|
Download README.md from michaelktuz/model_206285055_clip_large: direct link, hf CLI and curl.
- Browser
- Download file 768 Bytes
-
https://huggingface.co/michaelktuz/model_206285055_clip_large/resolve/main/README.md
- Command line
-
hf download hf://michaelktuz/model_206285055_clip_large/README.md
-
curl -L -o README.md https://huggingface.co/michaelktuz/model_206285055_clip_large/resolve/main/README.md
768 Bytes
metadata
license: apache-2.0
tags:
- approx-gelu
- clip
- concat-mlp
- flash
- groupnorm
- kaiming-normal
- lamb
- large
- matching
- polynomial
model_206285055_clip_large.py
Model Overview
A large-scale implementation of the clip architecture, built for matching tasks.
Architecture
- Architecture: clip
- Scale: large
- Attention: flash
- Fusion strategy: concat mlp
- Task head: matching
- Activation: approx gelu
- Normalization: groupnorm
- Initialization: kaiming normal
Training
- Optimizer: lamb
- LR scheduler: polynomial
Files
model_206285055_clip_large.py— main artifact of this repository
License
See the license field above.