Downloads · 30 days
5
8% of all-time downloads
keisuke-miyako/gemma-2-2B-it-onnx-int4
gemma-2-2B-it-onnx-int4 is a machine learning model from keisuke-miyako. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
c.f. https://github.com/huggingface/optimum/issues/1755
Downloads · 30 days
5
8% of all-time downloads
All-time downloads
64
Public
Repo size
8 GB
Likes
0
Public
Click a slice to open those files.
.data4 GB · 99%
From the Hugging Face model README
optimum-cli export onnx \
--model google/gemma-2b-it \
--opset 17 \
--framework pt \
~/.onnx/gemma-2b-it-pt
c.f. https://github.com/huggingface/optimum/issues/1755
fail
python -m onnxruntime_genai.models.builder \
-m ~/.onnx/gemma-2b-it-pt \
-o ~/.onnx/gemma-2b-it-onnx-int4-cpu \
-p int4 \
-e cpu
python \
-m onnxruntime_genai.models.builder \
-m google/gemma-2-2b-it \
-p fp16 \
-e cpu \
-o ~/.onnx/gemma-2b-it-onnx-fp16-cpu