Update README.md

README.md

@@ -1,6 +1,8 @@
 ---
-datasets: []
-language: []
+datasets:
+- crazyjeannot/fr_literary_dataset_large
+language:
+- fr
 library_name: sentence-transformers
 pipeline_tag: sentence-similarity
 tags:
@@ -8,35 +10,43 @@ tags:
 - sentence-similarity
 - feature-extraction
 widget: []
+license: apache-2.0
+base_model:
+- BAAI/bge-m3
 ---
 
-# SentenceTransformer
+# Literary Encoder
+
+This is an encoder model finetuned from the FlagOpen/FlagEmbedding family of models.
+
+The model is specialized for studying french literary fiction with a training corpus based on 40.000 passages from free from rights french literary novels.
+
+It maps paragraphs to a 1024-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
 
-This is a [sentence-transformers](https://www.SBERT.net) model trained. It maps sentences & paragraphs to a 1024-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
 
 ## Model Details
 
 ### Model Description
 - **Model Type:** Sentence Transformer
-<!-- - **Base model:** [Unknown](https://huggingface.co/unknown) -->
-- **Maximum Sequence Length:** 8192 tokens
-- **Output Dimensionality:** 1024 tokens
+- **Base model:** [BAAI/bge-m3](https://huggingface.co/BAAI/bge-m3)
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 1024
 - **Similarity Function:** Cosine Similarity
-<!-- - **Training Dataset:** Unknown -->
-<!-- - **Language:** Unknown -->
-<!-- - **License:** Unknown -->
+- **Training Dataset:** [crazyjeannot/fr_literary_dataset_large](https://huggingface.co/datasets/crazyjeannot/fr_literary_dataset_large)
+- **Language:** French
+- **License:** cc-by-2.5
 
 ### 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)
+- **Repository:** [Flag Embedding on GitHub](https://github.com/FlagOpen/FlagEmbedding)
+- **Hugging Face:** [BGE dense model on Hugging Face](https://huggingface.co/BAAI/bge-m3)
 
 ### Full Model Architecture
 
 ```
 SentenceTransformer(
-  (0): Transformer({'max_seq_length': 8192, 'do_lower_case': False}) with Transformer model: XLMRobertaModel 
+  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
   (1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
   (2): Normalize()
 )
@@ -44,71 +54,47 @@ SentenceTransformer(
 
 ## Usage
 
-### Direct Usage (Sentence Transformers)
-
-First install the Sentence Transformers library:
-
-```bash
-pip install -U sentence-transformers
-```
+### Direct Usage (FlagEmbedding)
 
 Then you can load this model and run inference.
 ```python
-from sentence_transformers import SentenceTransformer
+from FlagEmbedding import FlagModel
 
 # Download from the 🤗 Hub
-model = SentenceTransformer("sentence_transformers_model_id")
+model = FlagModel('crazyjeannot/literary_bge_base',
+                  query_instruction_for_retrieval="",
+                  use_fp16=True)
+
 # Run inference
 sentences = [
-    'The weather is lovely today.',
-    "It's so sunny outside!",
-    'He drove to the stadium.',
+    'Il y avait, du reste, cette chose assez triste, c’est que si M. de Marsantes, à l’esprit fort ouvert, eût apprécié un fils si différent de lui, Robert de Saint-Loup, parce qu’il était de ceux qui croient que le mérite est attaché à certaines formes de la vie, avait un souvenir affectueux mais un peu méprisant d’un père qui s’était occupé toute sa vie de chasse et de course, avait bâillé à Wagner et raffolé d’Offenbach.',
+    "D’ailleurs, les opinions tranchantes abondent dans un siècle où l’on ne doute de rien, hors de l’existence de Dieu ; mais comme les jugements généraux que l’on porte sur les peuples sont assez souvent démentis par l’expérience, je n’aurai garde de prononcer.",
+    'Il était chargé de remettre l’objet, quel qu’il fût, au commodore, et d’en prendre un reçu, comme preuve que lui et son camarade s’étaient acquittés de leur commission.',
 ]
 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.
-
-<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.*
--->
+### SentenceTransformer
 
-<!--
-## Bias, Risks and Limitations
+```python
+from sentence_transformers import SentenceTransformer
 
-*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
--->
+# Download from the 🤗 Hub
+model = SentenceTransformer("sentence_transformers_model_id")
 
-<!--
-### Recommendations
+# Run inference
+sentences = [
+    'Il y avait, du reste, cette chose assez triste, c’est que si M. de Marsantes, à l’esprit fort ouvert, eût apprécié un fils si différent de lui, Robert de Saint-Loup, parce qu’il était de ceux qui croient que le mérite est attaché à certaines formes de la vie, avait un souvenir affectueux mais un peu méprisant d’un père qui s’était occupé toute sa vie de chasse et de course, avait bâillé à Wagner et raffolé d’Offenbach.',
+    "D’ailleurs, les opinions tranchantes abondent dans un siècle où l’on ne doute de rien, hors de l’existence de Dieu ; mais comme les jugements généraux que l’on porte sur les peuples sont assez souvent démentis par l’expérience, je n’aurai garde de prononcer.",
+    'Il était chargé de remettre l’objet, quel qu’il fût, au commodore, et d’en prendre un reçu, comme preuve que lui et son camarade s’étaient acquittés de leur commission.',
+]
 
-*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
--->
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 1024]
+```
 
 ## Training Details
 
@@ -123,22 +109,17 @@ You can finetune this model on your own dataset.
 
 ## Citation
 
-### BibTeX
-
-<!--
-## Glossary
-
-*Clearly define terms in order to be accessible across audiences.*
--->
+If you find this repository useful, please consider giving a like and citation
 
-<!--
-## Model Card Authors
-
-*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
--->
-
-<!--
-## Model Card Contact
-
-*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
--->
+```
+@inproceedings{barre_latent_2024,
+      title={Latent {Structures} of {Intertextuality} in {French} {Fiction}}, 
+      author={Barré, Jean},
+      address = {Aarhus, Denmark},
+      series = {{CEUR} {Workshop} {Proceedings}},
+      booktitle = {Proceedings of the {Conference} on {Computational} {Humanities} {Research} CHR2024},
+      publisher = {CEUR},
+      editor = {Haverals, Wouter and Koolen, Marijn and Thompson, Laure},
+      year = {2024},
+}
+```