AirLLM how to do inference llm 70b in GPU 4G
How to do Inference with a 70 Billions parameters LLM in a domestic 4 GB GPU
Notebook:
https://github.com/olonok69/LLM_Noteb...
How to do Inference with a 70 Billions parameters LLM in a domestic 4 GB GPU
Notebook:
https://github.com/olonok69/LLM_Noteb...