Update eager runner and eval llama

Author: jackzhxng

examples/models/llama/eval_llama_lib.py

@@ -191,7 +191,7 @@ def gen_eval_wrapper(
 
     pt2e_quant_params, quantizers, quant_dtype = get_quantizer_and_quant_params(args)
     # GPTFastEvalWrapper: Create a wrapper around a pre-exported model
-    manager: LLMEdgeManager = _prepare_for_llama_export(model_name, args)
+    manager: LLMEdgeManager = _prepare_for_llama_export(args)
 
     if len(quantizers) != 0:
         manager = manager.export().pt2e_quantize(quantizers)

examples/models/llama/runner/eager.py

@@ -38,7 +38,7 @@ def __init__(self, args):
             model_args=model_args,
             device="cuda" if torch.cuda.is_available() else "cpu",
         )
-        manager: LLMEdgeManager = _prepare_for_llama_export("llama", args)
+        manager: LLMEdgeManager = _prepare_for_llama_export(args)
         self.model = manager.model.eval().to(device=self.device)
 
     def forward(