Giters

armbues / SiLLM

SiLLM simplifies the process of training and running Large Language Models (LLMs) on Apple Silicon by leveraging the MLX framework.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Installation Error

RassKbeer opened this issue · comments

commented

~% conda create -n newenv python=3.11

Using cached protobuf-4.25.3-cp37-abi3-macosx_10_9_universal2.whl (394 kB)
Installing collected packages: protobuf
Attempting uninstall: protobuf
Found existing installation: protobuf 5.26.1
Uninstalling protobuf-5.26.1:
Successfully uninstalled protobuf-5.26.1
ERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.
sillm-mlx 0.1.3 requires protobuf>=5.26.1, but you have protobuf 4.25.3 which is incompatible.

.
.
.

raise ValueError("Please set the environment variable SILLM_MODEL_DIR to the directory containing the models.")
ValueError: Please set the environment variable SILLM_MODEL_DIR to the directory containing the models.

commented

The protobuf version warning during installation shouldn't cause any issues and is unrelated.

The ValueError is not related to the installation but when running the web frontend via app.py. As outlined in the error message, you need to set an environment variable to specify the directory where your models are stored:
export SILLM_MODEL_DIR=/path/to/models