We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
block_name_to_quantize
quantize_model
1 parent 824e368 commit ed70d27Copy full SHA for ed70d27
optimum/gptq/constants.py
@@ -18,6 +18,7 @@
18
"model.decoder.layers",
19
"gpt_neox.layers",
20
"model.layers",
21
+ "model.language_model.layers",
22
# modules loaded by AutoModel vs AutoModelForCausalLM have different prefixes
23
"h",
24
"decoder.layers",
0 commit comments