huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-10 20:04:52 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update README.md

Browse Source 
added mission statement
This commit is contained in:
chris-aeviator 2023-08-27 12:52:48 +02:00 committed by GitHub
parent e605c2a43e
commit 3062fa035d
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 20 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
README.md
View File

@ -1,7 +1,27 @@
## Motivation
This repo aims to make the 🤗 Text Generation Inference more awesome by focussing on real world deployment scenarios that are not purely focussed on a 350M$ funded ecosystem.
TGI is well suited for distributed/ cloud burst/ on-demand workloads, yet HF's focus seems to be (enterprisy) long-running single model endpoints. We are aiming to change that.
![grafik](https://github.com/ohmytofu-ai/tgi-angryface/assets/11522213/65bc5e98-a62a-4c47-8bc2-8831d19880fc)
## Goals
- Support Model loading from wherever you want (HDFS, S3, HTTPS, …)
- Support Adapters (LORA/PEFT) without merging (possibly huge) Checkpoints and uploading them to 🤗
- Reduce operational cost by making TGI-😑 an disposable, hot swapable workhorse
- Get back to a truyl open source license
- Support more core frameworks than HF products
`</endOfMissionStatement>`
<div align="center">
![image](https://github.com/huggingface/text-generation-inference/assets/3841370/38ba1531-ea0d-4851-b31a-a6d4ddc944b0)
----
# Text Generation Inference
<a href="https://github.com/huggingface/text-generation-inference">