[Bugfix] Fix Sparse24 Compressed Tensors models (#33446)
Signed-off-by: Kyle Sayers <kylesayrs@gmail.com> Co-authored-by: Michael Goin <mgoin64@gmail.com>
This commit is contained in:
co-authored by
Michael Goin
parent
80f2ba6ea6
commit
e9cd691132
@@ -261,6 +261,7 @@ def get_quant_config(
|
||||
if (
|
||||
hf_quant_config is not None
|
||||
and hf_quant_config.get("quant_method") == "compressed-tensors"
|
||||
and "config_groups" in hf_quant_config
|
||||
):
|
||||
if hf_text_config is not None:
|
||||
n_heads = getattr(hf_text_config, "num_attention_heads", None)
|
||||
|
||||
Reference in New Issue
Block a user