huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-10 11:54:52 +00:00
Code Issues Packages Projects Releases Wiki Activity

Load quantize_config.json from local path

Browse Source
This commit is contained in:
Antoni Baum 2023-07-27 18:03:04 -07:00 committed by GitHub
parent 9f18f4c006
commit 987b0fff3a
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
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/utils/weights.py
View File

@ -220,9 +220,13 @@ class Weights:
return bits, groupsize
def _set_gptq_params(self, model_id):
def _set_gptq_params(self, model_id: str):
try:
filename = hf_hub_download(model_id, filename="quantize_config.json")
potential_local_path = Path(model_id, "quantize_config.json")
if potential_local_path.exists():
filename = potential_local_path
else:
filename = hf_hub_download(model_id, filename="quantize_config.json")
with open(filename, "r") as f:
data = json.load(f)
self.gptq_bits = data["bits"]