pip install missing dependencies

[VincyZhang]

When I use pip install intel-extension-for-transformers in a fresh conda environment, there are some packages missing that I have to manually install before I can run a model.

Please add these to setup.py as deps!

• accelerate
• neural-speed
• gguf
• there may be others, I installed some other things before I started writing these down

To reproduce, simply:

• conda create -n itrex python=3.9
• pip install intel-extension-for-transformers
• Run the following 3-line python script:

from intel_extension_for_transformers.transformers import AutoModelForCausalLM

model_name = "meta-llama/Llama-2-7b-hf"

model = AutoModelForCausalLM.from_pretrained(model_name, load_in_4bit=True)

[NeuralChatBot]

To add the required dependencies to setup.py, you can include the following lines:

# Add the required dependencies to setup.py as deps
deps = [
    "accelerate",
    "neural-speed",
    "gguf",
    # Add any other missing packages here
]

Now, when you create a new conda environment and install intel-extension-for-transformers, these dependencies will be automatically installed along with it. If you need help, please @NeuralChatBot

[VincyZhang]

This requirements need to be installed before running an model, intel-extension-for-transformers/requirements.txt at main · intel/intel-extension-for-transformers (github.com) Usually we suggest install dependency before running example. But I notice some just want to try our quick sample in Readme, and find out some dependencies are missing.

[VincyZhang]

@NeuralChatBot

[NeuralChatBot]

To address this issue, you can consider adding the missing dependencies to the requirements.txt file in the intel-extension-for-transformers repository. This will ensure that anyone who clones the repository and runs the examples will have all the necessary dependencies installed.