diff --git a/.ci/scripts/validate.sh b/.ci/scripts/validate.sh
index bc8146d03..12107f8d3 100644
--- a/.ci/scripts/validate.sh
+++ b/.ci/scripts/validate.sh
@@ -284,7 +284,7 @@ function eval_model_sanity_check() {
         echo "*************************************************"
         if [ "$DTYPE" != "float16" ]; then
             python3 -W ignore export.py --dtype ${DTYPE} --quant "$QUANT_OPTIONS" --checkpoint-path "$CHECKPOINT_PATH" --output-dso-path ${MODEL_DIR}/${MODEL_NAME}.so --device "$TARGET_DEVICE" || exit 1
-            python3 -W ignore eval.py --dtype ${DTYPE} --checkpoint-path "$CHECKPOINT_PATH" --temperature 0 --dso-path ${MODEL_DIR}/${MODEL_NAME}.so --device "$TARGET_DEVICE" --limit 5 > "$MODEL_DIR/output_eval_aoti" || exit 1
+            python3 -W ignore eval.py --dtype ${DTYPE} --checkpoint-path "$CHECKPOINT_PATH" --dso-path ${MODEL_DIR}/${MODEL_NAME}.so --device "$TARGET_DEVICE" --limit 5 > "$MODEL_DIR/output_eval_aoti" || exit 1
             cat "$MODEL_DIR/output_eval_aoti"
         fi;
 
diff --git a/cli.py b/cli.py
index a06ff5de1..f36d93346 100644
--- a/cli.py
+++ b/cli.py
@@ -61,27 +61,14 @@ def add_arguments_for_verb(parser, verb: str) -> None:
         help="Model name for well-known models",
     )
 
-    parser.add_argument(
-        "--chat",
-        action="store_true",
-        help="Whether to start an interactive chat session",
-    )
+    if verb in ["browser", "chat", "generate"]:
+        _add_generation_args(parser) 
+
     parser.add_argument(
         "--distributed",
         action="store_true",
         help="Whether to enable distributed inference",
     )
-    parser.add_argument(
-        "--gui",
-        action="store_true",
-        help="Whether to use a web UI for an interactive chat session",
-    )
-    parser.add_argument(
-        "--prompt",
-        type=str,
-        default="Hello, my name is",
-        help="Input prompt",
-    )
     parser.add_argument(
         "--is-chat-model",
         action="store_true",
@@ -93,54 +80,17 @@ def add_arguments_for_verb(parser, verb: str) -> None:
         default=None,
         help="Initialize torch seed",
     )
-    parser.add_argument(
-        "--num-samples",
-        type=int,
-        default=1,
-        help="Number of samples",
-    )
-    parser.add_argument(
-        "--max-new-tokens",
-        type=int,
-        default=200,
-        help="Maximum number of new tokens",
-    )
-    parser.add_argument(
-        "--top-k",
-        type=int,
-        default=200,
-        help="Top-k for sampling",
-    )
-    parser.add_argument(
-        "--temperature", type=float, default=0.8, help="Temperature for sampling"
-    )
     parser.add_argument(
         "--compile",
         action="store_true",
         help="Whether to compile the model with torch.compile",
     )
-    parser.add_argument(
-        "--compile-prefill",
-        action="store_true",
-        help="Whether to compile the prefill. Improves prefill perf, but has higher compile times.",
-    )
-    parser.add_argument(
-        "--sequential-prefill",
-        action="store_true",
-        help="Whether to perform prefill sequentially. Only used for model debug.",
-    )
     parser.add_argument(
         "--profile",
         type=Path,
         default=None,
         help="Profile path.",
     )
-    parser.add_argument(
-        "--speculate-k",
-        type=int,
-        default=5,
-        help="Speculative execution depth",
-    )
     parser.add_argument(
         "--draft-checkpoint-path",
         type=Path,
@@ -171,30 +121,10 @@ def add_arguments_for_verb(parser, verb: str) -> None:
         default=None,
         help="Use the specified model tokenizer file",
     )
-    parser.add_argument(
-        "--output-pte-path",
-        type=str,
-        default=None,
-        help="Output to the specified ExecuTorch .pte model file",
-    )
-    parser.add_argument(
-        "--output-dso-path",
-        type=str,
-        default=None,
-        help="Output to the specified AOT Inductor .dso model file",
-    )
-    parser.add_argument(
-        "--dso-path",
-        type=Path,
-        default=None,
-        help="Use the specified AOT Inductor .dso model file",
-    )
-    parser.add_argument(
-        "--pte-path",
-        type=Path,
-        default=None,
-        help="Use the specified ExecuTorch .pte model file",
-    )
+
+    _add_exported_model_input_args(parser)
+    _add_export_output_path_args(parser)
+
     parser.add_argument(
         "--dtype",
         default="fast",
@@ -259,6 +189,40 @@ def add_arguments_for_verb(parser, verb: str) -> None:
     _add_cli_metadata_args(parser)
 
