Hacker News Reader

I tried this on my M2 Macbook with 16gb of RAM but got:

"ggml_new_tensor_impl: not enough space in the context's memory pool (needed 18296202768, available 18217606000)"

Anyone got it working on an M1 with 8gb?

I got it working on an M1 with 16gb. Quite slow but it trains and returns responses.

What did you do to make it work? I'm getting an illegal hardware instruction when I try to run python privateGPT.py

Using embedded DuckDB with persistence: data will be stored in: db [1] 8281 illegal hardware instruction python privateGPT.py