Update README.md

README.md

@@ -6,8 +6,21 @@ language:
 # Text Classification GoEmotions
 
 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.
+The original model can be found [here](https://huggingface.co/minuva/MiniLMv2-toxic-jijgsaw)
 
-# Load the Model
+
+# Usage
+
+## Installation
+
+```bash
+pip install tokenizers
+pip install onnxruntime
+git clone https://huggingface.co/minuva/MiniLMv2-toxic-jijgsaw-onnx
+```
+
+
+## Load the Model
 
 ```py
 import os
@@ -18,9 +31,7 @@ from tokenizers import Tokenizer
 from onnxruntime import InferenceSession
 
 
-# !git clone https://huggingface.co/Ngit/MiniLM-L6-toxic-all-labels-onnx
-
-model_name = "Ngit/MiniLM-L6-toxic-all-labels-onnx"
+model_name = "minuva/MiniLMv2-toxic-jijgsaw-onnx"
 tokenizer = Tokenizer.from_pretrained(model_name)
 tokenizer.enable_padding(
     pad_token="<pad>",
@@ -31,9 +42,9 @@ batch_size = 16
 
 texts = ["This is pure trash",]
 outputs = []
-model = InferenceSession("MiniLM-L6-toxic-all-labels-onnx/model_optimized_quantized.onnx", providers=['CUDAExecutionProvider'])
+model = InferenceSession("MiniLMv2-toxic-jijgsaw-onnx/model_optimized_quantized.onnx", providers=['CUDAExecutionProvider'])
 
-with open(os.path.join("MiniLM-L6-toxic-all-labels-onnx", "config.json"), "r") as f:
+with open(os.path.join("MiniLMv2-toxic-jijgsaw-onnx", "config.json"), "r") as f:
             config = json.load(f)
 
 output_names = [output.name for output in model.get_outputs()]
@@ -43,13 +54,13 @@ for subtexts in np.array_split(np.array(texts), len(texts) // batch_size + 1):
             encodings = tokenizer.encode_batch(list(subtexts))
             inputs = {
                 "input_ids": np.vstack(
-                    [encoding.ids for encoding in encodings], dtype=np.int64
+                    [encoding.ids for encoding in encodings],
                 ),
                 "attention_mask": np.vstack(
-                    [encoding.attention_mask for encoding in encodings], dtype=np.int64
+                    [encoding.attention_mask for encoding in encodings],
                 ),
                 "token_type_ids": np.vstack(
-                    [encoding.type_ids for encoding in encodings], dtype=np.int64
+                    [encoding.type_ids for encoding in encodings],
                 ),
             }
 
@@ -77,7 +88,15 @@ for item in scores:
         scores.append(float(s))
     results.append({"labels": labels, "scores": scores})
 
-results
+res = []
+
+for result in results:
+    joined = list(zip(result['labels'], result['scores']))
+    max_score = max(joined, key=lambda x: x[1])    
+    res.append(max_score)
+
+res
+# [('toxic', 0.736885666847229)]
 ```
 
 # Training hyperparameters
@@ -96,7 +115,7 @@ The following hyperparameters were used during training:
 
 | Teacher (params)    |   Student (params)     | Set  (metric)     | Score (teacher)    |    Score (student)      |
 |--------------------|-------------|----------|--------| --------|
-| unitary/toxic-bert (110M) |  MiniLMv2-L6-H384-goemotions-v2-onnx (23M)  | Test (ROC_AUC)  | 0.98636 |  0.98130 |
+| unitary/toxic-bert (110M) |  MiniLMv2-toxic-jijgsaw-onnx (23M)  | Test (ROC_AUC)  | 0.98636 |  0.98130 |
 
 # Deployment