Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Log In
Sign Up
phanerozoic
/
1-parameter-classifier
like
0
Image Classification
PyTorch
detection-datasets/coco
binary-classification
minimal-models
interpretability
vision-transformer
feature-engram
circuit-synthesis
arxiv:
2603.22387
License:
fair-research-license
Model card
Files
Files and versions
xet
Community
main
1-parameter-classifier
/
stage_4b
251 MB
Ctrl+K
Ctrl+K
1 contributor
History:
3 commits
phanerozoic
Stage 4B: ship ep10 checkpoint (peak F1 0.726 vs ep15 0.723)
8266eec
verified
17 days ago
__pycache__
Stage 4B: 15.67M student + cosine loss on 768-D, F1 0.723 (+0.013 over Stage 4)
17 days ago
README.md
2.44 kB
Stage 4B: ship ep10 checkpoint (peak F1 0.726 vs ep15 0.723)
17 days ago
prepare_targets_768.py
Safe
1.68 kB
Stage 4B: 15.67M student + cosine loss on 768-D, F1 0.723 (+0.013 over Stage 4)
17 days ago
student.py
Safe
2.41 kB
Stage 4B: 15.67M student + cosine loss on 768-D, F1 0.723 (+0.013 over Stage 4)
17 days ago
student_ep10.safetensors
62.7 MB
xet
Stage 4B: 15.67M student + cosine loss on 768-D, F1 0.723 (+0.013 over Stage 4)
17 days ago
student_ep15.safetensors
62.7 MB
xet
Stage 4B: 15.67M student + cosine loss on 768-D, F1 0.723 (+0.013 over Stage 4)
17 days ago
student_ep5.safetensors
62.7 MB
xet
Stage 4B: 15.67M student + cosine loss on 768-D, F1 0.723 (+0.013 over Stage 4)
17 days ago
student_final.safetensors
62.7 MB
xet
Stage 4B: ship ep10 checkpoint (peak F1 0.726 vs ep15 0.723)
17 days ago
train.py
Safe
7.15 kB
Stage 4B: 15.67M student + cosine loss on 768-D, F1 0.723 (+0.013 over Stage 4)
17 days ago
training_log.json
Safe
3.08 kB
Stage 4B: 15.67M student + cosine loss on 768-D, F1 0.723 (+0.013 over Stage 4)
17 days ago