Update README.md

README.md

@@ -5,14 +5,18 @@ tags:
 - feature-extraction
 - sentence-similarity
 - transformers
-
+license: apache-2.0
+datasets:
+- shunk031/jsnli
+language:
+- ja
 ---
 
-# {MODEL_NAME}
+# sbert-jsnli-luke-japanese-base-lite
 
 This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
 
-<!--- Describe your model here -->
+The base model is [studio-ousia/luke-japanese-base-lite](studio-ousia/luke-japanese-base-lite) and was trained one epoch with [JSNLI](https://huggingface.co/datasets/shunk031/jsnli).
 
 ## Usage (Sentence-Transformers)
 
@@ -28,7 +32,7 @@ Then you can use the model like this:
 from sentence_transformers import SentenceTransformer
 sentences = ["This is an example sentence", "Each sentence is converted"]
 
-model = SentenceTransformer('{MODEL_NAME}')
+model = SentenceTransformer('oshizo/sbert-jsnli-luke-japanese-base-lite')
 embeddings = model.encode(sentences)
 print(embeddings)
 ```
@@ -54,8 +58,8 @@ def mean_pooling(model_output, attention_mask):
 sentences = ['This is an example sentence', 'Each sentence is converted']
 
 # Load model from HuggingFace Hub
-tokenizer = AutoTokenizer.from_pretrained('{MODEL_NAME}')
-model = AutoModel.from_pretrained('{MODEL_NAME}')
+tokenizer = AutoTokenizer.from_pretrained('oshizo/sbert-jsnli-luke-japanese-base-lite')
+model = AutoModel.from_pretrained('oshizo/sbert-jsnli-luke-japanese-base-lite')
 
 # Tokenize sentences
 encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
@@ -75,12 +79,13 @@ print(sentence_embeddings)
 
 ## Evaluation Results
 
-<!--- Describe how your model was evaluated -->
+The results of the evaluation by JSTS and JSICK are available [here](https://github.com/oshizo/JapaneseEmbeddingEval).
 
-For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name={MODEL_NAME})
+## Training
 
+Training scripts are available in [this repository](https://github.com/oshizo/JapaneseEmbeddingTrain).
+This model was trained 1 epoch on Google Colab Pro A100 and took approximately 35 minutes.
 
-## Training
 The model was trained with the parameters:
 
 **DataLoader**:
@@ -122,8 +127,4 @@ SentenceTransformer(
   (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: LukeModel 
   (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
 )
-```
-
-## Citing & Authors
-
-<!--- Describe where people can find more information -->
+```