Fix CPU Offloading (#1159)

SUMMARY:
- When updating the training args, `place_model_on_device` was missed
and as a result, when creating the trainer (which we really should not
be doing during oneshot...) the default value is left as True and the
trainer tries to move the model to a gpu, if it is available.
- We want this argument to be False as we handle the device map and
model initialization based on the calibration needs

TEST PLAN:
- `cpu_offloading_fp8.py` ran to completion without issue
- `mult_gpus_int8_device_map` made it past the error and is running

Author: dsikka

src/llmcompressor/args/training_arguments.py

@@ -30,3 +30,7 @@ class TrainingArguments(HFTrainingArgs):
             "checkpoints will be written."
         },
     )
+
+    @property
+    def place_model_on_device(self):
+        return False