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
4AshishKmr
/
pragnosia
like
0
Text Generation
PyTorch
English
ssm
recurrent
hybrid
long-context
grow-as-you-train
custom-architecture
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Copy to bucket
new
main
pragnosia
20.9 GB
Ctrl+K
Ctrl+K
1 contributor
History:
55 commits
4AshishKmr
update README.md (33tp milestone -> latest; SFT pipeline)
cc0b272
verified
1 day ago
data
add data/bpe.json
7 days ago
weights
update weights/spin_1022M_latest_state.json (33tp milestone -> latest; SFT pipeline)
1 day ago
.gitattributes
1.58 kB
add Pragnosia_paper.pdf
7 days ago
Pragnosia_paper.pdf
163 kB
xet
update Pragnosia_paper.pdf (token-matched control, self-directed goals, refreshed paper)
7 days ago
README.md
6.91 kB
update README.md (33tp milestone -> latest; SFT pipeline)
1 day ago
ablation_results.json
1.15 kB
add ablation_results.json
7 days ago
ablation_sweep.py
4.02 kB
add ablation_sweep.py
7 days ago
brain.py
90.2 kB
update brain.py (latest 1B = weighted-W, re-flipped long-context; LONG_W_WEIGHTS)
6 days ago
compare_results.json
1.16 kB
update compare_results.json (token-matched control, self-directed goals, refreshed paper)
7 days ago
eval_compare.py
4.69 kB
add eval_compare.py
7 days ago
eval_external.py
5.91 kB
add eval_external.py
7 days ago
faculty_test.py
7.65 kB
add faculty_test.py
7 days ago
grow.py
8.06 kB
add grow.py
7 days ago
identity_sentences.txt
4.69 kB
add identity_sentences.txt
7 days ago
lc_watch.py
2.64 kB
add lc_watch.py
7 days ago
learning_curve.py
2.5 kB
add learning_curve.py
7 days ago
learning_curves.json
3.06 kB
add learning_curves.json
7 days ago
pragnosia_284m.json
247 Bytes
add pragnosia_284m.json
7 days ago
pragnosia_565m.json
248 Bytes
add pragnosia_565m.json
7 days ago
pragnosia_baseline.json
243 Bytes
add pragnosia_baseline.json
7 days ago
pragnosia_self.txt
8.36 kB
update pragnosia_self.txt (latest 1B = weighted-W, re-flipped long-context; LONG_W_WEIGHTS)
6 days ago
prepare_posttrain.py
9.99 kB
update prepare_posttrain.py (33tp milestone -> latest; SFT pipeline)
1 day ago
prepare_sft.py
5.68 kB
update prepare_sft.py (33tp milestone -> latest; SFT pipeline)
1 day ago
run_fast.py
1.3 kB
add run_fast.py
7 days ago
s6_hybrid.py
28.1 kB
update s6_hybrid.py (latest 1B = weighted-W, re-flipped long-context; LONG_W_WEIGHTS)
6 days ago
train_pragnosia.py
33.1 kB
update train_pragnosia.py (latest 1B = weighted-W, re-flipped long-context; LONG_W_WEIGHTS)
6 days ago