Downloads · 30 days
5
5% of all-time downloads
demo-at-wsld-8/blip-at-wsld-fashion200k
blip-at-wsld-fashion200k is a image-text-to-text model from demo-at-wsld-8. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as apache-2.0.
Student model distill từ Salesforce/blip-image-captioning-large (Teacher) sang Salesforce/blip-image-captioning-base đã prune decoder (12 → 4 tầng), train trên Fashion-200k bằng combined loss:
Downloads · 30 days
5
5% of all-time downloads
All-time downloads
95
Public
Parameters
148M
3.9 GB on disk
Likes
0
Public
Click a slice to open those files.
.pth594 MB · 67%
From the Hugging Face model README
Student model distill từ Salesforce/blip-image-captioning-large (Teacher) sang
Salesforce/blip-image-captioning-base đã prune decoder (12 → 4 tầng), train trên
Fashion-200k bằng combined loss:
{ "BLEU-4": 0.2458812827818811, "BLEU-1": 0.6297635645404903, "ROUGE-1": 0.5509984919361472, "ROUGE-2": 0.33081984865850167, "ROUGE-L": 0.4506778285021464, "METEOR": 0.40850410599132086, "CIDEr": 0.6211192626331922 }
from huggingface_hub import hf_hub_download
from transformers import BlipForConditionalGeneration, BlipProcessor
import torch, json
repo_id = "demo-at-wsld-8/blip-at-wsld-fashion200k"
cfg = json.load(open(hf_hub_download(repo_id, "deploy_config.json"), encoding="utf-8"))
ckpt = hf_hub_download(repo_id, "student_at_wsld.pth")
# xem code dung lai kien truc (prune_decoder_layers, fix_decoder_layer_idx) trong app.py cua Space demo
Xem notebook Kaggle: https://www.kaggle.com/code/anhvunguyenquynh/at-wsld