Hugging Face's logo

Spaces:
Electro0023
/
Model
Sleeping

App Files Community
Model / main.py

Commit History

  1. Enable llama.cpp KV prompt cache (512 MB): ~21% off study-plan time

    Electro0023
    Verified signature
    03bbd94

  1. v2: Alpine base + runtime /admin/load (deepseek defaults + template kept)

    Electro0023
    Verified signature
    d330add

  1. Replace Gradio SmolVLM app with DeepSeek-7B-base GGUF OpenAI-compatible API (Docker)

    Electro0023
    Verified signature
    4621b74

  2. Replace Gradio SmolVLM app with DeepSeek-7B-base GGUF OpenAI-compatible API (Docker)

    Electro0023
    Verified signature
    e9e49b8

  1. Replace Gradio SmolVLM app with DeepSeek-7B-base GGUF OpenAI-compatible API (Docker)

    Electro0023
    Verified signature
    300bbfa