Hugging Face's logo 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

Spaces:
ProjetEngineering
/
coach-equestre-ai
Sleeping

App Files Files Community
Fetching metadata from the HF Docker repository...
coach-equestre-ai
13.7 MB
Ctrl+K
Ctrl+K
  • 4 contributors
History: 42 commits
NassimAI7's picture
NassimAI7
fix: Increase max_new_tokens to 512 for complete responses
d585da8 10 months ago
  • .gitattributes
    1.56 kB
    initial commit 10 months ago
  • .gitignore
    233 Bytes
    Add: RAG System (Phase 1) - Règlements FEI 10 months ago
  • Dockerfile
    1.77 kB
    build: Force Docker rebuild to apply CUDA OOM fixes 10 months ago
  • GEMINI_SETUP.md
    3.28 kB
    feat: Replace keyword classifier with Gemini Flash LLM Router 10 months ago
  • README.md
    201 Bytes
    initial commit 10 months ago
  • adapter_model.safetensors
    13.6 MB
    xet
    Upload adapter_model.safetensors 10 months ago
  • config.py
    3.08 kB
    fix: Increase max_new_tokens to 512 for complete responses 10 months ago
  • main.py
    18.2 kB
    fix: Resolve CUDA OOM and Gemini model name 10 months ago
  • requirements.txt
    925 Bytes
    feat: Replace keyword classifier with Gemini Flash LLM Router 10 months ago