From 8d7f18f41e9bd32090f73ad52532eb257563c95f Mon Sep 17 00:00:00 2001
From: fxmarty <9808326+fxmarty@users.noreply.github.com>
Date: Fri, 17 May 2024 08:53:08 +0000
Subject: [PATCH] diff nicer

---
 server/text_generation_server/models/flash_cohere.py     | 1 -
 server/text_generation_server/models/flash_dbrx.py       | 1 -
 server/text_generation_server/models/flash_gemma.py      | 1 -
 server/text_generation_server/models/flash_gpt2.py       | 1 -
 server/text_generation_server/models/flash_llama.py      | 1 -
 server/text_generation_server/models/flash_neox.py       | 1 -
 server/text_generation_server/models/flash_phi.py        | 1 -
 server/text_generation_server/models/flash_qwen2.py      | 1 -
 server/text_generation_server/models/flash_rw.py         | 1 -
 server/text_generation_server/models/flash_santacoder.py | 1 -
 server/text_generation_server/models/flash_starcoder2.py | 1 -
 server/text_generation_server/models/gpt_neox.py         | 1 -
 server/text_generation_server/models/idefics.py          | 1 -
 server/text_generation_server/models/mpt.py              | 1 -
 server/text_generation_server/models/opt.py              | 1 -
 server/text_generation_server/models/phi.py              | 1 -
 server/text_generation_server/models/rw.py               | 1 -
 server/text_generation_server/models/santacoder.py       | 1 -
 server/text_generation_server/models/seq2seq_lm.py       | 1 -
 server/text_generation_server/models/t5.py               | 1 -
 20 files changed, 20 deletions(-)

