In this video I will show you how to convert a model LLAMA3.2 3Billions to format Openvino IR and quantize it to 4Int. Later we will do inference in CPU using CoT prompts
Notebook:
https://github.com/olonok69/LLM_Notebooks/blob/main/quantization/openvino/llama3.2_3B/llama_3.2_int4.ipynb
