Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Log In
Sign Up
2264K
/
trimodal-hardcoded-moe-toy
like
0
English
multimodal
mixture-of-experts
transformer
vision
audio
text
jepa
License:
mit
Model card
Files
Files and versions
xet
Community
main
trimodal-hardcoded-moe-toy
Ctrl+K
Ctrl+K
1 contributor
History:
9 commits
2264K
Update model card: add Soft MoE ablation results
fcb4990
verified
about 1 month ago
.gitattributes
Safe
1.52 kB
initial commit
about 1 month ago
README.md
2.88 kB
Update model card: add Soft MoE ablation results
about 1 month ago
best.pt
pickle
Detected Pickle imports (3)
"torch.FloatStorage"
,
"torch._utils._rebuild_tensor_v2"
,
"collections.OrderedDict"
What is a pickle import?
145 MB
xet
Upload best.pt with huggingface_hub
about 1 month ago
config.json
179 Bytes
Upload config.json with huggingface_hub
about 1 month ago
data.py
6.27 kB
Upload data.py with huggingface_hub
about 1 month ago
model.py
7.02 kB
Upload model.py with huggingface_hub
about 1 month ago
train.py
7.37 kB
Upload train.py with huggingface_hub
about 1 month ago
training_log.json
12.2 kB
Upload training_log.json with huggingface_hub
about 1 month ago
