huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-10 03:44:54 +00:00
Code Issues Packages Projects Releases Wiki Activity

Loading config *after* checking for model name.

Browse Source
This commit is contained in:
Nicolas Patry 2023-05-15 10:01:59 +02:00
parent bef3458ee8
commit cd8477bcf8
1 changed files with 12 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
server/text_generation_server/models/__init__.py
View File

@ -99,6 +99,17 @@ def get_model(
else: else:
return Galactica(model_id, revision, quantize=quantize) return Galactica(model_id, revision, quantize=quantize)
if model_id.startswith("bigcode/"):
if sharded:
if not FLASH_ATTENTION:
raise NotImplementedError(
FLASH_ATT_ERROR_MESSAGE.format(f"Sharded Santacoder")
)
return FlashSantacoderSharded(model_id, revision, quantize=quantize)
else:
santacoder_cls = FlashSantacoder if FLASH_ATTENTION else SantaCoder
return santacoder_cls(model_id, revision, quantize=quantize)
config = AutoConfig.from_pretrained(model_id, revision=revision) config = AutoConfig.from_pretrained(model_id, revision=revision)
model_type = config.model_type model_type = config.model_type