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

nmitchko
/
deepseek-v4-Flash-CoLaR

Text Generation
PyTorch
colar_reasoning_head
colar
reasoning-compression
latent-reasoning
deepseek-v4
chain-of-thought
Model card Files Files and versions
xet
Community
deepseek-v4-Flash-CoLaR / sft-c16
319 MB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 1 commit
nmitchko's picture
nmitchko
Add sft-c16: phase6 Fix-B closed-loop SFT head (c=16, format_version 3)
55889a2 verified 20 days ago
  • colar_head_sft.pt

    Detected Pickle imports (3)

    • "torch._utils._rebuild_tensor_v2",
    • "torch.FloatStorage",
    • "collections.OrderedDict"

    What is a pickle import?

    159 MB
    xet
    Add sft-c16: phase6 Fix-B closed-loop SFT head (c=16, format_version 3) 20 days ago
  • colar_head_sft.safetensors
    159 MB
    xet
    Add sft-c16: phase6 Fix-B closed-loop SFT head (c=16, format_version 3) 20 days ago
  • config.json
    246 Bytes
    Add sft-c16: phase6 Fix-B closed-loop SFT head (c=16, format_version 3) 20 days ago