Update README.md

README.md

@@ -13,20 +13,6 @@ This model is an int4 model with group_size 128 of [microsoft/Phi-3-mini-4k-inst
 
 
 
-### INT4 Inference with AutoGPTQ's Kernel
-
-```python
-##pip install auto-gptq[triton] 
-##pip install triton==2.2.0
-from transformers import AutoModelForCausalLM, AutoTokenizer
-quantized_model_dir = "Intel/Phi-3-mini-4k-instruct-int4-inc"
-model = AutoModelForCausalLM.from_pretrained(quantized_model_dir,
-                                             device_map="auto",
-                                             trust_remote_code=False,
-                                             )
-tokenizer = AutoTokenizer.from_pretrained(quantized_model_dir, use_fast=True)
-print(tokenizer.decode(model.generate(**tokenizer("There is a girl who likes adventure,", return_tensors="pt").to(model.device),max_new_tokens=50)[0]))
-```