Update README.md
Browse files
README.md
CHANGED
|
@@ -21,15 +21,8 @@ pipeline_tag: text-generation
|
|
| 21 |
|
| 22 |
SmolLM2 is a family of compact language models available in three size: 135M, 360M, and 1.7B parameters. They are capable of solving a wide range of tasks while being lightweight enough to run on-device. Fine-tuning a language model like SmolLM involves several steps, from setting up the environment to training the model and saving the results. Below is a detailed step-by-step guide based on the provided notebook file
|
| 23 |
|
| 24 |
-
| **Notebook** | **Link** |
|
| 25 |
-
|--------------|----------|
|
| 26 |
-
| SmolLM-FT-360M | [SmolLM-FT-360M.ipynb](https://huggingface.co/datasets/prithivMLmods/FinetuneRT-Colab/blob/main/SmolLM-FT/SmolLM-FT-360M.ipynb) |
|
| 27 |
|
| 28 |
-
|
| 29 |
-
|
| 30 |
-
### How to use
|
| 31 |
-
|
| 32 |
-
### Transformers
|
| 33 |
```bash
|
| 34 |
pip install transformers
|
| 35 |
```
|
|
@@ -247,6 +240,37 @@ After training, save the fine-tuned model and tokenizer to a local directory.
|
|
| 247 |
```
|
| 248 |
|
| 249 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 250 |
### **Model & Quant**
|
| 251 |
|
| 252 |
| **Item** | **Link** |
|
|
|
|
| 21 |
|
| 22 |
SmolLM2 is a family of compact language models available in three size: 135M, 360M, and 1.7B parameters. They are capable of solving a wide range of tasks while being lightweight enough to run on-device. Fine-tuning a language model like SmolLM involves several steps, from setting up the environment to training the model and saving the results. Below is a detailed step-by-step guide based on the provided notebook file
|
| 23 |
|
|
|
|
|
|
|
|
|
|
| 24 |
|
| 25 |
+
# How to use with `Transformers`
|
|
|
|
|
|
|
|
|
|
|
|
|
| 26 |
```bash
|
| 27 |
pip install transformers
|
| 28 |
```
|
|
|
|
| 240 |
```
|
| 241 |
|
| 242 |
---
|
| 243 |
+
|
| 244 |
+
### **Run with Ollama [Ollama Run]**
|
| 245 |
+
|
| 246 |
+
Ollama makes running machine learning models simple and efficient. Follow these steps to set up and run your GGUF models quickly.
|
| 247 |
+
|
| 248 |
+
## Quick Start: Step-by-Step Guide
|
| 249 |
+
|
| 250 |
+
| Step | Description | Command / Instructions |
|
| 251 |
+
|------|-------------------------------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------|
|
| 252 |
+
| 1 | **Install Ollama 🦙** | Download Ollama from [https://ollama.com/download](https://ollama.com/download) and install it on your system. |
|
| 253 |
+
| 2 | **Create Your Model File** | - Create a file named after your model, e.g., `metallama`. |
|
| 254 |
+
| | | - Add the following line to specify the base model: |
|
| 255 |
+
| | | ```bash |
|
| 256 |
+
| | | FROM Llama-3.2-1B.F16.gguf |
|
| 257 |
+
| | | ``` |
|
| 258 |
+
| | | - Ensure the base model file is in the same directory. |
|
| 259 |
+
| 3 | **Create and Patch the Model** | Run the following commands to create and verify your model: |
|
| 260 |
+
| | | ```bash |
|
| 261 |
+
| | | ollama create metallama -f ./metallama |
|
| 262 |
+
| | | ollama list |
|
| 263 |
+
| | | ``` |
|
| 264 |
+
| 4 | **Run the Model** | Use the following command to start your model: |
|
| 265 |
+
| | | ```bash |
|
| 266 |
+
| | | ollama run metallama |
|
| 267 |
+
| | | ``` |
|
| 268 |
+
| 5 | **Interact with the Model** | Once the model is running, interact with it: |
|
| 269 |
+
| | | ```plaintext |
|
| 270 |
+
| | | >>> Tell me about Space X. |
|
| 271 |
+
| | | Space X, the private aerospace company founded by Elon Musk, is revolutionizing space exploration... |
|
| 272 |
+
| | | ``` |
|
| 273 |
+
|
| 274 |
### **Model & Quant**
|
| 275 |
|
| 276 |
| **Item** | **Link** |
|