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"