Cristian Sas
commited on
Update README.md
Browse files
README.md
CHANGED
|
@@ -118,7 +118,89 @@ print(tokenizer.decode(outputs[0], skip_special_tokens=True))
|
|
| 118 |
|
| 119 |
---
|
| 120 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 121 |
|
|
|
|
| 122 |
|
| 123 |
|
| 124 |

|
|
|
|
| 118 |
|
| 119 |
---
|
| 120 |
|
| 121 |
+
---
|
| 122 |
+
|
| 123 |
+
# **📌 Installation Guide: Ollama + LitSeek**
|
| 124 |
+
|
| 125 |
+
## **🔹 Step 1: Install Ollama**
|
| 126 |
+
Ollama is a lightweight framework for running large language models (LLMs) locally.
|
| 127 |
+
|
| 128 |
+
### **🖥️ For macOS & Linux**
|
| 129 |
+
1️⃣ **Open a terminal and run:**
|
| 130 |
+
```sh
|
| 131 |
+
curl -fsSL https://ollama.com/install.sh | sh
|
| 132 |
+
```
|
| 133 |
+
2️⃣ **Restart your terminal.**
|
| 134 |
+
|
| 135 |
+
### **🖥️ For Windows (WSL2 required)**
|
| 136 |
+
1️⃣ **Enable WSL2 and install Ubuntu:**
|
| 137 |
+
- Open PowerShell as Administrator and run:
|
| 138 |
+
```powershell
|
| 139 |
+
wsl --install
|
| 140 |
+
```
|
| 141 |
+
- Restart your computer.
|
| 142 |
+
|
| 143 |
+
2️⃣ **Install Ollama inside WSL2:**
|
| 144 |
+
```sh
|
| 145 |
+
curl -fsSL https://ollama.com/install.sh | sh
|
| 146 |
+
```
|
| 147 |
+
|
| 148 |
+
3️⃣ **Check if Ollama is installed correctly:**
|
| 149 |
+
```sh
|
| 150 |
+
ollama
|
| 151 |
+
```
|
| 152 |
+
If it prints the usage instructions, the installation is successful. 🎉
|
| 153 |
+
|
| 154 |
+
---
|
| 155 |
+
|
| 156 |
+
## **🔹 Step 2: Install LLMLit from Hugging Face**
|
| 157 |
+
LLMLit can be downloaded and run inside Ollama using the `ollama pull` command.
|
| 158 |
+
|
| 159 |
+
1️⃣ **Open a terminal and run:**
|
| 160 |
+
```sh
|
| 161 |
+
ollama pull llmlit/LeetSeek-R1-DLlama-8B
|
| 162 |
+
```
|
| 163 |
+
|
| 164 |
+
2️⃣ **Verify the installation:**
|
| 165 |
+
```sh
|
| 166 |
+
ollama list
|
| 167 |
+
```
|
| 168 |
+
You should see **LLMLit** in the list of installed models. ✅
|
| 169 |
+
|
| 170 |
+
---
|
| 171 |
+
|
| 172 |
+
## **🔹 Step 3: Run LLMLit in Ollama**
|
| 173 |
+
After installation, you can interact with **LLMLit** using:
|
| 174 |
+
|
| 175 |
+
```sh
|
| 176 |
+
ollama run llmlit/LeetSeek-R1-DLlama-8B
|
| 177 |
+
```
|
| 178 |
+
This starts a local session where you can chat with the model! 🤖
|
| 179 |
+
|
| 180 |
+
For custom prompts:
|
| 181 |
+
```sh
|
| 182 |
+
ollama run llmlit/LeetSeek-R1-DLlama-8B "Hello, how can I use LLMLit?"
|
| 183 |
+
```
|
| 184 |
+
|
| 185 |
+
---
|
| 186 |
+
|
| 187 |
+
## **🔹 Bonus: Use LLMLit in Python**
|
| 188 |
+
If you want to integrate **LLMLit** into a Python script, install the required library:
|
| 189 |
+
```sh
|
| 190 |
+
pip install ollama
|
| 191 |
+
```
|
| 192 |
+
|
| 193 |
+
Then, create a Python script:
|
| 194 |
+
```python
|
| 195 |
+
import ollama
|
| 196 |
+
|
| 197 |
+
response = ollama.chat(model='llmlit/LeetSeek-R1-DLlama-8B', messages=[{'role': 'user', 'content': 'How does LLMLit work?'}])
|
| 198 |
+
print(response['message']['content'])
|
| 199 |
+
```
|
| 200 |
+
|
| 201 |
+
---
|
| 202 |
|
| 203 |
+
🚀 **Done!** Now you have **Ollama + LLMLit** installed and ready to use locally!
|
| 204 |
|
| 205 |
|
| 206 |

|