Update README.md
Browse files
README.md
CHANGED
|
@@ -17,6 +17,12 @@ language:
|
|
| 17 |
- **License:** apache-2.0
|
| 18 |
- **Finetuned from model :** unsloth/DeepSeek-R1-Distill-Qwen-1.5B-unsloth-bnb-4bit
|
| 19 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 20 |
This qwen2 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
|
| 21 |
|
| 22 |
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
|
|
|
| 17 |
- **License:** apache-2.0
|
| 18 |
- **Finetuned from model :** unsloth/DeepSeek-R1-Distill-Qwen-1.5B-unsloth-bnb-4bit
|
| 19 |
|
| 20 |
+
Finetuned Qwen1.5B (R1 Distilled Version) on [this dataset](https://huggingface.co/datasets/tcotter/o1-medical-data-reasoning-w-summary),
|
| 21 |
+
which comes from [this dataset](https://huggingface.co/datasets/FreedomIntelligence/medical-o1-reasoning-SFT) but with an
|
| 22 |
+
additional "summary" produced by an in-house synthetic data generator.
|
| 23 |
+
|
| 24 |
+
This LoRA is therefore a LoRA which helps the model return a "\n\nFinal Answer: ..." after it's reasoning and initial response steps.
|
| 25 |
+
|
| 26 |
This qwen2 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
|
| 27 |
|
| 28 |
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|