docs(infr): remove dedicated model pages (#4877)

* docs(infr): remove dedicated model pages

* Apply suggestions from code review

* docs(infr): fix broken links

* docs(infr): fix 404

Author: bene2k1

changelog/february2025/2025-02-14-managed-inference-added-new-model-preview-deepseek-r1-d.mdx

@@ -9,7 +9,7 @@ category: ai-data
 product: managed-inference
 ---
 
-[DeepSeek R1 Distilled Llama 70B](/managed-inference/reference-content/deepseek-r1-distill-llama-70b/) is now available on Managed Inference.
+[DeepSeek R1 Distilled Llama 70B](/managed-inference/reference-content/model-catalog/#deepseek-r1-distill-llama-70b) is now available on Managed Inference.
 
 DeepSeek R1 Distilled Llama improves Llama model performance on reasoning use cases like mathematics or code.
 

changelog/september2024/2024-09-05-managed-inference-added-model-library-expanded.mdx

@@ -9,7 +9,7 @@ category: ai-data
 product: managed-inference
 ---
 
-[Meta Llama 3.1 8b](/managed-inference/reference-content/llama-3.1-8b-instruct/), [Meta Llama 3.1 70b](/managed-inference/reference-content/llama-3.1-70b-instruct/) and [Mistral Nemo](/managed-inference/reference-content/mistral-nemo-instruct-2407/) are available for deployment on Managed Inference. 
+[Meta Llama 3.1 8b](/managed-inference/reference-content/model-catalog/#llama-31-8b-instruct), [Meta Llama 3.1 70b](/managed-inference/reference-content/model-catalog/llama-31-70b-instruct) and [Mistral Nemo](/managed-inference/reference-content/model-catalog/#mistral-nemo-instruct-2407) are available for deployment on Managed Inference. 
 
 Released July 2024, these models all support a very large context window of up to 128k tokens, particularly useful for RAG applications.
 

menu/navigation.json

@@ -883,78 +883,6 @@
                   {
                     "label": "Managed Inference model catalog",
                     "slug": "model-catalog"
-                  },
-                  {
-                    "label": "BGE-Multilingual-Gemma2 model",
-                    "slug": "bge-multilingual-gemma2"
-                  },
-                  {
-                    "label": "Llama-3-8b-instruct model",
-                    "slug": "llama-3-8b-instruct"
-                  },
-                  {
-                    "label": "Llama-3-70b-instruct model",
-                    "slug": "llama-3-70b-instruct"
-                  },
-                  {
-                    "label": "Llama-3.1-8b-instruct model",
-                    "slug": "llama-3.1-8b-instruct"
-                  },
-                  {
-                    "label": "Llama-3.1-70b-instruct model",
-                    "slug": "llama-3.1-70b-instruct"
-                  },
-                  {
-                    "label": "Llama-3.1-nemotron-70b-instruct model",
-                    "slug": "llama-3.1-nemotron-70b-instruct"
-                  },
-                  {
-                    "label": "Llama-3.3-70b-instruct model",
-                    "slug": "llama-3.3-70b-instruct"
-                  },
-                  {
-                    "label": "DeepSeek-R1-Distill-Llama-70B model",
-                    "slug": "deepseek-r1-distill-llama-70b"
-                  },
-                  {
-                    "label": "DeepSeek-R1-Distill-Llama-8B model",
-                    "slug": "deepseek-r1-distill-llama-8b"
-                  },
-                  {
-                    "label": "Mistral-7b-instruct-v0.3 model",
-                    "slug": "mistral-7b-instruct-v0.3"
-                  },
-                  {
-                    "label": "Mistral-nemo-instruct-2407 model",
-                    "slug": "mistral-nemo-instruct-2407"
-                  },
-                  {
-                    "label": "Mixtral-8x7b-instruct-v0.1 model",
-                    "slug": "mixtral-8x7b-instruct-v0.1"
-                  },
-                  {
-                    "label": "Molmo-72b-0924 model",
-                    "slug": "molmo-72b-0924"
-                  },
-                  {
-                    "label": "Moshika-0.1-8b model",
-                    "slug": "moshika-0.1-8b"
-                  },
-                  {
-                    "label": "Moshiko-0.1-8b model",
-                    "slug": "moshiko-0.1-8b"
-                  },
-                  {
-                    "label": "Pixtral-12b-2409 model",
-                    "slug": "pixtral-12b-2409"
-                  },
-                  {
-                    "label": "Qwen2.5-coder-32b-instruct model",
-                    "slug": "qwen2.5-coder-32b-instruct"
-                  },
-                  {
-                    "label": "Sentence-t5-xxl model",
-                    "slug": "sentence-t5-xxl"
                   }
                 ],
                 "label": "Additional Content",

pages/generative-apis/faq.mdx

@@ -55,7 +55,7 @@ Note that in this example, the first line where the free tier applies will not d
 ## What is a token and how are they counted?
 A token is the minimum unit of content that is seen and processed by a model. Hence, token definitions depend on input types:
 - For text, on average, `1` token corresponds to `~4` characters, and thus `0.75` words (as words are on average five characters long)
-- For images, `1` token corresponds to a square of pixels. For example, [pixtral-12b-2409 model](https://www.scaleway.com/en/docs/managed-inference/reference-content/pixtral-12b-2409/#frequently-asked-questions) image tokens of `16x16` pixels (16-pixel height, and 16-pixel width, hence `256` pixels in total).
+- For images, `1` token corresponds to a square of pixels. For example, `pixtral-12b-2409` model image tokens of `16x16` pixels (16-pixel height, and 16-pixel width, hence `256` pixels in total).
 
 The exact token count and definition depend on [tokenizers](https://huggingface.co/learn/llm-course/en/chapter2/4) used by each model. When this difference is significant (such as for image processing), you can find detailed information in each model documentation (for instance in [`pixtral-12b-2409` size limit documentation](https://www.scaleway.com/en/docs/managed-inference/reference-content/pixtral-12b-2409/#frequently-asked-questions)). Otherwise, when the model is open, you can find this information in the model files on platforms such as Hugging Face, usually in the `tokenizer_config.json` file.
 

pages/managed-inference/how-to/import-custom-model.mdx

@@ -48,4 +48,4 @@ Scaleway provides a selection of common models for deployment from the Scaleway
     - Estimated cost.
    Once checked, click **Begin import** to finalize the process.
 
-Your imported model will now appear in the model library. You can proceed to [deploy your model on Managed Inference](/ai-data/managed-inference/how-to/create-deployment/).
+Your imported model will now appear in the model library. You can proceed to [deploy your model on Managed Inference](/managed-inference/how-to/create-deployment/).