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

alexz949
/
BasisServe-CALS

Text Generation
basisserve
low-rank-compression
kv-cache-compression
tensor-parallelism
palu
c1
global-kl
Model card Files Files and versions
xet
Community
BasisServe-CALS / checkpoints
Ctrl+K
Ctrl+K
  • 1 contributor
History: 64 commits
alexz949's picture
alexz949
Add checkpoints/attention_c1/llama31_8b_instruct_uniform_v96_128k_als6_retrievalmix/kvquant_nuq4_B (FP8 / KVQuant NUQ4 KV-cache arms, 2026-09-25)
7ca92f4 verified 25 days ago
  • attention_c1
    Add checkpoints/attention_c1/llama31_8b_instruct_uniform_v96_128k_als6_retrievalmix/kvquant_nuq4_B (FP8 / KVQuant NUQ4 KV-cache arms, 2026-09-25) 25 days ago
  • k_routing
    Add Llama-3.1-8B-Instruct V96-fitted B16R16 router and RULER provenance 30 days ago
  • kq_svd
    Publish BasisServe-CALS checkpoint collection (part 2) about 2 months ago
  • mlp_c1
    Publish BasisServe-CALS checkpoint collection (part 2) about 2 months ago
  • palu
    Publish BasisServe-CALS checkpoint collection (part 2) about 2 months ago
  • qwen3-32b-128k
    Upload folder using huggingface_hub about 1 month ago
  • qwen3-32b-64k
    Add 128K RULER artifact: checkpoints/qwen3-32b-64k/identity 27 days ago
  • qwen35-9b-128k
    Add checkpoints/qwen35-9b-128k/recal-mix48/loki_pca32_pre_rope (Qwen3.5 recal-mix48 baselines + LongBench Loki arms, 2026-09-25) 26 days ago