chore: remove LFS tracking, download embedding model from HuggingFace at runtime

.gitattributes

@@ -1 +1 @@
-*.safetensors filter=lfs diff=lfs merge=lfs -text
+# LFS tracking removed - models downloaded from HuggingFace at runtime

.gitignore

@@ -115,4 +115,5 @@ docs/
 data_old/
 backend/migrate_all_databases.py
 test_api.py
-backend/embedding/models--sentence-transformers--all-MiniLM-L6-v2
+# Embedding models (downloaded from HuggingFace at runtime)
+backend/embedding/

backend/embedding/models--sentence-transformers--paraphrase-multilingual-MiniLM-L12-v2/refs/main

@@ -1 +0,0 @@
-86741b4e3f5cb7765a600d3a3d55a0f6a6cb443d

backend/embedding/models--sentence-transformers--paraphrase-multilingual-MiniLM-L12-v2/snapshots/86741b4e3f5cb7765a600d3a3d55a0f6a6cb443d/1_Pooling/config.json

@@ -1,7 +0,0 @@
-{
-  "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
-}

backend/embedding/models--sentence-transformers--paraphrase-multilingual-MiniLM-L12-v2/snapshots/86741b4e3f5cb7765a600d3a3d55a0f6a6cb443d/README.md

@@ -1,156 +0,0 @@
----
-language:
-- multilingual
-- ar
-- bg
-- ca
-- cs
-- da
-- de
-- el
-- en
-- es
-- et
-- fa
-- fi
-- fr
-- gl
-- gu
-- he
-- hi
-- hr
-- hu
-- hy
-- id
-- it
-- ja
-- ka
-- ko
-- ku
-- lt
-- lv
-- mk
-- mn
-- mr
-- ms
-- my
-- nb
-- nl
-- pl
-- pt
-- ro
-- ru
-- sk
-- sl
-- sq
-- sr
-- sv
-- th
-- tr
-- uk
-- ur
-- vi
-license: apache-2.0
-library_name: sentence-transformers
-tags:
-- sentence-transformers
-- feature-extraction
-- sentence-similarity
-- transformers
-language_bcp47:
-- fr-ca
-- pt-br
-- zh-cn
-- zh-tw
-pipeline_tag: sentence-similarity
----
-
-# sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
-
-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.
-
-
-
-## 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('sentence-transformers/paraphrase-multilingual-MiniLM-L12-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
-
-
-# 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 = ['This is an example sentence', 'Each sentence is converted']
-
-# Load model from HuggingFace Hub
-tokenizer = AutoTokenizer.from_pretrained('sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2')
-model = AutoModel.from_pretrained('sentence-transformers/paraphrase-multilingual-MiniLM-L12-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, max pooling.
-sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
-
-print("Sentence embeddings:")
-print(sentence_embeddings)
-```
-
-
-
-## 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})
-)
-```
-
-## Citing & Authors
-
-This model was trained by [sentence-transformers](https://www.sbert.net/). 
-        
-If you find this model helpful, feel free to cite our publication [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://arxiv.org/abs/1908.10084):
-```bibtex 
-@inproceedings{reimers-2019-sentence-bert,
-    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
-    author = "Reimers, Nils and Gurevych, Iryna",
-    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
-    month = "11",
-    year = "2019",
-    publisher = "Association for Computational Linguistics",
-    url = "http://arxiv.org/abs/1908.10084",
-}
-```

backend/embedding/models--sentence-transformers--paraphrase-multilingual-MiniLM-L12-v2/snapshots/86741b4e3f5cb7765a600d3a3d55a0f6a6cb443d/config.json

@@ -1,24 +0,0 @@
-{
-  "_name_or_path": "old_models/paraphrase-multilingual-MiniLM-L12-v2/0_Transformer",
-  "architectures": [
-    "BertModel"
-  ],
-  "attention_probs_dropout_prob": 0.1,
-  "gradient_checkpointing": false,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 384,
-  "initializer_range": 0.02,
-  "intermediate_size": 1536,
-  "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 512,
-  "model_type": "bert",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
-  "pad_token_id": 0,
-  "position_embedding_type": "absolute",
-  "transformers_version": "4.7.0",
-  "type_vocab_size": 2,
-  "use_cache": true,
-  "vocab_size": 250037
-}

backend/embedding/models--sentence-transformers--paraphrase-multilingual-MiniLM-L12-v2/snapshots/86741b4e3f5cb7765a600d3a3d55a0f6a6cb443d/config_sentence_transformers.json

@@ -1,7 +0,0 @@
-{
-  "__version__": {
-    "sentence_transformers": "2.0.0",
-    "transformers": "4.7.0",
-    "pytorch": "1.9.0+cu102"
-  }
-}

backend/embedding/models--sentence-transformers--paraphrase-multilingual-MiniLM-L12-v2/snapshots/86741b4e3f5cb7765a600d3a3d55a0f6a6cb443d/model.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:eaa086f0ffee582aeb45b36e34cdd1fe2d6de2bef61f8a559a1bbc9bd955917b
-size 470641600

backend/embedding/models--sentence-transformers--paraphrase-multilingual-MiniLM-L12-v2/snapshots/86741b4e3f5cb7765a600d3a3d55a0f6a6cb443d/modules.json

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

backend/embedding/models--sentence-transformers--paraphrase-multilingual-MiniLM-L12-v2/snapshots/86741b4e3f5cb7765a600d3a3d55a0f6a6cb443d/sentence_bert_config.json

@@ -1,4 +0,0 @@
-{
-  "max_seq_length": 128,
-  "do_lower_case": false
-}

backend/embedding/models--sentence-transformers--paraphrase-multilingual-MiniLM-L12-v2/snapshots/86741b4e3f5cb7765a600d3a3d55a0f6a6cb443d/special_tokens_map.json

@@ -1 +0,0 @@
-{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}

backend/embedding/models--sentence-transformers--paraphrase-multilingual-MiniLM-L12-v2/snapshots/86741b4e3f5cb7765a600d3a3d55a0f6a6cb443d/tokenizer_config.json

@@ -1 +0,0 @@
-{"do_lower_case": true, "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "tokenize_chinese_chars": true, "strip_accents": null, "bos_token": "<s>", "eos_token": "</s>", "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "old_models/paraphrase-multilingual-MiniLM-L12-v2/0_Transformer"}