Update README.md

README.md

@@ -5,7 +5,7 @@ language:
 
 # Text Classification GoEmotions
 
-This model is a fined-tuned version of [nreimers/MiniLMv2-L6-H384-distilled-from-BERT-Large](https://huggingface.co/nreimers/MiniLMv2-L6-H384-distilled-from-BERT-Large) on the on the [Jigsaw 1st Kaggle competition](https://www.kaggle.com/competitions/jigsaw-toxic-comment-classification-challenge) dataset using [unitary/toxic-bert](https://huggingface.co/unitary/toxic-bert) as teacher model.
+This is a quantized onnx model and is a fined-tuned version of [nreimers/MiniLMv2-L6-H384-distilled-from-BERT-Large](https://huggingface.co/nreimers/MiniLMv2-L6-H384-distilled-from-BERT-Large) on the on the [Jigsaw 1st Kaggle competition](https://www.kaggle.com/competitions/jigsaw-toxic-comment-classification-challenge) dataset using [unitary/toxic-bert](https://huggingface.co/unitary/toxic-bert) as teacher model.
 
 # Load the Model
 
@@ -18,9 +18,9 @@ from tokenizers import Tokenizer
 from onnxruntime import InferenceSession
 
 
-# !git clone https://huggingface.co/Ngit/MiniLM-L6-toxic-all-labels
+# !git clone https://huggingface.co/Ngit/MiniLM-L6-toxic-all-labels-onnx
 
-model_name = "Ngit/MiniLM-L6-toxic-all-labels"
+model_name = "Ngit/MiniLM-L6-toxic-all-labels-onnx"
 tokenizer = Tokenizer.from_pretrained(model_name)
 tokenizer.enable_padding(
     pad_token="<pad>",
@@ -31,7 +31,7 @@ batch_size = 16
 
 texts = ["This is pure trash",]
 outputs = []
-model = InferenceSession("MiniLM-L6-toxic-all-labels-onnx/model_optimized.onnx", providers=['CUDAExecutionProvider'])
+model = InferenceSession("MiniLM-L6-toxic-all-labels-onnx/model_optimized_quantized.onnx", providers=['CUDAExecutionProvider'])
 
 with open(os.path.join("MiniLM-L6-toxic-all-labels-onnx", "config.json"), "r") as f:
             config = json.load(f)