huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-09 19:34:53 +00:00
Code Issues Packages Projects Releases Wiki Activity

fmt

Browse Source
This commit is contained in:
OlivierDehaene 2023-04-06 20:09:21 +02:00
parent 1111125092
commit e4ad3066bc
1 changed files with 6 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
server/text_generation_server/models/flash_llama.py
View File

@ -39,7 +39,9 @@ class FlashLlama(FlashCausalLM):
raise NotImplementedError("FlashLlama does not support quantization") raise NotImplementedError("FlashLlama does not support quantization")
tokenizer = LlamaTokenizer.from_pretrained( tokenizer = LlamaTokenizer.from_pretrained(
model_id, revision=revision, padding_side="left", model_id,
revision=revision,
padding_side="left",
) )
config = AutoConfig.from_pretrained( config = AutoConfig.from_pretrained(
@ -155,7 +157,9 @@ class FlashLlamaSharded(FlashLlama):
raise NotImplementedError("FlashLlama does not support quantization") raise NotImplementedError("FlashLlama does not support quantization")
tokenizer = LlamaTokenizer.from_pretrained( tokenizer = LlamaTokenizer.from_pretrained(
model_id, revision=revision, padding_side="left", model_id,
revision=revision,
padding_side="left",
) )
config = AutoConfig.from_pretrained( config = AutoConfig.from_pretrained(