init commit

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+pytorch_model.bin filter=lfs diff=lfs merge=lfs -text

1_Pooling/config.json

@@ -0,0 +1,7 @@
+{
+  "word_embedding_dimension": 768,
+  "pooling_mode_cls_token": true,
+  "pooling_mode_mean_tokens": false,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false
+}

README.md

@@ -0,0 +1,99 @@
+---
+pipeline_tag: sentence-similarity
+language:
+- pl
+tags:
+- sentence-transformers
+- feature-extraction
+- sentence-similarity
+- transformers
+datasets:
+- ipipan/polqa
+- ipipan/maupqa
+---
+
+# HerBERT-base Retrieval (v2)
+
+HerBERT Retrieval model encodes the Polish sentences or paragraphs into a 768-dimensional dense vector space and can be used for tasks like document retrieval or semantic search.
+
+It was initialized from the [HerBERT-base](https://huggingface.co/allegro/herbert-base-cased) model and fine-tuned on the [PolQA](https://huggingface.co/ipipan/polqa) and [MAUPQA](https://huggingface.co/ipipan/maupqa) datasets for 40,000 steps with a batch size of 256.
+
+The model was trained on question-passage pairs and works best on similar tasks. The training passages consisted of `title` and `text` concatenated with the special token `</s>`. Even if your passages don't have a `title`, it is still beneficial to prefix a passage `text` with the `</s>` token.
+## 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 = [
+    "W jakim mieście urodził się Zbigniew Herbert?", 
+    "Zbigniew Herbert</s>Zbigniew Bolesław Ryszard Herbert (ur. 29 października 1924 we Lwowie, zm. 28 lipca 1998 w Warszawie) – polski poeta, eseista i dramaturg.",
+]
+
+model = SentenceTransformer('ipipan/herbert-base-retrieval-v2')
+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
+
+
+def cls_pooling(model_output, attention_mask):
+    return model_output[0][:,0]
+
+
+# Sentences we want sentence embeddings for
+sentences = [
+    "W jakim mieście urodził się Zbigniew Herbert?", 
+    "Zbigniew Herbert</s>Zbigniew Bolesław Ryszard Herbert (ur. 29 października 1924 we Lwowie, zm. 28 lipca 1998 w Warszawie) – polski poeta, eseista i dramaturg.",
+]
+# Load model from HuggingFace Hub
+tokenizer = AutoTokenizer.from_pretrained('ipipan/herbert-base-retrieval-v2')
+model = AutoModel.from_pretrained('ipipan/herbert-base-retrieval-v2')
+
+# Tokenize sentences
+encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
+
+# Compute token embeddings
+with torch.no_grad():
+    model_output = model(**encoded_input)
+
+# Perform pooling. In this case, cls pooling.
+sentence_embeddings = cls_pooling(model_output, encoded_input['attention_mask'])
+
+print("Sentence embeddings:")
+print(sentence_embeddings)
+```
+
+## Full Model Architecture
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
+  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
+)
+```
+
+## Additional Information
+
+### Dataset Curators
+
+The model was created by Piotr Rybak from the [Institute of Computer Science, Polish Academy of Sciences](http://zil.ipipan.waw.pl/).
+
+### Licensing Information
+
+[More Information Needed]
+
+### Citation Information
+
+[More Information Needed]

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "../../../sellaservice/rt/model_all_filter5p_bs256_lr2e5_40k/",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 514,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "tokenizer_class": "HerbertTokenizerFast",
+  "torch_dtype": "float32",
+  "transformers_version": "4.30.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 50000
+}

config_sentence_transformers.json

@@ -0,0 +1,7 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.2.2",
+    "transformers": "4.30.1",
+    "pytorch": "2.0.1"
+  }
+}

modules.json

@@ -0,0 +1,14 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  }
+]

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef7f20de52fd7d1a0c2d5efbbc473cc16034278c168d073b00e5a63c5d1ddf26
+size 497839917

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 512,
+  "do_lower_case": false
+}

special_tokens_map.json

@@ -0,0 +1,8 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "mask_token": "<mask>",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "do_lowercase_and_remove_accent": false,
+  "id2lang": null,
+  "lang2id": null,
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "HerbertTokenizer",
+  "unk_token": "<unk>"
+}