Hugging Face
Models
Datasets
Spaces
Buckets
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
/
alephllm-nano-beatrix-training
Like
1
TensorBoard
Safetensors
English
aleph
byte-level
mixture-of-experts
linear-attention
research-log
nano
License:
cc-by-nc-sa-4.0
Model card
Files
Files and versions
xet
Metrics
Training metrics
Community
Copy to bucket
main
alephllm-nano-beatrix-training
/
bed
26.9 GB
Ctrl+K
Ctrl+K
1 contributor
History:
1,709 commits
AbstractPhil
nano capacity r16: alhena-both_s6_L24000_ctx4096_frdyn_cap_mode_sz32-128-256-512_r4_n30_o0_askany_gag50_cp4_g
ffae83b
verified
about 23 hours ago
curriculum
curriculum: CURRICULUM_bed_adamw_bodies-splat.md
12 days ago
preflight
nano capacity r16: lane2 claims L16R s6
about 23 hours ago
reports
nano capacity r16: alhena-both_s6_L24000_ctx4096_frdyn_cap_mode_sz32-128-256-512_r4_n30_o0_askany_gag50_cp4_g
about 23 hours ago
scale_members
scale members: alhena-both_s4_L24000_ctx4096_frdyn_cap_mode_sz32-128-256-512_r4_n30_o0_askany_gag50_cp4_gc48_kh50_va1_pt10b4h0_krt_ahdigit1_largerows_members_l16000_m32000
2 days ago
screens
screen: rows a step at 1,024, castor-both_s2_L12000_frdyn_cap_mode_sz32-128-256_r8_n30_o0_askany_p75 mb32 weights
14 days ago
weights
bed: alhena-both_s6_L24000_ctx4096_frdyn_cap_mode_sz32-128-256-512_r4_n30_o0_askany_gag50_cp4_gc48_kh50_va1_pt10b4h0_krt16r218_ahdigit1_rec16 weights
about 23 hours ago
manifest.json
Safe
307 kB
nano bed, the first night (2026-10-12): the card, the licences, the manifest, the run records, the results index
14 days ago