datasets not found error (mac), LLM config

akash10

Hi all, I am running a small language model pilot using RapidMinder. This is on Macbook. My env throws an error. "datasets not found".  I have installed datasets in conda env. 

Pls see image 1 - the model & 
image 2 - error.  

Conda is installed. datasets folder/ file is available. What I am missing?  Do I need to add anything to the path? if yes - how do I?

thanks,
Akash

RolandJones

Hi @akash10,

A couple of questions to help try and diagnose:

1. Are you able to run any of of the tutorial processes?
2. Which LLM are you using - just to test from my side?
3. Can you display the list of Python packages in your conda environment (I assume called rm_genai)

Best,
Roland

akash10

Hi @rjones13 thanks for getting back to me, really appreciate it.  Please note that I do not have an extensive background in Python. I am a PM lead and trying my hands with no-code AI ML Gen AI tools. 

A1) I can run several tutorials as well as other ML models that I am testing / building. I was trying my 1st lesson with small language model. The SML I am trying is a basic model for translation from Huggingface.

Q2) I am trying Model Helsinki-NLP/opus-mt-en-hi

A3) Package manager condo (anaconda) 

Path, 

bash-3.2$ echo $PATH

/Applications/conda/anaconda3/bin:/Applications/conda/anaconda3/condabin:/usr/local/bin:/System/Cryptexes/App/usr/bin:/usr/bin:/bin:/usr/sbin:/sbin:/var/run/com.apple.security.cryptexd/codex.system/bootstrap/usr/local/bin:/var/run/com.apple.security.cryptexd/codex.system/bootstrap/usr/bin:/var/run/com.apple.security.cryptexd/codex.system/bootstrap/usr/appleinternal/bin

I couldn’t or do not know the command to find env rm_genai and PATH variables. 

When I test rm_genai in Rampidminder, I see below and pic 

Python 3.10.8

Brotli @ file:///Users/runner/miniforge3/conda-bld/brotli-split_1695989934239/work

certifi @ file:///home/conda/feedstock_root/build_artifacts/certifi_1707022139797/work/certifi

charset-normalizer @ file:///home/conda/feedstock_root/build_artifacts/charset-normalizer_1698833585322/work

filelock @ file:///home/conda/feedstock_root/build_artifacts/filelock_1698714947081/work

gmpy2 @ file:///Users/runner/miniforge3/conda-bld/gmpy2_1666808753481/work

idna @ file:///home/conda/feedstock_root/build_artifacts/idna_1701026962277/work

Jinja2 @ file:///home/conda/feedstock_root/build_artifacts/jinja2_1704966972576/work

MarkupSafe @ file:///Users/runner/miniforge3/conda-bld/markupsafe_1706900061465/work

mpmath @ file:///home/conda/feedstock_root/build_artifacts/mpmath_1678228039184/work

networkx @ file:///home/conda/feedstock_root/build_artifacts/networkx_1698504735452/work

numpy @ file:///Users/runner/miniforge3/conda-bld/numpy_1660673193545/work

pandas==1.5.2

Pillow @ file:///Users/runner/miniforge3/conda-bld/pillow_1695247237784/work

PySocks @ file:///home/conda/feedstock_root/build_artifacts/pysocks_1661604839144/work

python-dateutil @ file:///home/conda/feedstock_root/build_artifacts/python-dateutil_1626286286081/work

pytz @ file:///home/conda/feedstock_root/build_artifacts/pytz_1706886791323/work

requests @ file:///home/conda/feedstock_root/build_artifacts/requests_1684774241324/work

six @ file:///home/conda/feedstock_root/build_artifacts/six_1620240208055/work

sympy @ file:///home/conda/feedstock_root/build_artifacts/sympy_1684180540116/work

torch @ file:///Users/runner/miniforge3/conda-bld/pytorch-recipe_1699115985439/work

torchaudio==2.0.0

torchvision @ file:///Users/runner/miniforge3/conda-bld/torchvision-split_1682949189328/work

typing_extensions @ file:///home/conda/feedstock_root/build_artifacts/typing_extensions_1702176139754/work

urllib3 @ file:///home/conda/feedstock_root/build_artifacts/urllib3_1708239446578/work

akash10

rjones13  - I was able to fix the issue.

Issues - Python version was not 3.11.5. I fixed the env, deleted rm_genai env and re-created env. All worked like a charm.

Thanks a ton!