Update quant_llama2_hqq_demo.py - remove old quantize()

mobiusml · Nov 21, 2023 · 7d36c42 · 7d36c42
1 parent 76619ae
commit 7d36c42
Showing 1 changed file with 0 additions and 1 deletion.
diff --git a/code/llama2_benchmark/quant_llama2_hqq_demo.py b/code/llama2_benchmark/quant_llama2_hqq_demo.py
@@ -26,7 +26,6 @@
 #quant_config = hqq_base_quant_config(nbits=2, group_size=16)
 #quant_config = hqq_base_quant_config(nbits=2, group_size=16, quant_scale=True) #scale is quantized to 8-bit/g=128
 
-#quantize_model(model, quant_config=quant_config)
 LlamaHQQ.quantize_model(model, quant_config=quant_config)
 
 # #Evaluate the quantized model