Dedupe local model instructions

Author: mrubens

docs/advanced-usage/local-models.md

@@ -21,113 +21,17 @@ Roo Code currently supports two main local model providers:
 1.  **Ollama:**  A popular open-source tool for running large language models locally.  It supports a wide range of models.
 2.  **LM Studio:**  A user-friendly desktop application that simplifies the process of downloading, configuring, and running local models.  It also provides a local server that emulates the OpenAI API.
 
-## Setting Up Ollama
+## Setting Up Local Models
 
-1.  **Download and Install Ollama:**  Download the Ollama installer for your operating system from the [Ollama website](https://ollama.com/). Follow the installation instructions. Make sure Ollama is running
+For detailed setup instructions, see:
 
-    ```bash
-    ollama serve
-    ```
+* [Setting up Ollama](../providers/ollama)
+* [Setting up LM Studio](../providers/lmstudio)
 
-2.  **Download a Model:**  Ollama supports many different models.  You can find a list of available models on the [Ollama website](https://ollama.com/library).  Some recommended models for coding tasks include:
-
-    *   `codellama:7b-code` (good starting point, smaller)
-    *   `codellama:13b-code` (better quality, larger)
-    *   `codellama:34b-code` (even better quality, very large)
-    *   `qwen2.5-coder:32b`
-    *   `mistralai/Mistral-7B-Instruct-v0.1` (good general-purpose model)
-    *   `deepseek-coder:6.7b-base` (good for coding tasks)
-    * `llama3:8b-instruct-q5_1` (good for general tasks)
-
-    To download a model, open your terminal and run:
-
-    ```bash
-    ollama pull <model_name>
-    ```
-
-    For example:
-
-    ```bash
-    ollama pull qwen2.5-coder:32b
-    ```
-
-3. **Configure the Model:** by default, Ollama uses a context window size of 2048 tokens, which is too small for Roo Code requests. You need to have at least 12k to get decent results, ideally - 32k. To configure a model, you actually need to set its parameters and save a copy of it.
-
-    ##### Using Ollama runtime
-   Load the model (we will use `qwen2.5-coder:32b` as an example):
-   
-    ```bash
-    ollama run qwen2.5-coder:32b
-    ```
-
-   Change context size parameter:
-
-    ```bash
-    /set parameter num_ctx 32768
-    ```
-
-    Save the model with a new name:
-
-    ```bash
-    /save your_model_name
-    ```
-    ##### Using Ollama command line
-    Alternatively, you can write all your settings into a text file and generate the model in the command-line.
-
-
-    Create a text file with model settings, and save it (~/qwen2.5-coder-32k.txt).  Here we've only used the `num_ctx` parameter, but you could include more parameters on the next line using the `PARAMETER name value` syntax.
-
-    ```text
-    FROM qwen2.5-coder:32b
-    # sets the context window size to 32768, this controls how many tokens the LLM can use as context to generate the next token
-    PARAMETER num_ctx 32768
-    ```
-    Change directory to the `.ollama/models` directory.  On most Macs, thats `~/.ollama/models` by default (`%HOMEPATH%\.ollama` on Windows).
-
-    ```bash
-    cd ~/.ollama/models
-    ```
-
-    Create your model from the settings text file you created.  The syntax is `ollama create (name of the model you want to see) -f (text file with settings)`
-
-    ```bash
-    ollama create qwen2.5-coder-32k -f ~/qwen2.5-coder-32k.txt
-    ```
-
-
-
-4.  **Configure Roo Code:**
-    *   Open the Roo Code sidebar (<Codicon name="rocket" /> icon).
-    *   Click the settings gear icon (<Codicon name="gear" />).
-    *   Select "ollama" as the API Provider.
-    *   Enter the Model name from the previous step (e.g., `your_model_name`) or choose it from the radio button list that should appear below `Model ID` if Ollama is currently running.
-    *   (Optional) You can configure the base URL if you're running Ollama on a different machine. The default is `http://localhost:11434`.
-    *   (Optional) Configure Model context size in Advanced settings, so Roo Code knows how to manage its sliding window.
-
-## Setting Up LM Studio
-
-1.  **Download and Install LM Studio:** Download LM Studio from the [LM Studio website](https://lmstudio.ai/).
-2.  **Download a Model:** Use the LM Studio interface to search for and download a model.  Some recommended models include those listed above for Ollama. Look for models in the GGUF format.
-3.  **Start the Local Server:**
-    *   In LM Studio, click the **"Local Server"** tab (the icon looks like `<->`).
-    *   Select your downloaded model.
-    *   Click **"Start Server"**.
-4.  **Configure Roo Code:**
-    *   Open the Roo Code sidebar (<Codicon name="rocket" /> icon).
-    *   Click the settings gear icon (<Codicon name="gear" />).
-    *   Select "lmstudio" as the API Provider.
-    *   Enter the Model ID.  This should be the name of the model file you loaded in LM Studio (e.g., `codellama-7b.Q4_0.gguf`).  LM Studio shows a list of "Currently loaded models" in its UI.
-    *   (Optional) You can configure the base URL if you're running LM Studio on a different machine. The default is `http://localhost:1234`.
+Both providers offer similar capabilities but with different user interfaces and workflows. Ollama provides more control through its command-line interface, while LM Studio offers a more user-friendly graphical interface.
 
 ## Troubleshooting
 
-*   **"Please check the LM Studio developer logs to debug what went wrong":** This error usually indicates a problem with the model or its configuration in LM Studio.  Try the following:
-    *   Make sure the LM Studio local server is running and that the correct model is loaded.
-    *   Check the LM Studio logs for any error messages.
-    *   Try restarting the LM Studio server.
-    *   Ensure your chosen model is compatible with Roo Code.  Some very small models may not work well.
-    *  Some models may require a larger context length.
-
 *   **"No connection could be made because the target machine actively refused it":**  This usually means that the Ollama or LM Studio server isn't running, or is running on a different port/address than Roo Code is configured to use.  Double-check the Base URL setting.
 
 *   **Slow Response Times:** Local models can be slower than cloud-based models, especially on less powerful hardware.  If performance is an issue, try using a smaller model.