Push Keras model using huggingface_hub.

README.md

@@ -4,50 +4,17 @@ library_name: keras
 
 ## Model description
 
->x100 smaller size vs. DistilBERT with less than 0.5 drop in accuracy evaluated on SST-2 test dataset 
+More information needed
 
-DistilBERT  -  67M  parameters  (92.2 accuracy)  
-DistlBiLSTM -  66K  parameters  (91.7 accuracy)
+## Intended uses & limitations
 
+More information needed
 
-## How to get Started with the model
-
-Example of ruuning prediction and evaluation on SST-2 test dataset
-​​
-
-```python
-import torch
-!pip install setfit  
-
-from datasets import load_dataset  
-import numpy as np  
-from sklearn.metrics import accuracy_score  
-from keras.preprocessing.text import Tokenizer  
-from keras.utils import pad_sequences  
-import tensorflow as tf  
-from huggingface_hub import from_pretrained_keras  
-  
-sst2 = load_dataset("SetFit/sst2")  
-augmented_sst2_dataset = load_dataset("jmamou/augmented-glue-sst2")
-
-tokenizer = Tokenizer(num_words=10000)  
-tokenizer.fit_on_texts(augmented_sst2_dataset['train']['sentence'])  
-test_sequences = tokenizer.texts_to_sequences(sst2['test']['text'])  
-test_padded = pad_sequences(test_sequences, padding='post', truncating='post', maxlen=64)  
-
-reloaded_model = from_pretrained_keras('moshew/distilbilstm-finetuned-sst-2-english')
-
-pred=reloaded_model.predict(test_padded)  
-pred_bin = np.argmax(pred,1)  
-accuracy_score(pred_bin, sst2['test']['label'])
-reloaded_model.summary()
-```
-0.9176276771004942  
+## Training and evaluation data
 
+More information needed
 
 ## Training procedure
- 
-Distillation with data augmentation  
 
 ### Training hyperparameters
 

keras_metadata.pb

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdc9162976c7f360a635a783e3fd4c8532cf10a283749e9f7992205d76f56b73
-size 31190959
+oid sha256:919c45b0d0ee9e0d922c8b4db2ad15746e1c5fe92afd8384a09d9075c43bc24c
+size 31191049

saved_model.pb

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e3ae73b513d680dab07db1b446fd42324270b1acdc3e844994a242ee83b4894
-size 4444324
+oid sha256:05da91ebaaec30e75ef2ea2718c02bef1fab0a671dcd6e8f5e4acd832229ed18
+size 4451217

variables/variables.data-00000-of-00001

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa81ae96adf7a5ffd50d2aa60afe8f3191970558fffb26ab6cb8d1e3679d748e
-size 2644550
+oid sha256:c26dab890f18c809e99d5a807d01325327075265ab409cbc8f8ce4bd0e9043b9
+size 2644586