Upload 11 files

Cased, trained on distilbert-base-cased, equation replaced with a placeholder equation, tables removed, 8 epochs, bs 16

README.md

@@ -86,7 +86,7 @@ The model was trained with the parameters:
 
 **DataLoader**:
 
-`torch.utils.data.dataloader.DataLoader` of length 25444 with parameters:
+`torch.utils.data.dataloader.DataLoader` of length 24663 with parameters:
 ```
 {'batch_size': 16, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
 ```
@@ -101,7 +101,7 @@ The model was trained with the parameters:
 Parameters of the fit()-Method:
 ```
 {
-    "epochs": 4,
+    "epochs": 8,
     "evaluation_steps": 0,
     "evaluator": "NoneType",
     "max_grad_norm": 1,
@@ -120,7 +120,7 @@ Parameters of the fit()-Method:
 ## Full Model Architecture
 ```
 SentenceTransformer(
-  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
+  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: DistilBertModel 
   (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})
 )
 ```

config.json

@@ -1,25 +1,25 @@
 {
-  "_name_or_path": "allenai/scibert_scivocab_cased",
+  "_name_or_path": "distilbert/distilbert-base-cased",
+  "activation": "gelu",
   "architectures": [
-    "BertModel"
+    "DistilBertModel"
   ],
-  "attention_probs_dropout_prob": 0.1,
-  "classifier_dropout": null,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
-  "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "bert",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "output_past": true,
   "pad_token_id": 0,
-  "position_embedding_type": "absolute",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
   "torch_dtype": "float32",
   "transformers_version": "4.39.3",
-  "type_vocab_size": 2,
-  "use_cache": true,
-  "vocab_size": 31116
+  "vocab_size": 28996
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff2d9a7b55a2a8465c79a0f39a49e753080836960026685a3abdd8fbeb16fa25
-size 439776096
+oid sha256:f200de77206679b93deec38235d4c2749f0888320dc6003162584c045f3fe3c0
+size 260774728

tokenizer_config.json

@@ -43,15 +43,13 @@
   },
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
-  "do_basic_tokenize": true,
-  "do_lower_case": true,
+  "do_lower_case": false,
   "mask_token": "[MASK]",
   "model_max_length": 1000000000000000019884624838656,
-  "never_split": null,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
   "strip_accents": null,
   "tokenize_chinese_chars": true,
-  "tokenizer_class": "BertTokenizer",
+  "tokenizer_class": "DistilBertTokenizer",
   "unk_token": "[UNK]"
 }