Update README.md
Browse files
README.md
CHANGED
|
@@ -33,7 +33,14 @@ This model is a fine-tuned version of **Qwen/Qwen2.5-3B-Instruct**, optimized fo
|
|
| 33 |
- **Enhancement**: After fine-tuning on GSM8K, additional reasoning layers were introduced using **DeepSeek-V3-Small**, leading to richer, more interpretable answers.
|
| 34 |
- **Training Objective**: Improve step-by-step mathematical reasoning and **enhance logical deductions** in model-generated responses.
|
| 35 |
|
| 36 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 37 |
|
| 38 |
You can load this model with `transformers`:
|
| 39 |
|
|
|
|
| 33 |
- **Enhancement**: After fine-tuning on GSM8K, additional reasoning layers were introduced using **DeepSeek-V3-Small**, leading to richer, more interpretable answers.
|
| 34 |
- **Training Objective**: Improve step-by-step mathematical reasoning and **enhance logical deductions** in model-generated responses.
|
| 35 |
|
| 36 |
+
I have adopted some code from Unsloth and here's an updated [notebook](https://colab.research.google.com/drive/1HV0YkyiTD55j1xLRBHwJ_q3ex82W5EXr?usp=sharing) on Colab. Please feel free to copy it and run it yourself.
|
| 37 |
+
|
| 38 |
+
You will need:
|
| 39 |
+
- Huggingface token
|
| 40 |
+
- Together.AI API Key
|
| 41 |
+
- Unsloth package
|
| 42 |
+
|
| 43 |
+
## How to Use Model for Inference
|
| 44 |
|
| 45 |
You can load this model with `transformers`:
|
| 46 |
|