metadata
language:
- en
tags:
- pytorch
- causal-lm
license: apache-2.0
datasets:
- EleutherAI/pile
This is a d-Matrix functional reference of the GPTJ-6B 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 BFP16-64, and all other operations transformed to approximated kernel simulations |
Usage
Install d-Matrix ML Tools first.
pip install dmx-mltools
The following is an example model and its evaluation.
from mltools.dmx import pipeline
pipe = pipeline(
task="text-generation",
model="d-matrix/gpt-j-6b",
dmx_config="BASELINE", # see above for other variants
trust_remote_code=True,
# device_map="auto", # enabling model parallel on multi-GPU nodes
)
results = pipe.evaluate(metric=["d-matrix/perplexity", "d-matrix/accuracy"], dataset="LAMBADA")