diff --git a/server/text_generation_server/models/flash_cohere.py b/server/text_generation_server/models/flash_cohere.py
index 8edaaa35..b907ee08 100644
--- a/server/text_generation_server/models/flash_cohere.py
+++ b/server/text_generation_server/models/flash_cohere.py
@@ -28,7 +28,6 @@ class FlashCohere(FlashCausalLM):
         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/flash_dbrx.py b/server/text_generation_server/models/flash_dbrx.py
index 6a9b9d7f..d5eb1a6e 100644
--- a/server/text_generation_server/models/flash_dbrx.py
+++ b/server/text_generation_server/models/flash_dbrx.py
@@ -30,7 +30,6 @@ class FlashDbrx(FlashCausalLM):
         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/flash_gemma.py b/server/text_generation_server/models/flash_gemma.py
index 70f1b65c..53bfd064 100644
--- a/server/text_generation_server/models/flash_gemma.py
+++ b/server/text_generation_server/models/flash_gemma.py
@@ -28,7 +28,6 @@ class FlashGemma(FlashCausalLM):
         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/flash_gpt2.py b/server/text_generation_server/models/flash_gpt2.py
index 65bb9920..0067a806 100644
--- a/server/text_generation_server/models/flash_gpt2.py
+++ b/server/text_generation_server/models/flash_gpt2.py
@@ -30,7 +30,6 @@ class FlashGPT2(FlashCausalLM):
         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/flash_llama.py b/server/text_generation_server/models/flash_llama.py
index 7395a41f..fa22322a 100644
--- a/server/text_generation_server/models/flash_llama.py
+++ b/server/text_generation_server/models/flash_llama.py
@@ -32,7 +32,6 @@ class FlashLlama(FlashCausalLM):
         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/flash_neox.py b/server/text_generation_server/models/flash_neox.py
index 9242a124..adefaeb2 100644
--- a/server/text_generation_server/models/flash_neox.py
+++ b/server/text_generation_server/models/flash_neox.py
@@ -29,7 +29,6 @@ class FlashNeoXSharded(FlashCausalLM):
         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/flash_phi.py b/server/text_generation_server/models/flash_phi.py
index 92f0a2b5..32b573a9 100644
--- a/server/text_generation_server/models/flash_phi.py
+++ b/server/text_generation_server/models/flash_phi.py
@@ -29,7 +29,6 @@ class FlashPhi(FlashCausalLM):
         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/flash_qwen2.py b/server/text_generation_server/models/flash_qwen2.py
index 5ee8ffe6..59064b30 100644
--- a/server/text_generation_server/models/flash_qwen2.py
+++ b/server/text_generation_server/models/flash_qwen2.py
@@ -34,7 +34,6 @@ class FlashQwen2(BaseFlashMistral):
         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/flash_rw.py b/server/text_generation_server/models/flash_rw.py
index ccc90179..e6350611 100644
--- a/server/text_generation_server/models/flash_rw.py
+++ b/server/text_generation_server/models/flash_rw.py
@@ -30,7 +30,6 @@ class FlashRWSharded(FlashCausalLM):
         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/flash_santacoder.py b/server/text_generation_server/models/flash_santacoder.py
index e1add297..2ad36b93 100644
--- a/server/text_generation_server/models/flash_santacoder.py
+++ b/server/text_generation_server/models/flash_santacoder.py
@@ -33,7 +33,6 @@ class FlashSantacoderSharded(FlashCausalLM):
         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/flash_starcoder2.py b/server/text_generation_server/models/flash_starcoder2.py
index 80323fb6..dc5d49be 100644
--- a/server/text_generation_server/models/flash_starcoder2.py
+++ b/server/text_generation_server/models/flash_starcoder2.py
@@ -33,7 +33,6 @@ class FlashStarcoder2(BaseFlashMistral):
         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/gpt_neox.py b/server/text_generation_server/models/gpt_neox.py
index 92fa5ce4..c0e1adf2 100644
--- a/server/text_generation_server/models/gpt_neox.py
+++ b/server/text_generation_server/models/gpt_neox.py
@@ -28,7 +28,6 @@ class GPTNeoxSharded(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.py b/server/text_generation_server/models/idefics.py
index 816c5e75..c1fe03e4 100644
--- a/server/text_generation_server/models/idefics.py
+++ b/server/text_generation_server/models/idefics.py
@@ -35,7 +35,6 @@ class IDEFICSSharded(IdeficsCausalLM):
         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/mpt.py b/server/text_generation_server/models/mpt.py
index 6f6e837f..8d8b4909 100644
--- a/server/text_generation_server/models/mpt.py
+++ b/server/text_generation_server/models/mpt.py
@@ -47,7 +47,6 @@ class MPTSharded(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/opt.py b/server/text_generation_server/models/opt.py
index 48584734..5b84f4ff 100644
--- a/server/text_generation_server/models/opt.py
+++ b/server/text_generation_server/models/opt.py
@@ -26,7 +26,6 @@ class OPTSharded(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/phi.py b/server/text_generation_server/models/phi.py
index d4dff836..d68866c1 100644
--- a/server/text_generation_server/models/phi.py
+++ b/server/text_generation_server/models/phi.py
@@ -26,7 +26,6 @@ class Phi(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("cuda")
diff --git a/server/text_generation_server/models/rw.py b/server/text_generation_server/models/rw.py
index c347c47d..d4764ded 100644
--- a/server/text_generation_server/models/rw.py
+++ b/server/text_generation_server/models/rw.py
@@ -16,7 +16,6 @@ class RW(CausalLM):
         dtype: Optional[torch.dtype] = None,
         trust_remote_code: bool = False,
     ):
-
         if speculator:
             raise RuntimeError("Medusa decoding is not enabled for AutoModel")
 
diff --git a/server/text_generation_server/models/santacoder.py b/server/text_generation_server/models/santacoder.py
index 188faf21..323e4324 100644
--- a/server/text_generation_server/models/santacoder.py
+++ b/server/text_generation_server/models/santacoder.py
@@ -23,7 +23,6 @@ class SantaCoder(CausalLM):
         dtype: Optional[torch.dtype] = None,
         trust_remote_code: bool = False,
     ):
-
         if torch.cuda.is_available():
             device = torch.device("cuda")
             dtype = torch.float16 if dtype is None else dtype
diff --git a/server/text_generation_server/models/seq2seq_lm.py b/server/text_generation_server/models/seq2seq_lm.py
index c5473107..710b0f7e 100644
--- a/server/text_generation_server/models/seq2seq_lm.py
+++ b/server/text_generation_server/models/seq2seq_lm.py
@@ -537,7 +537,6 @@ class Seq2SeqLM(Model):
         dtype: Optional[torch.dtype] = None,
         trust_remote_code: bool = False,
     ):
-
         if speculator:
             raise RuntimeError("Speculator decoding is not enabled for AutoModel")
 
diff --git a/server/text_generation_server/models/t5.py b/server/text_generation_server/models/t5.py
index 674e9318..8e0735e5 100644
--- a/server/text_generation_server/models/t5.py
+++ b/server/text_generation_server/models/t5.py
@@ -29,7 +29,6 @@ class T5Sharded(Seq2SeqLM):
         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}")