fix(inference): improve custom models requirements (#5079)

Author: fpagny

pages/managed-inference/reference-content/supported-models.mdx

@@ -52,6 +52,8 @@ Your model repository must include:
    * An `architectures` array (see [supported architectures](#supported-models-architecture) for the exact list of supported values).
    * `max_position_embeddings`
  * Model weights in the [`.safetensors`](https:/huggingface.co/docs/safetensors/index) format
+ * A `tokenizer.json` file
+   * If your are fine-tuning an existing model, we recommend you use the same `tokenizer.json` file from the base model.
  * A chat template included in either:
    * `tokenizer_config.json` as a `chat_template` field, or
    * `chat_template.json` as a `chat_template` field
@@ -232,4 +234,4 @@ Custom models must conform to one of the architectures listed below. Click to ex
   * `EAGLEModel`
   * `MedusaModel`
   * `MLPSpeculatorPreTrainedModel`
-</Concept>
+</Concept>