mirror of
https://github.com/huggingface/text-generation-inference.git
synced 2025-09-11 20:34:54 +00:00
Removing more dead code.
This commit is contained in:
parent
dbf9292afc
commit
24bbd7b822
@ -627,10 +627,11 @@ class CausalLM(Model):
|
||||
def batch_type(self) -> Type[CausalLMBatch]:
|
||||
return CausalLMBatch
|
||||
|
||||
def decode(self, generated_ids: List[int]) -> str:
|
||||
return self.tokenizer.decode(
|
||||
generated_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False
|
||||
)
|
||||
# This is not used anymore
|
||||
# def decode(self, generated_ids: List[int]) -> str:
|
||||
# return self.tokenizer.decode(
|
||||
# generated_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False
|
||||
# )
|
||||
|
||||
def forward(
|
||||
self, input_ids, attention_mask, position_ids, past_key_values: Optional = None
|
||||
|
@ -827,6 +827,7 @@ class FlashCausalLM(Model):
|
||||
aliases=None,
|
||||
# Used for Santacoder override of config
|
||||
num_kv_heads=None,
|
||||
skip_special_tokens: bool = True,
|
||||
):
|
||||
self.process_group, rank, world_size = initialize_torch_distributed()
|
||||
if torch.cuda.is_available():
|
||||
|
@ -668,10 +668,11 @@ class Seq2SeqLM(Model):
|
||||
def batch_type(self) -> Type[Seq2SeqLMBatch]:
|
||||
return Seq2SeqLMBatch
|
||||
|
||||
def decode(self, decoder_ids: List[int]) -> str:
|
||||
return self.tokenizer.decode(
|
||||
decoder_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False
|
||||
)
|
||||
# Not used anymore
|
||||
# def decode(self, decoder_ids: List[int]) -> str:
|
||||
# return self.tokenizer.decode(
|
||||
# decoder_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False
|
||||
# )
|
||||
|
||||
def forward(
|
||||
self,
|
||||
|
Loading…
Reference in New Issue
Block a user