Hugging Face's logo 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
/
alephllm-nano-beatrix-training

TensorBoard
Safetensors
English
aleph
byte-level
mixture-of-experts
linear-attention
research-log
nano
Model card Files Files and versions
xet
Metrics Training metrics Community
alephllm-nano-beatrix-training / bed
19.8 GB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 1,125 commits
AbstractPhil's picture
AbstractPhil
curriculum: CURRICULUM_bed_adamw_bodies-splat.md
7acd1b9 verified 6 days ago
  • curriculum
    curriculum: CURRICULUM_bed_adamw_bodies-splat.md 6 days ago
  • preflight
    bed AdamW re-run frames-registers: push probe 6 days ago
  • reports
    bed: d5s1-both_s2_L4000_wd0.1_ctx4096_frdyn_cap_mode_sized_sl32_sz32-128-256-512-1024_r4_n30_o0_askany_p75_stanneal1 record 6 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 8 days ago
  • weights
    bed: d5s1-both_s2_L4000_wd0.1_ctx4096_frdyn_cap_mode_sized_sl32_sz32-128-256-512-1024_r4_n30_o0_askany_p75_stanneal1 weights 6 days ago
  • manifest.json
    307 kB
    nano bed, the first night (2026-10-12): the card, the licences, the manifest, the run records, the results index 8 days ago