 
+# Add CLI Args representing user provided exported model files
+def _add_export_output_path_args(parser) -> None:
+    output_path_parser = parser.add_argument_group("Export Output Path Args", "Specify the output path for the exported model files")
+    output_path_parser.add_argument(
+        "--output-pte-path",
+        type=str,
+        default=None,
+        help="Output to the specified ExecuTorch .pte model file",
+    )
+    output_path_parser.add_argument(
+        "--output-dso-path",
+        type=str,
+        default=None,
+        help="Output to the specified AOT Inductor .dso model file",
+    )
+
+
+# Add CLI Args representing user provided exported model files
+def _add_exported_model_input_args(parser) -> None:
+    exported_model_path_parser = parser.add_argument_group("Exported Model Path Args", "Specify the path of the exported model files to ingest")
+    exported_model_path_parser.add_argument(
+        "--dso-path",
+        type=Path,
+        default=None,
+        help="Use the specified AOT Inductor .dso model file",
+    )
+    exported_model_path_parser.add_argument(
+        "--pte-path",
+        type=Path,
+        default=None,
+        help="Use the specified ExecuTorch .pte model file",
+    )
+
+    
 # Add CLI Args that are relevant to any subcommand execution
 def _add_cli_metadata_args(parser) -> None:
     parser.add_argument(
@@ -297,22 +261,81 @@ def _configure_artifact_inventory_args(parser, verb: str) -> None:
         )
 
 
+# Add CLI Args specific to user prompted generation
+def _add_generation_args(parser) -> None:
+    generator_parser = parser.add_argument_group("Generation Args", "Configs for generating output based on provided prompt")
+    generator_parser.add_argument(
+        "--prompt",
+        type=str,
+        default="Hello, my name is",
+        help="Input prompt for manual output generation",
+    )
+    generator_parser.add_argument(
+        "--chat",
+        action="store_true",
+        help="Whether to start an interactive chat session",
+    )
+    generator_parser.add_argument(
+        "--gui",
+        action="store_true",
+        help="Whether to use a web UI for an interactive chat session",
+    )
+    generator_parser.add_argument(
+        "--num-samples",
+        type=int,
+        default=1,
+        help="Number of samples",
+    )
+    generator_parser.add_argument(
+        "--max-new-tokens",
+        type=int,
+        default=200,
+        help="Maximum number of new tokens",
+    )
+    generator_parser.add_argument(
+        "--top-k",
+        type=int,
+        default=200,
+        help="Top-k for sampling",
+    )
+    generator_parser.add_argument(
+        "--temperature", type=float, default=0.8, help="Temperature for sampling"
+    )
+    generator_parser.add_argument(
+        "--compile-prefill",
+        action="store_true",
+        help="Whether to compile the prefill. Improves prefill perf, but has higher compile times.",
+    )
+    generator_parser.add_argument(
+        "--sequential-prefill",
+        action="store_true",
+        help="Whether to perform prefill sequentially. Only used for model debug.",
+    )
+    generator_parser.add_argument(
+        "--speculate-k",
+        type=int,
+        default=5,
+        help="Speculative execution depth",
+    )
+
+
 # Add CLI Args specific to Model Evaluation
 def _add_evaluation_args(parser) -> None:
-    parser.add_argument(
+    eval_parser = parser.add_argument_group("Evaluation Args", "Configs for evaluating model performance")
+    eval_parser.add_argument(
         "--tasks",
         nargs="+",
         type=str,
         default=["wikitext"],
         help="List of lm-eluther tasks to evaluate. Usage: --tasks task1 task2",
     )
-    parser.add_argument(
+    eval_parser.add_argument(
         "--limit",
         type=int,
         default=None,
         help="Number of samples to evaluate",
     )
-    parser.add_argument(
+    eval_parser.add_argument(
         "--max-seq-length",
         type=int,
         default=None,