ilotoki_thu/alpaca_lora_4bit
2
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Merge pull request #73 from dnouri/fix-monkeypatch-v1

Browse Source 
Bugfix in custom_monkey_patch for v1 models
This commit is contained in:
John Smith
2023-04-10 21:37:27 +08:00
committed by GitHub
parent 5d3267d80d ee7d94a1f3
commit 68e1b35660
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
text-generation-webui/custom_monkey_patch.py
View File

@@ -24,7 +24,7 @@ def load_model_llama(*args, **kwargs):
print('Apply auto switch and half') print('Apply auto switch and half')
for n, m in model.named_modules(): for n, m in model.named_modules():
if isinstance(m, Autograd4bitQuantLinear) or isinstance(m, Linear4bitLt): if isinstance(m, Autograd4bitQuantLinear) or isinstance(m, Linear4bitLt):
if m.groupsize == -1: if m.is_v1_model:
m.zeros = m.zeros.half() m.zeros = m.zeros.half()
m.scales = m.scales.half() m.scales = m.scales.half()
m.bias = m.bias.half() m.bias = m.bias.half()