Update README.md

README.md

@@ -1,88 +1,27 @@
 ---
 pipeline_tag: sentence-similarity
 tags:
-- sentence-transformers
 - feature-extraction
 - sentence-similarity
-
+- setfit
+- e5
+license: mit
+datasets:
+- KnutJaegersberg/wikipedia_categories
+- KnutJaegersberg/wikipedia_categories_labels
 ---
 
-# {MODEL_NAME}
-
-This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 1024 dimensional dense vector space and can be used for tasks like clustering or semantic search.
-
-<!--- Describe your model here -->
-
-## Usage (Sentence-Transformers)
-
-Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
-
-```
-pip install -U sentence-transformers
-```
-
-Then you can use the model like this:
-
-```python
-from sentence_transformers import SentenceTransformer
-sentences = ["This is an example sentence", "Each sentence is converted"]
-
-model = SentenceTransformer('{MODEL_NAME}')
-embeddings = model.encode(sentences)
-print(embeddings)
-```
-
-
-
-## Evaluation Results
-
-<!--- Describe how your model was evaluated -->
-
-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
-The model was trained with the parameters:
-
-**DataLoader**:
-
-`torch.utils.data.dataloader.DataLoader` of length 133200 with parameters:
-```
-{'batch_size': 8, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
-```
-
-**Loss**:
-
-`sentence_transformers.losses.CosineSimilarityLoss.CosineSimilarityLoss` 
+This English model predicts the top 2 levels of the wikipedia categories (roundabout 1100 labels). It is trained on the concatenation of the headlines of the lower level categories articles in few shot setting (i.e. 8 subcategories with their headline concatenations per level 2 category). 
+Accuracy on test data split of the higher category level (37 labels) is 73 % and on level 2 is 60%. 
+Note that these numbers are just an indicator that training worked, it will differ in production settings, which is why this classifier is meant for corpus exploration.  
+Use the wikipedia_categories_labels dataset as key. 
 
-Parameters of the fit()-Method:
-```
-{
-    "epochs": 2,
-    "evaluation_steps": 0,
-    "evaluator": "NoneType",
-    "max_grad_norm": 1,
-    "optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
-    "optimizer_params": {
-        "lr": 2e-05
-    },
-    "scheduler": "WarmupLinear",
-    "steps_per_epoch": 266400,
-    "warmup_steps": 26640,
-    "weight_decay": 0.01
-}
-```
 
 
-## Full Model Architecture
-```
-SentenceTransformer(
-  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
-  (1): Pooling({'word_embedding_dimension': 1024, '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})
-  (2): Normalize()
-)
-```
+from setfit import SetFitModel
 
-## Citing & Authors
+Download from Hub and run inference
+model = SetFitModel.from_pretrained("KnutJaegersberg/wikipedia_categories_setfit")
 
-<!--- Describe where people can find more information -->
+Run inference
+preds = model(["Rachel Dolezal Faces Felony Charges For Welfare Fraud", "Elon Musk just got lucky", "The hype on AI is different from the hype on other tech topics"])