jalr/tabbyAPI-ollama
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
No description
327 commits 1 branch 0 tags 1.4 MiB
Find a file
kingbri d45e847c7a API: Fix disconnect handling on streaming responses 
Starlette's StreamingResponse has an issue where it yields after
a request has disconnected. A bugfix to starlette will fix this
issue, but FastAPI uses starlette <= 0.36 which isn't ideal.

Therefore, switch back to sse-starlette which handles these disconnects
correctly.

Also don't try yielding after the request is disconnected. Just return
out of the generator instead.

Signed-off-by: kingbri <bdashore3@proton.me>
2024-03-10 17:43:13 -04:00
.github Create pull request template 2024-02-09 14:53:29 -05:00
backends/exllamav2 Logging: Switch to loguru 2024-03-08 01:00:48 -05:00
colab Tree: Refactor code organization 2024-01-25 00:15:40 -05:00
common API: Fix disconnect handling on streaming responses 2024-03-10 17:43:13 -04:00
docker Remove explicit pytorch & exllamav2 in Dockerfile 2024-02-25 18:03:01 +01:00
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
OAI Tree: Format 2024-03-08 01:00:48 -05:00
sampler_overrides Neutralize samplers (#59) 2024-02-08 00:23:09 -05:00
templates Templates: Update folder 2023-12-18 23:53:47 -05:00
tests Tree: Refactor code organization 2024-01-25 00:15:40 -05:00
.gitignore Tree: Unify sampler parameters and add override support 2024-01-25 00:15:40 -05:00
.ruff.toml feat: workflows for formatting/linting (#35) 2023-12-22 16:20:35 +00:00
config_sample.yml Additional clarification for override_base_seq_len 2024-03-02 09:29:50 -08:00
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 API: Fix disconnect handling on streaming responses 2024-03-10 17:43:13 -04:00
README.md Update README 2024-02-20 00:19:31 -05:00
requirements-amd.txt Requirements: Pin uvicorn 2024-03-10 01:23:36 -05:00
requirements-cu118.txt Requirements: Pin uvicorn 2024-03-10 01:23:36 -05:00
requirements-dev.txt feat: workflows for formatting/linting (#35) 2023-12-22 16:20:35 +00:00
requirements-nowheel.txt Requirements: Pin uvicorn 2024-03-10 01:23:36 -05:00
requirements.txt Requirements: Pin uvicorn 2024-03-10 01:23:36 -05:00
start.bat Tree: Format and cleanup start 2023-12-27 01:17:31 -05:00
start.py Tree: Refactor code organization 2024-01-25 00:15:40 -05:00
start.sh Start: Add shell script 2023-12-27 23:53:14 -05:00

README.md

TabbyAPI

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

Disclaimer

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

Getting Started

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

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)

Alternative Loaders/Backends

If you want to use a different model type than the ones listed above, here are some alternative backends with their own APIs:

Contributing

If you have issues with the project:

  • Describe the issues 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

Developers and Permissions

Creators/Developers: