Update README.md

README.md

@@ -29,35 +29,6 @@ For more information on quantization, check the [OpenVINO model optimization gui
 The provided OpenVINO™ IR model is compatible with:
 
 * OpenVINO version 2025.1.0 and higher
-* Optimum Intel 1.23.0 and higher
-
-## Running Model Inference with [Optimum Intel](https://huggingface.co/docs/optimum/intel/index)
-
-
-1. Install packages required for using [Optimum Intel](https://huggingface.co/docs/optimum/intel/index) integration with the OpenVINO backend:
-
-```
-pip install optimum[openvino]
-```
-
-2. Run model inference:
-
-```
-from transformers import AutoTokenizer
-from optimum.intel.openvino import OVModelForCausalLM
-
-model_id = "OpenVINO/Mistral-7B-Instruct-v0.2-int4-ov-cw"
-tokenizer = AutoTokenizer.from_pretrained(model_id)
-model = OVModelForCausalLM.from_pretrained(model_id)
-
-inputs = tokenizer("What is OpenVINO?", return_tensors="pt")
-
-outputs = model.generate(**inputs, max_length=200)
-text = tokenizer.batch_decode(outputs)[0]
-print(text)
-```
-
-For more examples and possible optimizations, refer to the [OpenVINO Large Language Model Inference Guide](https://docs.openvino.ai/2024/learn-openvino/llm_inference_guide.html).
 
 ## Running Model Inference with [OpenVINO GenAI](https://github.com/openvinotoolkit/openvino.genai)
 
@@ -71,8 +42,8 @@ pip install openvino-genai huggingface_hub
 ```
 import huggingface_hub as hf_hub
 
-model_id = "OpenVINO/Mistral-7B-Instruct-v0.2-int4-ov-cw"
-model_path = "Mistral-7B-Instruct-v0.2-int4-ov-cw"
+model_id = "OpenVINO/Mistral-7B-Instruct-v0.2-int4-cw-ov"
+model_path = "Mistral-7B-Instruct-v0.2-int4-cw-ov"
 
 hf_hub.snapshot_download(model_id, local_dir=model_path)
 
@@ -83,7 +54,7 @@ hf_hub.snapshot_download(model_id, local_dir=model_path)
 ```
 import openvino_genai as ov_genai
 
-device = "CPU"
+device = "NPU"
 pipe = ov_genai.LLMPipeline(model_path, device)
 print(pipe.generate("What is OpenVINO?", max_length=200))
 ```