Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
eac123
/
ptr-recurrent-depth
Like
2
vanilla-pytorch
ml-intern
research
recurrent-depth
length-generalization
pointer-chasing
arxiv:
10 papers
Model card
Files
Files and versions
xet
Community
Copy to bucket
new
main
ptr-recurrent-depth
58 MB
Ctrl+K
Ctrl+K
1 contributor
History:
159 commits
eac123
Upload results/rec1aligned-long-seed0_eval.json with huggingface_hub
76317ab
verified
about 14 hours ago
ckpts
Upload ckpts/rec1aligned-long-seed0.pt with huggingface_hub
about 14 hours ago
plots
Upload plots/budget_map.png with huggingface_hub
2 days ago
ptr
step_emb sized to K_MAX+2 (aligned evals unroll up to 64)
about 17 hours ago
results
Upload results/rec1aligned-long-seed0_eval.json with huggingface_hub
about 14 hours ago
.gitattributes
1.76 kB
Upload plots/training_curves.png with huggingface_hub
2 days ago
README.md
6.09 kB
final README: results, costs, reproduction
2 days ago
REPORT.md
13.3 kB
Upload REPORT.md with huggingface_hub
2 days ago
evaluate.py
5.01 kB
aligned evals: R=k per cell
about 17 hours ago
job_main.py
Safe
641 Bytes
generic job wrapper
2 days ago
job_runner.py
Safe
580 Bytes
generic stage runner for jobs
2 days ago
make_report.py
43.1 kB
per-k analysis, aligned section, k/R explainer, fixes discussion
about 17 hours ago
run_all.py
7.07 kB
stage4: aligned at 100k steps
about 15 hours ago
smoke_gpu.py
Safe
1.58 kB
GPU smoke wrapper
2 days ago
train.py
8.55 kB
aligned mode: R=k per batch, aligned probes
about 17 hours ago
validate.py
Safe
5.85 kB
architecture validation suite
2 days ago
