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
AbstractPhil
/
mini-beatrix-2s
Like
0
Text Generation
Safetensors
English
mini-beatrix
byte-level
linear-attention
splat-attention
aleph
custom_code
License:
mit
Model card
Files
Files and versions
xet
Community
Copy to bucket
new
main
mini-beatrix-2s
476 MB
Ctrl+K
Ctrl+K
1 contributor
History:
24 commits
AbstractPhil
load under transformers' remote-code loader: defer the imports it cannot resolve
c4f1fc0
verified
about 15 hours ago
.gitattributes
Safe
1.52 kB
initial commit
24 days ago
README.md
Safe
7.15 kB
README: the softmax twin (endpoint, the claim audit)
19 days ago
TECHNICAL.md
Safe
65.9 kB
TECHNICAL companion for the 2s era (verified code-side + hub-side, 2026-09-04)
19 days ago
address.py
Safe
4.35 kB
mini-beatrix-2s automodel: address.py (mission final 16.101B, alephllm 0.8.6)
24 days ago
alephlm.py
16.5 kB
load under transformers' remote-code loader: defer the imports it cannot resolve
about 15 hours ago
attention.py
Safe
16.6 kB
mini-beatrix-2s automodel: attention.py (mission final 16.101B, alephllm 0.8.6)
24 days ago
bank.py
Safe
2.22 kB
mini-beatrix-2s automodel: bank.py (mission final 16.101B, alephllm 0.8.6)
24 days ago
config.json
Safe
820 Bytes
mini-beatrix-2s automodel: config.json (mission final 16.101B, alephllm 0.8.6)
24 days ago
embedding.py
Safe
1.57 kB
mini-beatrix-2s automodel: embedding.py (mission final 16.101B, alephllm 0.8.6)
24 days ago
governor.py
Safe
6.32 kB
mirror alephllm 0.8.9 (same-session law): presets.py (v3 preset builder + registrations guarded for copies without the data stack; TrainConfig.phase_lr_scale/phase_seed_offset; Preset.data_scale/epoch_cap/rebalance_to), governor.py (raw_block: nested wrappers), alephlm.py (compile_hubs via raw_block). Gated: strict load of model.safetensors through the vendored path, logits parity 0.0 vs geolip.
5 days ago
head.py
Safe
2.16 kB
mini-beatrix-2s automodel: head.py (mission final 16.101B, alephllm 0.8.6)
24 days ago
model.safetensors
Safe
476 MB
xet
mini-beatrix-2s automodel: model.safetensors (mission final 16.101B, alephllm 0.8.6)
24 days ago
modeling_minibeatrix.py
Safe
4.14 kB
mini-beatrix-2s automodel: modeling_minibeatrix.py (mission final 16.101B, alephllm 0.8.6)
24 days ago
presets.py
18 kB
load under transformers' remote-code loader: defer the imports it cannot resolve
about 15 hours ago
relay.py
Safe
6.51 kB
mirror geolip 0.8.8: relay.py docstring cleanup + from_patchwork rename
9 days ago