diff --git a/server/text_generation_server/models/flash_llama.py b/server/text_generation_server/models/flash_llama.py
index fa22322a..796fbd47 100644
--- a/server/text_generation_server/models/flash_llama.py
+++ b/server/text_generation_server/models/flash_llama.py
@@ -10,7 +10,6 @@ from text_generation_server.models import FlashCausalLM
 from text_generation_server.models.custom_modeling.flash_llama_modeling import (
     FlashLlamaForCausalLM,
 )
-
 from text_generation_server.utils import (
     initialize_torch_distributed,
     weight_files,
diff --git a/server/text_generation_server/models/flash_mistral.py b/server/text_generation_server/models/flash_mistral.py
index 5f0d20f5..b83f49a4 100644
--- a/server/text_generation_server/models/flash_mistral.py
+++ b/server/text_generation_server/models/flash_mistral.py
@@ -318,7 +318,6 @@ class BaseFlashMistral(FlashCausalLM):
         trust_remote_code: bool = False,
         tokenizer_class=AutoTokenizer,
     ):
-
         self.process_group, rank, world_size = initialize_torch_distributed()
         if torch.cuda.is_available():
             device = torch.device(f"cuda:{rank}")
diff --git a/server/text_generation_server/models/galactica.py b/server/text_generation_server/models/galactica.py
index 93d004d7..4656fd45 100644
--- a/server/text_generation_server/models/galactica.py
+++ b/server/text_generation_server/models/galactica.py
@@ -21,7 +21,6 @@ from text_generation_server.utils import (
     Weights,
 )
 
-
 # CREDIT: Papers with code => https://github.com/paperswithcode/galai/blob/main/galai/utils.py
 
 # we split individual characters inside special tokens like [START_DNA]
@@ -172,7 +171,6 @@ class GalacticaSharded(CausalLM):
         dtype: Optional[torch.dtype] = None,
         trust_remote_code: bool = False,
     ):
-
         self.process_group, rank, world_size = initialize_torch_distributed()
         if torch.cuda.is_available():
             device = torch.device(f"cuda:{rank}")
diff --git a/server/text_generation_server/models/idefics_causal_lm.py b/server/text_generation_server/models/idefics_causal_lm.py
index dd26cc06..e78a9655 100644
--- a/server/text_generation_server/models/idefics_causal_lm.py
+++ b/server/text_generation_server/models/idefics_causal_lm.py
@@ -22,6 +22,7 @@ from text_generation_server.models.types import (
 from text_generation_server.pb import generate_pb2
 from text_generation_server.utils import NextTokenChooser, StoppingCriteria, Sampling
 from text_generation_server.models.vlm_causal_lm import split
+
 import re
 
 IMAGES = re.compile(r"!\[[^\]]*\]\((.*?)\s*(\"(?:.*[^\"])\")?\s*\)")
@@ -576,7 +577,6 @@ class IdeficsCausalLM(Model):
         dtype: Optional[torch.dtype] = None,
         trust_remote_code: bool = False,
     ):
-
         from text_generation_server.models.custom_modeling.idefics_modeling import (
             IdeficsForVisionText2Text,
         )
diff --git a/server/text_generation_server/models/mamba.py b/server/text_generation_server/models/mamba.py
index 36386365..b28b744f 100644
--- a/server/text_generation_server/models/mamba.py
+++ b/server/text_generation_server/models/mamba.py
@@ -412,7 +412,6 @@ class Mamba(Model):
         dtype: Optional[torch.dtype] = None,
         trust_remote_code: bool = False,
     ):
-
         self.process_group, _rank, world_size = initialize_torch_distributed()
         if world_size > 1:
             raise RuntimeError("Mamba does not support Tensor Parallelism (TP)")
@@ -476,7 +475,7 @@ class Mamba(Model):
                 except Exception:
                     logger.exception(f"Decode cuda graph warmup failed")
         else:
-            logger.info(f"Cuda Graphs are disabled (CUDA_GRAPHS='{CUDA_GRAPHS}').")
+            logger.info(f"Cuda Graphs are disabled (CUDA_GRAPHS={CUDA_GRAPHS}).")
 
         return None
 
diff --git a/server/text_generation_server/models/seq2seq_lm.py b/server/text_generation_server/models/seq2seq_lm.py
index 710b0f7e..6a0c812f 100644
--- a/server/text_generation_server/models/seq2seq_lm.py
+++ b/server/text_generation_server/models/seq2seq_lm.py
@@ -17,7 +17,6 @@ from text_generation_server.models.types import (
 from text_generation_server.pb import generate_pb2
 from text_generation_server.utils import NextTokenChooser, StoppingCriteria, Sampling
 
-
 tracer = trace.get_tracer(__name__)