initial upload

README.md

@@ -4,93 +4,88 @@ tags:
 - sentence-transformers
 - feature-extraction
 - sentence-similarity
-license: mit
-datasets:
-- sentence-transformers/embedding-training-data
-- clips/mfaq
-language:
-- da
-library_name: sentence-transformers
----
-
-*Performance is not great - updates coming...*
 
-# MiniLM-L6-danish-encoder 
+---
 
-This is a lightweight (~22 M parameters) [sentence-transformers](https://www.SBERT.net) model for Danish NLP: It maps sentences & paragraphs to a 384-dimensional dense vector space and can be used for tasks like clustering or semantic search. 
+# {MODEL_NAME}
 
-The maximum sequence length is 256 tokens.
+This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 384 dimensional dense vector space and can be used for tasks like clustering or semantic search.
 
-The model was not pre-trained from scratch but adapted from the English version with a [tokenizer](https://huggingface.co/KennethTM/bert-base-uncased-danish) trained on Danish text.
+<!--- Describe your model here -->
 
-# Usage (Sentence-Transformers)
+## 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 = ["En mand løber på vejen.", "En panda løber på vejen.", "En mand kører hurtigt forbi på cykel."]
+sentences = ["This is an example sentence", "Each sentence is converted"]
 
-model = SentenceTransformer('KennethTM/MiniLM-L6-danish-encoder')
+model = SentenceTransformer('{MODEL_NAME}')
 embeddings = model.encode(sentences)
 print(embeddings)
 ```
-# Usage (HuggingFace Transformers)
-Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
 
-```python
-from transformers import AutoTokenizer, AutoModel
-import torch
-import torch.nn.functional as F
 
-#Mean Pooling - Take attention mask into account for correct averaging
-def mean_pooling(model_output, attention_mask):
-    token_embeddings = model_output[0] #First element of model_output contains all token embeddings
-    input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
-    return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
 
-# Sentences we want sentence embeddings for
-sentences = ["En mand løber på vejen.", "En panda løber på vejen.", "En mand kører hurtigt forbi på cykel."]
+## Evaluation Results
 
-# Load model from HuggingFace Hub
-tokenizer = AutoTokenizer.from_pretrained('KennethTM/MiniLM-L6-danish-encoder')
-model = AutoModel.from_pretrained('KennethTM/MiniLM-L6-danish-encoder')
+<!--- Describe how your model was evaluated -->
 
-# Tokenize sentences
-encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
+For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name={MODEL_NAME})
 
-# Compute token embeddings
-with torch.no_grad():
-    model_output = model(**encoded_input)
 
-# Perform pooling
-sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
+## Training
+The model was trained with the parameters:
 
-# Normalize embeddings
-sentence_embeddings = F.normalize(sentence_embeddings, p=2, dim=1)
+**DataLoader**:
 
-print("Sentence embeddings:")
-print(sentence_embeddings)
+`torch.utils.data.dataloader.DataLoader` of length 14531 with parameters:
+```
+{'batch_size': 128, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
 ```
 
-# Evaluation
+**Loss**:
+
+`__main__.MultipleNegativesRankingLoss` with parameters:
+  ```
+  {'scale': 20.0, 'similarity_fct': 'cos_sim'}
+  ```
 
-The performance of the pretrained model was evaluated using [ScandEval](https://github.com/ScandEval/ScandEval).
+Parameters of the fit()-Method:
+```
+{
+    "epochs": 1,
+    "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": null,
+    "warmup_steps": 1454,
+    "weight_decay": 0.01
+}
+```
+
+
+## Full Model Architecture
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel 
+  (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})
+  (2): Normalize()
+)
+```
 
-| Task                     | Dataset      | Score (±SE)                     |
-|:-------------------------|:-------------|:--------------------------------|
-| sentiment-classification | angry-tweets | mcc = 36.14 (±1.07)             |
-|                          |              | macro_f1 = 56.57 (±0.84)        |
-| named-entity-recognition | dane         | micro_f1 = 55.56 (±1.69)        |
-|                          |              | micro_f1_no_misc = 57.44 (±1.9) |
-| linguistic-acceptability | scala-da     | mcc = 12.4 (±3.07)              |
-|                          |              | macro_f1 = 53.54 (±2.15)        |
-| question-answering       | scandiqa-da  | em = 17.87 (±1.15)              |
-|                          |              | f1 = 27.84 (±1.37)              |
-| speed                    | speed        | speed = 18.59 (±0.05)           |
+## Citing & Authors
 
+<!--- Describe where people can find more information -->

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b6a8c8f10ba5858880cfd968cfa14a7bd2e7fdfae7c8d9bca1b3aaba8e75cab
+oid sha256:034c21d9a02972167974cee34792364fb8a157f31e1c8f052f759fb90f3b6795
 size 90887145

sentence_bert_config.json

@@ -1,4 +1,4 @@
 {
-  "max_seq_length": 256,
+  "max_seq_length": 128,
   "do_lower_case": false
 }

tokenizer.json

@@ -2,7 +2,7 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 256,
+    "max_length": 128,
     "strategy": "LongestFirst",
     "stride": 0
   },

tokenizer_config.json

@@ -2,7 +2,7 @@
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
   "mask_token": "[MASK]",
-  "max_length": 256,
+  "max_length": 128,
   "model_max_length": 512,
   "pad_to_multiple_of": null,
   "pad_token": "[PAD]",