Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,13 @@
|
|
| 1 |
---
|
| 2 |
license: other
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: other
|
| 3 |
---
|
| 4 |
+
|
| 5 |
+
# MedLLAMA-LoRA
|
| 6 |
+
#### Experimental llama finetune on medical qa dataset
|
| 7 |
+
This model has not been evaluated yet, and should NOT be used for medical advice. It is an example of how LoRA can be used to create finetuned expert models from LLaMA
|
| 8 |
+
|
| 9 |
+
Training Details:
|
| 10 |
+
- 13b model, finetuned on 76k question-answer pairs
|
| 11 |
+
- superset of alpaca-data-cleaned with medical qa pairs adapted from icliniq dataset
|
| 12 |
+
- Trained for 18 hours on A100, minibatch size 10, batch size 256, cutoff_len 512, all other parameters default
|
| 13 |
+
- https://github.com/tloen/alpaca-lora
|