Spaces:

Electro0023
/

Model

Running

App Files Files Community

Model / main.py

Commit History

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

03bbd94

Running
verified

Electro0023 commited on 18 days ago

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

d330add
verified

Electro0023 commited on Jul 18

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

4621b74
verified

Electro0023 commited on Jul 15

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

e9e49b8
verified

Electro0023 commited on Jul 15

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

300bbfa
verified

Electro0023 commited on Jul 14