Commit cc779bed authored by Casper Hansen's avatar Casper Hansen
Browse files

Create generate method

parent d68441d0
......@@ -32,6 +32,10 @@ class BaseAWQForCausalLM(nn.Module):
def forward(self, *args, **kwargs):
return self.model(*args, **kwargs)
def generate(self, *args, **kwargs):
with torch.inference_mode():
return self.model.generate(*args, **kwargs)
@torch.no_grad()
def quantize(self, tokenizer=None, quant_config={}, n_samples=128, seqlen=512,
auto_scale=True, mse_range=True, run_search=False, run_quant=True,
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment