Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
pakphum
/
babylm2026-ipa
like
0
Safetensors
English
Dutch
Chinese
babylm_ipa
causal-lm
babylm
ipa
phonology
custom_code
License:
mit
Model card
Files
Files and versions
xet
Community
Copy to bucket
new
main
babylm2026-ipa
144 MB
Ctrl+K
Ctrl+K
1 contributor
History:
4 commits
pakphum
Fix: truncate inputs to max_seq_len in forward() to prevent RoPE shape mismatch
820fdd2
verified
about 2 months ago
.gitattributes
Safe
1.52 kB
initial commit
about 2 months ago
README.md
Safe
1.53 kB
Upload ipa_full/10M checkpoint (step 2,406)
about 2 months ago
config.json
Safe
509 Bytes
Upload ipa_full/10M checkpoint (step 2,406)
about 2 months ago
config.py
Safe
2.2 kB
Upload ipa_full/10M checkpoint (step 2,406)
about 2 months ago
hf_wrapper.py
Safe
16.7 kB
Fix: truncate inputs to max_seq_len in forward() to prevent RoPE shape mismatch
about 2 months ago
model.py
Safe
25.3 kB
Upload ipa_full/10M checkpoint (step 2,406)
about 2 months ago
model.safetensors
142 MB
xet
Upload ipa_full/10M checkpoint (step 2,406)
about 2 months ago
tokenizer.json
Safe
2.4 MB
Upload ipa_full/10M checkpoint (step 2,406)
about 2 months ago
tokenizer_config.json
Safe
223 Bytes
Upload ipa_full/10M checkpoint (step 2,406)
about 2 months ago
