nomic-ai/pygpt4all

6604 illegal hardware instruction

Lionardo opened this issue · 2 comments

I have the issue that I can't run the model inside my virtual env

my code:

from pygpt4all.models.gpt4all_j import GPT4All_J


def new_text_callback(text):
    print(text, end="")


model = GPT4All_J('./models/ggml-gpt4all-j-v1.3-groovy.bin')
model.generate("Once upon a time, ", n_predict=55,
               new_text_callback=new_text_callback)

I have pipenv active and run the script provided in the readme like so

pipenv run python3 gpt4all-j.py

gptj_model_load: loading model from './models/ggml-gpt4all-j-v1.3-groovy.bin' - please wait ...
gptj_model_load: n_vocab = 50400
gptj_model_load: n_ctx   = 2048
gptj_model_load: n_embd  = 4096
gptj_model_load: n_head  = 16
gptj_model_load: n_layer = 28
gptj_model_load: n_rot   = 64
gptj_model_load: f16     = 2
[1]    6604 illegal hardware instruction  pipenv run python3 gpt4all-j.py

Any idea as to how to go about this?

I'm using Mac m1 same

@Lionardo, @Canahmetozguven

I think it is duplicate of #57.
Please take a look at this comment