https://github.com/dnth/bentoml-model-chaining
Chain multiple models together using BentoML. Run inference with an API endpoint. Deploy anywhere Docker runs.
https://github.com/dnth/bentoml-model-chaining
Last synced: about 1 year ago
JSON representation
Chain multiple models together using BentoML. Run inference with an API endpoint. Deploy anywhere Docker runs.
- Host: GitHub
- URL: https://github.com/dnth/bentoml-model-chaining
- Owner: dnth
- License: apache-2.0
- Created: 2024-08-21T03:38:50.000Z (almost 2 years ago)
- Default Branch: main
- Last Pushed: 2024-10-21T08:45:16.000Z (over 1 year ago)
- Last Synced: 2025-06-14T13:46:10.513Z (about 1 year ago)
- Language: Python
- Homepage:
- Size: 6.46 MB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# bentoml-model-chaining
Chain multiple models together using BentoML. Deploy anywhere Docker runs.
## Object Detector
Models:
- YOLOv8
```bash
cd yolo/
bentoml serve .
```
## Image Captioner
Models:
- BLIP2
```bash
cd blip2
bentoml serve .
```
## Image Tagger
Models:
- RAM
- RAM++
```bash
cd ram
bentoml serve .
```
## Image Classification
Models:
- ResNet50
## Optical Character Recognition
Models:
- EasyOCR
## Compute Embeddings
Models:
- CLIP
- Sentence Transformers
## Zero-shot Classification
Models:
- CLIP
## Zero-shot Detection
Models:
- Grounding DINO
- OWLv2
```bash
cd owlv2
bentoml serve .
```
## Zero-shot Segmentation
Models:
- SAM
- SAM2
## Run Pipeline
Consists of running Image Tagger/Captioner -> Zero-shot Detection -> Segmentation
## Build and Push to Deploy
Build images and deploy to cloud.