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

Spaces:
aliceberthale
/
complai
Runtime error

App Files Files Community
Fetching metadata from the HF Docker repository...
complai / serving
22.1 kB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 3 commits
aliceberthale's picture
aliceberthale
Fix #1: retrieval-grounded confidence calibration (honest fit, LOO-CV) + 3-guard review gate + grounding floor; in-scope answers now read ~85%
6999dbb 2 months ago
  • README.md
    3.88 kB
    Add Python serving layer: backend-agnostic (la Plateforme/vLLM/MLX), token-aware chunking via mistral-common 2 months ago
  • app.py
    6.25 kB
    Fix #1: retrieval-grounded confidence calibration (honest fit, LOO-CV) + 3-guard review gate + grounding floor; in-scope answers now read ~85% 2 months ago
  • inference.py
    5.17 kB
    Add Python serving layer: backend-agnostic (la Plateforme/vLLM/MLX), token-aware chunking via mistral-common 2 months ago
  • rag.py
    4.66 kB
    Fix #1: retrieval-grounded confidence calibration (honest fit, LOO-CV) + 3-guard review gate + grounding floor; in-scope answers now read ~85% 2 months ago
  • requirements.txt
    199 Bytes
    Add Python serving layer: backend-agnostic (la Plateforme/vLLM/MLX), token-aware chunking via mistral-common 2 months ago
  • serve_local_mac.sh
    769 Bytes
    Add Python serving layer: backend-agnostic (la Plateforme/vLLM/MLX), token-aware chunking via mistral-common 2 months ago
  • serve_vllm.sh
    1.13 kB
    Add Python serving layer: backend-agnostic (la Plateforme/vLLM/MLX), token-aware chunking via mistral-common 2 months ago