Downloads · 30 days
294
0% of all-time downloads
t5-small-xsum-int8-dynamic-inc
Intel/t5-small-xsum-int8-dynamic-inc
t5-small-xsum-int8-dynamic-inc is a machine learning model from Intel. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as apache-2.0.
This is an INT8 PyTorch model quantized with huggingface/optimum-intel through the usage of Intel® Neural Compressor.
All-time downloads
178K
Public
Repo size
162 MB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.bin161 MB · 98%
At a glance
- Library
- transformers
- License
- apache-2.0
- Model type
- t5
- Access
- Public
- Created
- Sep 22, 2022
- Updated
- Mar 21, 2024
- SHA
- 2f02c5e3
Datasets
Model card
From the Hugging Face model README
INT8 T5 small finetuned on XSum
Post-training dynamic quantization
This is an INT8 PyTorch model quantized with huggingface/optimum-intel through the usage of Intel® Neural Compressor.
The original fp32 model comes from the fine-tuned model adasnew/t5-small-xsum.
The linear modules lm.head, fall back to fp32 for less than 1% relative accuracy loss.
Evaluation result
| INT8 | FP32 | |
|---|---|---|
| Accuracy (eval-rouge1) | 29.9008 | 29.9592 |
| Model size | 154M | 242M |
Load with optimum:
from optimum.intel import INCModelForSeq2SeqLM
model_id = "Intel/t5-small-xsum-int8-dynamic-inc"
int8_model = INCModelForSeq2SeqLM.from_pretrained(model_id)
- Library
- transformers
- Type
- t5
- License
- apache-2.0
- Created
- Sep 22, 2022
- Updated
- Mar 21, 2024