model-index

model-index
name results llama3-8b task dataset metrics type text-generation name type Wikitext wikitext type value perplexity (BASELINE) 7.259655927392236 type value perplexity (BASIC) 109.31862113631051

This is a d-Matrix functional reference of the LLAMA3-8B 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

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/EleutherAI/lm-evaluation-harness
cd lm-evaluation-harness
pip install -e .

from dmx.compressor.modeling import DmxModel
import lm_eval
from lm_eval.models.huggingface import HFLM

lm_eval.api.registry.register_model("hf", HFLM)
model_args = "pretrained=d-matrix/Llama3-8b,trust_remote_code=True"

lm = lm_eval.api.registry.get_model("hf").create_from_arg_string(model_args, {"batch_size": 1})

# Transform the model with DMX
lm._model = DmxModel.from_torch(lm._model)

eval_results = lm_eval.evaluate(lm, lm_eval.tasks.get_task_dict(["wikitext"]))  # Assign desired task, i.e. "wikitext"