Update README.md

README.md

@@ -48,12 +48,15 @@ as well as the English [MNLI dataset](https://huggingface.co/datasets/multi_nli)
 The main advantage of distilled models is that they are smaller (faster inference, lower memory requirements) than their teachers (XLM-RoBERTa-large).
 The disadvantage is that they lose some of the performance of their larger teachers. 
 
+For highest inference speed, I recommend using the [6-layer model](https://huggingface.co/MoritzLaurer/multilingual-MiniLMv2-L6-mnli-xnli)
+(the model on this page has 12 layers and is slower). For higher performance I recommend 
+[mDeBERTa-v3-base-mnli-xnli](https://huggingface.co/MoritzLaurer/mDeBERTa-v3-base-mnli-xnli) (as of 14.02.2023).
 
 ### How to use the model
 #### Simple zero-shot classification pipeline
 ```python
 from transformers import pipeline
-classifier = pipeline("zero-shot-classification", model="MoritzLaurer/xlm-v-base-mnli-xnli")
+classifier = pipeline("zero-shot-classification", model="MoritzLaurer/multilingual-MiniLMv2-L12-mnli-xnli")
 
 sequence_to_classify = "Angela Merkel ist eine Politikerin in Deutschland und Vorsitzende der CDU"
 candidate_labels = ["politics", "economy", "entertainment", "environment"]
@@ -66,7 +69,7 @@ from transformers import AutoTokenizer, AutoModelForSequenceClassification
 import torch
 device = torch.device("cuda") if torch.cuda.is_available() else torch.device("cpu")
 
-model_name = "MoritzLaurer/xlm-v-base-mnli-xnli"
+model_name = "MoritzLaurer/multilingual-MiniLMv2-L12-mnli-xnli"
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 model = AutoModelForSequenceClassification.from_pretrained(model_name)
 
@@ -94,6 +97,7 @@ and significantly reduces training costs.
 
 ### Training procedure
 The model was trained using the Hugging Face trainer with the following hyperparameters.
+The exact underlying model is [mMiniLMv2-L12-H384-distilled-from-XLMR-Large](https://huggingface.co/nreimers/mMiniLMv2-L12-H384-distilled-from-XLMR-Large).
 ```
 training_args = TrainingArguments(
     num_train_epochs=3,              # total number of training epochs
@@ -121,12 +125,12 @@ XLM-RoBERTa-large instead of -base (multilingual-MiniLM-L6-v2).
 |Datasets|avg_xnli|ar|bg|de|el|en|es|fr|hi|ru|sw|th|tr|ur|vi|zh|
 | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: |
 |Accuracy|0.75|0.73|0.78|0.762|0.754|0.821|0.779|0.775|0.724|0.76|0.689|0.738|0.732|0.7|0.762|0.751|
-|Speed (text/sec)|4535.0|4629.0|4417.0|4500.0|3938.0|4959.0|4634.0|4152.0|4190.0|4368.0|4630.0|4698.0|4929.0|4291.0|4420.0|5275.0|
+|Speed text/sec (A100 GPU, eval_batch=120)|4535.0|4629.0|4417.0|4500.0|3938.0|4959.0|4634.0|4152.0|4190.0|4368.0|4630.0|4698.0|4929.0|4291.0|4420.0|5275.0|
 
 |Datasets|mnli_m|mnli_mm|
 | :---: | :---: | :---: |
 |Accuracy|0.818|0.831|
-|Speed (text/sec)|2912.0|2902.0|
+|Speed text/sec (A100 GPU, eval_batch=120)|2912.0|2902.0|