Update README.md

README.md

@@ -12,13 +12,13 @@ from optimum.intel.openvino import OVModelForCausalLM
 
 ov_config = {"PERFORMANCE_HINT": "LATENCY", "NUM_STREAMS": "1", "CACHE_DIR": "", "INFERENCE_PRECISION_HINT": "f16"}
 
-tok = AutoTokenizer.from_pretrained("xriminact/llama-3-8b-instruct-openvino", trust_remote_code=True)
+tok = AutoTokenizer.from_pretrained("xriminact/llama-3-8b-instruct-openvino-int4", trust_remote_code=True)
 
 ov_model = OVModelForCausalLM.from_pretrained(
-    "xriminact/llama-3-8b-instruct-openvino",
+    "xriminact/llama-3-8b-instruct-openvino-int4",
     device="GPU",
     ov_config=ov_config,
-    config=AutoConfig.from_pretrained("xriminact/llama-3-8b-instruct-openvino", trust_remote_code=True),
+    config=AutoConfig.from_pretrained("xriminact/llama-3-8b-instruct-openvino-int4", trust_remote_code=True),
     trust_remote_code=True,
 )