d-matrix/CodeLlama-7b

This is a d-Matrix functional reference of the CODELLAMA-7B model. The reference provides the following functional configurations:

Configuration	Explanation
BASELINE	a reference functionally equivalent to the original model
BASIC	all linear algebraic operands quantized to MXINT8-64, and all other operations transformed to approximated kernel simulations

Usage

Install d-Matrix Dmx_Compressor first.

pip install dmx_compressor

The following is an example model and its evaluation.

git clone https://github.com/bigcode-project/bigcode-evaluation-harness.git
cd bigcode-evaluation-harness
pip install -e .

# code_eval.py included in HuggingFace repo
from code_eval import evaluate_model

eval_results = evaluate_model("d-matrix/CodeLlama-7b", dmx_config="BASELINE")  # For BASELINE configuration