|
|
e12a8add61
|
feat: add vLLM models configuration file
Build and Push RunPod Docker Image / build-and-push (push) Successful in 35s
Add models_huggingface_vllm.yaml with three vLLM models:
- Qwen/Qwen2.5-7B-Instruct (14GB) - Advanced multilingual reasoning
- meta-llama/Llama-3.1-8B-Instruct (17GB) - Extended 128K context
- BAAI/bge-large-en-v1.5 (1.3GB) - High-quality text embeddings
Total storage: ~32GB
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
|
2025-11-25 06:12:18 +01:00 |
|
