Update README.md

README.md

@@ -34,7 +34,7 @@ pip3 install huggingface-hub>=0.17.1
 Then you can download any individual model file to the current directory, at high speed, with a command like this:
 
 ```shell
-huggingface-cli download Esperanto/granite-3.0-2b-instruct-fp16-onnx --local-dir granite-3.0-2b-instruct-fp16-onnx --local-dir-use-symlinks False
+huggingface-cli download Esperanto/granite-3.0-2b-instruct-kvc-fp16-onnx --local-dir granite-3.0-2b-instruct-kvc-fp16-onnx --local-dir-use-symlinks False
 ```
 
 For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
@@ -130,8 +130,8 @@ def generate_text(model_path, prompt, tokenizer, max_gen_tokens, total_sequence,
 We now run the inferences:
 
 ```python
-tokenizer = AutoTokenizer.from_pretrained("Esperanto/granite-3.0-2b-instruct-fp16-onnx")
-model_path = "granite-3.0-2b-instruct-fp16-onnx/model.onnx"
+tokenizer = AutoTokenizer.from_pretrained("Esperanto/granite-3.0-2b-instruct-kvc-fp16-onnx")
+model_path = "granite-3.0-2b-instruct-kvc-fp16-onnx/model.onnx"
 
 max_gen_tokens = 20    #number of tokens we want tog eneral
 total_sequence = 128   #total sequence_length