diff --git a/flair/embeddings/document.py b/flair/embeddings/document.py
index 8f66a198ed..91aac0b9e0 100644
--- a/flair/embeddings/document.py
+++ b/flair/embeddings/document.py
@@ -691,10 +691,9 @@ def _add_embeddings_internal(self, sentences: list[Sentence]):
 
         lengths: list[int] = [len(sentence.tokens) for sentence in sentences]
         padding_length: int = max(max(lengths), self.min_sequence_length)
-
         pre_allocated_zero_tensor = torch.zeros(
             self.embeddings.embedding_length * padding_length,
-            dtype=self.convs[0].weight.dtype,
+            dtype=cast(torch.nn.Conv1d, self.convs[0]).weight.dtype,
             device=flair.device,
         )
 
diff --git a/flair/embeddings/token.py b/flair/embeddings/token.py
index 3d95c8ee0b..a9e6ba2199 100644
--- a/flair/embeddings/token.py
+++ b/flair/embeddings/token.py
@@ -1466,7 +1466,7 @@ def _add_embeddings_internal(self, sentences: list[Sentence]) -> list[Sentence]:
             word = token.text if self.field is None else token.get_label(self.field).value
 
             if word.strip() == "":
-                ids = [self.spm.vocab_size(), self.embedder.spm.vocab_size()]
+                ids = [self.spm.vocab_size(), self.spm.vocab_size()]
             else:
                 if self.do_preproc:
                     word = self._preprocess(word)
diff --git a/flair/file_utils.py b/flair/file_utils.py
index 518d69e809..53fac0f75b 100644
--- a/flair/file_utils.py
+++ b/flair/file_utils.py
@@ -382,4 +382,4 @@ def load_torch_state(model_file: str) -> dict[str, typing.Any]:
         # to load models on some Mac/Windows setups
         # see https://github.com/zalandoresearch/flair/issues/351
         f = load_big_file(model_file)
-        return torch.load(f, map_location="cpu")
+        return torch.load(f, map_location="cpu", weights_only=False)
diff --git a/flair/models/sequence_tagger_model.py b/flair/models/sequence_tagger_model.py
index ea028c3e70..25b5b374f3 100644
--- a/flair/models/sequence_tagger_model.py
+++ b/flair/models/sequence_tagger_model.py
@@ -862,8 +862,8 @@ def push_to_hub(
             self.save(local_model_path)
 
             # Determine if model card already exists
-            info = model_info(repo_id, use_auth_token=token)
-            write_readme = all(f.rfilename != "README.md" for f in info.siblings)
+            info = model_info(repo_id, token=token)
+            write_readme = info.siblings is None or all(f.rfilename != "README.md" for f in info.siblings)
 
             # Generate and save model card
             if write_readme:
diff --git a/requirements.txt b/requirements.txt
index 2704114ace..39cf750c66 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -17,7 +17,7 @@ scikit-learn>=1.0.2
 segtok>=1.5.11
 sqlitedict>=2.0.0
 tabulate>=0.8.10
-torch>=1.5.0,!=1.8
+torch>=1.13.1
 tqdm>=4.63.0
 transformer-smaller-training-vocab>=0.2.3
 transformers[sentencepiece]>=4.25.0,<5.0.0