ollama / server.py

Commit History

Switch to Gemma 2B - better warm-up
f898b17

Mohammedded commited on

Add retry logic and longer timeout
965ff86

Mohammedded commited on

Switch to HF Inference API - no compilation needed
0f61856

Mohammedded commited on

Fix: lazy import, simpler build
3695f6f

Mohammedded commited on

Switch to Qwen 1.5B - faster build, Arabic support
f3d11f2

Mohammedded commited on

Mistral 7B with GPU support
8e6569c

Mohammedded commited on

Add Mistral 7B LLM server
b2cea61

Mohammedded commited on