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

Support TheBloke exported models.

Browse Source
This commit is contained in:
Nicolas Patry 2023-09-25 10:02:49 +00:00
parent 2d8c034df3
commit cbf047b4ae
1 changed files with 12 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
server/text_generation_server/utils/weights.py
View File

@ -345,4 +345,15 @@ class Weights:
self.gptq_bits = data["bits"]
self.gptq_groupsize = data["group_size"]
except Exception:
pass
filename = "quant_config.json"
try:
if os.path.exists(os.path.join(model_id, filename)):
filename = os.path.join(model_id, filename)
else:
filename = hf_hub_download(model_id, filename=filename)
with open(filename, "r") as f:
data = json.load(f)
self.gptq_bits = data["w_bit"]
self.gptq_groupsize = data["q_group_size"]
except Exception:
pass