Update README.md

README.md

@@ -24,9 +24,26 @@ model-index:
 
 # Text Classification GoEmotions
 
-This a onnx quantized model and is fined-tuned version of [nreimers/MiniLMv2-L6-H384-distilled-from-RoBERTa-Large](https://huggingface.co/nreimers/MiniLMv2-L6-H384-distilled-from-RoBERTa-Large) on the on the [go_emotions](https://huggingface.co/datasets/go_emotions) dataset using [tasinho/text-classification-goemotions](https://huggingface.co/tasinhoque/text-classification-goemotions) as teacher model.
+This a ONNX quantized model and is fined-tuned version of [nreimers/MiniLMv2-L6-H384-distilled-from-RoBERTa-Large](https://huggingface.co/nreimers/MiniLMv2-L6-H384-distilled-from-RoBERTa-Large) on the on the [go_emotions](https://huggingface.co/datasets/go_emotions) dataset using [tasinho/text-classification-goemotions](https://huggingface.co/tasinhoque/text-classification-goemotions) as teacher model.
 
-# Load the Model
+# Usage
+
+## Transformers
+
+
+
+
+
+## No-transformers
+
+### Installation
+```bash
+pip install tokenizers
+pip install onnxruntime
+git clone https://huggingface.co/minuva/MiniLMv2-goemotions-v2-onnx
+```
+
+### Load the Model
 
 ```py
 import os
@@ -37,9 +54,8 @@ from tokenizers import Tokenizer
 from onnxruntime import InferenceSession
 
 
-# !git clone https://huggingface.co/Ngit/MiniLMv2-L6-H384-goemotions-v2-onnx
+model_name = "minuva/MiniLMv2-goemotions-v2-onnx"
 
-model_name = "Ngit/MiniLMv2-L6-H384-goemotions-v2-onnx"
 tokenizer = Tokenizer.from_pretrained(model_name)
 tokenizer.enable_padding(
     pad_token="<pad>",
@@ -50,9 +66,9 @@ batch_size = 16
 
 texts = ["I am angry",]
 outputs = []
-model = InferenceSession("MiniLMv2-L6-H384-goemotions-v2-onnx\model_optimized_quantized.onnx", providers=['CUDAExecutionProvider'])
+model = InferenceSession("MiniLMv2-goemotions-v2-onnx/model_optimized_quantized.onnx", providers=['CUDAExecutionProvider'])
 
-with open(os.path.join("MiniLMv2-L6-H384-goemotions-v2-onnx", "config.json"), "r") as f:
+with open(os.path.join("MiniLMv2-goemotions-v2-onnx", "config.json"), "r") as f:
             config = json.load(f)
 
 output_names = [output.name for output in model.get_outputs()]
@@ -62,13 +78,13 @@ 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],
                 ),
             }