Update README.md

removed download requirement

README.md

@@ -80,7 +80,7 @@ from optimum.neuron import NeuronModelForCausalLM
 #num_cores should be changed based on the instance.  inf2.24xlarge has 6 neuron processors (they have two cores each) so 12 total
 input_shapes = {"batch_size": 1, "sequence_length": 4096}
 compiler_args = {"num_cores": 8, "auto_cast_type": 'fp16'}
-model = NeuronModelForCausalLM.from_pretrained("SOLAR-10.7B-v1.0", export=True, **compiler_args, **input_shapes)
+model = NeuronModelForCausalLM.from_pretrained("upstage/SOLAR-10.7B-v1.0", export=True, **compiler_args, **input_shapes)
 model.save_pretrained("SOLAR-10.7B-v1.0-neuron-24xlarge-2.16-8core-4096")
 
 from transformers import AutoTokenizer