Update README.md

README.md

@@ -6,37 +6,32 @@ tags:
 pipeline_tag: sentence-similarity
 library_name: sentence-transformers
 ---
-
 # SentenceTransformer
 
-This is a [sentence-transformers](https://www.SBERT.net) model trained. It maps sentences & paragraphs to a None-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
+このモデルは実験的なモデルです。  
+詳細は[ブログ記事](https://note.com/oshizo/n/n473a0124585b)を、関連するソースコードは[リポジトリ](https://github.com/oshizo/japanese-clip-qwen2_vl/)を参照してください。
+
+
+前回のバージョン[oshizo/japanese-clip-qwen2_vl-exp-0101](https://huggingface.co/oshizo/japanese-clip-qwen2_vl-exp-0101)との差分
+* テキスト埋め込みモデルを[pkshatech/GLuCoSE-base-ja-v2](https://huggingface.co/pkshatech/GLuCoSE-base-ja-v2)に変更
+* 学習データを公開しました
+  * [oshizo/japanese-text-image-retrieval-train](https://huggingface.co/datasets/oshizo/japanese-text-image-retrieval-train)
+  * OCRテキストをもとにQwen2.5-14B質問を生成し、質問-ページ画像のペアによる学習を行いました
+  * ドキュメント画像の解像度（長いほうの辺）は588px、700px、896pxの三種類で学習を行いました（前回は588pxのみ）
+
 
 ## Model Details
 
 ### Model Description
 - **Model Type:** Sentence Transformer
 <!-- - **Base model:** [Unknown](https://huggingface.co/unknown) -->
-- **Maximum Sequence Length:** None tokens
-- **Output Dimensionality:** None dimensions
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 768 dimensions
 - **Similarity Function:** Cosine Similarity
 <!-- - **Training Dataset:** Unknown -->
 <!-- - **Language:** Unknown -->
 <!-- - **License:** Unknown -->
 
-### Model Sources
-
-- **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
-
-```
-SentenceTransformer(
-  (0): CLIPQwen2VLWrapper()
-)
-```
-
 ## Usage
 
 ### Direct Usage (Sentence Transformers)
@@ -44,96 +39,41 @@ SentenceTransformer(
 First install the Sentence Transformers library:
 
 ```bash
-pip install -U sentence-transformers
+pip install -U sentence-transformers fugashi SentencePiece 
 ```
 
 Then you can load this model and run inference.
 ```python
 from sentence_transformers import SentenceTransformer
+model = SentenceTransformer("oshizo/japanese-clip-qwen2_vl-exp-0126", trust_remote_code=True)
+
+import io
+import requests
+from PIL import Image
 
-# Download from the 🤗 Hub
-model = SentenceTransformer("oshizo/japanese-clip-qwen2_vl-exp-0126")
-# Run inference
 sentences = [
-    'The weather is lovely today.',
-    "It's so sunny outside!",
-    'He drove to the stadium.',
+    'モノクロの男性の肖像写真。軍服を着て石の階段に座っている。',
+    "庭で茶色の犬がこちらを向いて座っている。"
 ]
-embeddings = model.encode(sentences)
-print(embeddings.shape)
-# [3, 1024]
-
-# 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.
+text_embeddings = model.encode(sentences)
+text_embeddings.shape
+# (2, 1024)
 
-<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: 3.11.6
-- Sentence Transformers: 3.3.1
-- Transformers: 4.47.1
-- PyTorch: 2.5.1+cu121
-- Accelerate: 1.1.1
-- Datasets: 2.19.0
-- Tokenizers: 0.21.0
-
-## 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.*
--->
+image_urls = [
+    'https://upload.wikimedia.org/wikipedia/commons/7/73/Shigenobu_Okuma_5.jpg',
+    'https://upload.wikimedia.org/wikipedia/commons/7/78/Akita_inu.jpeg'
+]
+images = [
+     Image.open(io.BytesIO(requests.get(image_urls[0]).content)).resize((150, 240)),
+     Image.open(io.BytesIO(requests.get(image_urls[1]).content)).resize((240, 150))
+]
 
-<!--
-## Model Card Contact
+image_embeddings = model.encode(images)
+image_embeddings.shape
+# (2, 1024)
 
-*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
--->
+similarities = model.similarity(text_embeddings, image_embeddings)
+similarities
+# tensor([[ 2.6399e-01,  8.1531e-02],
+#         [-2.4970e-04,  3.1410e-01]])
+```