Spaces:
Runtime error
Runtime error
Commit History
-
v5: Minimal lazy-loading architecture for instant startup
MiniMax Agent- Remove ALL heavy imports from module level (torch, transformers) - Use background thread to load model after server starts - Server responds immediately to health checks - API returns 503 if model is still loading - Fixes 30-minute timeout issue on Hugging Face Spacesee3c612 -
Update Dockerfile to use app_v4 with background model loading
MiniMax Agent7ae4b71 -
Add v4 with background model loading - prevents timeout by loading model after server starts
MiniMax Agent44ffe48 -
Add complete local Ollama setup with OpenELM - includes setup script, API server, test scripts, and documentation
MiniMax Agent41831f1 -
Fix tokenizer issues: add sentencepiece dependency and robust loading strategy
MiniMax Agentd36a46f -
Implement lazy loading - model loads on first request to avoid startup timeouts
MiniMax Agent2aeb5c7 -
Fix OpenELM tokenizer loading - use LlamaTokenizer as fallback
MiniMax Agent3daef91 -
Add OpenAI API compatible endpoints for OpenELM models
MiniMax Agentc126015 -
Add Anthropic API compatible wrapper for OpenELM models
MiniMax Agent9604400 -
Add application files
MiniMax Agent91bc5ae -
initial commit
Verified signature46c654e