Flamingo for Classification
Overview
This repository is a compact, custom PyTorch implementation of Flamingo for Classification. The tiny configuration is intended for code review, smoke tests, and small controlled experiments rather than as a production-ready pretrained release.
Comments and corrections can be left in the discussion tab.
Limitations
- weights are random-init, so outputs carry no signal
- robustness, fairness and domain transfer are untested
- the API may change without notice while the design settles
Quick Check
Run python train.py --help for the built-in smoke test. Because this is a custom implementation, generic automatic loading APIs require an explicit adapter before use.
Training Details
- Weights initialized with a orthogonal scheme.
- Runs on a single consumer GPU.
- Full smoke test takes minutes, not hours.
- No distributed setup required.
Repository Status
One Python module contains the model and a runnable example.
Generated configuration lives in config.json; the recipe in training_args.json.
The checkpoint is an initialization artifact and should not be read as a trained model.
Scores are deliberately absent.
Default Experiment Recipe
The included configuration uses lion with a exponential schedule. These are starting values in the script, not evidence of a completed run. For a meaningful evaluation, train all baselines with the same data exposure, tuning budget, and random seeds.
Architecture
- Architecture: Flamingo
- Scale: tiny
- Attention: grouped query
- Fusion: tensor fusion
- Activation: approx gelu
- Normalization: rmsnorm
Files
| File | Purpose |
|---|---|
train.py |
primary artifact |
README.md |
this documentation |
config.json |
architecture configuration |
training_args.json |
default experiment settings |
model.safetensors |
initialization checkpoint |
NOTES.md |
informal to-do notes |
License
Released under bsd-3-clause. Review the source-data terms separately when this repository is used with external datasets.
- Downloads last month
- -