[Docs] fix rope_scaling doc string (#25072)

fix rope_scaling doc string

src/transformers/models/deprecated/open_llama/configuration_open_llama.py

@@ -68,7 +68,7 @@ class OpenLlamaConfig(PretrainedConfig):
         tie_word_embeddings(`bool`, *optional*, defaults to `False`):
             Whether to tie weight embeddings
         rope_scaling (`Dict`, *optional*):
-            Dictionary containing the scaling configuration for the RoPE embeddings. Currently supports three scaling
+            Dictionary containing the scaling configuration for the RoPE embeddings. Currently supports two scaling
             strategies: linear and dynamic. Their scaling factor must be an float greater than 1. The expected format
             is `{"type": strategy name, "factor": scaling factor}`. When using this flag, don't update
             `max_position_embeddings` to the expected new maximum. See the following thread for more information on how

src/transformers/models/gpt_neox/configuration_gpt_neox.py

@@ -79,7 +79,7 @@ class GPTNeoXConfig(PretrainedConfig):
             Whether to use a "parallel" formulation in each Transformer layer, which can provide a slight training
             speedup at large scales (e.g. 20B).
         rope_scaling (`Dict`, *optional*):
-            Dictionary containing the scaling configuration for the RoPE embeddings. Currently supports three scaling
+            Dictionary containing the scaling configuration for the RoPE embeddings. Currently supports two scaling
             strategies: linear and dynamic. Their scaling factor must be an float greater than 1. The expected format
             is `{"type": strategy name, "factor": scaling factor}`. When using this flag, don't update
             `max_position_embeddings` to the expected new maximum. See the following thread for more information on how

src/transformers/models/llama/configuration_llama.py

@@ -78,7 +78,7 @@ class LlamaConfig(PretrainedConfig):
         tie_word_embeddings(`bool`, *optional*, defaults to `False`):
             Whether to tie weight embeddings
         rope_scaling (`Dict`, *optional*):
-            Dictionary containing the scaling configuration for the RoPE embeddings. Currently supports three scaling
+            Dictionary containing the scaling configuration for the RoPE embeddings. Currently supports two scaling
             strategies: linear and dynamic. Their scaling factor must be an float greater than 1. The expected format
             is `{"type": strategy name, "factor": scaling factor}`. When using this flag, don't update
             `max_position_embeddings` to the expected new maximum. See the following thread for more information on how