diff --git a/docs/docs/providers/post_training/inline_huggingface-gpu.mdx b/docs/docs/providers/post_training/inline_huggingface-gpu.mdx
index 965f964a9..ac7644de7 100644
--- a/docs/docs/providers/post_training/inline_huggingface-gpu.mdx
+++ b/docs/docs/providers/post_training/inline_huggingface-gpu.mdx
@@ -18,7 +18,7 @@ HuggingFace-based post-training provider for fine-tuning models using the Huggin
 | `distributed_backend` | `Literal['fsdp', 'deepspeed'` | No |  |  |
 | `checkpoint_format` | `Literal['full_state', 'huggingface'` | No | huggingface |  |
 | `chat_template` | `<class 'str'>` | No | `&lt;|user|&gt;`<br/>`{input}`<br/>`&lt;|assistant|&gt;`<br/>`{output}` |  |
-| `model_specific_config` | `<class 'dict'>` | No | `&#123;'trust_remote_code': True, 'attn_implementation': 'sdpa'&#125;` |  |
+| `model_specific_config` | `<class 'dict'>` | No | `{'trust_remote_code': True, 'attn_implementation': 'sdpa'}` |  |
 | `max_seq_length` | `<class 'int'>` | No | 2048 |  |
 | `gradient_checkpointing` | `<class 'bool'>` | No | False |  |
 | `save_total_limit` | `<class 'int'>` | No | 3 |  |