Intel
/

gpt-neox-japanese-2.7b-int8-inc

Text Generation

neural-compressor

Intel® Neural Compressor

PostTrainingStatic

Model card Files Files and versions Community

echarlaix HF staff commited on Mar 21

Commit

1e61ddd

•

1 Parent(s): 75ed00f

update loading instructions

Files changed (1) hide show

README.md +4 -5

README.md CHANGED Viewed

@@ -53,9 +53,8 @@ The calibration dataloader is the train dataloader. The default calibration samp
 #### Load with Intel® Neural Compressor:
 ```python
-from optimum.intel.neural_compressor.quantization import IncQuantizedModelForCausalLM
-int8_model = IncQuantizedModelForCausalLM.from_pretrained(
-    "Intel/gpt-neox-japanese-2.7b-int8",
-)
-```

 #### Load with Intel® Neural Compressor:
 ```python
+from optimum.intel import INCModelForCausalLM
+model_id = "Intel/gpt-neox-japanese-2.7b-int8"
+int8_model = INCModelForCausalLM.from_pretrained(model_id)
+```