Spaces:
Runtime error
Runtime error
Commit ·
65e80b8
1
Parent(s): fc34b65
docs(llm,network): Added docs for ollama install and running and networking problems with WSL2 on Windows
Browse files- docs/llm.md +64 -0
- docs/network.md +39 -0
docs/llm.md
ADDED
|
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# How to Run Deepseek Locally
|
| 2 |
+
|
| 3 |
+
This guide explains how to run the Deepseek model locally using Ollama as your server. Follow these steps to set up and use the model.
|
| 4 |
+
|
| 5 |
+
## Prerequisites
|
| 6 |
+
|
| 7 |
+
Ensure you have Ollama installed on your machine. If not, follow the installation instructions for Windows at:
|
| 8 |
+
|
| 9 |
+
[Ollama Installation Guide](https://ollama.com/download/windows)
|
| 10 |
+
|
| 11 |
+
## Getting Started with Deepseek Model
|
| 12 |
+
|
| 13 |
+
### Step 1: Pull the Deepseek Model
|
| 14 |
+
|
| 15 |
+
To use models in Ollama, start by downloading the desired model using the `pull` command. Open your terminal and run:
|
| 16 |
+
|
| 17 |
+
```bash
|
| 18 |
+
ollama pull <model>
|
| 19 |
+
```
|
| 20 |
+
|
| 21 |
+
### Step 2: Run the Model
|
| 22 |
+
|
| 23 |
+
After downloading, you can start the model with the following command:
|
| 24 |
+
|
| 25 |
+
```bash
|
| 26 |
+
ollama run <model>
|
| 27 |
+
```
|
| 28 |
+
|
| 29 |
+
This command activates the model, allowing you to enter queries or instructions, and receive responses.
|
| 30 |
+
|
| 31 |
+
### Step 3: Using the Model with OpenAI API Specifications
|
| 32 |
+
|
| 33 |
+
Ollama is now compatible with the OpenAI Chat Completions API. This allows you to use additional tooling and applications with Ollama locally. Here's how to set it up:
|
| 34 |
+
|
| 35 |
+
```python
|
| 36 |
+
from openai import OpenAI
|
| 37 |
+
|
| 38 |
+
model_name = "<model name>"
|
| 39 |
+
# Initialize the OpenAI client
|
| 40 |
+
client = OpenAI(
|
| 41 |
+
base_url = 'http://localhost:11434/v1',
|
| 42 |
+
api_key='ollama', # This is required but unused
|
| 43 |
+
)
|
| 44 |
+
|
| 45 |
+
# Create chat completions
|
| 46 |
+
response = client.chat.completions.create(
|
| 47 |
+
model=model_name,
|
| 48 |
+
messages=[
|
| 49 |
+
{"role": "system", "content": "You are a helpful assistant."},
|
| 50 |
+
{"role": "user", "content": "Who won the world series in 2020?"},
|
| 51 |
+
{"role": "assistant", "content": "The LA Dodgers won in 2020."},
|
| 52 |
+
{"role": "user", "content": "Where was it played?"}
|
| 53 |
+
]
|
| 54 |
+
)
|
| 55 |
+
|
| 56 |
+
# Print the response
|
| 57 |
+
print(response.choices[0].message.content)
|
| 58 |
+
```
|
| 59 |
+
|
| 60 |
+
### Step 4: Configuring WSL2 for Local Server Access
|
| 61 |
+
|
| 62 |
+
If you are using WSL2 and wish to access the Ollama server running on your Windows machine, you need to configure WSL2 with mirror mode to share localhost between WSL2 and Windows. For more details, see:
|
| 63 |
+
|
| 64 |
+
[Network Configuration Guide](network.md)
|
docs/network.md
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Accessing Network Applications with WSL
|
| 2 |
+
|
| 3 |
+
This guide details how to access network applications using the Windows Subsystem for Linux (WSL) by mirroring the network configuration. This method allows you to use `localhost` to connect seamlessly between Windows and WSL.
|
| 4 |
+
|
| 5 |
+
## Step 1: Create a WSL Configuration File
|
| 6 |
+
|
| 7 |
+
To configure network mirroring in WSL, you need to create a `.wslconfig` file in your home directory.
|
| 8 |
+
|
| 9 |
+
1. **Open File Explorer:** Paste `%UserProfile%` in the address bar to navigate to your home directory.
|
| 10 |
+
2. **Create the File:** Right-click in the folder, select "New > Text Document," and name the file `.wslconfig`.
|
| 11 |
+
|
| 12 |
+
### Configure the File
|
| 13 |
+
|
| 14 |
+
Copy and paste the following content into the `.wslconfig` file:
|
| 15 |
+
|
| 16 |
+
```text
|
| 17 |
+
[wsl2]
|
| 18 |
+
networkingMode=mirrored
|
| 19 |
+
```
|
| 20 |
+
|
| 21 |
+
## Step 2: Restart WSL
|
| 22 |
+
|
| 23 |
+
For the changes to take effect, you need to restart the WSL virtual machine.
|
| 24 |
+
|
| 25 |
+
Open a Command Prompt or PowerShell window and execute the following commands:
|
| 26 |
+
|
| 27 |
+
```bash
|
| 28 |
+
# Shut down WSL
|
| 29 |
+
wsl --shutdown
|
| 30 |
+
|
| 31 |
+
# Start WSL
|
| 32 |
+
wsl
|
| 33 |
+
```
|
| 34 |
+
|
| 35 |
+
## Further Information
|
| 36 |
+
|
| 37 |
+
For additional details and advanced settings, refer to the official WSL Networking documentation:
|
| 38 |
+
|
| 39 |
+
[WSL Networking Documentation](https://learn.microsoft.com/en-us/windows/wsl/networking)
|