huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-10 20:04:52 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix(server): Failing quantize config after local read.

Browse Source
This commit is contained in:
Nicolas Patry 2023-07-31 15:49:06 +00:00
parent 2a13f1a046
commit 7a2136eeb8
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
server/text_generation_server/utils/weights.py
View File

@ -224,7 +224,7 @@ class Weights:
def _set_gptq_params(self, model_id): def _set_gptq_params(self, model_id):
filename = "quantize_config.json" filename = "quantize_config.json"
try: try:
if not os.path.exists(os.path.join(model_id, filename)): if os.path.exists(os.path.join(model_id, filename)):
filename = os.path.join(model_id, filename) filename = os.path.join(model_id, filename)
else: else:
filename = hf_hub_download(model_id, filename=filename) filename = hf_hub_download(model_id, filename=filename)