Update README.md
Browse files
README.md
CHANGED
|
@@ -14,6 +14,7 @@ tags:
|
|
| 14 |
- llama
|
| 15 |
- CoT
|
| 16 |
- Thinker
|
|
|
|
| 17 |
---
|
| 18 |
|
| 19 |
|
|
@@ -21,15 +22,9 @@ tags:
|
|
| 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 |
-
|
| 31 |
-
|
| 32 |
-
### Transformers
|
| 33 |
```bash
|
| 34 |
pip install transformers
|
| 35 |
```
|
|
@@ -254,10 +249,14 @@ After training, save the fine-tuned model and tokenizer to a local directory.
|
|
| 254 |
| **Model** | [SmolLM2-CoT-360M](https://huggingface.co/prithivMLmods/SmolLM2-CoT-360M) |
|
| 255 |
| **Quantized Version** | [SmolLM2-CoT-360M-GGUF](https://huggingface.co/prithivMLmods/SmolLM2-CoT-360M-GGUF) |
|
| 256 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 257 |
### **Conclusion**
|
| 258 |
|
| 259 |
Fine-tuning SmolLM involves setting up the environment, loading the model and dataset, configuring training parameters, and running the training loop. By following these steps, you can adapt SmolLM to your specific use case, whether it’s for reasoning tasks, chat-based applications, or other NLP tasks.
|
| 260 |
|
| 261 |
This process is highly customizable, so feel free to experiment with different datasets, hyperparameters, and training strategies to achieve the best results for your project.
|
| 262 |
|
| 263 |
-
---
|
|
|
|
| 14 |
- llama
|
| 15 |
- CoT
|
| 16 |
- Thinker
|
| 17 |
+
- LlamaForCausalLM
|
| 18 |
---
|
| 19 |
|
| 20 |
|
|
|
|
| 22 |
|
| 23 |
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
|
| 24 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 25 |
---
|
| 26 |
|
| 27 |
+
# How to use `Transformers`
|
|
|
|
|
|
|
| 28 |
```bash
|
| 29 |
pip install transformers
|
| 30 |
```
|
|
|
|
| 249 |
| **Model** | [SmolLM2-CoT-360M](https://huggingface.co/prithivMLmods/SmolLM2-CoT-360M) |
|
| 250 |
| **Quantized Version** | [SmolLM2-CoT-360M-GGUF](https://huggingface.co/prithivMLmods/SmolLM2-CoT-360M-GGUF) |
|
| 251 |
|
| 252 |
+
| **Notebook** | **Link** |
|
| 253 |
+
|--------------|----------|
|
| 254 |
+
| SmolLM-FT-360M | [SmolLM-FT-360M.ipynb](https://huggingface.co/datasets/prithivMLmods/FinetuneRT-Colab/blob/main/SmolLM-FT/SmolLM-FT-360M.ipynb) |
|
| 255 |
+
|
| 256 |
### **Conclusion**
|
| 257 |
|
| 258 |
Fine-tuning SmolLM involves setting up the environment, loading the model and dataset, configuring training parameters, and running the training loop. By following these steps, you can adapt SmolLM to your specific use case, whether it’s for reasoning tasks, chat-based applications, or other NLP tasks.
|
| 259 |
|
| 260 |
This process is highly customizable, so feel free to experiment with different datasets, hyperparameters, and training strategies to achieve the best results for your project.
|
| 261 |
|
| 262 |
+
---
|