Update README.md
Browse files
README.md
CHANGED
|
@@ -44,7 +44,6 @@ The model was trained on a carefully selected set of public datasets:
|
|
| 44 |
|
| 45 |
* **Medical Reasoning:** `FreedomIntelligence/medical-o1-reasoning-SFT`
|
| 46 |
* **Mathematical Reasoning:** `unsloth/OpenMathReasoning-mini`
|
| 47 |
-
* *(Note: While `madrylab/gsm8k-platinum` is listed in the metadata, `unsloth/OpenMathReasoning-mini` was the primary math dataset utilized in the provided training script.)*
|
| 48 |
* **General Conversation:** `mlabonne/guanaco-llama2-1k`
|
| 49 |
|
| 50 |
### Training Procedure
|
|
|
|
| 44 |
|
| 45 |
* **Medical Reasoning:** `FreedomIntelligence/medical-o1-reasoning-SFT`
|
| 46 |
* **Mathematical Reasoning:** `unsloth/OpenMathReasoning-mini`
|
|
|
|
| 47 |
* **General Conversation:** `mlabonne/guanaco-llama2-1k`
|
| 48 |
|
| 49 |
### Training Procedure
|