prithivMLmods
commited on
Update README.md
Browse files
README.md
CHANGED
@@ -138,3 +138,56 @@ To customize the password length, modify the `password_length` variable in the s
|
|
138 |
|
139 |
Llama 3.2 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align with human preferences for helpfulness and safety.
|
140 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
138 |
|
139 |
Llama 3.2 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align with human preferences for helpfulness and safety.
|
140 |
|
141 |
+
# **Run with Ollama [ Ollama Run ]**
|
142 |
+
|
143 |
+
Ollama simplifies running machine learning models. This guide walks you through downloading, installing, and running GGUF models in minutes.
|
144 |
+
|
145 |
+
## Table of Contents
|
146 |
+
|
147 |
+
- [Download and Install](#download-and-install)
|
148 |
+
- [Run GGUF Models](#run-gguf-models)
|
149 |
+
- [Running the Model](#running-the-model)
|
150 |
+
- [Sample Usage](#sample-usage)
|
151 |
+
|
152 |
+
## Download and Install
|
153 |
+
|
154 |
+
Download Ollama from [https://ollama.com/download](https://ollama.com/download) and install it on your Windows or Mac system.
|
155 |
+
|
156 |
+
## Run GGUF Models
|
157 |
+
|
158 |
+
1. **Create the Model File**
|
159 |
+
Create a model file, e.g., `metallama`.
|
160 |
+
|
161 |
+
2. **Add the Template Command**
|
162 |
+
Include a `FROM` line in the file to specify the base model:
|
163 |
+
```bash
|
164 |
+
FROM Llama-3.2-1B.F16.gguf
|
165 |
+
```
|
166 |
+
|
167 |
+
3. **Create and Patch the Model**
|
168 |
+
Run the following command:
|
169 |
+
```bash
|
170 |
+
ollama create metallama -f ./metallama
|
171 |
+
```
|
172 |
+
Verify the model with:
|
173 |
+
```bash
|
174 |
+
ollama list
|
175 |
+
```
|
176 |
+
|
177 |
+
## Running the Model
|
178 |
+
|
179 |
+
Run your model with:
|
180 |
+
```bash
|
181 |
+
ollama run metallama
|
182 |
+
```
|
183 |
+
|
184 |
+
### Sample Usage
|
185 |
+
|
186 |
+
Interact with the model:
|
187 |
+
```plaintext
|
188 |
+
>>> write a mini passage about space x
|
189 |
+
Space X, the private aerospace company founded by Elon Musk, is revolutionizing the field of space exploration...
|
190 |
+
```
|
191 |
+
|
192 |
+
---
|
193 |
+
With these steps, you can easily run custom models using Ollama. Adjust as needed for your specific use case.
|