Delete SBERT_AL

SBERT_AL/1_Pooling/config.json

@@ -1,10 +0,0 @@
-{
-  "word_embedding_dimension": 768,
-  "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,
-  "include_prompt": true
-}

SBERT_AL/README.md

@@ -1,127 +0,0 @@
----
-library_name: sentence-transformers
-pipeline_tag: sentence-similarity
-tags:
-- sentence-transformers
-- feature-extraction
-- sentence-similarity
-- transformers
-
----
-
-# {MODEL_NAME}
-
-This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 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)
-```
-
-
-
-## 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('{MODEL_NAME}')
-model = AutoModel.from_pretrained('{MODEL_NAME}')
-
-# 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, mean pooling.
-sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
-
-print("Sentence embeddings:")
-print(sentence_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 168 with parameters:
-```
-{'batch_size': 16, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
-```
-
-**Loss**:
-
-`sentence_transformers.losses.CosineSimilarityLoss.CosineSimilarityLoss` 
-
-Parameters of the fit()-Method:
-```
-{
-    "epochs": 2,
-    "evaluation_steps": 16,
-    "evaluator": "sentence_transformers.evaluation.EmbeddingSimilarityEvaluator.EmbeddingSimilarityEvaluator",
-    "max_grad_norm": 1,
-    "optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
-    "optimizer_params": {
-        "lr": 2e-05
-    },
-    "scheduler": "WarmupLinear",
-    "steps_per_epoch": null,
-    "warmup_steps": 100,
-    "weight_decay": 0.01
-}
-```
-
-
-## Full Model Architecture
-```
-SentenceTransformer(
-  (0): Transformer({'max_seq_length': 75, 'do_lower_case': False}) with Transformer model: MPNetModel 
-  (1): Pooling({'word_embedding_dimension': 768, '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, 'include_prompt': True})
-)
-```
-
-## Citing & Authors
-
-<!--- Describe where people can find more information -->

SBERT_AL/config.json

@@ -1,24 +0,0 @@
-{
-  "_name_or_path": "AL/SBERT_AL",
-  "architectures": [
-    "MPNetModel"
-  ],
-  "attention_probs_dropout_prob": 0.1,
-  "bos_token_id": 0,
-  "eos_token_id": 2,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
-  "initializer_range": 0.02,
-  "intermediate_size": 3072,
-  "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 514,
-  "model_type": "mpnet",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
-  "pad_token_id": 1,
-  "relative_attention_num_buckets": 32,
-  "torch_dtype": "float32",
-  "transformers_version": "4.38.2",
-  "vocab_size": 30527
-}

SBERT_AL/config_sentence_transformers.json

@@ -1,9 +0,0 @@
-{
-  "__version__": {
-    "sentence_transformers": "2.0.0",
-    "transformers": "4.7.0",
-    "pytorch": "1.9.0+cu102"
-  },
-  "prompts": {},
-  "default_prompt_name": null
-}

SBERT_AL/model.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:8cd6ec94b7759319bdb2e423e4e2468a8f526ea0011c962a55140822abc92bf4
-size 437967672

SBERT_AL/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"
-  }
-]

SBERT_AL/sentence_bert_config.json

@@ -1,4 +0,0 @@
-{
-  "max_seq_length": 75,
-  "do_lower_case": false
-}

SBERT_AL/special_tokens_map.json

@@ -1,51 +0,0 @@
-{
-  "bos_token": {
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "cls_token": {
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "mask_token": {
-    "content": "<mask>",
-    "lstrip": true,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "<pad>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "sep_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "[UNK]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
-}

SBERT_AL/tokenizer_config.json

@@ -1,66 +0,0 @@
-{
-  "added_tokens_decoder": {
-    "0": {
-      "content": "<s>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "1": {
-      "content": "<pad>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "2": {
-      "content": "</s>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "104": {
-      "content": "[UNK]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "30526": {
-      "content": "<mask>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    }
-  },
-  "bos_token": "<s>",
-  "clean_up_tokenization_spaces": true,
-  "cls_token": "<s>",
-  "do_basic_tokenize": true,
-  "do_lower_case": true,
-  "eos_token": "</s>",
-  "mask_token": "<mask>",
-  "max_length": 75,
-  "model_max_length": 512,
-  "never_split": null,
-  "pad_to_multiple_of": null,
-  "pad_token": "<pad>",
-  "pad_token_type_id": 0,
-  "padding_side": "right",
-  "sep_token": "</s>",
-  "stride": 0,
-  "strip_accents": null,
-  "tokenize_chinese_chars": true,
-  "tokenizer_class": "MPNetTokenizer",
-  "truncation_side": "right",
-  "truncation_strategy": "longest_first",
-  "unk_token": "[UNK]"
-}