Upload TFBertForSequenceClassification

README.md

@@ -4,12 +4,6 @@ tags:
 model-index:
 - name: xtremedistil-l6-h256-uncased-nli
   results: []
-datasets:
-- alisawuffles/WANLI
-- snli
-- multi_nli
-- anli
-pipeline_tag: text-classification
 ---
 
 <!-- This model card has been generated automatically according to the information Keras had access to. You should
@@ -17,8 +11,8 @@ probably proofread and complete it, then remove this comment. -->
 
 # xtremedistil-l6-h256-uncased-nli
 
-The model base is [xtremedistil-l6-h256-uncased](https://huggingface.co/microsoft/xtremedistil-l6-h256-uncased).
-It has been fine-tuned on: snli, wanli, mnli, anli
+This model was trained from scratch on an unknown dataset.
+It achieves the following results on the evaluation set:
 
 
 ## Model description
@@ -49,4 +43,5 @@ The following hyperparameters were used during training:
 
 - Transformers 4.31.0
 - TensorFlow 2.12.0
-- Tokenizers 0.13.3
+- Datasets 2.14.4
+- Tokenizers 0.13.3

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d6194e8973e74eb82b2cf424b025b8a84c61b889933a24ecfae294a922f6cf5
+oid sha256:e567ca24afc2498079d5887e4bbc181128eaea99603b4105f613397d1b776076
 size 51152184