clevaway/j.a.r.v.i.s

Jarvis model: A Fine-tune of llama2, works 100% offline with Ollama

j.a.r.v.i.s's Issues

Does Ollama costs Money?

I don't find anything. :(

Try a different LLM

As people mentioned before LLaMa is very slow due it's huge size... So why don't we try different models for example
"phi3" from microsoft.... in the context of day to day uses llama and phi3 won't have big difference.... but phi3 is lightwieght and is much more quick than llama. It has 3.8B parameters.... If we wan't to make to useable then LLaMa won't be good choice...

try "ollama run phi3"... You will get an idea

no requirements.txt file supplied

this makes installing the correct version difficult especially as modules tend to change their formats or functions around

after many pip install commands. I finally got to this freeze list under Ubuntu 23.10 python 3.11.5

annotated-types==0.6.0
anyio==4.3.0
asttokens==2.4.1
beautifulsoup4==4.12.3
blinker==1.7.0
certifi==2024.2.2
charset-normalizer==3.3.2
click==8.1.7
decorator==4.4.2
elevenlabs==1.1.2
executing==2.0.1
Flask==3.0.3
h11==0.14.0
httpcore==1.0.5
httpx==0.27.0
idna==3.7
imageio==2.34.1
imageio-ffmpeg==0.4.9
ipython==8.23.0
itsdangerous==2.2.0
jedi==0.19.1
Jinja2==3.1.3
MarkupSafe==2.1.5
matplotlib-inline==0.1.7
MouseInfo==0.1.3
moviepy==1.0.3
numpy==1.26.4
parso==0.8.4
pexpect==4.9.0
pillow==10.3.0
proglog==0.1.10
prompt-toolkit==3.0.43
ptyprocess==0.7.0
pure-eval==0.2.2
PyAudio==0.2.14
PyAutoGUI==0.9.54
pydantic==2.7.1
pydantic_core==2.18.2
PyGetWindow==0.0.9
Pygments==2.17.2
PyMsgBox==1.0.9
pyperclip==1.8.2
PyRect==0.2.0
PyScreeze==0.1.30
python-dotenv==1.0.1
python3-xlib==0.15
pytweening==1.2.0
pywhatkit==5.4
requests==2.31.0
six==1.16.0
sniffio==1.3.1
soupsieve==2.5
SpeechRecognition==3.10.3
stack-data==0.6.3
tqdm==4.66.2
traitlets==5.14.3
typing_extensions==4.11.0
urllib3==2.2.1
wcwidth==0.2.13
websockets==12.0
Werkzeug==3.0.2
wikipedia==1.4.0

JARVIS GROQ endpoints Option

Can you modify JARVIS to call GROQ endpoints? For those of us without GPUs GROQ is an incredibly low cost and highspeed option for inference. Even for people with GPUs GROQ can outperform a GPU for inference.

I have an error with elevenlabs.

PS C:\Users...\J.A.R.V.I.S-main\J.A.R.V.I.S-main> python main.py
Traceback (most recent call last):
File "C:\Users...\J.A.R.V.I.S-main\J.A.R.V.I.S-main\main.py", line 8, in
from modules.Interlocus import Interlocus
File "C:\Users...\J.A.R.V.I.S-main\J.A.R.V.I.S-main\modules\Interlocus.py", line 5, in
from elevenlabs import generate, play
ImportError: cannot import name 'generate' from 'elevenlabs' (C:\Users...\elevenlabs_init_.py)

so slow

Why is it so slow

Which Python Version?

Which Python Version?

install steps not clear

ollama run fotiecodes/jarvis runs fine and can chat to jarvis but when calling ollama run jarvis:latest this doesn't work.

$ ollama run jarvis:latest
pulling manifest 
Error: pull model manifest: file does not exist

when running this projects code, it fails finding jarvis:latest

...
You said: what time is it
Time requested
11:13 AM
Saying:  {'error': 'Error 404: {"error":"model \'jarvis:latest\' not found, try pulling it first"}'}

which is strange because this worked fine

$ ollama list
NAME                    	ID          	SIZE  	MODIFIED       
fotiecodes/jarvis:latest	e784ce3e1255	3.8 GB	57 minutes ago	

so it's clearly there, just not finding it.

please add step by step installation and running guide that would help new users to contribute easily thanks