How to Install and test LLaMA 2 Locally [2023]

In this video we will show you how to install and test the Meta's LLAMA 2 model locally on your machine with easy to follow steps.

#llama2

[daniel]

can I send http requests using api instead of the ui method you provided?

[InspiredDailyStories]

Hi following your guide what is the minimum specs needed to run this.

[skrolreapr]

someone please help. Ive already gotten in to the web page where I can use the model, and download it.

but when I go to download the model, it starts downloading and it will pause at some point, then stay paused perpetually in downloading the model..

ive been trying to download directly through github, but keep running into errors when I try to import the model from there..
idk what to do.

[cahyoonsby]

please help, when run command python server.py
errror like this.
Traceback (most recent call last):
File "C:\Users\pc\text-generation-webui\server.py", line 4, in <module>
from modules import shared
File "C:\Users\pc\text-generation-webui\modules\shared.py", line 8, in <module>
import yaml
ModuleNotFoundError: No module named 'yaml'

(textgeneration)

thx

[gustavm]

When trying to load the model, I get an error saying "AssertionError: Torch not compiled with CUDA enabled" Any idea what that's about?

[nathanameru]

does anyone know a tutorial for running the llm as a function

[evewithaccent]

How can i load the AI without an nvidia gpu

[anthonyhoang]

Is this the Microsoft CEO talking to me??!

[lucas_nardi]

AssertionError: Torch not compiled with CUDA enabled

[ameraai]

Error:
File "C:\Users\Gustavo Teixeira\miniconda3\envs\textgeneration\lib\site-packages\requests\models.py", line 824, in generate


raise RequestsSSLError(e)
requests.exceptions.SSLError: [SSL: decryption failed or bad record mac (_ssl.c:2548)

[briancahill]

When trying to load the model, I get an error saying "AssertionError: Torch not compiled with CUDA enabled" Any idea what that's about?