questions.

A FastAPI based application that allows for generating text using an LLM (large language model) using the Exllamav2 backend

TabbyAPI is also the official API backend server for ExllamaV2.

Disclaimer

This project is marked as rolling release. There may be bugs and changes down the line. Please be aware that you might need to reinstall dependencies if needed.

TabbyAPI is a hobby project made for a small amount of users. It is not meant to run on production servers. For that, please look at other solutions that support those workloads.

Getting Started

Important

This README does not have instructions for setting up. Please read the Wiki.

Read the Wiki for more information. It contains user-facing documentation for installation, configuration, sampling, API usage, and so much more.

Features

  • OpenAI compatible API
  • Loading/unloading models
  • HuggingFace model downloading
  • Embedding model support
  • JSON schema + Regex + EBNF support
  • AI Horde support
  • Speculative decoding via draft models
  • Multi-lora with independent scaling (ex. a weight of 0.9)
  • Inbuilt proxy to override client request parameters/samplers
  • Flexible Jinja2 template engine for chat completions that conforms to HuggingFace
  • Concurrent inference with asyncio
  • Utilizes modern python paradigms
  • Continuous batching engine using paged attention
  • Fast classifer-free guidance

And much more. If something is missing here, PR it in!

Supported Model Types

TabbyAPI uses Exllamav2 as a powerful and fast backend for model inference, loading, etc. Therefore, the following types of models are supported:

  • Exl2 (Highly recommended)

  • GPTQ

  • FP16 (using Exllamav2's loader)

In addition, TabbyAPI supports parallel batching using paged attention for Nvidia Ampere GPUs and higher.

Contributing

Use the template when creating issues or pull requests, otherwise the developers may not look at your post.

If you have issues with the project:

  • Describe the issue in detail

  • If you have a feature request, please indicate it as such.

If you have a Pull Request

  • Describe the pull request in detail, what, and why you are changing something

Acknowldgements

TabbyAPI would not exist without the work of other contributors and FOSS projects:

Developers and Permissions

Creators/Developers: