11-47
/

Nano.Deep.Reasoner.11m-HyperMini

nano_deep_reasoner_hypermini

recurrent-transformer

adaptive-computation

chain-of-thought

adaptive-reasoning

Model card Files Files and versions

Nano.Deep.Reasoner.11m-HyperMini

212 MB

Ctrl+K

Ctrl+K

1 contributor

History: 12 commits

Plans11's picture

RESERVED Session 6 | 200,000 examples | crash-safe reservation

a27bcf6 verified 11 days ago

.gitattributes

1.63 kB
RESERVED Session 4 | 200,000 examples | crash-safe reservation 11 days ago
README.md

1.74 kB
RESERVED Session 6 | 200,000 examples | crash-safe reservation 11 days ago
config.json

1.08 kB
RESERVED Session 1 | 20,000 examples | crash-safe reservation 11 days ago
example_ledger.json

47.5 MB
xet

RESERVED Session 6 | 200,000 examples | crash-safe reservation 11 days ago
model.safetensors

59.7 MB
xet

HyperMini Session 5 complete | 200,000 examples | loss=0.172932 11 days ago
optimizer.pt

88.8 MB
xet

HyperMini Session 5 complete | 200,000 examples | loss=0.172932 11 days ago
rng_state.pt

10.9 kB
xet

HyperMini Session 5 complete | 200,000 examples | loss=0.172932 11 days ago
token_id_manifest.json

701 Bytes
RESERVED Session 1 | 20,000 examples | crash-safe reservation 11 days ago
tokenizer.json

1.07 MB
RESERVED Session 1 | 20,000 examples | crash-safe reservation 11 days ago
tokenizer_config.json

243 Bytes
HyperMini Session 3 complete | 20,000 examples | loss=1.343789 11 days ago
training_state.json

14.8 MB
xet

RESERVED Session 6 | 200,000 examples | crash-safe reservation 11 days ago