Intel
/

t5-small-xsum-int8-dynamic-inc

Text2Text Generation

Intel® Neural Compressor

neural-compressor

PostTrainingDynamic

Inference Endpoints

text-generation-inference

Model card Files Files and versions Community

echarlaix HF staff commited on Mar 21

Commit

2f02c5e

•

1 Parent(s): aea34d3

update loading instructions

Files changed (1) hide show

README.md +4 -4

README.md CHANGED Viewed

@@ -31,8 +31,8 @@ The linear modules **lm.head**, fall back to fp32 for less than 1% relative accu
 ### Load with optimum:
 ```python
-from optimum.intel.neural_compressor.quantization import IncQuantizedModelForSeq2SeqLM
-int8_model = IncQuantizedModelForSeq2SeqLM.from_pretrained(
-    'Intel/t5-small-xsum-int8-dynamic',
-)
 ```

 ### Load with optimum:
 ```python
+from optimum.intel import INCModelForSeq2SeqLM
+model_id = "Intel/t5-small-xsum-int8-dynamic-inc"
+int8_model = INCModelForSeq2SeqLM.from_pretrained(model_id)
 ```