update readme with `docker` setup and link to `import.md`

README.md

@@ -15,6 +15,10 @@ Get up and running with large language models locally.
 
 [Download](https://ollama.ai/download/Ollama-darwin.zip)
 
+### Windows
+
+Coming soon!
+
 ### Linux & WSL2
 
 ```
@@ -23,9 +27,13 @@ curl https://ollama.ai/install.sh | sh
 
 [Manual install instructions](https://github.com/jmorganca/ollama/blob/main/docs/linux.md)
 
-### Windows
+### Docker
 
-coming soon
+```
+docker run -d -v ollama:/root/.ollama -p 11434:11434 --name ollama ollama/ollama
+```
+
+For GPU support, use `--gpus=all`. See the Docker [image](https://hub.docker.com/r/ollama/ollama) for more information.
 
 ## Quickstart
 
@@ -56,11 +64,11 @@ Here are some example open-source models that can be downloaded:
 
 ## Customize your own model
 
-### Import from GGUF or GGML
+### Import from GGUF
 
-Ollama supports importing GGUF and GGML file formats in the Modelfile. This means if you have a model that is not in the Ollama library, you can create it, iterate on it, and upload it to the Ollama library to share with others when you are ready.
+Ollama supports importing GGUF models in the Modelfile:
 
-1. Create a file named Modelfile, and add a `FROM` instruction with the local filepath to the model you want to import.
+1. Create a file named `Modelfile`, with a `FROM` instruction with the local filepath to the model you want to import.
 
    ```
    FROM ./vicuna-33b.Q4_0.gguf
@@ -69,15 +77,19 @@ Ollama supports importing GGUF and GGML file formats in the Modelfile. This mean
 2. Create the model in Ollama
 
    ```
-   ollama create name -f path_to_modelfile
+   ollama create example -f Modelfile
    ```
 
 3. Run the model
 
    ```
-   ollama run name
+   ollama run example
    ```
 
+### Import from PyTorch or Safetensors
+
+See the [guide](docs/import.md) on importing models for more information.
+
 ### Customize a prompt
 
 Models from the Ollama library can be customized with a prompt. The example

docs/faq.md

 # FAQ
 
+## How can I view the logs?
+
+On macOS:
+
+```
+cat ~/.ollama/logs/server.log
+```
+
+On Linux:
+
+```
+journalctl -u ollama
+```
+
+If you're running `ollama serve` directly, the logs will be printed to the console.
+
 ## How can I expose the Ollama server?
 
 ```bash
@@ -14,5 +30,5 @@ OLLAMA_ORIGINS=http://192.168.1.1:*,https://example.com ollama serve
 
 ## Where are models stored?
 
-* macOS: Raw model data is stored under `~/.ollama/models`.
-* Linux: Raw model data is stored under `/usr/share/ollama/.ollama/models`
+- macOS: Raw model data is stored under `~/.ollama/models`.
+- Linux: Raw model data is stored under `/usr/share/ollama/.ollama/models`

docs/import.md

@@ -23,7 +23,7 @@ git clone https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1
 cd Mistral-7B-Instruct-v0.1
 ```
 
-### Step 2: Convert and quantize (PyTorch and Safetensors)
+### Step 2: Convert and quantize (for PyTorch and Safetensors)
 
 A [Docker image](https://hub.docker.com/r/ollama/quantize) with the tooling required to convert and quantize models is available.
 

docs/linux.md

@@ -80,4 +80,3 @@ To view logs of Ollama running as a startup service, run:
 ```bash
 journalctl -u ollama
 ```
-