Update README.md

README.md

@@ -1,141 +1,94 @@
 ---
+language:
+- ja
 tags:
-- sentence-transformers
 - sentence-similarity
 - feature-extraction
 base_model: sbintuitions/modernbert-ja-70m
+widget: []
 pipeline_tag: sentence-similarity
-library_name: sentence-transformers
+license: apache-2.0
+datasets:
+- cl-nagoya/ruri-v3-dataset-pt
 ---
 
-# SentenceTransformer based on sbintuitions/modernbert-ja-70m
+# Ruri: Japanese General Text Embeddings
 
-This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sbintuitions/modernbert-ja-70m](https://huggingface.co/sbintuitions/modernbert-ja-70m). It maps sentences & paragraphs to a 384-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
+**⚠️Notes:**
+**This model is a pretrained version and has not been fine-tuned.**  
+For the fine-tuned version, please use [cl-nagoya/ruri-v3-70m](https://huggingface.co/cl-nagoya/ruri-v3-310m)!
 
-## Model Details
+## Fine-tuned Model Series
 
-### Model Description
-- **Model Type:** Sentence Transformer
-- **Base model:** [sbintuitions/modernbert-ja-70m](https://huggingface.co/sbintuitions/modernbert-ja-70m) <!-- at revision 4c79ac9aad6f8399f7493c35dde895e7a5d79bf8 -->
-- **Maximum Sequence Length:** 8192 tokens
-- **Output Dimensionality:** 384 dimensions
-- **Similarity Function:** Cosine Similarity
-<!-- - **Training Dataset:** Unknown -->
-<!-- - **Language:** Unknown -->
-<!-- - **License:** Unknown -->
+**Ruri v3** is a general-purpose Japanese text embedding model built on top of [**ModernBERT-Ja**](https://huggingface.co/collections/sbintuitions/modernbert-ja-67b68fe891132877cf67aa0a).
+We provide Ruri-v3 in several model sizes. Below is a summary of each model.
 
-### Model Sources
+|ID| #Param. | #Param.<br>w/o Emb.|Dim.|#Layers|Avg. JMTEB|
+|-|-|-|-|-|-|
+|[cl-nagoya/ruri-v3-30m](https://huggingface.co/cl-nagoya/ruri-v3-30m)|37M|10M|256|10|74.51|
+|[cl-nagoya/ruri-v3-70m](https://huggingface.co/cl-nagoya/ruri-v3-70m)|70M|31M|384|13|75.48|
+|[cl-nagoya/ruri-v3-130m](https://huggingface.co/cl-nagoya/ruri-v3-130m)|132M|80M|512|19|76.55|
+|[cl-nagoya/ruri-v3-310m](https://huggingface.co/cl-nagoya/ruri-v3-310m)|315M|236M|768|25|77.24|
 
-- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
-- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
-- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
-
-### Full Model Architecture
-
-```
-MySentenceTransformer(
-  (0): Transformer({'max_seq_length': 8192, 'do_lower_case': False}) with Transformer model: ModernBertModel 
-  (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
-)
-```
 
 ## Usage
 
-### Direct Usage (Sentence Transformers)
-
-First install the Sentence Transformers library:
+You can use our models directly with the transformers library v4.48.0 or higher:
 
 ```bash
-pip install -U sentence-transformers
+pip install -U "transformers>=4.48.0"
+```
+
+Additionally, if your GPUs support Flash Attention 2, we recommend using our models with Flash Attention 2.
+
+```
+pip install flash-attn --no-build-isolation
 ```
 
 Then you can load this model and run inference.
 ```python
+import torch.nn.functional as F
 from sentence_transformers import SentenceTransformer
 
 # Download from the 🤗 Hub
-model = SentenceTransformer("hpprc/ruri-v3-70m-pt-2")
-# Run inference
+model = SentenceTransformer("cl-nagoya/ruri-v3-pt-70m")
+
+# Ruri v3 employs a 1+3 prefix scheme to distinguish between different types of text inputs:
+# "" (empty string) is used for encoding semantic meaning.
+# "トピック: " is used for classification, clustering, and encoding topical information.
+# "検索クエリ: " is used for queries in retrieval tasks.
+# "検索文書: " is used for documents to be retrieved.
 sentences = [
-    'The weather is lovely today.',
-    "It's so sunny outside!",
-    'He drove to the stadium.',
+    "川べりでサーフボードを持った人たちがいます",
+    "サーファーたちが川べりに立っています",
+    "トピック: 瑠璃色のサーファー",
+    "検索クエリ: 瑠璃色はどんな色？",
+    "検索文書: 瑠璃色（るりいろ）は、紫みを帯びた濃い青。名は、半貴石の瑠璃（ラピスラズリ、英: lapis lazuli）による。JIS慣用色名では「こい紫みの青」（略号 dp-pB）と定義している[1][2]。",
 ]
-embeddings = model.encode(sentences)
-print(embeddings.shape)
-# [3, 384]
-
-# Get the similarity scores for the embeddings
-similarities = model.similarity(embeddings, embeddings)
-print(similarities.shape)
-# [3, 3]
-```
-
-<!--
-### Direct Usage (Transformers)
-
-<details><summary>Click to see the direct usage in Transformers</summary>
-
-</details>
--->
-
-<!--
-### Downstream Usage (Sentence Transformers)
 
-You can finetune this model on your own dataset.
+embeddings = model.encode(sentences, convert_to_tensor=True)
+print(embeddings.size())
+# [5, 384]
 
-<details><summary>Click to expand</summary>
-
-</details>
--->
-
-<!--
-### Out-of-Scope Use
-
-*List how the model may foreseeably be misused and address what users ought not to do with the model.*
--->
-
-<!--
-## Bias, Risks and Limitations
-
-*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
--->
-
-<!--
-### Recommendations
-
-*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
--->
-
-## Training Details
-
-### Framework Versions
-- Python: 3.10.13
-- Sentence Transformers: 3.4.1
-- Transformers: 4.48.3
-- PyTorch: 2.5.1+cu124
-- Accelerate: 1.3.0
-- Datasets: 3.3.0
-- Tokenizers: 0.21.0
+similarities = F.cosine_similarity(embeddings.unsqueeze(0), embeddings.unsqueeze(1), dim=2)
+print(similarities)
+```
 
 ## Citation
 
-### BibTeX
-
-<!--
-## Glossary
-
-*Clearly define terms in order to be accessible across audiences.*
--->
-
-<!--
-## Model Card Authors
-
-*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
--->
+```bibtex
+@misc{
+  Ruri,
+  title={{Ruri: Japanese General Text Embeddings}}, 
+  author={Hayato Tsukagoshi and Ryohei Sasano},
+  year={2024},
+  eprint={2409.07737},
+  archivePrefix={arXiv},
+  primaryClass={cs.CL},
+  url={https://arxiv.org/abs/2409.07737}, 
+}
+```
 
-<!--
-## Model Card Contact
 
-*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
--->
+## License
+This model is published under the [Apache License, Version 2.0](https://www.apache.org/licenses/LICENSE-2.0).