Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Log In
Sign Up
gbyuvd
/
Mo2BERTa-v2-proto
like
0
Fill-Mask
English
qwen3
mixture-of-recursions
adaptive-computation
bert
encoder
mlm
research
proof-of-concept
frozen-kv
arxiv:
2507.10524
arxiv:
2305.07759
License:
mit
Model card
Files
Files and versions
xet
Community
main
Mo2BERTa-v2-proto
60.4 MB
Ctrl+K
Ctrl+K
1 contributor
History:
12 commits
gbyuvd
Update README.md
89345ed
verified
18 days ago
checkpoints
Upload 12 files
22 days ago
.gitattributes
Safe
1.81 kB
Upload 12 files
22 days ago
MoRBERT_v2.ipynb
Safe
552 kB
Upload MoRBERT_v2.ipynb
22 days ago
README.md
Safe
21.9 kB
Update README.md
18 days ago
TinyStories-valid.txt
Safe
19.4 MB
xet
Upload 12 files
22 days ago
config.json
Safe
896 Bytes
Dummy Config for Download Tracking
22 days ago
isoflop_triangulation_600t.png
Safe
538 kB
xet
Upload 12 files
22 days ago
routing_frozen_kv_mor_bert_frozenkv_step09787.png
184 kB
xet
Upload 12 files
22 days ago
routing_full_skip_mor_bert_step09787.png
173 kB
xet
Upload 12 files
22 days ago
training_logs_isodepth.json
Safe
72.5 kB
Upload 12 files
22 days ago
training_logs_isoparam.json
Safe
82.7 kB
Upload 12 files
22 days ago
training_logs_mor_bert.json
Safe
240 kB
Upload 12 files
22 days ago
training_logs_mor_bert_frozenkv.json
Safe
240 kB
Upload 12 files
22 days ago
