Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • Docs
  • Enterprise
  • Pricing

  • Log In
  • Sign Up

Spaces:
kshitijthakkar
/
loggenix-moe-0.4B-A0.2B-demo
Sleeping

App Files Files Community
Fetching metadata from the HF Docker repository...
loggenix-moe-0.4B-A0.2B-demo
105 kB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 16 commits
Mandark-droid
Increase Ollama timeouts and add retry logic for reliability
d234c13 2 months ago
  • .gitattributes
    1.56 kB
    Initial setup: Loggenix MoE 0.4B-A0.2B demo space 2 months ago
  • .gitignore
    3.63 kB
    Initial setup: Loggenix MoE 0.4B-A0.2B demo space 2 months ago
  • Dockerfile
    1.37 kB
    Fix Ollama install: use v0.15.2 tar.zst format with zstd extraction 2 months ago
  • README.md
    2.75 kB
    Initial setup: Loggenix MoE 0.4B-A0.2B demo space 2 months ago
  • enhanced_app.py
    61.4 kB
    Set F16 as default quantization, pull both F16 and Q8_0 on startup 2 months ago
  • entrypoint.sh
    1.4 kB
    Set F16 as default quantization, pull both F16 and Q8_0 on startup 2 months ago
  • model_handler.py
    14.8 kB
    Add backend/quantization selection and HF auth for private models 2 months ago
  • model_handler_ollama.py
    17.8 kB
    Increase Ollama timeouts and add retry logic for reliability 2 months ago
  • requirements.txt
    329 Bytes
    Initial setup: Loggenix MoE 0.4B-A0.2B demo space 2 months ago