Model: Read scale_pos_emb from config

In newer versions of exllamav2, this value is read from the model's
config.json. This value will still default to 1.0 anyways.

Signed-off-by: kingbri <bdashore3@proton.me>

model.py

@@ -126,7 +126,9 @@ class ModelContainer:
             self.config.max_seq_len = target_max_seq_len
 
         # Set the rope scale
-        self.config.scale_pos_emb = unwrap(kwargs.get("rope_scale"), 1.0)
+        self.config.scale_pos_emb = unwrap(
+            kwargs.get("rope_scale"), self.config.scale_pos_emb
+        )
 
         # Automatically calculate rope alpha
         self.config.scale_alpha_value = unwrap(